Merge branch 'master' into test-merge-for-6.8test-merge-for-6.8

2002 files changed, 28521 insertions, 22226 deletions

diff --git a/.mailmap b/.mailmap
index 43031441b2d922..68e72a6017a0ee 100644
--- a/.mailmap
+++ b/.mailmap
@@ -117,6 +117,7 @@ Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com>
 Changbin Du <changbin.du@intel.com> <changbin.du@intel.com>
 Chao Yu <chao@kernel.org> <chao2.yu@samsung.com>
 Chao Yu <chao@kernel.org> <yuchao0@huawei.com>
+Chester Lin <chester62515@gmail.com> <clin@suse.com>
 Chris Chiu <chris.chiu@canonical.com> <chiu@endlessm.com>
 Chris Chiu <chris.chiu@canonical.com> <chiu@endlessos.org>
 Chris Lew <quic_clew@quicinc.com> <clew@codeaurora.org>
@@ -190,6 +191,10 @@ Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@linux.alibaba.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@redhat.com>
+Geliang Tang <geliang.tang@linux.dev> <geliang.tang@suse.com>
+Geliang Tang <geliang.tang@linux.dev> <geliangtang@xiaomi.com>
+Geliang Tang <geliang.tang@linux.dev> <geliangtang@gmail.com>
+Geliang Tang <geliang.tang@linux.dev> <geliangtang@163.com>
 Georgi Djakov <djakov@kernel.org> <georgi.djakov@linaro.org>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
@@ -265,6 +270,9 @@ Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
 Jernej Skrabec <jernej.skrabec@gmail.com> <jernej.skrabec@siol.net>
 Jessica Zhang <quic_jesszhan@quicinc.com> <jesszhan@codeaurora.org>
 Jilai Wang <quic_jilaiw@quicinc.com> <jilaiw@codeaurora.org>
+Jiri Kosina <jikos@kernel.org> <jikos@jikos.cz>
+Jiri Kosina <jikos@kernel.org> <jkosina@suse.cz>
+Jiri Kosina <jikos@kernel.org> <jkosina@suse.com>
 Jiri Pirko <jiri@resnulli.us> <jiri@nvidia.com>
 Jiri Pirko <jiri@resnulli.us> <jiri@mellanox.com>
 Jiri Pirko <jiri@resnulli.us> <jpirko@redhat.com>
diff --git a/CREDITS b/CREDITS
index f33a33fd237170..81845c39e3cf37 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2944,6 +2944,14 @@ D: IPX development and support
 N: Venkatesh Pallipadi (Venki)
 D: x86/HPET
 
+N: Antti Palosaari
+E: crope@iki.fi
+D: Various DVB drivers
+W: https://palosaari.fi/linux/
+S: Yliopistokatu 1 D 513
+S: FI-90570 Oulu
+S: FINLAND
+
 N: Kyungmin Park
 E: kyungmin.park@samsung.com
 D: Samsung S5Pv210 and Exynos4210 mobile platforms
diff --git a/Documentation/ABI/testing/sysfs-bus-optee-devices b/Documentation/ABI/testing/sysfs-bus-optee-devices
index 0f58701367b66a..af31e5a22d89fc 100644
--- a/Documentation/ABI/testing/sysfs-bus-optee-devices
+++ b/Documentation/ABI/testing/sysfs-bus-optee-devices
@@ -6,3 +6,12 @@ Description:
 		OP-TEE bus provides reference to registered drivers under this directory. The <uuid>
 		matches Trusted Application (TA) driver and corresponding TA in secure OS. Drivers
 		are free to create needed API under optee-ta-<uuid> directory.
+
+What:		/sys/bus/tee/devices/optee-ta-<uuid>/need_supplicant
+Date:		November 2023
+KernelVersion:	6.7
+Contact:	op-tee@lists.trustedfirmware.org
+Description:
+		Allows to distinguish whether an OP-TEE based TA/device requires user-space
+		tee-supplicant to function properly or not. This attribute will be present for
+		devices which depend on tee-supplicant to be running.
diff --git a/Documentation/ABI/testing/sysfs-class-led b/Documentation/ABI/testing/sysfs-class-led
index b2ff0012c0f2b8..2e24ac3bd7efa4 100644
--- a/Documentation/ABI/testing/sysfs-class-led
+++ b/Documentation/ABI/testing/sysfs-class-led
@@ -59,15 +59,6 @@ Description:
 		brightness. Reading this file when no hw brightness change
 		event has happened will return an ENODATA error.
 
-What:		/sys/class/leds/<led>/color
-Date:		June 2023
-KernelVersion:	6.5
-Description:
-		Color of the LED.
-
-		This is a read-only file. Reading this file returns the color
-		of the LED as a string (e.g: "red", "green", "multicolor").
-
 What:		/sys/class/leds/<led>/trigger
 Date:		March 2006
 KernelVersion:	2.6.17
diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst
index 4b8399ac592ba3..ced7b335e2e001 100644
--- a/Documentation/arch/arm64/elf_hwcaps.rst
+++ b/Documentation/arch/arm64/elf_hwcaps.rst
@@ -174,7 +174,7 @@ HWCAP2_DCPODP
     Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010.
 
 HWCAP2_SVE2
-    Functionality implied by ID_AA64ZFR0_EL1.SVEVer == 0b0001.
+    Functionality implied by ID_AA64ZFR0_EL1.SVEver == 0b0001.
 
 HWCAP2_SVEAES
     Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001.
@@ -222,7 +222,7 @@ HWCAP2_RNG
     Functionality implied by ID_AA64ISAR0_EL1.RNDR == 0b0001.
 
 HWCAP2_BTI
-    Functionality implied by ID_AA64PFR0_EL1.BT == 0b0001.
+    Functionality implied by ID_AA64PFR1_EL1.BT == 0b0001.
 
 HWCAP2_MTE
     Functionality implied by ID_AA64PFR1_EL1.MTE == 0b0010, as described
@@ -232,7 +232,7 @@ HWCAP2_ECV
     Functionality implied by ID_AA64MMFR0_EL1.ECV == 0b0001.
 
 HWCAP2_AFP
-    Functionality implied by ID_AA64MFR1_EL1.AFP == 0b0001.
+    Functionality implied by ID_AA64MMFR1_EL1.AFP == 0b0001.
 
 HWCAP2_RPRES
     Functionality implied by ID_AA64ISAR2_EL1.RPRES == 0b0001.
diff --git a/Documentation/arch/loongarch/introduction.rst b/Documentation/arch/loongarch/introduction.rst
index 8c568cfc210798..5e6db78abeaf50 100644
--- a/Documentation/arch/loongarch/introduction.rst
+++ b/Documentation/arch/loongarch/introduction.rst
@@ -375,9 +375,9 @@ Developer web site of Loongson and LoongArch (Software and Documentation):
 
 Documentation of LoongArch ISA:
 
-  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.02-CN.pdf (in Chinese)
+  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.10-CN.pdf (in Chinese)
 
-  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.02-EN.pdf (in English)
+  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.10-EN.pdf (in English)
 
 Documentation of LoongArch ELF psABI:
 
diff --git a/Documentation/arch/riscv/uabi.rst b/Documentation/arch/riscv/uabi.rst
index 8960fac42c40f3..54d199dce78bf5 100644
--- a/Documentation/arch/riscv/uabi.rst
+++ b/Documentation/arch/riscv/uabi.rst
@@ -42,6 +42,26 @@ An example string following the order is::
 
    rv64imadc_zifoo_zigoo_zafoo_sbar_scar_zxmbaz_xqux_xrux
 
+"isa" and "hart isa" lines in /proc/cpuinfo
+-------------------------------------------
+
+The "isa" line in /proc/cpuinfo describes the lowest common denominator of
+RISC-V ISA extensions recognized by the kernel and implemented on all harts. The
+"hart isa" line, in contrast, describes the set of extensions recognized by the
+kernel on the particular hart being described, even if those extensions may not
+be present on all harts in the system.
+
+In both lines, the presence of an extension guarantees only that the hardware
+has the described capability. Additional kernel support or policy changes may be
+required before an extension's capability is fully usable by userspace programs.
+Similarly, for S-mode extensions, presence in one of these lines does not
+guarantee that the kernel is taking advantage of the extension, or that the
+feature will be visible in guest VMs managed by this kernel.
+
+Inversely, the absence of an extension in these lines does not necessarily mean
+the hardware does not support that feature. The running kernel may not recognize
+the extension, or may have deliberately removed it from the listing.
+
 Misaligned accesses
 -------------------
 
diff --git a/Documentation/arch/x86/boot.rst b/Documentation/arch/x86/boot.rst
index f5d2f2414de8b6..22cc7a040dae05 100644
--- a/Documentation/arch/x86/boot.rst
+++ b/Documentation/arch/x86/boot.rst
@@ -77,7 +77,7 @@ Protocol 2.14	BURNT BY INCORRECT COMMIT
 Protocol 2.15	(Kernel 5.5) Added the kernel_info and kernel_info.setup_type_max.
 =============	============================================================
 
-.. note::
+  .. note::
      The protocol version number should be changed only if the setup header
      is changed. There is no need to update the version number if boot_params
      or kernel_info are changed. Additionally, it is recommended to use
diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst
index 0d2647fb358d7c..723408e399abd8 100644
--- a/Documentation/bpf/kfuncs.rst
+++ b/Documentation/bpf/kfuncs.rst
@@ -37,16 +37,14 @@ prototype in a header for the wrapper kfunc.
 An example is given below::
 
         /* Disables missing prototype warnings */
-        __diag_push();
-        __diag_ignore_all("-Wmissing-prototypes",
-                          "Global kfuncs as their definitions will be in BTF");
+        __bpf_kfunc_start_defs();
 
         __bpf_kfunc struct task_struct *bpf_find_get_task_by_vpid(pid_t nr)
         {
                 return find_get_task_by_vpid(nr);
         }
 
-        __diag_pop();
+        __bpf_kfunc_end_defs();
 
 A wrapper kfunc is often needed when we need to annotate parameters of the
 kfunc. Otherwise one may directly make the kfunc visible to the BPF program by
diff --git a/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml b/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml
index 987aa83c264943..df20a3c9c74479 100644
--- a/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml
@@ -9,6 +9,9 @@ title: Analog Devices ADV7533/35 HDMI Encoders
 maintainers:
   - Laurent Pinchart <laurent.pinchart@ideasonboard.com>
 
+allOf:
+  - $ref: /schemas/sound/dai-common.yaml#
+
 description: |
   The ADV7533 and ADV7535 are HDMI audio and video transmitters
   compatible with HDMI 1.4 and DVI 1.0. They support color space
@@ -89,6 +92,9 @@ properties:
     $ref: /schemas/types.yaml#/definitions/uint32
     enum: [ 1, 2, 3, 4 ]
 
+  "#sound-dai-cells":
+    const: 0
+
   ports:
     description:
       The ADV7533/35 has two video ports and one audio port.
diff --git a/Documentation/devicetree/bindings/display/fsl,lcdif.yaml b/Documentation/devicetree/bindings/display/fsl,lcdif.yaml
index fc11ab5fc4654e..1c2be8d6f63340 100644
--- a/Documentation/devicetree/bindings/display/fsl,lcdif.yaml
+++ b/Documentation/devicetree/bindings/display/fsl,lcdif.yaml
@@ -51,7 +51,10 @@ properties:
     minItems: 1
 
   interrupts:
-    maxItems: 1
+    items:
+      - description: LCDIF DMA interrupt
+      - description: LCDIF Error interrupt
+    minItems: 1
 
   power-domains:
     maxItems: 1
@@ -131,6 +134,21 @@ allOf:
     then:
       required:
         - power-domains
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - fsl,imx23-lcdif
+    then:
+      properties:
+        interrupts:
+          minItems: 2
+          maxItems: 2
+    else:
+      properties:
+        interrupts:
+          maxItems: 1
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.yaml
index 537e5304b73006..ed24b617090b06 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.yaml
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.yaml
@@ -10,7 +10,6 @@ maintainers:
   - Chun-Kuang Hu <chunkuang.hu@kernel.org>
   - Philipp Zabel <p.zabel@pengutronix.de>
   - Jitao Shi <jitao.shi@mediatek.com>
-  - Xinlei Lee <xinlei.lee@mediatek.com>
 
 description: |
   The MediaTek DSI function block is a sink of the display subsystem and can
diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml
index 73674baea75d32..f9160d7bac3caa 100644
--- a/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml
+++ b/Documentation/devicetree/bindings/display/panel/panel-simple-dsi.yaml
@@ -42,6 +42,8 @@ properties:
       - lg,acx467akm-7
         # LG Corporation 7" WXGA TFT LCD panel
       - lg,ld070wx3-sl01
+        # LG Corporation 5" HD TFT LCD panel
+      - lg,lh500wx1-sd03
         # One Stop Displays OSD101T2587-53TS 10.1" 1920x1200 panel
       - osddisplays,osd101t2587-53ts
         # Panasonic 10" WUXGA TFT LCD panel
diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml
index 3ec9ee95045fbc..11422af3477e58 100644
--- a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml
+++ b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml
@@ -208,8 +208,6 @@ properties:
       - lemaker,bl035-rgb-002
         # LG 7" (800x480 pixels) TFT LCD panel
       - lg,lb070wv8
-        # LG Corporation 5" HD TFT LCD panel
-      - lg,lh500wx1-sd03
         # LG LP079QX1-SP0V 7.9" (1536x2048 pixels) TFT LCD panel
       - lg,lp079qx1-sp0v
         # LG 9.7" (2048x1536 pixels) TFT LCD panel
diff --git a/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml b/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml
index 509d20c091af82..6a206111d4e0f0 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml
@@ -62,6 +62,9 @@ properties:
         - description: MPM pin number
         - description: GIC SPI number for the MPM pin
 
+  '#power-domain-cells':
+    const: 0
+
 required:
   - compatible
   - reg
@@ -93,4 +96,5 @@ examples:
                            <86 183>,
                            <90 260>,
                            <91 260>;
+        #power-domain-cells = <0>;
     };
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index 9f6a5ccbcefef4..d14d123ad7a028 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -275,12 +275,12 @@ allOf:
       properties:
         rx-internal-delay-ps:
           description:
-            RGMII Receive Clock Delay defined in pico seconds.This is used for
+            RGMII Receive Clock Delay defined in pico seconds. This is used for
             controllers that have configurable RX internal delays. If this
             property is present then the MAC applies the RX delay.
         tx-internal-delay-ps:
           description:
-            RGMII Transmit Clock Delay defined in pico seconds.This is used for
+            RGMII Transmit Clock Delay defined in pico seconds. This is used for
             controllers that have configurable TX internal delays. If this
             property is present then the MAC applies the TX delay.
 
diff --git a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml
index f43186f9860756..d9287be898772f 100644
--- a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml
+++ b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml
@@ -15,9 +15,11 @@ allOf:
 
 properties:
   compatible:
-    enum:
-      - fsl,imx23-ocotp
-      - fsl,imx28-ocotp
+    items:
+      - enum:
+          - fsl,imx23-ocotp
+          - fsl,imx28-ocotp
+      - const: fsl,ocotp
 
   reg:
     maxItems: 1
@@ -35,7 +37,7 @@ unevaluatedProperties: false
 examples:
   - |
     ocotp: efuse@8002c000 {
-        compatible = "fsl,imx28-ocotp";
+        compatible = "fsl,imx28-ocotp", "fsl,ocotp";
         #address-cells = <1>;
         #size-cells = <1>;
         reg = <0x8002c000 0x2000>;
diff --git a/Documentation/devicetree/bindings/perf/riscv,pmu.yaml b/Documentation/devicetree/bindings/perf/riscv,pmu.yaml
index c8448de2f2a07c..d01c677ad3c765 100644
--- a/Documentation/devicetree/bindings/perf/riscv,pmu.yaml
+++ b/Documentation/devicetree/bindings/perf/riscv,pmu.yaml
@@ -90,7 +90,7 @@ properties:
             bitmap of all MHPMCOUNTERx that can monitor the range of events
 
 dependencies:
-  "riscv,event-to-mhpmevent": [ "riscv,event-to-mhpmcounters" ]
+  riscv,event-to-mhpmevent: [ "riscv,event-to-mhpmcounters" ]
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/pinctrl/nxp,s32g2-siul2-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/nxp,s32g2-siul2-pinctrl.yaml
index d49aafd8c5f4d9..a24286e4def623 100644
--- a/Documentation/devicetree/bindings/pinctrl/nxp,s32g2-siul2-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/nxp,s32g2-siul2-pinctrl.yaml
@@ -9,7 +9,7 @@ title: NXP S32G2 pin controller
 
 maintainers:
   - Ghennadi Procopciuc <Ghennadi.Procopciuc@oss.nxp.com>
-  - Chester Lin <clin@suse.com>
+  - Chester Lin <chester62515@gmail.com>
 
 description: |
   S32G2 pinmux is implemented in SIUL2 (System Integration Unit Lite2),
diff --git a/Documentation/devicetree/bindings/pwm/imx-pwm.yaml b/Documentation/devicetree/bindings/pwm/imx-pwm.yaml
index c01dff3b7f843e..a84a240a61dc1f 100644
--- a/Documentation/devicetree/bindings/pwm/imx-pwm.yaml
+++ b/Documentation/devicetree/bindings/pwm/imx-pwm.yaml
@@ -14,12 +14,10 @@ allOf:
 
 properties:
   "#pwm-cells":
-    description: |
-      Should be 2 for i.MX1 and 3 for i.MX27 and newer SoCs. See pwm.yaml
-      in this directory for a description of the cells format.
-    enum:
-      - 2
-      - 3
+    description:
+      The only third cell flag supported by this binding is
+      PWM_POLARITY_INVERTED. fsl,imx1-pwm does not support this flags.
+    const: 3
 
   compatible:
     oneOf:
diff --git a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
index e4fa6a07b4fa2c..1309bf5ae0cdd1 100644
--- a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
+++ b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
@@ -233,6 +233,7 @@ allOf:
               - rockchip,rk3399-grf
               - rockchip,rk3399-pmugrf
               - rockchip,rk3568-pmugrf
+              - rockchip,rk3588-pmugrf
               - rockchip,rv1108-grf
               - rockchip,rv1108-pmugrf
 
diff --git a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml
index 462ead5a1cec32..2cf3d016db42c1 100644
--- a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml
+++ b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml
@@ -36,6 +36,7 @@ properties:
           - qcom,sm8350-ufshc
           - qcom,sm8450-ufshc
           - qcom,sm8550-ufshc
+          - qcom,sm8650-ufshc
       - const: qcom,ufshc
       - const: jedec,ufs-2.0
 
@@ -122,6 +123,7 @@ allOf:
               - qcom,sm8350-ufshc
               - qcom,sm8450-ufshc
               - qcom,sm8550-ufshc
+              - qcom,sm8650-ufshc
     then:
       properties:
         clocks:
diff --git a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
index ff3a1707ef570f..6d4cfd943f5847 100644
--- a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
+++ b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
@@ -36,7 +36,11 @@ properties:
 
   vdd-supply:
     description:
-      VDD power supply to the hub
+      3V3 power supply to the hub
+
+  vdd2-supply:
+    description:
+      1V2 power supply to the hub
 
   peer-hub:
     $ref: /schemas/types.yaml#/definitions/phandle
@@ -62,6 +66,7 @@ allOf:
       properties:
         reset-gpios: false
         vdd-supply: false
+        vdd2-supply: false
         peer-hub: false
         i2c-bus: false
     else:
diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
index e889158ca20578..915c8205623b3a 100644
--- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
@@ -521,8 +521,8 @@ examples:
 
             interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 488 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 489 IRQ_TYPE_LEVEL_HIGH>;
+                         <GIC_SPI 488 IRQ_TYPE_EDGE_BOTH>,
+                         <GIC_SPI 489 IRQ_TYPE_EDGE_BOTH>;
             interrupt-names = "hs_phy_irq", "ss_phy_irq",
                           "dm_hs_phy_irq", "dp_hs_phy_irq";
 
diff --git a/Documentation/devicetree/bindings/usb/usb-hcd.yaml b/Documentation/devicetree/bindings/usb/usb-hcd.yaml
index 692dd60e3f73f3..45a19d4928afa6 100644
--- a/Documentation/devicetree/bindings/usb/usb-hcd.yaml
+++ b/Documentation/devicetree/bindings/usb/usb-hcd.yaml
@@ -41,7 +41,7 @@ examples:
   - |
     usb {
         phys = <&usb2_phy1>, <&usb3_phy1>;
-        phy-names = "usb";
+        phy-names = "usb2", "usb3";
         #address-cells = <1>;
         #size-cells = <0>;
 
diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst
index 57c6ae23b3fcf9..cc4626d6ee4f83 100644
--- a/Documentation/filesystems/erofs.rst
+++ b/Documentation/filesystems/erofs.rst
@@ -91,6 +91,10 @@ compatibility checking tool (fsck.erofs), and a debugging tool (dump.erofs):
 
 - git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs-utils.git
 
+For more information, please also refer to the documentation site:
+
+- https://erofs.docs.kernel.org
+
 Bugs and patches are welcome, please kindly help us and send to the following
 linux-erofs mailing list:
 
diff --git a/Documentation/filesystems/fuse-io.rst b/Documentation/filesystems/fuse-io.rst
index 255a368fe534b4..6464de4266ad50 100644
--- a/Documentation/filesystems/fuse-io.rst
+++ b/Documentation/filesystems/fuse-io.rst
@@ -15,7 +15,8 @@ The direct-io mode can be selected with the FOPEN_DIRECT_IO flag in the
 FUSE_OPEN reply.
 
 In direct-io mode the page cache is completely bypassed for reads and writes.
-No read-ahead takes place. Shared mmap is disabled.
+No read-ahead takes place. Shared mmap is disabled by default. To allow shared
+mmap, the FUSE_DIRECT_IO_ALLOW_MMAP flag may be enabled in the FUSE_INIT reply.
 
 In cached mode reads may be satisfied from the page cache, and data may be
 read-ahead by the kernel to fill the cache.  The cache is always kept consistent
diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index c6ba4889575a09..572d83a414d0d0 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -71,6 +71,10 @@ definitions:
         name: roce-bit
       -
         name: migratable-bit
+      -
+        name: ipsec-crypto-bit
+      -
+        name: ipsec-packet-bit
   -
     type: enum
     name: sb-threshold-type
diff --git a/Documentation/networking/smc-sysctl.rst b/Documentation/networking/smc-sysctl.rst
index 6d8acdbe9be1de..769149d98773a2 100644
--- a/Documentation/networking/smc-sysctl.rst
+++ b/Documentation/networking/smc-sysctl.rst
@@ -44,18 +44,16 @@ smcr_testlink_time - INTEGER
 
 wmem - INTEGER
 	Initial size of send buffer used by SMC sockets.
-	The default value inherits from net.ipv4.tcp_wmem[1].
 
 	The minimum value is 16KiB and there is no hard limit for max value, but
 	only allowed 512KiB for SMC-R and 1MiB for SMC-D.
 
-	Default: 16K
+	Default: 64KiB
 
 rmem - INTEGER
 	Initial size of receive buffer (RMB) used by SMC sockets.
-	The default value inherits from net.ipv4.tcp_rmem[1].
 
 	The minimum value is 16KiB and there is no hard limit for max value, but
 	only allowed 512KiB for SMC-R and 1MiB for SMC-D.
 
-	Default: 128K
+	Default: 64KiB
diff --git a/Documentation/networking/tcp_ao.rst b/Documentation/networking/tcp_ao.rst
index cfa5bf1cc5423c..8a58321acce72f 100644
--- a/Documentation/networking/tcp_ao.rst
+++ b/Documentation/networking/tcp_ao.rst
@@ -99,7 +99,7 @@ also [6.1]::
    when it is no longer considered permitted.
 
 Linux TCP-AO will try its best to prevent you from removing a key that's
-being used, considering it a key management failure. But sine keeping
+being used, considering it a key management failure. But since keeping
 an outdated key may become a security issue and as a peer may
 unintentionally prevent the removal of an old key by always setting
 it as RNextKeyID - a forced key removal mechanism is provided, where
diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index 7feacc20835e42..84ee60fceef24c 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -193,9 +193,23 @@ Review timelines
 Generally speaking, the patches get triaged quickly (in less than
 48h). But be patient, if your patch is active in patchwork (i.e. it's
 listed on the project's patch list) the chances it was missed are close to zero.
-Asking the maintainer for status updates on your
-patch is a good way to ensure your patch is ignored or pushed to the
-bottom of the priority list.
+
+The high volume of development on netdev makes reviewers move on
+from discussions relatively quickly. New comments and replies
+are very unlikely to arrive after a week of silence. If a patch
+is no longer active in patchwork and the thread went idle for more
+than a week - clarify the next steps and/or post the next version.
+
+For RFC postings specifically, if nobody responded in a week - reviewers
+either missed the posting or have no strong opinions. If the code is ready,
+repost as a PATCH.
+
+Emails saying just "ping" or "bump" are considered rude. If you can't figure
+out the status of the patch from patchwork or where the discussion has
+landed - describe your best guess and ask if it's correct. For example::
+
+  I don't understand what the next steps are. Person X seems to be unhappy
+  with A, should I do B and repost the patches?
 
 .. _Changes requested:
 
diff --git a/Documentation/trace/coresight/coresight.rst b/Documentation/trace/coresight/coresight.rst
index 4a71ea6cb39076..826e59a698da19 100644
--- a/Documentation/trace/coresight/coresight.rst
+++ b/Documentation/trace/coresight/coresight.rst
@@ -130,7 +130,7 @@ Misc:
 Device Tree Bindings
 --------------------
 
-See Documentation/devicetree/bindings/arm/arm,coresight-\*.yaml for details.
+See ``Documentation/devicetree/bindings/arm/arm,coresight-*.yaml`` for details.
 
 As of this writing drivers for ITM, STMs and CTIs are not provided but are
 expected to be added as the solution matures.
diff --git a/Documentation/trace/fprobetrace.rst b/Documentation/trace/fprobetrace.rst
index 8e9bebcf0a2e8f..e35e6b18df40cd 100644
--- a/Documentation/trace/fprobetrace.rst
+++ b/Documentation/trace/fprobetrace.rst
@@ -59,8 +59,12 @@ Synopsis of fprobe-events
                   and bitfield are supported.
 
   (\*1) This is available only when BTF is enabled.
-  (\*2) only for the probe on function entry (offs == 0).
-  (\*3) only for return probe.
+  (\*2) only for the probe on function entry (offs == 0). Note, this argument access
+        is best effort, because depending on the argument type, it may be passed on
+        the stack. But this only support the arguments via registers.
+  (\*3) only for return probe. Note that this is also best effort. Depending on the
+        return value type, it might be passed via a pair of registers. But this only
+        accesses one register.
   (\*4) this is useful for fetching a field of data structures.
   (\*5) "u" means user-space dereference.
 
diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index 8a2dfee3814544..bf9cecb69fc9e3 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -61,8 +61,12 @@ Synopsis of kprobe_events
 		  (x8/x16/x32/x64), "char", "string", "ustring", "symbol", "symstr"
                   and bitfield are supported.
 
-  (\*1) only for the probe on function entry (offs == 0).
-  (\*2) only for return probe.
+  (\*1) only for the probe on function entry (offs == 0). Note, this argument access
+        is best effort, because depending on the argument type, it may be passed on
+        the stack. But this only support the arguments via registers.
+  (\*2) only for return probe. Note that this is also best effort. Depending on the
+        return value type, it might be passed via a pair of registers. But this only
+        accesses one register.
   (\*3) this is useful for fetching a field of data structures.
   (\*4) "u" means user-space dereference. See :ref:`user_mem_access`.
 
diff --git a/Documentation/translations/zh_CN/arch/loongarch/introduction.rst b/Documentation/translations/zh_CN/arch/loongarch/introduction.rst
index 59d6bf33050cb8..bf463c5a4c5144 100644
--- a/Documentation/translations/zh_CN/arch/loongarch/introduction.rst
+++ b/Documentation/translations/zh_CN/arch/loongarch/introduction.rst
@@ -338,9 +338,9 @@ Loongson与LoongArch的开发者网站（软件与文档资源）：
 
 LoongArch指令集架构的文档：
 
-  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.02-CN.pdf （中文版）
+  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.10-CN.pdf （中文版）
 
-  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.02-EN.pdf （英文版）
+  https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.10-EN.pdf （英文版）
 
 LoongArch的ELF psABI文档：
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 350d00657f6b59..7cef2d2ef8d708 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -171,13 +171,10 @@ S:	Supported
 F:	drivers/soc/fujitsu/a64fx-diag.c
 
 A8293 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/a8293*
 
 AACRAID SCSI RAID DRIVER
@@ -576,23 +573,17 @@ F:	drivers/iio/accel/adxl372_i2c.c
 F:	drivers/iio/accel/adxl372_spi.c
 
 AF9013 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/af9013*
 
 AF9033 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/af9033*
 
 AFFS FILE SYSTEM
@@ -650,13 +641,10 @@ F:	fs/aio.c
 F:	include/linux/*aio*.h
 
 AIRSPY MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/airspy/
 
 ALACRITECH GIGABIT ETHERNET DRIVER
@@ -2155,6 +2143,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
 F:	arch/arm/boot/dts/nxp/imx/
 F:	arch/arm/boot/dts/nxp/mxs/
+F:	arch/arm64/boot/dts/freescale/
 X:	arch/arm64/boot/dts/freescale/fsl-*
 X:	arch/arm64/boot/dts/freescale/qoriq-*
 X:	drivers/media/i2c/
@@ -2535,7 +2524,7 @@ F:	drivers/*/*/*wpcm*
 F:	drivers/*/*wpcm*
 
 ARM/NXP S32G ARCHITECTURE
-M:	Chester Lin <clin@suse.com>
+M:	Chester Lin <chester62515@gmail.com>
 R:	Andreas Färber <afaerber@suse.de>
 R:	Matthias Brugger <mbrugger@suse.com>
 R:	NXP S32 Linux Team <s32@nxp.com>
@@ -5076,7 +5065,6 @@ CLANG CONTROL FLOW INTEGRITY SUPPORT
 M:	Sami Tolvanen <samitolvanen@google.com>
 M:	Kees Cook <keescook@chromium.org>
 R:	Nathan Chancellor <nathan@kernel.org>
-R:	Nick Desaulniers <ndesaulniers@google.com>
 L:	llvm@lists.linux.dev
 S:	Supported
 B:	https://github.com/ClangBuiltLinux/linux/issues
@@ -5091,8 +5079,9 @@ F:	.clang-format
 
 CLANG/LLVM BUILD SUPPORT
 M:	Nathan Chancellor <nathan@kernel.org>
-M:	Nick Desaulniers <ndesaulniers@google.com>
-R:	Tom Rix <trix@redhat.com>
+R:	Nick Desaulniers <ndesaulniers@google.com>
+R:	Bill Wendling <morbo@google.com>
+R:	Justin Stitt <justinstitt@google.com>
 L:	llvm@lists.linux.dev
 S:	Supported
 W:	https://clangbuiltlinux.github.io/
@@ -5242,7 +5231,6 @@ F:	drivers/platform/x86/compal-laptop.c
 
 COMPILER ATTRIBUTES
 M:	Miguel Ojeda <ojeda@kernel.org>
-R:	Nick Desaulniers <ndesaulniers@google.com>
 S:	Maintained
 F:	include/linux/compiler_attributes.h
 
@@ -5605,13 +5593,10 @@ F:	Documentation/driver-api/media/drivers/cx88*
 F:	drivers/media/pci/cx88/
 
 CXD2820R MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/cxd2820r*
 
 CXGB3 ETHERNET DRIVER (CXGB3)
@@ -5724,13 +5709,10 @@ F:	Documentation/devicetree/bindings/input/cypress-sf.yaml
 F:	drivers/input/keyboard/cypress-sf.c
 
 CYPRESS_FIRMWARE MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/common/cypress_firmware*
 
 CYTTSP TOUCHSCREEN DRIVER
@@ -6068,10 +6050,8 @@ M:	Mikulas Patocka <mpatocka@redhat.com>
 M:	dm-devel@lists.linux.dev
 L:	dm-devel@lists.linux.dev
 S:	Maintained
-W:	http://sources.redhat.com/dm
 Q:	http://patchwork.kernel.org/project/dm-devel/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm.git
-T:	quilt http://people.redhat.com/agk/patches/linux/editing/
 F:	Documentation/admin-guide/device-mapper/
 F:	drivers/md/Kconfig
 F:	drivers/md/Makefile
@@ -7320,53 +7300,38 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/pci/dt3155/
 
 DVB_USB_AF9015 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/af9015*
 
 DVB_USB_AF9035 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/af9035*
 
 DVB_USB_ANYSEE MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/anysee*
 
 DVB_USB_AU6610 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/au6610*
 
 DVB_USB_CE6230 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/ce6230*
 
 DVB_USB_CXUSB MEDIA DRIVER
@@ -7380,22 +7345,17 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/usb/dvb-usb/cxusb*
 
 DVB_USB_EC168 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/ec168*
 
 DVB_USB_GL861 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/gl861*
 
 DVB_USB_MXL111SF MEDIA DRIVER
@@ -7409,23 +7369,18 @@ T:	git git://linuxtv.org/mkrufky/mxl111sf.git
 F:	drivers/media/usb/dvb-usb-v2/mxl111sf*
 
 DVB_USB_RTL28XXU MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/rtl28xxu*
 
 DVB_USB_V2 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/dvb-usb-v2/dvb_usb*
 F:	drivers/media/usb/dvb-usb-v2/usb_urb.c
 
@@ -7467,13 +7422,10 @@ F:	Documentation/devicetree/bindings/input/e3x0-button.txt
 F:	drivers/input/misc/e3x0-button.c
 
 E4000 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/e4000*
 
 EARTH_PT1 MEDIA DRIVER
@@ -7489,13 +7441,10 @@ S:	Odd Fixes
 F:	drivers/media/pci/pt3/
 
 EC100 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/ec100*
 
 ECRYPT FILE SYSTEM
@@ -7855,6 +7804,7 @@ R:	Yue Hu <huyue2@coolpad.com>
 R:	Jeffle Xu <jefflexu@linux.alibaba.com>
 L:	linux-erofs@lists.ozlabs.org
 S:	Maintained
+W:	https://erofs.docs.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git
 F:	Documentation/ABI/testing/sysfs-fs-erofs
 F:	Documentation/filesystems/erofs.rst
@@ -8112,13 +8062,10 @@ F:	drivers/media/tuners/fc0011.c
 F:	drivers/media/tuners/fc0011.h
 
 FC2580 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/fc2580*
 
 FCOE SUBSYSTEM (libfc, libfcoe, fcoe)
@@ -8950,7 +8897,6 @@ S:	Maintained
 F:	scripts/get_maintainer.pl
 
 GFS2 FILE SYSTEM
-M:	Bob Peterson <rpeterso@redhat.com>
 M:	Andreas Gruenbacher <agruenba@redhat.com>
 L:	gfs2@lists.linux.dev
 S:	Supported
@@ -9249,13 +9195,10 @@ F:	include/trace/events/habanalabs.h
 F:	include/uapi/drm/habanalabs_accel.h
 
 HACKRF MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/hackrf/
 
 HANDSHAKE UPCALL FOR TRANSPORT LAYER SECURITY
@@ -9581,6 +9524,7 @@ F:	drivers/bus/hisi_lpc.c
 HISILICON NETWORK SUBSYSTEM 3 DRIVER (HNS3)
 M:	Yisen Zhuang <yisen.zhuang@huawei.com>
 M:	Salil Mehta <salil.mehta@huawei.com>
+M:	Jijie Shao <shaojijie@huawei.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 W:	http://www.hisilicon.com
@@ -9628,6 +9572,7 @@ F:	drivers/crypto/hisilicon/sgl.c
 F:	include/linux/hisi_acc_qm.h
 
 HISILICON ROCE DRIVER
+M:	Chengchang Tang <tangchengchang@huawei.com>
 M:	Junxian Huang <huangjunxian6@hisilicon.com>
 L:	linux-rdma@vger.kernel.org
 S:	Maintained
@@ -11025,7 +10970,6 @@ F:	drivers/net/wireless/intel/iwlwifi/
 
 INTEL WMI SLIM BOOTLOADER (SBL) FIRMWARE UPDATE DRIVER
 M:	Jithu Joseph <jithu.joseph@intel.com>
-R:	Maurice Ma <maurice.ma@intel.com>
 S:	Maintained
 W:	https://slimbootloader.github.io/security/firmware-update.html
 F:	drivers/platform/x86/intel/wmi/sbl-fw-update.c
@@ -11329,13 +11273,10 @@ F:	Documentation/hwmon/it87.rst
 F:	drivers/hwmon/it87.c
 
 IT913X MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/it913x*
 
 ITE IT66121 HDMI BRIDGE DRIVER
@@ -11517,7 +11458,6 @@ F:	fs/autofs/
 KERNEL BUILD + files below scripts/ (unless maintained elsewhere)
 M:	Masahiro Yamada <masahiroy@kernel.org>
 R:	Nathan Chancellor <nathan@kernel.org>
-R:	Nick Desaulniers <ndesaulniers@google.com>
 R:	Nicolas Schier <nicolas@fjasle.eu>
 L:	linux-kbuild@vger.kernel.org
 S:	Maintained
@@ -12209,6 +12149,13 @@ F:	include/linux/nd.h
 F:	include/uapi/linux/ndctl.h
 F:	tools/testing/nvdimm/
 
+LIBRARY CODE
+M:	Andrew Morton <akpm@linux-foundation.org>
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-nonmm-unstable
+F:	lib/*
+
 LICENSES and SPDX stuff
 M:	Thomas Gleixner <tglx@linutronix.de>
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
@@ -12241,6 +12188,8 @@ LINUX FOR POWERPC (32-BIT AND 64-BIT)
 M:	Michael Ellerman <mpe@ellerman.id.au>
 R:	Nicholas Piggin <npiggin@gmail.com>
 R:	Christophe Leroy <christophe.leroy@csgroup.eu>
+R:	Aneesh Kumar K.V <aneesh.kumar@kernel.org>
+R:	Naveen N. Rao <naveen.n.rao@linux.ibm.com>
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Supported
 W:	https://github.com/linuxppc/wiki/wiki
@@ -12688,13 +12637,10 @@ W:	http://www.tazenda.demon.co.uk/phil/linux-hp
 F:	arch/m68k/hp300/
 
 M88DS3103 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/m88ds3103*
 
 M88RS2000 MEDIA DRIVER
@@ -13779,7 +13725,6 @@ F:	drivers/net/ethernet/mellanox/mlxfw/
 MELLANOX HARDWARE PLATFORM SUPPORT
 M:	Hans de Goede <hdegoede@redhat.com>
 M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
-M:	Mark Gross <markgross@kernel.org>
 M:	Vadim Pasternak <vadimp@nvidia.com>
 L:	platform-driver-x86@vger.kernel.org
 S:	Supported
@@ -14388,7 +14333,6 @@ F:	drivers/platform/surface/surface_gpe.c
 MICROSOFT SURFACE HARDWARE PLATFORM SUPPORT
 M:	Hans de Goede <hdegoede@redhat.com>
 M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
-M:	Mark Gross <markgross@kernel.org>
 M:	Maximilian Luz <luzmaximilian@gmail.com>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
@@ -14590,20 +14534,16 @@ F:	include/asm-generic/tlb.h
 F:	mm/mmu_gather.c
 
 MN88472 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 F:	drivers/media/dvb-frontends/mn88472*
 
 MN88473 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 F:	drivers/media/dvb-frontends/mn88473*
 
@@ -14691,23 +14631,17 @@ S:	Orphan
 F:	drivers/platform/x86/msi-wmi.c
 
 MSI001 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/msi001*
 
 MSI2500 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/usb/msi2500/
 
 MSTAR INTERRUPT CONTROLLER DRIVER
@@ -14995,6 +14929,7 @@ M:	Jakub Kicinski <kuba@kernel.org>
 M:	Paolo Abeni <pabeni@redhat.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
+P:	Documentation/process/maintainer-netdev.rst
 Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
@@ -15046,6 +14981,7 @@ M:	Jakub Kicinski <kuba@kernel.org>
 M:	Paolo Abeni <pabeni@redhat.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
+P:	Documentation/process/maintainer-netdev.rst
 Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 B:	mailto:netdev@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
@@ -15056,6 +14992,7 @@ F:	Documentation/networking/
 F:	Documentation/process/maintainer-netdev.rst
 F:	Documentation/userspace-api/netlink/
 F:	include/linux/in.h
+F:	include/linux/indirect_call_wrapper.h
 F:	include/linux/net.h
 F:	include/linux/netdevice.h
 F:	include/net/
@@ -15068,6 +15005,7 @@ F:	lib/random32.c
 F:	net/
 F:	tools/net/
 F:	tools/testing/selftests/net/
+X:	net/9p/
 X:	net/bluetooth/
 
 NETWORKING [IPSEC]
@@ -17775,13 +17713,10 @@ F:	drivers/bus/fsl-mc/
 F:	include/uapi/linux/fsl_mc.h
 
 QT1010 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/qt1010*
 
 QUALCOMM ATH12K WIRELESS DRIVER
@@ -17948,6 +17883,8 @@ L:	iommu@lists.linux.dev
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
 F:	drivers/iommu/arm/arm-smmu/qcom_iommu.c
+F:	drivers/iommu/arm/arm-smmu/arm-smmu-qcom*
+F:	drivers/iommu/msm_iommu*
 
 QUALCOMM IPC ROUTER (QRTR) DRIVER
 M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
@@ -18834,33 +18771,24 @@ S:	Maintained
 F:	drivers/tty/rpmsg_tty.c
 
 RTL2830 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/rtl2830*
 
 RTL2832 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/rtl2832*
 
 RTL2832_SDR MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/rtl2832_sdr*
 
 RTL8180 WIRELESS DRIVER
@@ -19637,7 +19565,6 @@ S:	Maintained
 F:	drivers/misc/sgi-xp/
 
 SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS
-M:	Karsten Graul <kgraul@linux.ibm.com>
 M:	Wenjia Zhang <wenjia@linux.ibm.com>
 M:	Jan Karcher <jaka@linux.ibm.com>
 R:	D. Wythe <alibuda@linux.alibaba.com>
@@ -19670,13 +19597,10 @@ F:	drivers/media/platform/renesas/sh_vou.c
 F:	include/media/drv-intf/sh_vou.h
 
 SI2157 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/si2157*
 
 SI2165 MEDIA DRIVER
@@ -19688,13 +19612,10 @@ Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 F:	drivers/media/dvb-frontends/si2165*
 
 SI2168 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/si2168*
 
 SI470X FM RADIO RECEIVER I2C DRIVER
@@ -21196,33 +21117,24 @@ W:	http://tcp-lp-mod.sourceforge.net/
 F:	net/ipv4/tcp_lp.c
 
 TDA10071 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/dvb-frontends/tda10071*
 
 TDA18212 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/tda18212*
 
 TDA18218 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/tda18218*
 
 TDA18250 MEDIA DRIVER
@@ -21769,7 +21681,9 @@ F:	Documentation/devicetree/bindings/counter/ti-eqep.yaml
 F:	drivers/counter/ti-eqep.c
 
 TI ETHERNET SWITCH DRIVER (CPSW)
-R:	Grygorii Strashko <grygorii.strashko@ti.com>
+R:	Siddharth Vadapalli <s-vadapalli@ti.com>
+R:	Ravi Gunasekaran <r-gunasekaran@ti.com>
+R:	Roger Quadros <rogerq@kernel.org>
 L:	linux-omap@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -21793,6 +21707,15 @@ F:	Documentation/devicetree/bindings/media/i2c/ti,ds90*
 F:	drivers/media/i2c/ds90*
 F:	include/media/i2c/ds90*
 
+TI ICSSG ETHERNET DRIVER (ICSSG)
+R:	MD Danish Anwar <danishanwar@ti.com>
+R:	Roger Quadros <rogerq@kernel.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/net/ti,icss*.yaml
+F:	drivers/net/ethernet/ti/icssg/*
+
 TI J721E CSI2RX DRIVER
 M:	Jai Luthra <j-luthra@ti.com>
 L:	linux-media@vger.kernel.org
@@ -22068,6 +21991,7 @@ F:	drivers/watchdog/tqmx86_wdt.c
 TRACING
 M:	Steven Rostedt <rostedt@goodmis.org>
 M:	Masami Hiramatsu <mhiramat@kernel.org>
+R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
 L:	linux-kernel@vger.kernel.org
 L:	linux-trace-kernel@vger.kernel.org
 S:	Maintained
@@ -22146,13 +22070,10 @@ F:	include/uapi/linux/serial_core.h
 F:	include/uapi/linux/tty.h
 
 TUA9001 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org
-W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/tua9001*
 
 TULIP NETWORK DRIVERS
@@ -23198,13 +23119,6 @@ W:	https://linuxtv.org
 T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/test-drivers/vivid/*
 
-VLYNQ BUS
-M:	Florian Fainelli <f.fainelli@gmail.com>
-L:	openwrt-devel@lists.openwrt.org (subscribers-only)
-S:	Maintained
-F:	drivers/vlynq/vlynq.c
-F:	include/linux/vlynq.h
-
 VM SOCKETS (AF_VSOCK)
 M:	Stefano Garzarella <sgarzare@redhat.com>
 L:	virtualization@lists.linux.dev
@@ -23661,7 +23575,6 @@ F:	drivers/platform/x86/x86-android-tablets/
 X86 PLATFORM DRIVERS
 M:	Hans de Goede <hdegoede@redhat.com>
 M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
-M:	Mark Gross <markgross@kernel.org>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 Q:	https://patchwork.kernel.org/project/platform-driver-x86/list/
@@ -23699,6 +23612,20 @@ F:	arch/x86/kernel/dumpstack.c
 F:	arch/x86/kernel/stacktrace.c
 F:	arch/x86/kernel/unwind_*.c
 
+X86 TRUST DOMAIN EXTENSIONS (TDX)
+M:	Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+R:	Dave Hansen <dave.hansen@linux.intel.com>
+L:	x86@kernel.org
+L:	linux-coco@lists.linux.dev
+S:	Supported
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/tdx
+F:	arch/x86/boot/compressed/tdx*
+F:	arch/x86/coco/tdx/
+F:	arch/x86/include/asm/shared/tdx.h
+F:	arch/x86/include/asm/tdx.h
+F:	arch/x86/virt/vmx/tdx/
+F:	drivers/virt/coco/tdx-guest
+
 X86 VDSO
 M:	Andy Lutomirski <luto@kernel.org>
 L:	linux-kernel@vger.kernel.org
@@ -23879,8 +23806,7 @@ T:	git git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git
 P:	Documentation/filesystems/xfs-maintainer-entry-profile.rst
 F:	Documentation/ABI/testing/sysfs-fs-xfs
 F:	Documentation/admin-guide/xfs.rst
-F:	Documentation/filesystems/xfs-delayed-logging-design.rst
-F:	Documentation/filesystems/xfs-self-describing-metadata.rst
+F:	Documentation/filesystems/xfs-*
 F:	fs/xfs/
 F:	include/uapi/linux/dqblk_xfs.h
 F:	include/uapi/linux/fsmap.h
@@ -24092,20 +24018,16 @@ S:	Orphan
 F:	drivers/net/wireless/zydas/zd1211rw/
 
 ZD1301 MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org/
-W:	http://palosaari.fi/linux/
 Q:	https://patchwork.linuxtv.org/project/linux-media/list/
 F:	drivers/media/usb/dvb-usb-v2/zd1301*
 
 ZD1301_DEMOD MEDIA DRIVER
-M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	https://linuxtv.org/
-W:	http://palosaari.fi/linux/
 Q:	https://patchwork.linuxtv.org/project/linux-media/list/
 F:	drivers/media/dvb-frontends/zd1301_demod*
 
diff --git a/Makefile b/Makefile
index a82587fbdad38a..ee995fc2b0e5c3 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
-PATCHLEVEL = 6
+PATCHLEVEL = 7
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc7
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 3162db540ee96c..1b0483c51cc169 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -49,7 +49,6 @@ config ARC
 	select OF
 	select OF_EARLY_FLATTREE
 	select PCI_SYSCALL if PCI
-	select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING
 	select HAVE_ARCH_JUMP_LABEL if ISA_ARCV2 && !CPU_ENDIAN_BE32
 	select TRACE_IRQFLAGS_SUPPORT
 
@@ -232,10 +231,6 @@ config ARC_CACHE_PAGES
 	  Note that Global I/D ENABLE + Per Page DISABLE works but corollary
 	  Global DISABLE + Per Page ENABLE won't work
 
-config ARC_CACHE_VIPT_ALIASING
-	bool "Support VIPT Aliasing D$"
-	depends on ARC_HAS_DCACHE && ISA_ARCOMPACT
-
 endif #ARC_CACHE
 
 config ARC_HAS_ICCM
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index bd5b1a9a054402..563af3e75f01f2 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -44,31 +44,10 @@ void dma_cache_wback(phys_addr_t start, unsigned long sz);
 
 #define flush_cache_dup_mm(mm)			/* called on fork (VIVT only) */
 
-#ifndef CONFIG_ARC_CACHE_VIPT_ALIASING
-
 #define flush_cache_mm(mm)			/* called on munmap/exit */
 #define flush_cache_range(mm, u_vstart, u_vend)
 #define flush_cache_page(vma, u_vaddr, pfn)	/* PF handling/COW-break */
 
-#else	/* VIPT aliasing dcache */
-
-/* To clear out stale userspace mappings */
-void flush_cache_mm(struct mm_struct *mm);
-void flush_cache_range(struct vm_area_struct *vma,
-	unsigned long start,unsigned long end);
-void flush_cache_page(struct vm_area_struct *vma,
-	unsigned long user_addr, unsigned long page);
-
-/*
- * To make sure that userspace mapping is flushed to memory before
- * get_user_pages() uses a kernel mapping to access the page
- */
-#define ARCH_HAS_FLUSH_ANON_PAGE
-void flush_anon_page(struct vm_area_struct *vma,
-	struct page *page, unsigned long u_vaddr);
-
-#endif	/* CONFIG_ARC_CACHE_VIPT_ALIASING */
-
 /*
  * A new pagecache page has PG_arch_1 clear - thus dcache dirty by default
  * This works around some PIO based drivers which don't call flush_dcache_page
@@ -76,28 +55,6 @@ void flush_anon_page(struct vm_area_struct *vma,
  */
 #define PG_dc_clean	PG_arch_1
 
-#define CACHE_COLORS_NUM	4
-#define CACHE_COLORS_MSK	(CACHE_COLORS_NUM - 1)
-#define CACHE_COLOR(addr)	(((unsigned long)(addr) >> (PAGE_SHIFT)) & CACHE_COLORS_MSK)
-
-/*
- * Simple wrapper over config option
- * Bootup code ensures that hardware matches kernel configuration
- */
-static inline int cache_is_vipt_aliasing(void)
-{
-	return IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING);
-}
-
-/*
- * checks if two addresses (after page aligning) index into same cache set
- */
-#define addr_not_cache_congruent(addr1, addr2)				\
-({									\
-	cache_is_vipt_aliasing() ? 					\
-		(CACHE_COLOR(addr1) != CACHE_COLOR(addr2)) : 0;		\
-})
-
 #define copy_to_user_page(vma, page, vaddr, dst, src, len)		\
 do {									\
 	memcpy(dst, src, len);						\
diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h
index 4d13320e0c1b63..3802a2daaf8692 100644
--- a/arch/arc/include/asm/entry-arcv2.h
+++ b/arch/arc/include/asm/entry-arcv2.h
@@ -291,4 +291,36 @@
 				/* M = 8-1  N = 8 */
 .endm
 
+.macro SAVE_ABI_CALLEE_REGS
+	push	r13
+	push	r14
+	push	r15
+	push	r16
+	push	r17
+	push	r18
+	push	r19
+	push	r20
+	push	r21
+	push	r22
+	push	r23
+	push	r24
+	push	r25
+.endm
+
+.macro RESTORE_ABI_CALLEE_REGS
+	pop	r25
+	pop	r24
+	pop	r23
+	pop	r22
+	pop	r21
+	pop	r20
+	pop	r19
+	pop	r18
+	pop	r17
+	pop	r16
+	pop	r15
+	pop	r14
+	pop	r13
+.endm
+
 #endif
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index a0e760eb35a80e..92c3e9f1325219 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -33,6 +33,91 @@
 #include <asm/irqflags-compact.h>
 #include <asm/thread_info.h>	/* For THREAD_SIZE */
 
+/* Note on the LD/ST addr modes with addr reg wback
+ *
+ * LD.a same as LD.aw
+ *
+ * LD.a    reg1, [reg2, x]  => Pre Incr
+ *      Eff Addr for load = [reg2 + x]
+ *
+ * LD.ab   reg1, [reg2, x]  => Post Incr
+ *      Eff Addr for load = [reg2]
+ */
+
+.macro PUSHAX aux
+	lr	r9, [\aux]
+	push	r9
+.endm
+
+.macro POPAX aux
+	pop	r9
+	sr	r9, [\aux]
+.endm
+
+.macro  SAVE_R0_TO_R12
+	push	r0
+	push	r1
+	push	r2
+	push	r3
+	push	r4
+	push	r5
+	push	r6
+	push	r7
+	push	r8
+	push	r9
+	push	r10
+	push	r11
+	push	r12
+.endm
+
+.macro RESTORE_R12_TO_R0
+	pop	r12
+	pop	r11
+	pop	r10
+	pop	r9
+	pop	r8
+	pop	r7
+	pop	r6
+	pop	r5
+	pop	r4
+	pop	r3
+	pop	r2
+	pop	r1
+	pop	r0
+.endm
+
+.macro SAVE_ABI_CALLEE_REGS
+	push	r13
+	push	r14
+	push	r15
+	push	r16
+	push	r17
+	push	r18
+	push	r19
+	push	r20
+	push	r21
+	push	r22
+	push	r23
+	push	r24
+	push	r25
+.endm
+
+.macro RESTORE_ABI_CALLEE_REGS
+	pop	r25
+	pop	r24
+	pop	r23
+	pop	r22
+	pop	r21
+	pop	r20
+	pop	r19
+	pop	r18
+	pop	r17
+	pop	r16
+	pop	r15
+	pop	r14
+	pop	r13
+.endm
+
 /*--------------------------------------------------------------
  * Switch to Kernel Mode stack if SP points to User Mode stack
  *
@@ -235,7 +320,7 @@
 	SWITCH_TO_KERNEL_STK
 
 
-	PUSH	0x003\LVL\()abcd    /* Dummy ECR */
+	st.a	0x003\LVL\()abcd, [sp, -4]	/* Dummy ECR */
 	sub	sp, sp, 8	    /* skip orig_r0 (not needed)
 				       skip pt_regs->sp, already saved above */
 
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index 49c2e090cb5c1f..cf1ba376e992c6 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -21,114 +21,12 @@
 #include <asm/entry-arcv2.h>
 #endif
 
-/* Note on the LD/ST addr modes with addr reg wback
- *
- * LD.a same as LD.aw
- *
- * LD.a    reg1, [reg2, x]  => Pre Incr
- *      Eff Addr for load = [reg2 + x]
- *
- * LD.ab   reg1, [reg2, x]  => Post Incr
- *      Eff Addr for load = [reg2]
- */
-
-.macro PUSH reg
-	st.a	\reg, [sp, -4]
-.endm
-
-.macro PUSHAX aux
-	lr	r9, [\aux]
-	PUSH	r9
-.endm
-
-.macro POP reg
-	ld.ab	\reg, [sp, 4]
-.endm
-
-.macro POPAX aux
-	POP	r9
-	sr	r9, [\aux]
-.endm
-
-/*--------------------------------------------------------------
- * Helpers to save/restore Scratch Regs:
- * used by Interrupt/Exception Prologue/Epilogue
- *-------------------------------------------------------------*/
-.macro  SAVE_R0_TO_R12
-	PUSH	r0
-	PUSH	r1
-	PUSH	r2
-	PUSH	r3
-	PUSH	r4
-	PUSH	r5
-	PUSH	r6
-	PUSH	r7
-	PUSH	r8
-	PUSH	r9
-	PUSH	r10
-	PUSH	r11
-	PUSH	r12
-.endm
-
-.macro RESTORE_R12_TO_R0
-	POP	r12
-	POP	r11
-	POP	r10
-	POP	r9
-	POP	r8
-	POP	r7
-	POP	r6
-	POP	r5
-	POP	r4
-	POP	r3
-	POP	r2
-	POP	r1
-	POP	r0
-
-.endm
-
-/*--------------------------------------------------------------
- * Helpers to save/restore callee-saved regs:
- * used by several macros below
- *-------------------------------------------------------------*/
-.macro SAVE_R13_TO_R25
-	PUSH	r13
-	PUSH	r14
-	PUSH	r15
-	PUSH	r16
-	PUSH	r17
-	PUSH	r18
-	PUSH	r19
-	PUSH	r20
-	PUSH	r21
-	PUSH	r22
-	PUSH	r23
-	PUSH	r24
-	PUSH	r25
-.endm
-
-.macro RESTORE_R25_TO_R13
-	POP	r25
-	POP	r24
-	POP	r23
-	POP	r22
-	POP	r21
-	POP	r20
-	POP	r19
-	POP	r18
-	POP	r17
-	POP	r16
-	POP	r15
-	POP	r14
-	POP	r13
-.endm
-
 /*
  * save user mode callee regs as struct callee_regs
  *  - needed by fork/do_signal/unaligned-access-emulation.
  */
 .macro SAVE_CALLEE_SAVED_USER
-	SAVE_R13_TO_R25
+	SAVE_ABI_CALLEE_REGS
 .endm
 
 /*
@@ -136,18 +34,18 @@
  *  - could have been changed by ptrace tracer or unaligned-access fixup
  */
 .macro RESTORE_CALLEE_SAVED_USER
-	RESTORE_R25_TO_R13
+	RESTORE_ABI_CALLEE_REGS
 .endm
 
 /*
  * save/restore kernel mode callee regs at the time of context switch
  */
 .macro SAVE_CALLEE_SAVED_KERNEL
-	SAVE_R13_TO_R25
+	SAVE_ABI_CALLEE_REGS
 .endm
 
 .macro RESTORE_CALLEE_SAVED_KERNEL
-	RESTORE_R25_TO_R13
+	RESTORE_ABI_CALLEE_REGS
 .endm
 
 /*--------------------------------------------------------------
diff --git a/arch/arc/include/asm/hugepage.h b/arch/arc/include/asm/hugepage.h
index ef8d4166370c8d..8a2441670a8f67 100644
--- a/arch/arc/include/asm/hugepage.h
+++ b/arch/arc/include/asm/hugepage.h
@@ -10,6 +10,13 @@
 #include <linux/types.h>
 #include <asm-generic/pgtable-nopmd.h>
 
+/*
+ * Hugetlb definitions.
+ */
+#define HPAGE_SHIFT		PMD_SHIFT
+#define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
+#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
+
 static inline pte_t pmd_pte(pmd_t pmd)
 {
 	return __pte(pmd_val(pmd));
diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h
index de1566e32cb89d..68e8301c0df2c1 100644
--- a/arch/arc/include/asm/kprobes.h
+++ b/arch/arc/include/asm/kprobes.h
@@ -32,9 +32,6 @@ struct kprobe;
 
 void arch_remove_kprobe(struct kprobe *p);
 
-int kprobe_exceptions_notify(struct notifier_block *self,
-			     unsigned long val, void *data);
-
 struct prev_kprobe {
 	struct kprobe *kp;
 	unsigned long status;
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 4a2b30fb5a985e..00b9318e551e7e 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -54,6 +54,10 @@ struct pt_regs {
 	ecr_reg ecr;
 };
 
+struct callee_regs {
+	unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
+};
+
 #define MAX_REG_OFFSET offsetof(struct pt_regs, ecr)
 
 #else
@@ -92,16 +96,14 @@ struct pt_regs {
 	unsigned long status32;
 };
 
-#define MAX_REG_OFFSET offsetof(struct pt_regs, status32)
-
-#endif
-
-/* Callee saved registers - need to be saved only when you are scheduled out */
-
 struct callee_regs {
 	unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
 };
 
+#define MAX_REG_OFFSET offsetof(struct pt_regs, status32)
+
+#endif
+
 #define instruction_pointer(regs)	((regs)->ret)
 #define profile_pc(regs)		instruction_pointer(regs)
 
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 4dcf8589b708ac..d08a5092c2b4d4 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -153,7 +153,7 @@ static int arcv2_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len)
 {
 	int n = 0;
 #ifdef CONFIG_ISA_ARCV2
-	const char *release, *cpu_nm, *isa_nm = "ARCv2";
+	const char *release = "", *cpu_nm = "HS38", *isa_nm = "ARCv2";
 	int dual_issue = 0, dual_enb = 0, mpy_opt, present;
 	int bpu_full, bpu_cache, bpu_pred, bpu_ret_stk;
 	char mpy_nm[16], lpb_nm[32];
@@ -172,8 +172,6 @@ static int arcv2_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len)
 	 * releases only update it.
 	 */
 
-	cpu_nm = "HS38";
-
 	if (info->arcver > 0x50 && info->arcver <= 0x53) {
 		release = arc_hs_rel[info->arcver - 0x51].str;
 	} else {
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 0b3bb529d24632..8f6f4a5429646f 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -62,7 +62,7 @@ struct rt_sigframe {
 	unsigned int sigret_magic;
 };
 
-static int save_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs)
+static int save_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs)
 {
 	int err = 0;
 #ifndef CONFIG_ISA_ARCOMPACT
@@ -75,12 +75,12 @@ static int save_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs)
 #else
 	v2abi.r58 = v2abi.r59 = 0;
 #endif
-	err = __copy_to_user(&mctx->v2abi, &v2abi, sizeof(v2abi));
+	err = __copy_to_user(&mctx->v2abi, (void const *)&v2abi, sizeof(v2abi));
 #endif
 	return err;
 }
 
-static int restore_arcv2_regs(struct sigcontext *mctx, struct pt_regs *regs)
+static int restore_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs)
 {
 	int err = 0;
 #ifndef CONFIG_ISA_ARCOMPACT
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index f7e05c14663750..9106ceac323c43 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -145,10 +145,9 @@ dc_chk:
 	p_dc->sz_k = 1 << (dbcr.sz - 1);
 
 	n += scnprintf(buf + n, len - n,
-			"D-Cache\t\t: %uK, %dway/set, %uB Line, %s%s%s\n",
+			"D-Cache\t\t: %uK, %dway/set, %uB Line, %s%s\n",
 			p_dc->sz_k, assoc, p_dc->line_len,
 			vipt ? "VIPT" : "PIPT",
-			p_dc->colors > 1 ? " aliasing" : "",
 			IS_USED_CFG(CONFIG_ARC_HAS_DCACHE));
 
 slc_chk:
@@ -703,51 +702,10 @@ static inline void arc_slc_enable(void)
  * Exported APIs
  */
 
-/*
- * Handle cache congruency of kernel and userspace mappings of page when kernel
- * writes-to/reads-from
- *
- * The idea is to defer flushing of kernel mapping after a WRITE, possible if:
- *  -dcache is NOT aliasing, hence any U/K-mappings of page are congruent
- *  -U-mapping doesn't exist yet for page (finalised in update_mmu_cache)
- *  -In SMP, if hardware caches are coherent
- *
- * There's a corollary case, where kernel READs from a userspace mapped page.
- * If the U-mapping is not congruent to K-mapping, former needs flushing.
- */
 void flush_dcache_folio(struct folio *folio)
 {
-	struct address_space *mapping;
-
-	if (!cache_is_vipt_aliasing()) {
-		clear_bit(PG_dc_clean, &folio->flags);
-		return;
-	}
-
-	/* don't handle anon pages here */
-	mapping = folio_flush_mapping(folio);
-	if (!mapping)
-		return;
-
-	/*
-	 * pagecache page, file not yet mapped to userspace
-	 * Make a note that K-mapping is dirty
-	 */
-	if (!mapping_mapped(mapping)) {
-		clear_bit(PG_dc_clean, &folio->flags);
-	} else if (folio_mapped(folio)) {
-		/* kernel reading from page with U-mapping */
-		phys_addr_t paddr = (unsigned long)folio_address(folio);
-		unsigned long vaddr = folio_pos(folio);
-
-		/*
-		 * vaddr is not actually the virtual address, but is
-		 * congruent to every user mapping.
-		 */
-		if (addr_not_cache_congruent(paddr, vaddr))
-			__flush_dcache_pages(paddr, vaddr,
-						folio_nr_pages(folio));
-	}
+	clear_bit(PG_dc_clean, &folio->flags);
+	return;
 }
 EXPORT_SYMBOL(flush_dcache_folio);
 
@@ -921,44 +879,6 @@ noinline void flush_cache_all(void)
 
 }
 
-#ifdef CONFIG_ARC_CACHE_VIPT_ALIASING
-
-void flush_cache_mm(struct mm_struct *mm)
-{
-	flush_cache_all();
-}
-
-void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr,
-		      unsigned long pfn)
-{
-	phys_addr_t paddr = pfn << PAGE_SHIFT;
-
-	u_vaddr &= PAGE_MASK;
-
-	__flush_dcache_pages(paddr, u_vaddr, 1);
-
-	if (vma->vm_flags & VM_EXEC)
-		__inv_icache_pages(paddr, u_vaddr, 1);
-}
-
-void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
-		       unsigned long end)
-{
-	flush_cache_all();
-}
-
-void flush_anon_page(struct vm_area_struct *vma, struct page *page,
-		     unsigned long u_vaddr)
-{
-	/* TBD: do we really need to clear the kernel mapping */
-	__flush_dcache_pages((phys_addr_t)page_address(page), u_vaddr, 1);
-	__flush_dcache_pages((phys_addr_t)page_address(page),
-			    (phys_addr_t)page_address(page), 1);
-
-}
-
-#endif
-
 void copy_user_highpage(struct page *to, struct page *from,
 	unsigned long u_vaddr, struct vm_area_struct *vma)
 {
@@ -966,46 +886,11 @@ void copy_user_highpage(struct page *to, struct page *from,
 	struct folio *dst = page_folio(to);
 	void *kfrom = kmap_atomic(from);
 	void *kto = kmap_atomic(to);
-	int clean_src_k_mappings = 0;
-
-	/*
-	 * If SRC page was already mapped in userspace AND it's U-mapping is
-	 * not congruent with K-mapping, sync former to physical page so that
-	 * K-mapping in memcpy below, sees the right data
-	 *
-	 * Note that while @u_vaddr refers to DST page's userspace vaddr, it is
-	 * equally valid for SRC page as well
-	 *
-	 * For !VIPT cache, all of this gets compiled out as
-	 * addr_not_cache_congruent() is 0
-	 */
-	if (page_mapcount(from) && addr_not_cache_congruent(kfrom, u_vaddr)) {
-		__flush_dcache_pages((unsigned long)kfrom, u_vaddr, 1);
-		clean_src_k_mappings = 1;
-	}
 
 	copy_page(kto, kfrom);
 
-	/*
-	 * Mark DST page K-mapping as dirty for a later finalization by
-	 * update_mmu_cache(). Although the finalization could have been done
-	 * here as well (given that both vaddr/paddr are available).
-	 * But update_mmu_cache() already has code to do that for other
-	 * non copied user pages (e.g. read faults which wire in pagecache page
-	 * directly).
-	 */
 	clear_bit(PG_dc_clean, &dst->flags);
-
-	/*
-	 * if SRC was already usermapped and non-congruent to kernel mapping
-	 * sync the kernel mapping back to physical page
-	 */
-	if (clean_src_k_mappings) {
-		__flush_dcache_pages((unsigned long)kfrom,
-					(unsigned long)kfrom, 1);
-	} else {
-		clear_bit(PG_dc_clean, &src->flags);
-	}
+	clear_bit(PG_dc_clean, &src->flags);
 
 	kunmap_atomic(kto);
 	kunmap_atomic(kfrom);
@@ -1140,17 +1025,8 @@ static noinline void __init arc_cache_init_master(void)
 			      dc->line_len, L1_CACHE_BYTES);
 
 		/* check for D-Cache aliasing on ARCompact: ARCv2 has PIPT */
-		if (is_isa_arcompact()) {
-			int handled = IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING);
-
-			if (dc->colors > 1) {
-				if (!handled)
-					panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
-				if (CACHE_COLORS_NUM != dc->colors)
-					panic("CACHE_COLORS_NUM not optimized for config\n");
-			} else if (handled && dc->colors == 1) {
-				panic("Disable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
-			}
+		if (is_isa_arcompact() && dc->colors > 1) {
+			panic("Aliasing VIPT cache not supported\n");
 		}
 	}
 
diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c
index fce5fa2b4f5214..3c1c7ae732925c 100644
--- a/arch/arc/mm/mmap.c
+++ b/arch/arc/mm/mmap.c
@@ -14,10 +14,6 @@
 
 #include <asm/cacheflush.h>
 
-#define COLOUR_ALIGN(addr, pgoff)			\
-	((((addr) + SHMLBA - 1) & ~(SHMLBA - 1)) +	\
-	 (((pgoff) << PAGE_SHIFT) & (SHMLBA - 1)))
-
 /*
  * Ensure that shared mappings are correctly aligned to
  * avoid aliasing issues with VIPT caches.
@@ -31,21 +27,13 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
-	int do_align = 0;
-	int aliasing = cache_is_vipt_aliasing();
 	struct vm_unmapped_area_info info;
 
 	/*
-	 * We only need to do colour alignment if D cache aliases.
-	 */
-	if (aliasing)
-		do_align = filp || (flags & MAP_SHARED);
-
-	/*
 	 * We enforce the MAP_FIXED case.
 	 */
 	if (flags & MAP_FIXED) {
-		if (aliasing && flags & MAP_SHARED &&
+		if (flags & MAP_SHARED &&
 		    (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
 			return -EINVAL;
 		return addr;
@@ -55,10 +43,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		return -ENOMEM;
 
 	if (addr) {
-		if (do_align)
-			addr = COLOUR_ALIGN(addr, pgoff);
-		else
-			addr = PAGE_ALIGN(addr);
+		addr = PAGE_ALIGN(addr);
 
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
@@ -70,7 +55,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.length = len;
 	info.low_limit = mm->mmap_base;
 	info.high_limit = TASK_SIZE;
-	info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
+	info.align_mask = 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
 	return vm_unmapped_area(&info);
 }
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index e536b2dcd4b024..ad702b49aeb3b8 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -478,21 +478,15 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
 
 	create_tlb(vma, vaddr, ptep);
 
-	if (page == ZERO_PAGE(0)) {
+	if (page == ZERO_PAGE(0))
 		return;
-	}
 
 	/*
-	 * Exec page : Independent of aliasing/page-color considerations,
-	 *	       since icache doesn't snoop dcache on ARC, any dirty
-	 *	       K-mapping of a code page needs to be wback+inv so that
-	 *	       icache fetch by userspace sees code correctly.
-	 * !EXEC page: If K-mapping is NOT congruent to U-mapping, flush it
-	 *	       so userspace sees the right data.
-	 *  (Avoids the flush for Non-exec + congruent mapping case)
+	 * For executable pages, since icache doesn't snoop dcache, any
+	 * dirty K-mapping of a code page needs to be wback+inv so that
+	 * icache fetch by userspace sees code correctly.
 	 */
-	if ((vma->vm_flags & VM_EXEC) ||
-	     addr_not_cache_congruent(paddr, vaddr)) {
+	if (vma->vm_flags & VM_EXEC) {
 		struct folio *folio = page_folio(page);
 		int dirty = !test_and_set_bit(PG_dc_clean, &folio->flags);
 		if (dirty) {
diff --git a/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts b/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts
index 1ab8184302db44..5a2869a18bd555 100644
--- a/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts
+++ b/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts
@@ -36,9 +36,7 @@
 	gpios = <&gpio 42 GPIO_ACTIVE_HIGH>;
 };
 
-&leds {
-	/delete-node/ led_act;
-};
+/delete-node/ &led_act;
 
 &pm {
 	/delete-property/ system-power-controller;
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts b/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts
index a3f247c722b438..0342a79ccd5db2 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts
@@ -37,9 +37,9 @@
 
 &clks {
 	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
-			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>;
+			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>, <&clks IMX6QDL_CLK_ENET_REF_SEL>;
 	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
-				 <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>;
+				 <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, <&clk50m_phy>;
 };
 
 &hdmi {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi
index 4ffe99ed55ca2c..07dcecbe485dca 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi
@@ -121,6 +121,8 @@
 			max-speed = <100>;
 			interrupt-parent = <&gpio5>;
 			interrupts = <6 IRQ_TYPE_LEVEL_LOW>;
+			clocks = <&clks IMX6UL_CLK_ENET_REF>;
+			clock-names = "rmii-ref";
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
index 29b8fd03567a54..5387da8a2a0a37 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
@@ -454,7 +454,7 @@
 			};
 
 			gpt1: timer@302d0000 {
-				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
+				compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt";
 				reg = <0x302d0000 0x10000>;
 				interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX7D_GPT1_ROOT_CLK>,
@@ -463,7 +463,7 @@
 			};
 
 			gpt2: timer@302e0000 {
-				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
+				compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt";
 				reg = <0x302e0000 0x10000>;
 				interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX7D_GPT2_ROOT_CLK>,
@@ -473,7 +473,7 @@
 			};
 
 			gpt3: timer@302f0000 {
-				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
+				compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt";
 				reg = <0x302f0000 0x10000>;
 				interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX7D_GPT3_ROOT_CLK>,
@@ -483,7 +483,7 @@
 			};
 
 			gpt4: timer@30300000 {
-				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
+				compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt";
 				reg = <0x30300000 0x10000>;
 				interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX7D_GPT4_ROOT_CLK>,
diff --git a/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts b/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts
index a400c108f66a2d..6c5e6856648af9 100644
--- a/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts
+++ b/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts
@@ -8,6 +8,7 @@
 #include "imx28-lwe.dtsi"
 
 / {
+	model = "Liebherr XEA board";
 	compatible = "lwn,imx28-xea", "fsl,imx28";
 };
 
diff --git a/arch/arm/boot/dts/rockchip/rk3128.dtsi b/arch/arm/boot/dts/rockchip/rk3128.dtsi
index 7bf557c9956149..01edf244ddeef6 100644
--- a/arch/arm/boot/dts/rockchip/rk3128.dtsi
+++ b/arch/arm/boot/dts/rockchip/rk3128.dtsi
@@ -848,7 +848,7 @@
 			};
 
 			sdmmc_pwren: sdmmc-pwren {
-				rockchip,pins = <1 RK_PB6 1 &pcfg_pull_default>;
+				rockchip,pins = <1 RK_PB6 RK_FUNC_GPIO &pcfg_pull_default>;
 			};
 
 			sdmmc_bus4: sdmmc-bus4 {
diff --git a/arch/arm/boot/dts/rockchip/rk322x.dtsi b/arch/arm/boot/dts/rockchip/rk322x.dtsi
index ffc16d6b97e1bd..a721744cbfd17f 100644
--- a/arch/arm/boot/dts/rockchip/rk322x.dtsi
+++ b/arch/arm/boot/dts/rockchip/rk322x.dtsi
@@ -215,9 +215,9 @@
 
 			power-domain@RK3228_PD_VOP {
 				reg = <RK3228_PD_VOP>;
-				clocks =<&cru ACLK_VOP>,
-					<&cru DCLK_VOP>,
-					<&cru HCLK_VOP>;
+				clocks = <&cru ACLK_VOP>,
+					 <&cru DCLK_VOP>,
+					 <&cru HCLK_VOP>;
 				pm_qos = <&qos_vop>;
 				#power-domain-cells = <0>;
 			};
diff --git a/arch/arm/boot/dts/ti/omap/am33xx.dtsi b/arch/arm/boot/dts/ti/omap/am33xx.dtsi
index 1a2cd5baf40210..5b9e01a8aa5d5a 100644
--- a/arch/arm/boot/dts/ti/omap/am33xx.dtsi
+++ b/arch/arm/boot/dts/ti/omap/am33xx.dtsi
@@ -359,6 +359,7 @@
 					<SYSC_IDLE_NO>,
 					<SYSC_IDLE_SMART>,
 					<SYSC_IDLE_SMART_WKUP>;
+			ti,sysc-delay-us = <2>;
 			clocks = <&l3s_clkctrl AM3_L3S_USB_OTG_HS_CLKCTRL 0>;
 			clock-names = "fck";
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/ti/omap/dra7.dtsi b/arch/arm/boot/dts/ti/omap/dra7.dtsi
index 3f3e52e3b37526..6509c742fb58c9 100644
--- a/arch/arm/boot/dts/ti/omap/dra7.dtsi
+++ b/arch/arm/boot/dts/ti/omap/dra7.dtsi
@@ -147,7 +147,7 @@
 
 		l3-noc@44000000 {
 			compatible = "ti,dra7-l3-noc";
-			reg = <0x44000000 0x1000>,
+			reg = <0x44000000 0x1000000>,
 			      <0x45000000 0x1000>;
 			interrupts-extended = <&crossbar_mpu GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
 					      <&wakeupgen GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index 23c131b0854bd3..9e81b1849e4c3a 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -100,7 +100,6 @@ CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_CONNECTOR=y
 CONFIG_MTD=y
-CONFIG_MTD_AR7_PARTS=m
 CONFIG_MTD_CMDLINE_PARTS=m
 CONFIG_MTD_OF_PARTS=m
 CONFIG_MTD_AFS_PARTS=m
diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h
index 72529f5e2bed95..a41b503b7dcde0 100644
--- a/arch/arm/include/asm/arm_pmuv3.h
+++ b/arch/arm/include/asm/arm_pmuv3.h
@@ -23,6 +23,8 @@
 #define PMUSERENR		__ACCESS_CP15(c9,  0, c14, 0)
 #define PMINTENSET		__ACCESS_CP15(c9,  0, c14, 1)
 #define PMINTENCLR		__ACCESS_CP15(c9,  0, c14, 2)
+#define PMCEID2			__ACCESS_CP15(c9,  0, c14, 4)
+#define PMCEID3			__ACCESS_CP15(c9,  0, c14, 5)
 #define PMMIR			__ACCESS_CP15(c9,  0, c14, 6)
 #define PMCCFILTR		__ACCESS_CP15(c14, 0, c15, 7)
 
@@ -150,21 +152,6 @@ static inline u64 read_pmccntr(void)
 	return read_sysreg(PMCCNTR);
 }
 
-static inline void write_pmxevcntr(u32 val)
-{
-	write_sysreg(val, PMXEVCNTR);
-}
-
-static inline u32 read_pmxevcntr(void)
-{
-	return read_sysreg(PMXEVCNTR);
-}
-
-static inline void write_pmxevtyper(u32 val)
-{
-	write_sysreg(val, PMXEVTYPER);
-}
-
 static inline void write_pmcntenset(u32 val)
 {
 	write_sysreg(val, PMCNTENSET);
@@ -205,16 +192,6 @@ static inline void write_pmuserenr(u32 val)
 	write_sysreg(val, PMUSERENR);
 }
 
-static inline u32 read_pmceid0(void)
-{
-	return read_sysreg(PMCEID0);
-}
-
-static inline u32 read_pmceid1(void)
-{
-	return read_sysreg(PMCEID1);
-}
-
 static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {}
 static inline void kvm_clr_pmu_events(u32 clr) {}
 static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr)
@@ -231,6 +208,7 @@ static inline void kvm_vcpu_pmu_resync_el0(void) {}
 
 /* PMU Version in DFR Register */
 #define ARMV8_PMU_DFR_VER_NI        0
+#define ARMV8_PMU_DFR_VER_V3P1      0x4
 #define ARMV8_PMU_DFR_VER_V3P4      0x5
 #define ARMV8_PMU_DFR_VER_V3P5      0x6
 #define ARMV8_PMU_DFR_VER_IMP_DEF   0xF
@@ -251,4 +229,24 @@ static inline bool is_pmuv3p5(int pmuver)
 	return pmuver >= ARMV8_PMU_DFR_VER_V3P5;
 }
 
+static inline u64 read_pmceid0(void)
+{
+	u64 val = read_sysreg(PMCEID0);
+
+	if (read_pmuver() >= ARMV8_PMU_DFR_VER_V3P1)
+		val |= (u64)read_sysreg(PMCEID2) << 32;
+
+	return val;
+}
+
+static inline u64 read_pmceid1(void)
+{
+	u64 val = read_sysreg(PMCEID1);
+
+	if (read_pmuver() >= ARMV8_PMU_DFR_VER_V3P1)
+		val |= (u64)read_sysreg(PMCEID3) << 32;
+
+	return val;
+}
+
 #endif
diff --git a/arch/arm/include/asm/kexec.h b/arch/arm/include/asm/kexec.h
index e62832dcba7600..a8287e7ab9d41a 100644
--- a/arch/arm/include/asm/kexec.h
+++ b/arch/arm/include/asm/kexec.h
@@ -2,8 +2,6 @@
 #ifndef _ARM_KEXEC_H
 #define _ARM_KEXEC_H
 
-#ifdef CONFIG_KEXEC
-
 /* Maximum physical address we can use pages from */
 #define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
 /* Maximum address we can reach in physical address mode */
@@ -82,6 +80,4 @@ static inline struct page *boot_pfn_to_page(unsigned long boot_pfn)
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* CONFIG_KEXEC */
-
 #endif /* _ARM_KEXEC_H */
diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h
index e26a278d301ab0..5b8dbf1b0be49e 100644
--- a/arch/arm/include/asm/kprobes.h
+++ b/arch/arm/include/asm/kprobes.h
@@ -40,8 +40,6 @@ struct kprobe_ctlblk {
 
 void arch_remove_kprobe(struct kprobe *);
 int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
-int kprobe_exceptions_notify(struct notifier_block *self,
-			     unsigned long val, void *data);
 
 /* optinsn template addresses */
 extern __visible kprobe_opcode_t optprobe_template_entry[];
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index d53f56d6f84085..771264d4726a73 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -59,7 +59,7 @@ obj-$(CONFIG_FUNCTION_TRACER)	+= entry-ftrace.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o insn.o patch.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o insn.o patch.o
 obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o insn.o patch.o
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o
 # Main staffs in KPROBES are in arch/arm/probes/ .
 obj-$(CONFIG_KPROBES)		+= patch.o insn.o
 obj-$(CONFIG_OABI_COMPAT)	+= sys_oabi-compat.o
diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c
index 2157493b78a9bd..df69af9323754f 100644
--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -501,6 +501,10 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 
 	name = devm_kasprintf(&pdev->dev,
 				GFP_KERNEL, "mmdc%d", ret);
+	if (!name) {
+		ret = -ENOMEM;
+		goto pmu_release_id;
+	}
 
 	pmu_mmdc->mmdc_ipg_clk = mmdc_ipg_clk;
 	pmu_mmdc->devtype_data = (struct fsl_mmdc_devtype_data *)of_id->data;
@@ -523,9 +527,10 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 
 pmu_register_err:
 	pr_warn("MMDC Perf PMU failed (%d), disabled\n", ret);
-	ida_simple_remove(&mmdc_ida, pmu_mmdc->id);
 	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	hrtimer_cancel(&pmu_mmdc->hrtimer);
+pmu_release_id:
+	ida_simple_remove(&mmdc_ida, pmu_mmdc->id);
 pmu_free:
 	kfree(pmu_mmdc);
 	return ret;
diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c
index 98999aa8cc0c09..7f387706368a68 100644
--- a/arch/arm/mach-omap2/id.c
+++ b/arch/arm/mach-omap2/id.c
@@ -793,11 +793,16 @@ void __init omap_soc_device_init(void)
 
 	soc_dev_attr->machine  = soc_name;
 	soc_dev_attr->family   = omap_get_family();
+	if (!soc_dev_attr->family) {
+		kfree(soc_dev_attr);
+		return;
+	}
 	soc_dev_attr->revision = soc_rev;
 	soc_dev_attr->custom_attr_group = omap_soc_groups[0];
 
 	soc_dev = soc_device_register(soc_dev_attr);
 	if (IS_ERR(soc_dev)) {
+		kfree(soc_dev_attr->family);
 		kfree(soc_dev_attr);
 		return;
 	}
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 9afdc4c4a5dc15..a395b6c0aae2a9 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -484,7 +484,8 @@ static int __init xen_guest_init(void)
 	 * for secondary CPUs as they are brought up.
 	 * For uniformity we use VCPUOP_register_vcpu_info even on cpu0.
 	 */
-	xen_vcpu_info = alloc_percpu(struct vcpu_info);
+	xen_vcpu_info = __alloc_percpu(sizeof(struct vcpu_info),
+				       1 << fls(sizeof(struct vcpu_info) - 1));
 	if (xen_vcpu_info == NULL)
 		return -ENOMEM;
 
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 4bd85cc0d32bfa..9a2d3723cd0fa9 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -158,7 +158,7 @@ endif
 
 all:	$(notdir $(KBUILD_IMAGE))
 
-
+vmlinuz.efi: Image
 Image vmlinuz.efi: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi
index 15290e6892fca4..fc7315b9440659 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi
@@ -68,10 +68,7 @@
 &emac0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&ext_rgmii_pins>;
-	phy-mode = "rgmii";
 	phy-handle = <&ext_rgmii_phy>;
-	allwinner,rx-delay-ps = <3100>;
-	allwinner,tx-delay-ps = <700>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts
index d83852e72f0634..b5d713926a341a 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts
@@ -13,6 +13,9 @@
 };
 
 &emac0 {
+	allwinner,rx-delay-ps = <3100>;
+	allwinner,tx-delay-ps = <700>;
+	phy-mode = "rgmii";
 	phy-supply = <&reg_dcdce>;
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts b/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts
index 00fe28caac939a..b3b1b8692125f9 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts
@@ -13,6 +13,8 @@
 };
 
 &emac0 {
+	allwinner,tx-delay-ps = <700>;
+	phy-mode = "rgmii-rxid";
 	phy-supply = <&reg_dldo1>;
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi b/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi
index 5ce5fbf2b38e4a..f69b0c17560aee 100644
--- a/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi
@@ -82,12 +82,9 @@
 		pinctrl-0 = <&pinctrl_wifi_pdn>;
 		gpio = <&lsio_gpio1 28 GPIO_ACTIVE_HIGH>;
 		enable-active-high;
+		regulator-always-on;
 		regulator-name = "wifi_pwrdn_fake_regulator";
 		regulator-settling-time-us = <100>;
-
-		regulator-state-mem {
-			regulator-off-in-suspend;
-		};
 	};
 
 	reg_pcie_switch: regulator-pcie-switch {
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi
index ce66d30a4839b1..b0bb77150adccb 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi
@@ -149,7 +149,7 @@ dma_subsys: bus@5a000000 {
 		clock-names = "ipg", "per";
 		assigned-clocks = <&clk IMX_SC_R_LCD_0_PWM_0 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <24000000>;
-		#pwm-cells = <2>;
+		#pwm-cells = <3>;
 		power-domains = <&pd IMX_SC_R_LCD_0_PWM_0>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi
index 49ad3413db9487..7e510b21bbac55 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi
@@ -29,7 +29,7 @@ lsio_subsys: bus@5d000000 {
 			 <&pwm0_lpcg 1>;
 		assigned-clocks = <&clk IMX_SC_R_PWM_0 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <24000000>;
-		#pwm-cells = <2>;
+		#pwm-cells = <3>;
 		interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
 		status = "disabled";
 	};
@@ -42,7 +42,7 @@ lsio_subsys: bus@5d000000 {
 			 <&pwm1_lpcg 1>;
 		assigned-clocks = <&clk IMX_SC_R_PWM_1 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <24000000>;
-		#pwm-cells = <2>;
+		#pwm-cells = <3>;
 		interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
 		status = "disabled";
 	};
@@ -55,7 +55,7 @@ lsio_subsys: bus@5d000000 {
 			 <&pwm2_lpcg 1>;
 		assigned-clocks = <&clk IMX_SC_R_PWM_2 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <24000000>;
-		#pwm-cells = <2>;
+		#pwm-cells = <3>;
 		interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
 		status = "disabled";
 	};
@@ -68,7 +68,7 @@ lsio_subsys: bus@5d000000 {
 			 <&pwm3_lpcg 1>;
 		assigned-clocks = <&clk IMX_SC_R_PWM_3 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <24000000>;
-		#pwm-cells = <2>;
+		#pwm-cells = <3>;
 		interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
 		status = "disabled";
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index c9a610ba483689..1264da6012f929 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -2072,6 +2072,7 @@
 				phys = <&usb3_phy0>, <&usb3_phy0>;
 				phy-names = "usb2-phy", "usb3-phy";
 				snps,gfladj-refclk-lpm-sel-quirk;
+				snps,parkmode-disable-ss-quirk;
 			};
 
 		};
@@ -2114,6 +2115,7 @@
 				phys = <&usb3_phy1>, <&usb3_phy1>;
 				phy-names = "usb2-phy", "usb3-phy";
 				snps,gfladj-refclk-lpm-sel-quirk;
+				snps,parkmode-disable-ss-quirk;
 			};
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
index 4b1ce9fc175847..c6dc3ba0d43b23 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
@@ -1649,6 +1649,7 @@
 			phys = <&usb3_phy0>, <&usb3_phy0>;
 			phy-names = "usb2-phy", "usb3-phy";
 			power-domains = <&pgc_otg1>;
+			snps,parkmode-disable-ss-quirk;
 			status = "disabled";
 		};
 
@@ -1680,6 +1681,7 @@
 			phys = <&usb3_phy1>, <&usb3_phy1>;
 			phy-names = "usb2-phy", "usb3-phy";
 			power-domains = <&pgc_otg2>;
+			snps,parkmode-disable-ss-quirk;
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi
index 01539df335f8c2..8439dd6b393534 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi
@@ -96,6 +96,17 @@
 	status = "okay";
 };
 
+&edma3 {
+	power-domains = <&pd IMX_SC_R_DMA_1_CH0>,
+		     <&pd IMX_SC_R_DMA_1_CH1>,
+		     <&pd IMX_SC_R_DMA_1_CH2>,
+		     <&pd IMX_SC_R_DMA_1_CH3>,
+		     <&pd IMX_SC_R_DMA_1_CH4>,
+		     <&pd IMX_SC_R_DMA_1_CH5>,
+		     <&pd IMX_SC_R_DMA_1_CH6>,
+		     <&pd IMX_SC_R_DMA_1_CH7>;
+};
+
 &flexcan1 {
 	fsl,clk-source = /bits/ 8 <1>;
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi
index f22c1ac391c9b9..c4a0082f30d316 100644
--- a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi
@@ -483,7 +483,7 @@
 			};
 		};
 
-		gpioe: gpio@2d000080 {
+		gpioe: gpio@2d000000 {
 				compatible = "fsl,imx8ulp-gpio";
 				reg = <0x2d000000 0x1000>;
 				gpio-controller;
@@ -498,7 +498,7 @@
 				gpio-ranges = <&iomuxc1 0 32 24>;
 		};
 
-		gpiof: gpio@2d010080 {
+		gpiof: gpio@2d010000 {
 				compatible = "fsl,imx8ulp-gpio";
 				reg = <0x2d010000 0x1000>;
 				gpio-controller;
@@ -534,7 +534,7 @@
 			};
 		};
 
-		gpiod: gpio@2e200080 {
+		gpiod: gpio@2e200000 {
 			compatible = "fsl,imx8ulp-gpio";
 			reg = <0x2e200000 0x1000>;
 			gpio-controller;
diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
index f06139bdff97e3..3c5c67ebee5d30 100644
--- a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
+++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
@@ -577,7 +577,7 @@
 		fsl,pins = <
 			MX93_PAD_UART2_TXD__LPUART2_TX		0x31e
 			MX93_PAD_UART2_RXD__LPUART2_RX		0x31e
-			MX93_PAD_SAI1_TXD0__LPUART2_RTS_B	0x31e
+			MX93_PAD_SAI1_TXD0__LPUART2_RTS_B	0x51e
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi
index ceccf476644072..34c0540276d166 100644
--- a/arch/arm64/boot/dts/freescale/imx93.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93.dtsi
@@ -417,7 +417,7 @@
 					compatible = "fsl,imx93-src-slice";
 					reg = <0x44462400 0x400>, <0x44465800 0x400>;
 					#power-domain-cells = <0>;
-					clocks = <&clk IMX93_CLK_MEDIA_AXI>,
+					clocks = <&clk IMX93_CLK_NIC_MEDIA_GATE>,
 						 <&clk IMX93_CLK_MEDIA_APB>;
 				};
 			};
@@ -957,7 +957,7 @@
 			};
 		};
 
-		gpio2: gpio@43810080 {
+		gpio2: gpio@43810000 {
 			compatible = "fsl,imx93-gpio", "fsl,imx8ulp-gpio";
 			reg = <0x43810000 0x1000>;
 			gpio-controller;
@@ -972,7 +972,7 @@
 			gpio-ranges = <&iomuxc 0 4 30>;
 		};
 
-		gpio3: gpio@43820080 {
+		gpio3: gpio@43820000 {
 			compatible = "fsl,imx93-gpio", "fsl,imx8ulp-gpio";
 			reg = <0x43820000 0x1000>;
 			gpio-controller;
@@ -988,7 +988,7 @@
 				      <&iomuxc 26 34 2>, <&iomuxc 28 0 4>;
 		};
 
-		gpio4: gpio@43830080 {
+		gpio4: gpio@43830000 {
 			compatible = "fsl,imx93-gpio", "fsl,imx8ulp-gpio";
 			reg = <0x43830000 0x1000>;
 			gpio-controller;
@@ -1003,7 +1003,7 @@
 			gpio-ranges = <&iomuxc 0 38 28>, <&iomuxc 28 36 2>;
 		};
 
-		gpio1: gpio@47400080 {
+		gpio1: gpio@47400000 {
 			compatible = "fsl,imx93-gpio", "fsl,imx8ulp-gpio";
 			reg = <0x47400000 0x1000>;
 			gpio-controller;
diff --git a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
index 3b7a176b79047d..c46682150e502a 100644
--- a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
+++ b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
@@ -73,7 +73,7 @@
 		};
 	};
 
-	memory {
+	memory@40000000 {
 		reg = <0 0x40000000 0 0x40000000>;
 	};
 
diff --git a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts
index a885a3fbe45622..2dc1bdc74e2124 100644
--- a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts
+++ b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts
@@ -55,7 +55,7 @@
 		};
 	};
 
-	memory {
+	memory@40000000 {
 		reg = <0 0x40000000 0 0x20000000>;
 	};
 
diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts
index af4a4309bda4b9..b876e501216be8 100644
--- a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts
+++ b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts
@@ -126,6 +126,7 @@
 		compatible = "sff,sfp";
 		i2c-bus = <&i2c_sfp1>;
 		los-gpios = <&pio 46 GPIO_ACTIVE_HIGH>;
+		maximum-power-milliwatt = <3000>;
 		mod-def0-gpios = <&pio 49 GPIO_ACTIVE_LOW>;
 		tx-disable-gpios = <&pio 20 GPIO_ACTIVE_HIGH>;
 		tx-fault-gpios = <&pio 7 GPIO_ACTIVE_HIGH>;
@@ -137,6 +138,7 @@
 		i2c-bus = <&i2c_sfp2>;
 		los-gpios = <&pio 31 GPIO_ACTIVE_HIGH>;
 		mod-def0-gpios = <&pio 47 GPIO_ACTIVE_LOW>;
+		maximum-power-milliwatt = <3000>;
 		tx-disable-gpios = <&pio 15 GPIO_ACTIVE_HIGH>;
 		tx-fault-gpios = <&pio 48 GPIO_ACTIVE_HIGH>;
 	};
@@ -150,16 +152,16 @@
 			trip = <&cpu_trip_active_high>;
 		};
 
-		cpu-active-low {
+		cpu-active-med {
 			/* active: set fan to cooling level 1 */
 			cooling-device = <&fan 1 1>;
-			trip = <&cpu_trip_active_low>;
+			trip = <&cpu_trip_active_med>;
 		};
 
-		cpu-passive {
-			/* passive: set fan to cooling level 0 */
+		cpu-active-low {
+			/* active: set fan to cooling level 0 */
 			cooling-device = <&fan 0 0>;
-			trip = <&cpu_trip_passive>;
+			trip = <&cpu_trip_active_low>;
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
index 24eda00e320d3a..fc751e049953c2 100644
--- a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
@@ -374,6 +374,10 @@
 			reg = <0 0x11230000 0 0x1000>,
 			      <0 0x11c20000 0 0x1000>;
 			interrupts = <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
+			assigned-clocks = <&topckgen CLK_TOP_EMMC_416M_SEL>,
+					  <&topckgen CLK_TOP_EMMC_250M_SEL>;
+			assigned-clock-parents = <&apmixedsys CLK_APMIXED_MPLL>,
+						 <&topckgen CLK_TOP_NET1PLL_D5_D2>;
 			clocks = <&topckgen CLK_TOP_EMMC_416M_SEL>,
 				 <&infracfg CLK_INFRA_MSDC_HCK_CK>,
 				 <&infracfg CLK_INFRA_MSDC_CK>,
@@ -610,22 +614,34 @@
 			thermal-sensors = <&thermal 0>;
 
 			trips {
+				cpu_trip_crit: crit {
+					temperature = <125000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+
+				cpu_trip_hot: hot {
+					temperature = <120000>;
+					hysteresis = <2000>;
+					type = "hot";
+				};
+
 				cpu_trip_active_high: active-high {
 					temperature = <115000>;
 					hysteresis = <2000>;
 					type = "active";
 				};
 
-				cpu_trip_active_low: active-low {
+				cpu_trip_active_med: active-med {
 					temperature = <85000>;
 					hysteresis = <2000>;
 					type = "active";
 				};
 
-				cpu_trip_passive: passive {
-					temperature = <40000>;
+				cpu_trip_active_low: active-low {
+					temperature = <60000>;
 					hysteresis = <2000>;
-					type = "passive";
+					type = "active";
 				};
 			};
 		};
diff --git a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
index 5122963d8743ab..d258c80213b264 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
@@ -44,7 +44,7 @@
 		id-gpio = <&pio 16 GPIO_ACTIVE_HIGH>;
 	};
 
-	usb_p1_vbus: regulator@0 {
+	usb_p1_vbus: regulator-usb-p1 {
 		compatible = "regulator-fixed";
 		regulator-name = "usb_vbus";
 		regulator-min-microvolt = <5000000>;
@@ -53,7 +53,7 @@
 		enable-active-high;
 	};
 
-	usb_p0_vbus: regulator@1 {
+	usb_p0_vbus: regulator-usb-p0 {
 		compatible = "regulator-fixed";
 		regulator-name = "vbus";
 		regulator-min-microvolt = <5000000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-evb.dts b/arch/arm64/boot/dts/mediatek/mt8183-evb.dts
index ce336a48c89732..77f9ab94c00bd9 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-evb.dts
@@ -31,14 +31,14 @@
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
-		scp_mem_reserved: scp_mem_region {
+		scp_mem_reserved: memory@50000000 {
 			compatible = "shared-dma-pool";
 			reg = <0 0x50000000 0 0x2900000>;
 			no-map;
 		};
 	};
 
-	ntc@0 {
+	thermal-sensor {
 		compatible = "murata,ncp03wf104";
 		pullup-uv = <1800000>;
 		pullup-ohm = <390000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi
index bf97b60ae4d17e..820260348de9b6 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi
@@ -91,6 +91,8 @@
 
 &dsi0 {
 	status = "okay";
+	/delete-property/#size-cells;
+	/delete-property/#address-cells;
 	/delete-node/panel@0;
 	ports {
 		port {
@@ -441,20 +443,20 @@
 	};
 
 	touchscreen_pins: touchscreen-pins {
-		touch_int_odl {
+		touch-int-odl {
 			pinmux = <PINMUX_GPIO155__FUNC_GPIO155>;
 			input-enable;
 			bias-pull-up;
 		};
 
-		touch_rst_l {
+		touch-rst-l {
 			pinmux = <PINMUX_GPIO156__FUNC_GPIO156>;
 			output-high;
 		};
 	};
 
 	trackpad_pins: trackpad-pins {
-		trackpad_int {
+		trackpad-int {
 			pinmux = <PINMUX_GPIO7__FUNC_GPIO7>;
 			input-enable;
 			bias-disable; /* pulled externally */
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
index bf7de35ffcbc8a..7881a27be02970 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
@@ -116,7 +116,7 @@
 		#size-cells = <2>;
 		ranges;
 
-		scp_mem_reserved: scp_mem_region {
+		scp_mem_reserved: memory@50000000 {
 			compatible = "shared-dma-pool";
 			reg = <0 0x50000000 0 0x2900000>;
 			no-map;
@@ -460,7 +460,7 @@
 
 &pio {
 	aud_pins_default: audiopins {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO97__FUNC_I2S2_MCK>,
 				<PINMUX_GPIO98__FUNC_I2S2_BCK>,
 				<PINMUX_GPIO101__FUNC_I2S2_LRCK>,
@@ -482,7 +482,7 @@
 	};
 
 	aud_pins_tdm_out_on: audiotdmouton {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO169__FUNC_TDM_BCK_2ND>,
 				<PINMUX_GPIO170__FUNC_TDM_LRCK_2ND>,
 				<PINMUX_GPIO171__FUNC_TDM_DATA0_2ND>,
@@ -494,7 +494,7 @@
 	};
 
 	aud_pins_tdm_out_off: audiotdmoutoff {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO169__FUNC_GPIO169>,
 				<PINMUX_GPIO170__FUNC_GPIO170>,
 				<PINMUX_GPIO171__FUNC_GPIO171>,
@@ -508,13 +508,13 @@
 	};
 
 	bt_pins: bt-pins {
-		pins_bt_en {
+		pins-bt-en {
 			pinmux = <PINMUX_GPIO120__FUNC_GPIO120>;
 			output-low;
 		};
 	};
 
-	ec_ap_int_odl: ec_ap_int_odl {
+	ec_ap_int_odl: ec-ap-int-odl {
 		pins1 {
 			pinmux = <PINMUX_GPIO151__FUNC_GPIO151>;
 			input-enable;
@@ -522,7 +522,7 @@
 		};
 	};
 
-	h1_int_od_l: h1_int_od_l {
+	h1_int_od_l: h1-int-od-l {
 		pins1 {
 			pinmux = <PINMUX_GPIO153__FUNC_GPIO153>;
 			input-enable;
@@ -530,7 +530,7 @@
 	};
 
 	i2c0_pins: i2c0 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO82__FUNC_SDA0>,
 				 <PINMUX_GPIO83__FUNC_SCL0>;
 			mediatek,pull-up-adv = <3>;
@@ -539,7 +539,7 @@
 	};
 
 	i2c1_pins: i2c1 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO81__FUNC_SDA1>,
 				 <PINMUX_GPIO84__FUNC_SCL1>;
 			mediatek,pull-up-adv = <3>;
@@ -548,7 +548,7 @@
 	};
 
 	i2c2_pins: i2c2 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO103__FUNC_SCL2>,
 				 <PINMUX_GPIO104__FUNC_SDA2>;
 			bias-disable;
@@ -557,7 +557,7 @@
 	};
 
 	i2c3_pins: i2c3 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO50__FUNC_SCL3>,
 				 <PINMUX_GPIO51__FUNC_SDA3>;
 			mediatek,pull-up-adv = <3>;
@@ -566,7 +566,7 @@
 	};
 
 	i2c4_pins: i2c4 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO105__FUNC_SCL4>,
 				 <PINMUX_GPIO106__FUNC_SDA4>;
 			bias-disable;
@@ -575,7 +575,7 @@
 	};
 
 	i2c5_pins: i2c5 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO48__FUNC_SCL5>,
 				 <PINMUX_GPIO49__FUNC_SDA5>;
 			mediatek,pull-up-adv = <3>;
@@ -584,7 +584,7 @@
 	};
 
 	i2c6_pins: i2c6 {
-		pins_bus {
+		pins-bus {
 			pinmux = <PINMUX_GPIO11__FUNC_SCL6>,
 				 <PINMUX_GPIO12__FUNC_SDA6>;
 			bias-disable;
@@ -592,7 +592,7 @@
 	};
 
 	mmc0_pins_default: mmc0-pins-default {
-		pins_cmd_dat {
+		pins-cmd-dat {
 			pinmux = <PINMUX_GPIO123__FUNC_MSDC0_DAT0>,
 				 <PINMUX_GPIO128__FUNC_MSDC0_DAT1>,
 				 <PINMUX_GPIO125__FUNC_MSDC0_DAT2>,
@@ -607,13 +607,13 @@
 			mediatek,pull-up-adv = <01>;
 		};
 
-		pins_clk {
+		pins-clk {
 			pinmux = <PINMUX_GPIO124__FUNC_MSDC0_CLK>;
 			drive-strength = <MTK_DRIVE_14mA>;
 			mediatek,pull-down-adv = <10>;
 		};
 
-		pins_rst {
+		pins-rst {
 			pinmux = <PINMUX_GPIO133__FUNC_MSDC0_RSTB>;
 			drive-strength = <MTK_DRIVE_14mA>;
 			mediatek,pull-down-adv = <01>;
@@ -621,7 +621,7 @@
 	};
 
 	mmc0_pins_uhs: mmc0-pins-uhs {
-		pins_cmd_dat {
+		pins-cmd-dat {
 			pinmux = <PINMUX_GPIO123__FUNC_MSDC0_DAT0>,
 				 <PINMUX_GPIO128__FUNC_MSDC0_DAT1>,
 				 <PINMUX_GPIO125__FUNC_MSDC0_DAT2>,
@@ -636,19 +636,19 @@
 			mediatek,pull-up-adv = <01>;
 		};
 
-		pins_clk {
+		pins-clk {
 			pinmux = <PINMUX_GPIO124__FUNC_MSDC0_CLK>;
 			drive-strength = <MTK_DRIVE_14mA>;
 			mediatek,pull-down-adv = <10>;
 		};
 
-		pins_ds {
+		pins-ds {
 			pinmux = <PINMUX_GPIO131__FUNC_MSDC0_DSL>;
 			drive-strength = <MTK_DRIVE_14mA>;
 			mediatek,pull-down-adv = <10>;
 		};
 
-		pins_rst {
+		pins-rst {
 			pinmux = <PINMUX_GPIO133__FUNC_MSDC0_RSTB>;
 			drive-strength = <MTK_DRIVE_14mA>;
 			mediatek,pull-up-adv = <01>;
@@ -656,7 +656,7 @@
 	};
 
 	mmc1_pins_default: mmc1-pins-default {
-		pins_cmd_dat {
+		pins-cmd-dat {
 			pinmux = <PINMUX_GPIO31__FUNC_MSDC1_CMD>,
 				 <PINMUX_GPIO32__FUNC_MSDC1_DAT0>,
 				 <PINMUX_GPIO34__FUNC_MSDC1_DAT1>,
@@ -666,7 +666,7 @@
 			mediatek,pull-up-adv = <10>;
 		};
 
-		pins_clk {
+		pins-clk {
 			pinmux = <PINMUX_GPIO29__FUNC_MSDC1_CLK>;
 			input-enable;
 			mediatek,pull-down-adv = <10>;
@@ -674,7 +674,7 @@
 	};
 
 	mmc1_pins_uhs: mmc1-pins-uhs {
-		pins_cmd_dat {
+		pins-cmd-dat {
 			pinmux = <PINMUX_GPIO31__FUNC_MSDC1_CMD>,
 				 <PINMUX_GPIO32__FUNC_MSDC1_DAT0>,
 				 <PINMUX_GPIO34__FUNC_MSDC1_DAT1>,
@@ -685,7 +685,7 @@
 			mediatek,pull-up-adv = <10>;
 		};
 
-		pins_clk {
+		pins-clk {
 			pinmux = <PINMUX_GPIO29__FUNC_MSDC1_CLK>;
 			drive-strength = <MTK_DRIVE_8mA>;
 			mediatek,pull-down-adv = <10>;
@@ -693,15 +693,15 @@
 		};
 	};
 
-	panel_pins_default: panel_pins_default {
-		panel_reset {
+	panel_pins_default: panel-pins-default {
+		panel-reset {
 			pinmux = <PINMUX_GPIO45__FUNC_GPIO45>;
 			output-low;
 			bias-pull-up;
 		};
 	};
 
-	pwm0_pin_default: pwm0_pin_default {
+	pwm0_pin_default: pwm0-pin-default {
 		pins1 {
 			pinmux = <PINMUX_GPIO176__FUNC_GPIO176>;
 			output-high;
@@ -713,14 +713,14 @@
 	};
 
 	scp_pins: scp {
-		pins_scp_uart {
+		pins-scp-uart {
 			pinmux = <PINMUX_GPIO110__FUNC_TP_URXD1_AO>,
 				 <PINMUX_GPIO112__FUNC_TP_UTXD1_AO>;
 		};
 	};
 
 	spi0_pins: spi0 {
-		pins_spi {
+		pins-spi {
 			pinmux = <PINMUX_GPIO85__FUNC_SPI0_MI>,
 				 <PINMUX_GPIO86__FUNC_GPIO86>,
 				 <PINMUX_GPIO87__FUNC_SPI0_MO>,
@@ -730,7 +730,7 @@
 	};
 
 	spi1_pins: spi1 {
-		pins_spi {
+		pins-spi {
 			pinmux = <PINMUX_GPIO161__FUNC_SPI1_A_MI>,
 				 <PINMUX_GPIO162__FUNC_SPI1_A_CSB>,
 				 <PINMUX_GPIO163__FUNC_SPI1_A_MO>,
@@ -740,20 +740,20 @@
 	};
 
 	spi2_pins: spi2 {
-		pins_spi {
+		pins-spi {
 			pinmux = <PINMUX_GPIO0__FUNC_SPI2_CSB>,
 				 <PINMUX_GPIO1__FUNC_SPI2_MO>,
 				 <PINMUX_GPIO2__FUNC_SPI2_CLK>;
 			bias-disable;
 		};
-		pins_spi_mi {
+		pins-spi-mi {
 			pinmux = <PINMUX_GPIO94__FUNC_SPI2_MI>;
 			mediatek,pull-down-adv = <00>;
 		};
 	};
 
 	spi3_pins: spi3 {
-		pins_spi {
+		pins-spi {
 			pinmux = <PINMUX_GPIO21__FUNC_SPI3_MI>,
 				 <PINMUX_GPIO22__FUNC_SPI3_CSB>,
 				 <PINMUX_GPIO23__FUNC_SPI3_MO>,
@@ -763,7 +763,7 @@
 	};
 
 	spi4_pins: spi4 {
-		pins_spi {
+		pins-spi {
 			pinmux = <PINMUX_GPIO17__FUNC_SPI4_MI>,
 				 <PINMUX_GPIO18__FUNC_SPI4_CSB>,
 				 <PINMUX_GPIO19__FUNC_SPI4_MO>,
@@ -773,7 +773,7 @@
 	};
 
 	spi5_pins: spi5 {
-		pins_spi {
+		pins-spi {
 			pinmux = <PINMUX_GPIO13__FUNC_SPI5_MI>,
 				 <PINMUX_GPIO14__FUNC_SPI5_CSB>,
 				 <PINMUX_GPIO15__FUNC_SPI5_MO>,
@@ -783,63 +783,63 @@
 	};
 
 	uart0_pins_default: uart0-pins-default {
-		pins_rx {
+		pins-rx {
 			pinmux = <PINMUX_GPIO95__FUNC_URXD0>;
 			input-enable;
 			bias-pull-up;
 		};
-		pins_tx {
+		pins-tx {
 			pinmux = <PINMUX_GPIO96__FUNC_UTXD0>;
 		};
 	};
 
 	uart1_pins_default: uart1-pins-default {
-		pins_rx {
+		pins-rx {
 			pinmux = <PINMUX_GPIO121__FUNC_URXD1>;
 			input-enable;
 			bias-pull-up;
 		};
-		pins_tx {
+		pins-tx {
 			pinmux = <PINMUX_GPIO115__FUNC_UTXD1>;
 		};
-		pins_rts {
+		pins-rts {
 			pinmux = <PINMUX_GPIO47__FUNC_URTS1>;
 			output-enable;
 		};
-		pins_cts {
+		pins-cts {
 			pinmux = <PINMUX_GPIO46__FUNC_UCTS1>;
 			input-enable;
 		};
 	};
 
 	uart1_pins_sleep: uart1-pins-sleep {
-		pins_rx {
+		pins-rx {
 			pinmux = <PINMUX_GPIO121__FUNC_GPIO121>;
 			input-enable;
 			bias-pull-up;
 		};
-		pins_tx {
+		pins-tx {
 			pinmux = <PINMUX_GPIO115__FUNC_UTXD1>;
 		};
-		pins_rts {
+		pins-rts {
 			pinmux = <PINMUX_GPIO47__FUNC_URTS1>;
 			output-enable;
 		};
-		pins_cts {
+		pins-cts {
 			pinmux = <PINMUX_GPIO46__FUNC_UCTS1>;
 			input-enable;
 		};
 	};
 
 	wifi_pins_pwrseq: wifi-pins-pwrseq {
-		pins_wifi_enable {
+		pins-wifi-enable {
 			pinmux = <PINMUX_GPIO119__FUNC_GPIO119>;
 			output-low;
 		};
 	};
 
 	wifi_pins_wakeup: wifi-pins-wakeup {
-		pins_wifi_wakeup {
+		pins-wifi-wakeup {
 			pinmux = <PINMUX_GPIO113__FUNC_GPIO113>;
 			input-enable;
 		};
diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi
index 5169779d01dfb4..976dc968b3ca14 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi
@@ -1210,127 +1210,6 @@
 			nvmem-cell-names = "calibration-data";
 		};
 
-		thermal_zones: thermal-zones {
-			cpu_thermal: cpu-thermal {
-				polling-delay-passive = <100>;
-				polling-delay = <500>;
-				thermal-sensors = <&thermal 0>;
-				sustainable-power = <5000>;
-
-				trips {
-					threshold: trip-point0 {
-						temperature = <68000>;
-						hysteresis = <2000>;
-						type = "passive";
-					};
-
-					target: trip-point1 {
-						temperature = <80000>;
-						hysteresis = <2000>;
-						type = "passive";
-					};
-
-					cpu_crit: cpu-crit {
-						temperature = <115000>;
-						hysteresis = <2000>;
-						type = "critical";
-					};
-				};
-
-				cooling-maps {
-					map0 {
-						trip = <&target>;
-						cooling-device = <&cpu0
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>,
-								 <&cpu1
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>,
-								 <&cpu2
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>,
-								 <&cpu3
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>;
-						contribution = <3072>;
-					};
-					map1 {
-						trip = <&target>;
-						cooling-device = <&cpu4
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>,
-								 <&cpu5
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>,
-								 <&cpu6
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>,
-								 <&cpu7
-							THERMAL_NO_LIMIT
-							THERMAL_NO_LIMIT>;
-						contribution = <1024>;
-					};
-				};
-			};
-
-			/* The tzts1 ~ tzts6 don't need to polling */
-			/* The tzts1 ~ tzts6 don't need to thermal throttle */
-
-			tzts1: tzts1 {
-				polling-delay-passive = <0>;
-				polling-delay = <0>;
-				thermal-sensors = <&thermal 1>;
-				sustainable-power = <5000>;
-				trips {};
-				cooling-maps {};
-			};
-
-			tzts2: tzts2 {
-				polling-delay-passive = <0>;
-				polling-delay = <0>;
-				thermal-sensors = <&thermal 2>;
-				sustainable-power = <5000>;
-				trips {};
-				cooling-maps {};
-			};
-
-			tzts3: tzts3 {
-				polling-delay-passive = <0>;
-				polling-delay = <0>;
-				thermal-sensors = <&thermal 3>;
-				sustainable-power = <5000>;
-				trips {};
-				cooling-maps {};
-			};
-
-			tzts4: tzts4 {
-				polling-delay-passive = <0>;
-				polling-delay = <0>;
-				thermal-sensors = <&thermal 4>;
-				sustainable-power = <5000>;
-				trips {};
-				cooling-maps {};
-			};
-
-			tzts5: tzts5 {
-				polling-delay-passive = <0>;
-				polling-delay = <0>;
-				thermal-sensors = <&thermal 5>;
-				sustainable-power = <5000>;
-				trips {};
-				cooling-maps {};
-			};
-
-			tztsABB: tztsABB {
-				polling-delay-passive = <0>;
-				polling-delay = <0>;
-				thermal-sensors = <&thermal 6>;
-				sustainable-power = <5000>;
-				trips {};
-				cooling-maps {};
-			};
-		};
-
 		pwm0: pwm@1100e000 {
 			compatible = "mediatek,mt8183-disp-pwm";
 			reg = <0 0x1100e000 0 0x1000>;
@@ -2105,4 +1984,125 @@
 			power-domains = <&spm MT8183_POWER_DOMAIN_CAM>;
 		};
 	};
+
+	thermal_zones: thermal-zones {
+		cpu_thermal: cpu-thermal {
+			polling-delay-passive = <100>;
+			polling-delay = <500>;
+			thermal-sensors = <&thermal 0>;
+			sustainable-power = <5000>;
+
+			trips {
+				threshold: trip-point0 {
+					temperature = <68000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				target: trip-point1 {
+					temperature = <80000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu_crit: cpu-crit {
+					temperature = <115000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&target>;
+					cooling-device = <&cpu0
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>,
+							 <&cpu1
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>,
+							 <&cpu2
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>,
+							 <&cpu3
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>;
+					contribution = <3072>;
+				};
+				map1 {
+					trip = <&target>;
+					cooling-device = <&cpu4
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>,
+							 <&cpu5
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>,
+							 <&cpu6
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>,
+							 <&cpu7
+						THERMAL_NO_LIMIT
+						THERMAL_NO_LIMIT>;
+					contribution = <1024>;
+				};
+			};
+		};
+
+		/* The tzts1 ~ tzts6 don't need to polling */
+		/* The tzts1 ~ tzts6 don't need to thermal throttle */
+
+		tzts1: tzts1 {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&thermal 1>;
+			sustainable-power = <5000>;
+			trips {};
+			cooling-maps {};
+		};
+
+		tzts2: tzts2 {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&thermal 2>;
+			sustainable-power = <5000>;
+			trips {};
+			cooling-maps {};
+		};
+
+		tzts3: tzts3 {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&thermal 3>;
+			sustainable-power = <5000>;
+			trips {};
+			cooling-maps {};
+		};
+
+		tzts4: tzts4 {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&thermal 4>;
+			sustainable-power = <5000>;
+			trips {};
+			cooling-maps {};
+		};
+
+		tzts5: tzts5 {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&thermal 5>;
+			sustainable-power = <5000>;
+			trips {};
+			cooling-maps {};
+		};
+
+		tztsABB: tztsABB {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&thermal 6>;
+			sustainable-power = <5000>;
+			trips {};
+			cooling-maps {};
+		};
+	};
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8186.dtsi b/arch/arm64/boot/dts/mediatek/mt8186.dtsi
index f04ae70c470aa3..df0c04f2ba1da9 100644
--- a/arch/arm64/boot/dts/mediatek/mt8186.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8186.dtsi
@@ -924,7 +924,8 @@
 					reg = <MT8186_POWER_DOMAIN_CSIRX_TOP>;
 					clocks = <&topckgen CLK_TOP_SENINF>,
 						 <&topckgen CLK_TOP_SENINF1>;
-					clock-names = "csirx_top0", "csirx_top1";
+					clock-names = "subsys-csirx-top0",
+						      "subsys-csirx-top1";
 					#power-domain-cells = <0>;
 				};
 
@@ -942,7 +943,8 @@
 					reg = <MT8186_POWER_DOMAIN_ADSP_AO>;
 					clocks = <&topckgen CLK_TOP_AUDIODSP>,
 						 <&topckgen CLK_TOP_ADSP_BUS>;
-					clock-names = "audioadsp", "adsp_bus";
+					clock-names = "audioadsp",
+						      "subsys-adsp-bus";
 					#address-cells = <1>;
 					#size-cells = <0>;
 					#power-domain-cells = <1>;
@@ -975,8 +977,11 @@
 						 <&mmsys CLK_MM_SMI_COMMON>,
 						 <&mmsys CLK_MM_SMI_GALS>,
 						 <&mmsys CLK_MM_SMI_IOMMU>;
-					clock-names = "disp", "mdp", "smi_infra", "smi_common",
-						     "smi_gals", "smi_iommu";
+					clock-names = "disp", "mdp",
+						      "subsys-smi-infra",
+						      "subsys-smi-common",
+						      "subsys-smi-gals",
+						      "subsys-smi-iommu";
 					mediatek,infracfg = <&infracfg_ao>;
 					#address-cells = <1>;
 					#size-cells = <0>;
@@ -993,15 +998,17 @@
 
 					power-domain@MT8186_POWER_DOMAIN_CAM {
 						reg = <MT8186_POWER_DOMAIN_CAM>;
-						clocks = <&topckgen CLK_TOP_CAM>,
-							 <&topckgen CLK_TOP_SENINF>,
+						clocks = <&topckgen CLK_TOP_SENINF>,
 							 <&topckgen CLK_TOP_SENINF1>,
 							 <&topckgen CLK_TOP_SENINF2>,
 							 <&topckgen CLK_TOP_SENINF3>,
+							 <&camsys CLK_CAM2MM_GALS>,
 							 <&topckgen CLK_TOP_CAMTM>,
-							 <&camsys CLK_CAM2MM_GALS>;
-						clock-names = "cam-top", "cam0", "cam1", "cam2",
-							     "cam3", "cam-tm", "gals";
+							 <&topckgen CLK_TOP_CAM>;
+						clock-names = "cam0", "cam1", "cam2",
+							      "cam3", "gals",
+							      "subsys-cam-tm",
+							      "subsys-cam-top";
 						mediatek,infracfg = <&infracfg_ao>;
 						#address-cells = <1>;
 						#size-cells = <0>;
@@ -1020,9 +1027,9 @@
 
 					power-domain@MT8186_POWER_DOMAIN_IMG {
 						reg = <MT8186_POWER_DOMAIN_IMG>;
-						clocks = <&topckgen CLK_TOP_IMG1>,
-							 <&imgsys1 CLK_IMG1_GALS_IMG1>;
-						clock-names = "img-top", "gals";
+						clocks = <&imgsys1 CLK_IMG1_GALS_IMG1>,
+							 <&topckgen CLK_TOP_IMG1>;
+						clock-names = "gals", "subsys-img-top";
 						mediatek,infracfg = <&infracfg_ao>;
 						#address-cells = <1>;
 						#size-cells = <0>;
@@ -1041,8 +1048,11 @@
 							 <&ipesys CLK_IPE_LARB20>,
 							 <&ipesys CLK_IPE_SMI_SUBCOM>,
 							 <&ipesys CLK_IPE_GALS_IPE>;
-						clock-names = "ipe-top", "ipe-larb0", "ipe-larb1",
-							      "ipe-smi", "ipe-gals";
+						clock-names = "subsys-ipe-top",
+							      "subsys-ipe-larb0",
+							      "subsys-ipe-larb1",
+							      "subsys-ipe-smi",
+							      "subsys-ipe-gals";
 						mediatek,infracfg = <&infracfg_ao>;
 						#power-domain-cells = <0>;
 					};
@@ -1061,7 +1071,9 @@
 						clocks = <&topckgen CLK_TOP_WPE>,
 							 <&wpesys CLK_WPE_SMI_LARB8_CK_EN>,
 							 <&wpesys CLK_WPE_SMI_LARB8_PCLK_EN>;
-						clock-names = "wpe0", "larb-ck", "larb-pclk";
+						clock-names = "wpe0",
+							      "subsys-larb-ck",
+							      "subsys-larb-pclk";
 						mediatek,infracfg = <&infracfg_ao>;
 						#power-domain-cells = <0>;
 					};
@@ -1656,7 +1668,7 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 
-			gpu_speedbin: gpu-speed-bin@59c {
+			gpu_speedbin: gpu-speedbin@59c {
 				reg = <0x59c 0x4>;
 				bits = <0 3>;
 			};
diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
index dd5b89b7319039..5a7cab489ff3ac 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
@@ -389,7 +389,7 @@
 	pinctrl-0 = <&i2c7_pins>;
 
 	pmic@34 {
-		#interrupt-cells = <1>;
+		#interrupt-cells = <2>;
 		compatible = "mediatek,mt6360";
 		reg = <0x34>;
 		interrupt-controller;
diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
index 54c674c45b49a2..e0ac2e9f5b7204 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
@@ -627,6 +627,8 @@
 
 					power-domain@MT8195_POWER_DOMAIN_VENC_CORE1 {
 						reg = <MT8195_POWER_DOMAIN_VENC_CORE1>;
+						clocks = <&vencsys_core1 CLK_VENC_CORE1_LARB>;
+						clock-names = "venc1-larb";
 						mediatek,infracfg = <&infracfg_ao>;
 						#power-domain-cells = <0>;
 					};
@@ -689,6 +691,8 @@
 
 						power-domain@MT8195_POWER_DOMAIN_VENC {
 							reg = <MT8195_POWER_DOMAIN_VENC>;
+							clocks = <&vencsys CLK_VENC_LARB>;
+							clock-names = "venc0-larb";
 							mediatek,infracfg = <&infracfg_ao>;
 							#power-domain-cells = <0>;
 						};
@@ -2665,7 +2669,7 @@
 			reg = <0 0x1b010000 0 0x1000>;
 			mediatek,larb-id = <20>;
 			mediatek,smi = <&smi_common_vpp>;
-			clocks = <&vencsys_core1 CLK_VENC_CORE1_LARB>,
+			clocks = <&vencsys_core1 CLK_VENC_CORE1_VENC>,
 				 <&vencsys_core1 CLK_VENC_CORE1_GALS>,
 				 <&vppsys0 CLK_VPP0_GALS_VDO0_VDO1_VENCSYS_CORE1>;
 			clock-names = "apb", "smi", "gals";
diff --git a/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts b/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts
index 70b465f7c6a7fb..00ac59a873e8dd 100644
--- a/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts
@@ -238,6 +238,7 @@
 	mt6360: pmic@34 {
 		compatible = "mediatek,mt6360";
 		reg = <0x34>;
+		interrupt-parent = <&pio>;
 		interrupts = <128 IRQ_TYPE_EDGE_FALLING>;
 		interrupt-names = "IRQB";
 		interrupt-controller;
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
index de0a1f2af983be..7d4c5324c61bce 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
@@ -86,7 +86,7 @@
 	sgtl5000_clk: sgtl5000-oscillator {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
-		clock-frequency  = <24576000>;
+		clock-frequency = <24576000>;
 	};
 
 	dc_12v: dc-12v-regulator {
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index e729e7a22b23a6..cc8209795c3e53 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -668,7 +668,7 @@
 
 	vdec: video-codec@ff360000 {
 		compatible = "rockchip,rk3328-vdec", "rockchip,rk3399-vdec";
-		reg = <0x0 0xff360000 0x0 0x400>;
+		reg = <0x0 0xff360000 0x0 0x480>;
 		interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru ACLK_RKVDEC>, <&cru HCLK_RKVDEC>,
 			 <&cru SCLK_VDEC_CABAC>, <&cru SCLK_VDEC_CORE>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
index 5c1929d41cc0b7..cacbad35cfc854 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
@@ -509,8 +509,7 @@ ap_i2c_tp: &i2c5 {
 &pci_rootport {
 	mvl_wifi: wifi@0,0 {
 		compatible = "pci1b4b,2b42";
-		reg = <0x83010000 0x0 0x00000000 0x0 0x00100000
-		       0x83010000 0x0 0x00100000 0x0 0x00100000>;
+		reg = <0x0000 0x0 0x0 0x0 0x0>;
 		interrupt-parent = <&gpio0>;
 		interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
 		pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts
index 853e88455e750e..9e4b12ed62cbed 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet-dumo.dts
@@ -34,8 +34,8 @@
 &pci_rootport {
 	wifi@0,0 {
 		compatible = "qcom,ath10k";
-		reg = <0x00010000 0x0 0x00000000 0x0 0x00000000>,
-		      <0x03010010 0x0 0x00000000 0x0 0x00200000>;
+		reg = <0x00000000 0x0 0x00000000 0x0 0x00000000>,
+		      <0x03000010 0x0 0x00000000 0x0 0x00200000>;
 		qcom,ath10k-calibration-variant = "GO_DUMO";
 	};
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
index c9bf1d5c3a4264..789fd0dcc88baa 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
@@ -489,6 +489,7 @@ ap_i2c_audio: &i2c8 {
 		#address-cells = <3>;
 		#size-cells = <2>;
 		ranges;
+		device_type = "pci";
 	};
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index faf02e59d6c73c..da0dfb237f853f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -1109,7 +1109,9 @@
 			power-domain@RK3399_PD_VDU {
 				reg = <RK3399_PD_VDU>;
 				clocks = <&cru ACLK_VDU>,
-					 <&cru HCLK_VDU>;
+					 <&cru HCLK_VDU>,
+					 <&cru SCLK_VDU_CA>,
+					 <&cru SCLK_VDU_CORE>;
 				pm_qos = <&qos_video_m1_r>,
 					 <&qos_video_m1_w>;
 				#power-domain-cells = <0>;
@@ -1384,7 +1386,7 @@
 
 	vdec: video-codec@ff660000 {
 		compatible = "rockchip,rk3399-vdec";
-		reg = <0x0 0xff660000 0x0 0x400>;
+		reg = <0x0 0xff660000 0x0 0x480>;
 		interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH 0>;
 		clocks = <&cru ACLK_VDU>, <&cru HCLK_VDU>,
 			 <&cru SCLK_VDU_CA>, <&cru SCLK_VDU_CORE>;
diff --git a/arch/arm64/boot/dts/rockchip/rk356x.dtsi b/arch/arm64/boot/dts/rockchip/rk356x.dtsi
index 0964761e3ce9eb..c19c0f1b3778fe 100644
--- a/arch/arm64/boot/dts/rockchip/rk356x.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk356x.dtsi
@@ -977,7 +977,7 @@
 			     <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-names = "sys", "pmc", "msi", "legacy", "err";
+		interrupt-names = "sys", "pmc", "msg", "legacy", "err";
 		bus-range = <0x0 0xf>;
 		clocks = <&cru ACLK_PCIE20_MST>, <&cru ACLK_PCIE20_SLV>,
 			 <&cru ACLK_PCIE20_DBI>, <&cru PCLK_PCIE20>,
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
index 9570b34aca2e93..d88c0e85235651 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
@@ -235,13 +235,13 @@
 &pinctrl {
 	fan {
 		fan_int: fan-int {
-			rockchip,pins = <0 RK_PA4 RK_FUNC_GPIO &pcfg_pull_none>;
+			rockchip,pins = <0 RK_PA4 RK_FUNC_GPIO &pcfg_pull_up>;
 		};
 	};
 
 	hym8563 {
 		hym8563_int: hym8563-int {
-			rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>;
+			rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_up>;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts b/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts
index 8f399c4317bdad..e3a839a12dc6f0 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts
@@ -38,7 +38,7 @@
 	leds {
 		compatible = "gpio-leds";
 		pinctrl-names = "default";
-		pinctrl-0 =<&leds_gpio>;
+		pinctrl-0 = <&leds_gpio>;
 
 		led-1 {
 			gpios = <&gpio1 RK_PA2 GPIO_ACTIVE_HIGH>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi
index 63151d9d237755..30db12c4fc82b5 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi
@@ -369,7 +369,7 @@
 		emmc_data_strobe: emmc-data-strobe {
 			rockchip,pins =
 				/* emmc_data_strobe */
-				<2 RK_PA2 1 &pcfg_pull_none>;
+				<2 RK_PA2 1 &pcfg_pull_down>;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi
index 7064c0e9179f1d..8aa0499f9b032d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi
@@ -1362,7 +1362,6 @@
 			     <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH 0>,
 			     <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH 0>,
 			     <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH 0>;
-		interrupt-names = "ch0", "ch1", "ch2", "ch3";
 		rockchip,pmu = <&pmu1grf>;
 	};
 
diff --git a/arch/arm64/include/asm/arm_pmuv3.h b/arch/arm64/include/asm/arm_pmuv3.h
index 18dc2fb3d7b7b2..c27404fa4418ad 100644
--- a/arch/arm64/include/asm/arm_pmuv3.h
+++ b/arch/arm64/include/asm/arm_pmuv3.h
@@ -46,12 +46,12 @@ static inline u32 read_pmuver(void)
 			ID_AA64DFR0_EL1_PMUVer_SHIFT);
 }
 
-static inline void write_pmcr(u32 val)
+static inline void write_pmcr(u64 val)
 {
 	write_sysreg(val, pmcr_el0);
 }
 
-static inline u32 read_pmcr(void)
+static inline u64 read_pmcr(void)
 {
 	return read_sysreg(pmcr_el0);
 }
@@ -71,21 +71,6 @@ static inline u64 read_pmccntr(void)
 	return read_sysreg(pmccntr_el0);
 }
 
-static inline void write_pmxevcntr(u32 val)
-{
-	write_sysreg(val, pmxevcntr_el0);
-}
-
-static inline u32 read_pmxevcntr(void)
-{
-	return read_sysreg(pmxevcntr_el0);
-}
-
-static inline void write_pmxevtyper(u32 val)
-{
-	write_sysreg(val, pmxevtyper_el0);
-}
-
 static inline void write_pmcntenset(u32 val)
 {
 	write_sysreg(val, pmcntenset_el0);
@@ -106,7 +91,7 @@ static inline void write_pmintenclr(u32 val)
 	write_sysreg(val, pmintenclr_el1);
 }
 
-static inline void write_pmccfiltr(u32 val)
+static inline void write_pmccfiltr(u64 val)
 {
 	write_sysreg(val, pmccfiltr_el0);
 }
@@ -126,12 +111,12 @@ static inline void write_pmuserenr(u32 val)
 	write_sysreg(val, pmuserenr_el0);
 }
 
-static inline u32 read_pmceid0(void)
+static inline u64 read_pmceid0(void)
 {
 	return read_sysreg(pmceid0_el0);
 }
 
-static inline u32 read_pmceid1(void)
+static inline u64 read_pmceid1(void)
 {
 	return read_sysreg(pmceid1_el0);
 }
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index 05cd82eeca1365..be7a3680dadff7 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -37,8 +37,6 @@ struct kprobe_ctlblk {
 
 void arch_remove_kprobe(struct kprobe *);
 int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
-int kprobe_exceptions_notify(struct notifier_block *self,
-			     unsigned long val, void *data);
 void __kretprobe_trampoline(void);
 void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b19a8aee684c87..79ce70fbb751c6 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -834,6 +834,12 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 		pte = set_pte_bit(pte, __pgprot(PTE_DIRTY));
 
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
+	/*
+	 * If we end up clearing hw dirtiness for a sw-dirty PTE, set hardware
+	 * dirtiness again.
+	 */
+	if (pte_sw_dirty(pte))
+		pte = pte_mkdirty(pte);
 	return pte;
 }
 
diff --git a/arch/arm64/include/asm/setup.h b/arch/arm64/include/asm/setup.h
index f4af547ef54caa..2e4d7da74fb87a 100644
--- a/arch/arm64/include/asm/setup.h
+++ b/arch/arm64/include/asm/setup.h
@@ -21,9 +21,22 @@ static inline bool arch_parse_debug_rodata(char *arg)
 	extern bool rodata_enabled;
 	extern bool rodata_full;
 
-	if (arg && !strcmp(arg, "full")) {
+	if (!arg)
+		return false;
+
+	if (!strcmp(arg, "full")) {
+		rodata_enabled = rodata_full = true;
+		return true;
+	}
+
+	if (!strcmp(arg, "off")) {
+		rodata_enabled = rodata_full = false;
+		return true;
+	}
+
+	if (!strcmp(arg, "on")) {
 		rodata_enabled = true;
-		rodata_full = true;
+		rodata_full = false;
 		return true;
 	}
 
diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h
index 17f687510c4851..abb57bc543054f 100644
--- a/arch/arm64/include/asm/syscall_wrapper.h
+++ b/arch/arm64/include/asm/syscall_wrapper.h
@@ -44,9 +44,6 @@
 		return sys_ni_syscall();						\
 	}
 
-#define COMPAT_SYS_NI(name) \
-	SYSCALL_ALIAS(__arm64_compat_sys_##name, sys_ni_posix_timers);
-
 #endif /* CONFIG_COMPAT */
 
 #define __SYSCALL_DEFINEx(x, name, ...)						\
@@ -54,7 +51,6 @@
 	ALLOW_ERROR_INJECTION(__arm64_sys##name, ERRNO);			\
 	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));		\
 	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
-	asmlinkage long __arm64_sys##name(const struct pt_regs *regs);		\
 	asmlinkage long __arm64_sys##name(const struct pt_regs *regs)		\
 	{									\
 		return __se_sys##name(SC_ARM64_REGS_TO_ARGS(x,__VA_ARGS__));	\
@@ -82,6 +78,5 @@
 	}
 
 asmlinkage long __arm64_sys_ni_syscall(const struct pt_regs *__unused);
-#define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers);
 
 #endif /* __ASM_SYSCALL_WRAPPER_H */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index f6b2e2906fc9aa..91d2d671496911 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -999,6 +999,37 @@ static void init_32bit_cpu_features(struct cpuinfo_32bit *info)
 	init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2);
 }
 
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+static bool enable_pseudo_nmi;
+
+static int __init early_enable_pseudo_nmi(char *p)
+{
+	return kstrtobool(p, &enable_pseudo_nmi);
+}
+early_param("irqchip.gicv3_pseudo_nmi", early_enable_pseudo_nmi);
+
+static __init void detect_system_supports_pseudo_nmi(void)
+{
+	struct device_node *np;
+
+	if (!enable_pseudo_nmi)
+		return;
+
+	/*
+	 * Detect broken MediaTek firmware that doesn't properly save and
+	 * restore GIC priorities.
+	 */
+	np = of_find_compatible_node(NULL, NULL, "arm,gic-v3");
+	if (np && of_property_read_bool(np, "mediatek,broken-save-restore-fw")) {
+		pr_info("Pseudo-NMI disabled due to MediaTek Chromebook GICR save problem\n");
+		enable_pseudo_nmi = false;
+	}
+	of_node_put(np);
+}
+#else /* CONFIG_ARM64_PSEUDO_NMI */
+static inline void detect_system_supports_pseudo_nmi(void) { }
+#endif
+
 void __init init_cpu_features(struct cpuinfo_arm64 *info)
 {
 	/* Before we start using the tables, make sure it is sorted */
@@ -1058,6 +1089,13 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 	init_cpucap_indirect_list();
 
 	/*
+	 * Detect broken pseudo-NMI. Must be called _before_ the call to
+	 * setup_boot_cpu_capabilities() since it interacts with
+	 * can_use_gic_priorities().
+	 */
+	detect_system_supports_pseudo_nmi();
+
+	/*
 	 * Detect and enable early CPU capabilities based on the boot CPU,
 	 * after we have initialised the CPU feature infrastructure.
 	 */
@@ -1801,6 +1839,10 @@ static int __init __kpti_install_ng_mappings(void *__unused)
 
 static void __init kpti_install_ng_mappings(void)
 {
+	/* Check whether KPTI is going to be used */
+	if (!cpus_have_cap(ARM64_UNMAP_KERNEL_AT_EL0))
+		return;
+
 	/*
 	 * We don't need to rewrite the page-tables if either we've done
 	 * it already or we have KASLR enabled and therefore have not
@@ -2085,14 +2127,6 @@ static void cpu_enable_e0pd(struct arm64_cpu_capabilities const *cap)
 #endif /* CONFIG_ARM64_E0PD */
 
 #ifdef CONFIG_ARM64_PSEUDO_NMI
-static bool enable_pseudo_nmi;
-
-static int __init early_enable_pseudo_nmi(char *p)
-{
-	return kstrtobool(p, &enable_pseudo_nmi);
-}
-early_param("irqchip.gicv3_pseudo_nmi", early_enable_pseudo_nmi);
-
 static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry,
 				   int scope)
 {
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index be95b523c10181..defbab84e9e5c7 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -965,10 +965,7 @@ static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
 
 static bool ipi_should_be_nmi(enum ipi_msg_type ipi)
 {
-	DECLARE_STATIC_KEY_FALSE(supports_pseudo_nmis);
-
-	if (!system_uses_irq_prio_masking() ||
-	    !static_branch_likely(&supports_pseudo_nmis))
+	if (!system_uses_irq_prio_masking())
 		return false;
 
 	switch (ipi) {
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index e5f75f1f108539..4796104c447181 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -410,7 +410,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_pmu_vcpu_destroy(vcpu);
-
+	kvm_vgic_vcpu_destroy(vcpu);
 	kvm_arm_vcpu_destroy(vcpu);
 }
 
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index c8c3cb81278321..e949e1d0fd9f7b 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -368,7 +368,7 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm)
 		vgic_v4_teardown(kvm);
 }
 
-void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
+static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
@@ -379,29 +379,39 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 	vgic_flush_pending_lpis(vcpu);
 
 	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
-	vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
+		vgic_unregister_redist_iodev(vcpu);
+		vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
+	}
 }
 
-static void __kvm_vgic_destroy(struct kvm *kvm)
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	mutex_lock(&kvm->slots_lock);
+	__kvm_vgic_vcpu_destroy(vcpu);
+	mutex_unlock(&kvm->slots_lock);
+}
+
+void kvm_vgic_destroy(struct kvm *kvm)
 {
 	struct kvm_vcpu *vcpu;
 	unsigned long i;
 
-	lockdep_assert_held(&kvm->arch.config_lock);
+	mutex_lock(&kvm->slots_lock);
 
 	vgic_debug_destroy(kvm);
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_vgic_vcpu_destroy(vcpu);
+		__kvm_vgic_vcpu_destroy(vcpu);
+
+	mutex_lock(&kvm->arch.config_lock);
 
 	kvm_vgic_dist_destroy(kvm);
-}
 
-void kvm_vgic_destroy(struct kvm *kvm)
-{
-	mutex_lock(&kvm->arch.config_lock);
-	__kvm_vgic_destroy(kvm);
 	mutex_unlock(&kvm->arch.config_lock);
+	mutex_unlock(&kvm->slots_lock);
 }
 
 /**
@@ -469,25 +479,26 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 		type = VGIC_V3;
 	}
 
-	if (ret) {
-		__kvm_vgic_destroy(kvm);
+	if (ret)
 		goto out;
-	}
+
 	dist->ready = true;
 	dist_base = dist->vgic_dist_base;
 	mutex_unlock(&kvm->arch.config_lock);
 
 	ret = vgic_register_dist_iodev(kvm, dist_base, type);
-	if (ret) {
+	if (ret)
 		kvm_err("Unable to register VGIC dist MMIO regions\n");
-		kvm_vgic_destroy(kvm);
-	}
-	mutex_unlock(&kvm->slots_lock);
-	return ret;
 
+	goto out_slots;
 out:
 	mutex_unlock(&kvm->arch.config_lock);
+out_slots:
 	mutex_unlock(&kvm->slots_lock);
+
+	if (ret)
+		kvm_vgic_destroy(kvm);
+
 	return ret;
 }
 
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index 89117ba2528a0a..a764b0ab8bf913 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -820,7 +820,7 @@ out_unlock:
 	return ret;
 }
 
-static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu)
+void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu)
 {
 	struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
 
@@ -833,6 +833,8 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm)
 	unsigned long c;
 	int ret = 0;
 
+	lockdep_assert_held(&kvm->slots_lock);
+
 	kvm_for_each_vcpu(c, vcpu, kvm) {
 		ret = vgic_register_redist_iodev(vcpu);
 		if (ret)
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index 339a55194b2c63..74a67ad87f29de 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -436,6 +436,10 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
 	if (ret)
 		goto out;
 
+	/* Silently exit if the vLPI is already mapped */
+	if (irq->hw)
+		goto out;
+
 	/*
 	 * Emit the mapping request. If it fails, the ITS probably
 	 * isn't v4 compatible, so let's silently bail out. Holding
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 0ab09b0d44404b..8d134569d0a1f6 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -241,6 +241,7 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq);
 int vgic_v3_save_pending_tables(struct kvm *kvm);
 int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count);
 int vgic_register_redist_iodev(struct kvm_vcpu *vcpu);
+void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu);
 bool vgic_v3_check_base(struct kvm *kvm);
 
 void vgic_v3_load(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 8e2017ba5f1b11..924843f1f661bf 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -29,8 +29,8 @@ bool can_set_direct_map(void)
 	 *
 	 * KFENCE pool requires page-granular mapping if initialized late.
 	 */
-	return (rodata_enabled && rodata_full) || debug_pagealloc_enabled() ||
-		arm64_kfence_can_set_direct_map();
+	return rodata_full || debug_pagealloc_enabled() ||
+	       arm64_kfence_can_set_direct_map();
 }
 
 static int change_page_range(pte_t *ptep, unsigned long addr, void *data)
@@ -105,8 +105,7 @@ static int change_memory_common(unsigned long addr, int numpages,
 	 * If we are manipulating read-only permissions, apply the same
 	 * change to the linear mapping of the pages that back this VM area.
 	 */
-	if (rodata_enabled &&
-	    rodata_full && (pgprot_val(set_mask) == PTE_RDONLY ||
+	if (rodata_full && (pgprot_val(set_mask) == PTE_RDONLY ||
 			    pgprot_val(clear_mask) == PTE_RDONLY)) {
 		for (i = 0; i < area->nr_pages; i++) {
 			__change_memory_common((u64)page_address(area->pages[i]),
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index d889a0b97bc18f..ee123820a4760a 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -136,6 +136,7 @@ config LOONGARCH
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_PREEMPT_DYNAMIC_KEY
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RETHOOK
 	select HAVE_RSEQ
diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index b86f2ff3165928..4ba8d67ddb0977 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -68,6 +68,9 @@ LDFLAGS_vmlinux			+= -static -n -nostdlib
 ifdef CONFIG_AS_HAS_EXPLICIT_RELOCS
 cflags-y			+= $(call cc-option,-mexplicit-relocs)
 KBUILD_CFLAGS_KERNEL		+= $(call cc-option,-mdirect-extern-access)
+KBUILD_CFLAGS_KERNEL		+= $(call cc-option,-fdirect-access-external-data)
+KBUILD_AFLAGS_MODULE		+= $(call cc-option,-fno-direct-access-external-data)
+KBUILD_CFLAGS_MODULE		+= $(call cc-option,-fno-direct-access-external-data)
 KBUILD_AFLAGS_MODULE		+= $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax)
 KBUILD_CFLAGS_MODULE		+= $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax)
 else
@@ -80,7 +83,7 @@ endif
 
 ifeq ($(CONFIG_RELOCATABLE),y)
 KBUILD_CFLAGS_KERNEL		+= -fPIE
-LDFLAGS_vmlinux			+= -static -pie --no-dynamic-linker -z notext
+LDFLAGS_vmlinux			+= -static -pie --no-dynamic-linker -z notext $(call ld-option, --apply-dynamic-relocs)
 endif
 
 cflags-y += $(call cc-option, -mno-check-zero-division)
@@ -140,6 +143,8 @@ vdso-install-y += arch/loongarch/vdso/vdso.so.dbg
 
 all:	$(notdir $(KBUILD_IMAGE))
 
+vmlinuz.efi: vmlinux.efi
+
 vmlinux.elf vmlinux.efi vmlinuz.efi: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(bootvars-y) $(boot)/$@
 
diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h
index c9544f358c3399..655db7d7a42796 100644
--- a/arch/loongarch/include/asm/asmmacro.h
+++ b/arch/loongarch/include/asm/asmmacro.h
@@ -609,8 +609,7 @@
 	lu32i.d	\reg, 0
 	lu52i.d	\reg, \reg, 0
 	.pushsection ".la_abs", "aw", %progbits
-	768:
-	.dword	768b-766b
+	.dword	766b
 	.dword	\sym
 	.popsection
 #endif
diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h
index e27f0c72d3242b..99af8b3160a88f 100644
--- a/arch/loongarch/include/asm/atomic.h
+++ b/arch/loongarch/include/asm/atomic.h
@@ -36,19 +36,19 @@
 static inline void arch_atomic_##op(int i, atomic_t *v)			\
 {									\
 	__asm__ __volatile__(						\
-	"am"#asm_op"_db.w" " $zero, %1, %0	\n"			\
+	"am"#asm_op".w" " $zero, %1, %0	\n"				\
 	: "+ZB" (v->counter)						\
 	: "r" (I)							\
 	: "memory");							\
 }
 
-#define ATOMIC_OP_RETURN(op, I, asm_op, c_op)				\
-static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v)	\
+#define ATOMIC_OP_RETURN(op, I, asm_op, c_op, mb, suffix)		\
+static inline int arch_atomic_##op##_return##suffix(int i, atomic_t *v)	\
 {									\
 	int result;							\
 									\
 	__asm__ __volatile__(						\
-	"am"#asm_op"_db.w" " %1, %2, %0		\n"			\
+	"am"#asm_op#mb".w" " %1, %2, %0		\n"			\
 	: "+ZB" (v->counter), "=&r" (result)				\
 	: "r" (I)							\
 	: "memory");							\
@@ -56,13 +56,13 @@ static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 	return result c_op I;						\
 }
 
-#define ATOMIC_FETCH_OP(op, I, asm_op)					\
-static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
+#define ATOMIC_FETCH_OP(op, I, asm_op, mb, suffix)			\
+static inline int arch_atomic_fetch_##op##suffix(int i, atomic_t *v)	\
 {									\
 	int result;							\
 									\
 	__asm__ __volatile__(						\
-	"am"#asm_op"_db.w" " %1, %2, %0		\n"			\
+	"am"#asm_op#mb".w" " %1, %2, %0		\n"			\
 	: "+ZB" (v->counter), "=&r" (result)				\
 	: "r" (I)							\
 	: "memory");							\
@@ -72,29 +72,53 @@ static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
 
 #define ATOMIC_OPS(op, I, asm_op, c_op)					\
 	ATOMIC_OP(op, I, asm_op)					\
-	ATOMIC_OP_RETURN(op, I, asm_op, c_op)				\
-	ATOMIC_FETCH_OP(op, I, asm_op)
+	ATOMIC_OP_RETURN(op, I, asm_op, c_op, _db,         )		\
+	ATOMIC_OP_RETURN(op, I, asm_op, c_op,    , _relaxed)		\
+	ATOMIC_FETCH_OP(op, I, asm_op, _db,         )			\
+	ATOMIC_FETCH_OP(op, I, asm_op,    , _relaxed)
 
 ATOMIC_OPS(add, i, add, +)
 ATOMIC_OPS(sub, -i, add, +)
 
+#define arch_atomic_add_return		arch_atomic_add_return
+#define arch_atomic_add_return_acquire	arch_atomic_add_return
+#define arch_atomic_add_return_release	arch_atomic_add_return
 #define arch_atomic_add_return_relaxed	arch_atomic_add_return_relaxed
+#define arch_atomic_sub_return		arch_atomic_sub_return
+#define arch_atomic_sub_return_acquire	arch_atomic_sub_return
+#define arch_atomic_sub_return_release	arch_atomic_sub_return
 #define arch_atomic_sub_return_relaxed	arch_atomic_sub_return_relaxed
+#define arch_atomic_fetch_add		arch_atomic_fetch_add
+#define arch_atomic_fetch_add_acquire	arch_atomic_fetch_add
+#define arch_atomic_fetch_add_release	arch_atomic_fetch_add
 #define arch_atomic_fetch_add_relaxed	arch_atomic_fetch_add_relaxed
+#define arch_atomic_fetch_sub		arch_atomic_fetch_sub
+#define arch_atomic_fetch_sub_acquire	arch_atomic_fetch_sub
+#define arch_atomic_fetch_sub_release	arch_atomic_fetch_sub
 #define arch_atomic_fetch_sub_relaxed	arch_atomic_fetch_sub_relaxed
 
 #undef ATOMIC_OPS
 
 #define ATOMIC_OPS(op, I, asm_op)					\
 	ATOMIC_OP(op, I, asm_op)					\
-	ATOMIC_FETCH_OP(op, I, asm_op)
+	ATOMIC_FETCH_OP(op, I, asm_op, _db,         )			\
+	ATOMIC_FETCH_OP(op, I, asm_op,    , _relaxed)
 
 ATOMIC_OPS(and, i, and)
 ATOMIC_OPS(or, i, or)
 ATOMIC_OPS(xor, i, xor)
 
+#define arch_atomic_fetch_and		arch_atomic_fetch_and
+#define arch_atomic_fetch_and_acquire	arch_atomic_fetch_and
+#define arch_atomic_fetch_and_release	arch_atomic_fetch_and
 #define arch_atomic_fetch_and_relaxed	arch_atomic_fetch_and_relaxed
+#define arch_atomic_fetch_or		arch_atomic_fetch_or
+#define arch_atomic_fetch_or_acquire	arch_atomic_fetch_or
+#define arch_atomic_fetch_or_release	arch_atomic_fetch_or
 #define arch_atomic_fetch_or_relaxed	arch_atomic_fetch_or_relaxed
+#define arch_atomic_fetch_xor		arch_atomic_fetch_xor
+#define arch_atomic_fetch_xor_acquire	arch_atomic_fetch_xor
+#define arch_atomic_fetch_xor_release	arch_atomic_fetch_xor
 #define arch_atomic_fetch_xor_relaxed	arch_atomic_fetch_xor_relaxed
 
 #undef ATOMIC_OPS
@@ -172,18 +196,18 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v)
 static inline void arch_atomic64_##op(long i, atomic64_t *v)		\
 {									\
 	__asm__ __volatile__(						\
-	"am"#asm_op"_db.d " " $zero, %1, %0	\n"			\
+	"am"#asm_op".d " " $zero, %1, %0	\n"			\
 	: "+ZB" (v->counter)						\
 	: "r" (I)							\
 	: "memory");							\
 }
 
-#define ATOMIC64_OP_RETURN(op, I, asm_op, c_op)					\
-static inline long arch_atomic64_##op##_return_relaxed(long i, atomic64_t *v)	\
+#define ATOMIC64_OP_RETURN(op, I, asm_op, c_op, mb, suffix)			\
+static inline long arch_atomic64_##op##_return##suffix(long i, atomic64_t *v)	\
 {										\
 	long result;								\
 	__asm__ __volatile__(							\
-	"am"#asm_op"_db.d " " %1, %2, %0		\n"			\
+	"am"#asm_op#mb".d " " %1, %2, %0		\n"			\
 	: "+ZB" (v->counter), "=&r" (result)					\
 	: "r" (I)								\
 	: "memory");								\
@@ -191,13 +215,13 @@ static inline long arch_atomic64_##op##_return_relaxed(long i, atomic64_t *v)	\
 	return result c_op I;							\
 }
 
-#define ATOMIC64_FETCH_OP(op, I, asm_op)					\
-static inline long arch_atomic64_fetch_##op##_relaxed(long i, atomic64_t *v)	\
+#define ATOMIC64_FETCH_OP(op, I, asm_op, mb, suffix)				\
+static inline long arch_atomic64_fetch_##op##suffix(long i, atomic64_t *v)	\
 {										\
 	long result;								\
 										\
 	__asm__ __volatile__(							\
-	"am"#asm_op"_db.d " " %1, %2, %0		\n"			\
+	"am"#asm_op#mb".d " " %1, %2, %0		\n"			\
 	: "+ZB" (v->counter), "=&r" (result)					\
 	: "r" (I)								\
 	: "memory");								\
@@ -207,29 +231,53 @@ static inline long arch_atomic64_fetch_##op##_relaxed(long i, atomic64_t *v)	\
 
 #define ATOMIC64_OPS(op, I, asm_op, c_op)				      \
 	ATOMIC64_OP(op, I, asm_op)					      \
-	ATOMIC64_OP_RETURN(op, I, asm_op, c_op)				      \
-	ATOMIC64_FETCH_OP(op, I, asm_op)
+	ATOMIC64_OP_RETURN(op, I, asm_op, c_op, _db,         )		      \
+	ATOMIC64_OP_RETURN(op, I, asm_op, c_op,    , _relaxed)		      \
+	ATOMIC64_FETCH_OP(op, I, asm_op, _db,         )			      \
+	ATOMIC64_FETCH_OP(op, I, asm_op,    , _relaxed)
 
 ATOMIC64_OPS(add, i, add, +)
 ATOMIC64_OPS(sub, -i, add, +)
 
+#define arch_atomic64_add_return		arch_atomic64_add_return
+#define arch_atomic64_add_return_acquire	arch_atomic64_add_return
+#define arch_atomic64_add_return_release	arch_atomic64_add_return
 #define arch_atomic64_add_return_relaxed	arch_atomic64_add_return_relaxed
+#define arch_atomic64_sub_return		arch_atomic64_sub_return
+#define arch_atomic64_sub_return_acquire	arch_atomic64_sub_return
+#define arch_atomic64_sub_return_release	arch_atomic64_sub_return
 #define arch_atomic64_sub_return_relaxed	arch_atomic64_sub_return_relaxed
+#define arch_atomic64_fetch_add			arch_atomic64_fetch_add
+#define arch_atomic64_fetch_add_acquire		arch_atomic64_fetch_add
+#define arch_atomic64_fetch_add_release		arch_atomic64_fetch_add
 #define arch_atomic64_fetch_add_relaxed		arch_atomic64_fetch_add_relaxed
+#define arch_atomic64_fetch_sub			arch_atomic64_fetch_sub
+#define arch_atomic64_fetch_sub_acquire		arch_atomic64_fetch_sub
+#define arch_atomic64_fetch_sub_release		arch_atomic64_fetch_sub
 #define arch_atomic64_fetch_sub_relaxed		arch_atomic64_fetch_sub_relaxed
 
 #undef ATOMIC64_OPS
 
 #define ATOMIC64_OPS(op, I, asm_op)					      \
 	ATOMIC64_OP(op, I, asm_op)					      \
-	ATOMIC64_FETCH_OP(op, I, asm_op)
+	ATOMIC64_FETCH_OP(op, I, asm_op, _db,         )			      \
+	ATOMIC64_FETCH_OP(op, I, asm_op,    , _relaxed)
 
 ATOMIC64_OPS(and, i, and)
 ATOMIC64_OPS(or, i, or)
 ATOMIC64_OPS(xor, i, xor)
 
+#define arch_atomic64_fetch_and		arch_atomic64_fetch_and
+#define arch_atomic64_fetch_and_acquire	arch_atomic64_fetch_and
+#define arch_atomic64_fetch_and_release	arch_atomic64_fetch_and
 #define arch_atomic64_fetch_and_relaxed	arch_atomic64_fetch_and_relaxed
+#define arch_atomic64_fetch_or		arch_atomic64_fetch_or
+#define arch_atomic64_fetch_or_acquire	arch_atomic64_fetch_or
+#define arch_atomic64_fetch_or_release	arch_atomic64_fetch_or
 #define arch_atomic64_fetch_or_relaxed	arch_atomic64_fetch_or_relaxed
+#define arch_atomic64_fetch_xor		arch_atomic64_fetch_xor
+#define arch_atomic64_fetch_xor_acquire	arch_atomic64_fetch_xor
+#define arch_atomic64_fetch_xor_release	arch_atomic64_fetch_xor
 #define arch_atomic64_fetch_xor_relaxed	arch_atomic64_fetch_xor_relaxed
 
 #undef ATOMIC64_OPS
diff --git a/arch/loongarch/include/asm/efi.h b/arch/loongarch/include/asm/efi.h
index 091897d40b0375..91d81f9730ab3f 100644
--- a/arch/loongarch/include/asm/efi.h
+++ b/arch/loongarch/include/asm/efi.h
@@ -32,6 +32,6 @@ static inline unsigned long efi_get_kimg_min_align(void)
 
 #define EFI_KIMG_PREFERRED_ADDRESS	PHYSADDR(VMLINUX_LOAD_ADDRESS)
 
-unsigned long kernel_entry_address(void);
+unsigned long kernel_entry_address(unsigned long kernel_addr);
 
 #endif /* _ASM_LOONGARCH_EFI_H */
diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h
index b9a4ab54285c11..9b16a3b8e70608 100644
--- a/arch/loongarch/include/asm/elf.h
+++ b/arch/loongarch/include/asm/elf.h
@@ -293,7 +293,7 @@ extern const char *__elf_platform;
 #define ELF_PLAT_INIT(_r, load_addr)	do { \
 	_r->regs[1] = _r->regs[2] = _r->regs[3] = _r->regs[4] = 0;	\
 	_r->regs[5] = _r->regs[6] = _r->regs[7] = _r->regs[8] = 0;	\
-	_r->regs[9] = _r->regs[10] = _r->regs[11] = _r->regs[12] = 0;	\
+	_r->regs[9] = _r->regs[10] /* syscall n */ = _r->regs[12] = 0;	\
 	_r->regs[13] = _r->regs[14] = _r->regs[15] = _r->regs[16] = 0;	\
 	_r->regs[17] = _r->regs[18] = _r->regs[19] = _r->regs[20] = 0;	\
 	_r->regs[21] = _r->regs[22] = _r->regs[23] = _r->regs[24] = 0;	\
diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h
index 008a88ead60d9a..d8f637f9e400bc 100644
--- a/arch/loongarch/include/asm/inst.h
+++ b/arch/loongarch/include/asm/inst.h
@@ -65,6 +65,8 @@ enum reg2_op {
 	revbd_op	= 0x0f,
 	revh2w_op	= 0x10,
 	revhd_op	= 0x11,
+	extwh_op	= 0x16,
+	extwb_op	= 0x17,
 	iocsrrdb_op     = 0x19200,
 	iocsrrdh_op     = 0x19201,
 	iocsrrdw_op     = 0x19202,
@@ -572,6 +574,8 @@ static inline void emit_##NAME(union loongarch_instruction *insn,	\
 DEF_EMIT_REG2_FORMAT(revb2h, revb2h_op)
 DEF_EMIT_REG2_FORMAT(revb2w, revb2w_op)
 DEF_EMIT_REG2_FORMAT(revbd, revbd_op)
+DEF_EMIT_REG2_FORMAT(extwh, extwh_op)
+DEF_EMIT_REG2_FORMAT(extwb, extwb_op)
 
 #define DEF_EMIT_REG2I5_FORMAT(NAME, OP)				\
 static inline void emit_##NAME(union loongarch_instruction *insn,	\
@@ -623,6 +627,9 @@ DEF_EMIT_REG2I12_FORMAT(lu52id, lu52id_op)
 DEF_EMIT_REG2I12_FORMAT(andi, andi_op)
 DEF_EMIT_REG2I12_FORMAT(ori, ori_op)
 DEF_EMIT_REG2I12_FORMAT(xori, xori_op)
+DEF_EMIT_REG2I12_FORMAT(ldb, ldb_op)
+DEF_EMIT_REG2I12_FORMAT(ldh, ldh_op)
+DEF_EMIT_REG2I12_FORMAT(ldw, ldw_op)
 DEF_EMIT_REG2I12_FORMAT(ldbu, ldbu_op)
 DEF_EMIT_REG2I12_FORMAT(ldhu, ldhu_op)
 DEF_EMIT_REG2I12_FORMAT(ldwu, ldwu_op)
@@ -701,9 +708,12 @@ static inline void emit_##NAME(union loongarch_instruction *insn,	\
 	insn->reg3_format.rk = rk;					\
 }
 
+DEF_EMIT_REG3_FORMAT(addw, addw_op)
 DEF_EMIT_REG3_FORMAT(addd, addd_op)
 DEF_EMIT_REG3_FORMAT(subd, subd_op)
 DEF_EMIT_REG3_FORMAT(muld, muld_op)
+DEF_EMIT_REG3_FORMAT(divd, divd_op)
+DEF_EMIT_REG3_FORMAT(modd, modd_op)
 DEF_EMIT_REG3_FORMAT(divdu, divdu_op)
 DEF_EMIT_REG3_FORMAT(moddu, moddu_op)
 DEF_EMIT_REG3_FORMAT(and, and_op)
@@ -715,6 +725,9 @@ DEF_EMIT_REG3_FORMAT(srlw, srlw_op)
 DEF_EMIT_REG3_FORMAT(srld, srld_op)
 DEF_EMIT_REG3_FORMAT(sraw, sraw_op)
 DEF_EMIT_REG3_FORMAT(srad, srad_op)
+DEF_EMIT_REG3_FORMAT(ldxb, ldxb_op)
+DEF_EMIT_REG3_FORMAT(ldxh, ldxh_op)
+DEF_EMIT_REG3_FORMAT(ldxw, ldxw_op)
 DEF_EMIT_REG3_FORMAT(ldxbu, ldxbu_op)
 DEF_EMIT_REG3_FORMAT(ldxhu, ldxhu_op)
 DEF_EMIT_REG3_FORMAT(ldxwu, ldxwu_op)
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index 9b4957cefa8ad2..46366e783c8411 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -1098,12 +1098,11 @@
 
 static __always_inline u64 drdtime(void)
 {
-	int rID = 0;
 	u64 val = 0;
 
 	__asm__ __volatile__(
-		"rdtime.d %0, %1 \n\t"
-		: "=r"(val), "=r"(rID)
+		"rdtime.d %0, $zero\n\t"
+		: "=r"(val)
 		:
 		);
 	return val;
diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h
index b9f567e6601668..9b36ac003f8907 100644
--- a/arch/loongarch/include/asm/percpu.h
+++ b/arch/loongarch/include/asm/percpu.h
@@ -32,7 +32,7 @@ static inline void set_my_cpu_offset(unsigned long off)
 #define __my_cpu_offset __my_cpu_offset
 
 #define PERCPU_OP(op, asm_op, c_op)					\
-static inline unsigned long __percpu_##op(void *ptr,			\
+static __always_inline unsigned long __percpu_##op(void *ptr,		\
 			unsigned long val, int size)			\
 {									\
 	unsigned long ret;						\
@@ -40,13 +40,13 @@ static inline unsigned long __percpu_##op(void *ptr,			\
 	switch (size) {							\
 	case 4:								\
 		__asm__ __volatile__(					\
-		"am"#asm_op".w"	" %[ret], %[val], %[ptr]	\n"		\
+		"am"#asm_op".w"	" %[ret], %[val], %[ptr]	\n"	\
 		: [ret] "=&r" (ret), [ptr] "+ZB"(*(u32 *)ptr)		\
 		: [val] "r" (val));					\
 		break;							\
 	case 8:								\
 		__asm__ __volatile__(					\
-		"am"#asm_op".d" " %[ret], %[val], %[ptr]	\n"		\
+		"am"#asm_op".d" " %[ret], %[val], %[ptr]	\n"	\
 		: [ret] "=&r" (ret), [ptr] "+ZB"(*(u64 *)ptr)		\
 		: [val] "r" (val));					\
 		break;							\
@@ -63,7 +63,7 @@ PERCPU_OP(and, and, &)
 PERCPU_OP(or, or, |)
 #undef PERCPU_OP
 
-static inline unsigned long __percpu_read(void *ptr, int size)
+static __always_inline unsigned long __percpu_read(void __percpu *ptr, int size)
 {
 	unsigned long ret;
 
@@ -100,7 +100,7 @@ static inline unsigned long __percpu_read(void *ptr, int size)
 	return ret;
 }
 
-static inline void __percpu_write(void *ptr, unsigned long val, int size)
+static __always_inline void __percpu_write(void __percpu *ptr, unsigned long val, int size)
 {
 	switch (size) {
 	case 1:
@@ -132,8 +132,7 @@ static inline void __percpu_write(void *ptr, unsigned long val, int size)
 	}
 }
 
-static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
-						int size)
+static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, int size)
 {
 	switch (size) {
 	case 1:
diff --git a/arch/loongarch/include/asm/setup.h b/arch/loongarch/include/asm/setup.h
index a0bc159ce8bdc0..ee52fb1e996316 100644
--- a/arch/loongarch/include/asm/setup.h
+++ b/arch/loongarch/include/asm/setup.h
@@ -25,7 +25,7 @@ extern void set_merr_handler(unsigned long offset, void *addr, unsigned long len
 #ifdef CONFIG_RELOCATABLE
 
 struct rela_la_abs {
-	long offset;
+	long pc;
 	long symvalue;
 };
 
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 4fcc168f073231..3c808c6803703c 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -57,7 +57,7 @@ obj-$(CONFIG_MAGIC_SYSRQ)	+= sysrq.o
 
 obj-$(CONFIG_RELOCATABLE)	+= relocate.o
 
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 
 obj-$(CONFIG_UNWINDER_GUESS)	+= unwind_guess.o
diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c
index 6c3eff9af9fb1e..1acfa704c8d09b 100644
--- a/arch/loongarch/kernel/relocate.c
+++ b/arch/loongarch/kernel/relocate.c
@@ -52,7 +52,7 @@ static inline void __init relocate_absolute(long random_offset)
 	for (p = begin; (void *)p < end; p++) {
 		long v = p->symvalue;
 		uint32_t lu12iw, ori, lu32id, lu52id;
-		union loongarch_instruction *insn = (void *)p - p->offset;
+		union loongarch_instruction *insn = (void *)p->pc;
 
 		lu12iw = (v >> 12) & 0xfffff;
 		ori    = v & 0xfff;
@@ -102,6 +102,14 @@ static inline __init unsigned long get_random_boot(void)
 	return hash;
 }
 
+static int __init nokaslr(char *p)
+{
+	pr_info("KASLR is disabled.\n");
+
+	return 0; /* Print a notice and silence the boot warning */
+}
+early_param("nokaslr", nokaslr);
+
 static inline __init bool kaslr_disabled(void)
 {
 	char *str;
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index ef35c871244f08..5bca12d16e0691 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -504,8 +504,9 @@ asmlinkage void start_secondary(void)
 	unsigned int cpu;
 
 	sync_counter();
-	cpu = smp_processor_id();
+	cpu = raw_smp_processor_id();
 	set_my_cpu_offset(per_cpu_offset(cpu));
+	rcutree_report_cpu_starting(cpu);
 
 	cpu_probe();
 	constant_clockevent_init();
diff --git a/arch/loongarch/kernel/stacktrace.c b/arch/loongarch/kernel/stacktrace.c
index 92270f14db9482..f623feb2129f12 100644
--- a/arch/loongarch/kernel/stacktrace.c
+++ b/arch/loongarch/kernel/stacktrace.c
@@ -32,7 +32,7 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
 	}
 
 	for (unwind_start(&state, task, regs);
-	     !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) {
+	     !unwind_done(&state); unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);
 		if (!addr || !consume_entry(cookie, addr))
 			break;
diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index 3064af94db9c2e..e7015f7b70e37c 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -58,14 +58,16 @@ static int constant_set_state_oneshot(struct clock_event_device *evt)
 	return 0;
 }
 
-static int constant_set_state_oneshot_stopped(struct clock_event_device *evt)
+static int constant_set_state_periodic(struct clock_event_device *evt)
 {
+	unsigned long period;
 	unsigned long timer_config;
 
 	raw_spin_lock(&state_lock);
 
-	timer_config = csr_read64(LOONGARCH_CSR_TCFG);
-	timer_config &= ~CSR_TCFG_EN;
+	period = const_clock_freq / HZ;
+	timer_config = period & CSR_TCFG_VAL;
+	timer_config |= (CSR_TCFG_PERIOD | CSR_TCFG_EN);
 	csr_write64(timer_config, LOONGARCH_CSR_TCFG);
 
 	raw_spin_unlock(&state_lock);
@@ -73,16 +75,14 @@ static int constant_set_state_oneshot_stopped(struct clock_event_device *evt)
 	return 0;
 }
 
-static int constant_set_state_periodic(struct clock_event_device *evt)
+static int constant_set_state_shutdown(struct clock_event_device *evt)
 {
-	unsigned long period;
 	unsigned long timer_config;
 
 	raw_spin_lock(&state_lock);
 
-	period = const_clock_freq / HZ;
-	timer_config = period & CSR_TCFG_VAL;
-	timer_config |= (CSR_TCFG_PERIOD | CSR_TCFG_EN);
+	timer_config = csr_read64(LOONGARCH_CSR_TCFG);
+	timer_config &= ~CSR_TCFG_EN;
 	csr_write64(timer_config, LOONGARCH_CSR_TCFG);
 
 	raw_spin_unlock(&state_lock);
@@ -90,11 +90,6 @@ static int constant_set_state_periodic(struct clock_event_device *evt)
 	return 0;
 }
 
-static int constant_set_state_shutdown(struct clock_event_device *evt)
-{
-	return 0;
-}
-
 static int constant_timer_next_event(unsigned long delta, struct clock_event_device *evt)
 {
 	unsigned long timer_config;
@@ -161,7 +156,7 @@ int constant_clockevent_init(void)
 	cd->rating = 320;
 	cd->cpumask = cpumask_of(cpu);
 	cd->set_state_oneshot = constant_set_state_oneshot;
-	cd->set_state_oneshot_stopped = constant_set_state_oneshot_stopped;
+	cd->set_state_oneshot_stopped = constant_set_state_shutdown;
 	cd->set_state_periodic = constant_set_state_periodic;
 	cd->set_state_shutdown = constant_set_state_shutdown;
 	cd->set_next_event = constant_timer_next_event;
diff --git a/arch/loongarch/kernel/unwind.c b/arch/loongarch/kernel/unwind.c
index ba324ba76fa156..a463d6961344c0 100644
--- a/arch/loongarch/kernel/unwind.c
+++ b/arch/loongarch/kernel/unwind.c
@@ -28,6 +28,5 @@ bool default_next_frame(struct unwind_state *state)
 
 	} while (!get_stack_info(state->sp, state->task, info));
 
-	state->error = true;
 	return false;
 }
diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c
index 55afc27320e12a..929ae240280a5f 100644
--- a/arch/loongarch/kernel/unwind_prologue.c
+++ b/arch/loongarch/kernel/unwind_prologue.c
@@ -227,7 +227,7 @@ static bool next_frame(struct unwind_state *state)
 	} while (!get_stack_info(state->sp, state->task, info));
 
 out:
-	state->error = true;
+	state->stack_info.type = STACK_TYPE_UNKNOWN;
 	return false;
 }
 
diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c
index 71d0539e2d0b02..2aae72e638713a 100644
--- a/arch/loongarch/mm/pgtable.c
+++ b/arch/loongarch/mm/pgtable.c
@@ -13,13 +13,13 @@ struct page *dmw_virt_to_page(unsigned long kaddr)
 {
 	return pfn_to_page(virt_to_pfn(kaddr));
 }
-EXPORT_SYMBOL_GPL(dmw_virt_to_page);
+EXPORT_SYMBOL(dmw_virt_to_page);
 
 struct page *tlb_virt_to_page(unsigned long kaddr)
 {
 	return pfn_to_page(pte_pfn(*virt_to_kpte(kaddr)));
 }
-EXPORT_SYMBOL_GPL(tlb_virt_to_page);
+EXPORT_SYMBOL(tlb_virt_to_page);
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index db9342b2d0e660..4fcd6cd6da234d 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -411,7 +411,11 @@ static int add_exception_handler(const struct bpf_insn *insn,
 	off_t offset;
 	struct exception_table_entry *ex;
 
-	if (!ctx->image || !ctx->prog->aux->extable || BPF_MODE(insn->code) != BPF_PROBE_MEM)
+	if (!ctx->image || !ctx->prog->aux->extable)
+		return 0;
+
+	if (BPF_MODE(insn->code) != BPF_PROBE_MEM &&
+	    BPF_MODE(insn->code) != BPF_PROBE_MEMSX)
 		return 0;
 
 	if (WARN_ON_ONCE(ctx->num_exentries >= ctx->prog->aux->num_exentries))
@@ -450,7 +454,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 {
 	u8 tm = -1;
 	u64 func_addr;
-	bool func_addr_fixed;
+	bool func_addr_fixed, sign_extend;
 	int i = insn - ctx->prog->insnsi;
 	int ret, jmp_offset;
 	const u8 code = insn->code;
@@ -468,8 +472,25 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 	/* dst = src */
 	case BPF_ALU | BPF_MOV | BPF_X:
 	case BPF_ALU64 | BPF_MOV | BPF_X:
-		move_reg(ctx, dst, src);
-		emit_zext_32(ctx, dst, is32);
+		switch (off) {
+		case 0:
+			move_reg(ctx, dst, src);
+			emit_zext_32(ctx, dst, is32);
+			break;
+		case 8:
+			move_reg(ctx, t1, src);
+			emit_insn(ctx, extwb, dst, t1);
+			emit_zext_32(ctx, dst, is32);
+			break;
+		case 16:
+			move_reg(ctx, t1, src);
+			emit_insn(ctx, extwh, dst, t1);
+			emit_zext_32(ctx, dst, is32);
+			break;
+		case 32:
+			emit_insn(ctx, addw, dst, src, LOONGARCH_GPR_ZERO);
+			break;
+		}
 		break;
 
 	/* dst = imm */
@@ -534,39 +555,71 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 	/* dst = dst / src */
 	case BPF_ALU | BPF_DIV | BPF_X:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
-		emit_zext_32(ctx, dst, is32);
-		move_reg(ctx, t1, src);
-		emit_zext_32(ctx, t1, is32);
-		emit_insn(ctx, divdu, dst, dst, t1);
-		emit_zext_32(ctx, dst, is32);
+		if (!off) {
+			emit_zext_32(ctx, dst, is32);
+			move_reg(ctx, t1, src);
+			emit_zext_32(ctx, t1, is32);
+			emit_insn(ctx, divdu, dst, dst, t1);
+			emit_zext_32(ctx, dst, is32);
+		} else {
+			emit_sext_32(ctx, dst, is32);
+			move_reg(ctx, t1, src);
+			emit_sext_32(ctx, t1, is32);
+			emit_insn(ctx, divd, dst, dst, t1);
+			emit_sext_32(ctx, dst, is32);
+		}
 		break;
 
 	/* dst = dst / imm */
 	case BPF_ALU | BPF_DIV | BPF_K:
 	case BPF_ALU64 | BPF_DIV | BPF_K:
-		move_imm(ctx, t1, imm, is32);
-		emit_zext_32(ctx, dst, is32);
-		emit_insn(ctx, divdu, dst, dst, t1);
-		emit_zext_32(ctx, dst, is32);
+		if (!off) {
+			move_imm(ctx, t1, imm, is32);
+			emit_zext_32(ctx, dst, is32);
+			emit_insn(ctx, divdu, dst, dst, t1);
+			emit_zext_32(ctx, dst, is32);
+		} else {
+			move_imm(ctx, t1, imm, false);
+			emit_sext_32(ctx, t1, is32);
+			emit_sext_32(ctx, dst, is32);
+			emit_insn(ctx, divd, dst, dst, t1);
+			emit_sext_32(ctx, dst, is32);
+		}
 		break;
 
 	/* dst = dst % src */
 	case BPF_ALU | BPF_MOD | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
-		emit_zext_32(ctx, dst, is32);
-		move_reg(ctx, t1, src);
-		emit_zext_32(ctx, t1, is32);
-		emit_insn(ctx, moddu, dst, dst, t1);
-		emit_zext_32(ctx, dst, is32);
+		if (!off) {
+			emit_zext_32(ctx, dst, is32);
+			move_reg(ctx, t1, src);
+			emit_zext_32(ctx, t1, is32);
+			emit_insn(ctx, moddu, dst, dst, t1);
+			emit_zext_32(ctx, dst, is32);
+		} else {
+			emit_sext_32(ctx, dst, is32);
+			move_reg(ctx, t1, src);
+			emit_sext_32(ctx, t1, is32);
+			emit_insn(ctx, modd, dst, dst, t1);
+			emit_sext_32(ctx, dst, is32);
+		}
 		break;
 
 	/* dst = dst % imm */
 	case BPF_ALU | BPF_MOD | BPF_K:
 	case BPF_ALU64 | BPF_MOD | BPF_K:
-		move_imm(ctx, t1, imm, is32);
-		emit_zext_32(ctx, dst, is32);
-		emit_insn(ctx, moddu, dst, dst, t1);
-		emit_zext_32(ctx, dst, is32);
+		if (!off) {
+			move_imm(ctx, t1, imm, is32);
+			emit_zext_32(ctx, dst, is32);
+			emit_insn(ctx, moddu, dst, dst, t1);
+			emit_zext_32(ctx, dst, is32);
+		} else {
+			move_imm(ctx, t1, imm, false);
+			emit_sext_32(ctx, t1, is32);
+			emit_sext_32(ctx, dst, is32);
+			emit_insn(ctx, modd, dst, dst, t1);
+			emit_sext_32(ctx, dst, is32);
+		}
 		break;
 
 	/* dst = -dst */
@@ -712,6 +765,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 		break;
 
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
+	case BPF_ALU64 | BPF_END | BPF_FROM_LE:
 		switch (imm) {
 		case 16:
 			emit_insn(ctx, revb2h, dst, dst);
@@ -720,8 +774,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 			break;
 		case 32:
 			emit_insn(ctx, revb2w, dst, dst);
-			/* zero-extend 32 bits into 64 bits */
-			emit_zext_32(ctx, dst, is32);
+			/* clear the upper 32 bits */
+			emit_zext_32(ctx, dst, true);
 			break;
 		case 64:
 			emit_insn(ctx, revbd, dst, dst);
@@ -828,7 +882,11 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 
 	/* PC += off */
 	case BPF_JMP | BPF_JA:
-		jmp_offset = bpf2la_offset(i, off, ctx);
+	case BPF_JMP32 | BPF_JA:
+		if (BPF_CLASS(code) == BPF_JMP)
+			jmp_offset = bpf2la_offset(i, off, ctx);
+		else
+			jmp_offset = bpf2la_offset(i, imm, ctx);
 		if (emit_uncond_jmp(ctx, jmp_offset) < 0)
 			goto toofar;
 		break;
@@ -855,8 +913,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 
 	/* function return */
 	case BPF_JMP | BPF_EXIT:
-		emit_sext_32(ctx, regmap[BPF_REG_0], true);
-
 		if (i == ctx->prog->len - 1)
 			break;
 
@@ -879,42 +935,61 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 	case BPF_LDX | BPF_PROBE_MEM | BPF_W:
 	case BPF_LDX | BPF_PROBE_MEM | BPF_H:
 	case BPF_LDX | BPF_PROBE_MEM | BPF_B:
+	/* dst_reg = (s64)*(signed size *)(src_reg + off) */
+	case BPF_LDX | BPF_MEMSX | BPF_B:
+	case BPF_LDX | BPF_MEMSX | BPF_H:
+	case BPF_LDX | BPF_MEMSX | BPF_W:
+	case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
+	case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
+	case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
+		sign_extend = BPF_MODE(insn->code) == BPF_MEMSX ||
+			      BPF_MODE(insn->code) == BPF_PROBE_MEMSX;
 		switch (BPF_SIZE(code)) {
 		case BPF_B:
 			if (is_signed_imm12(off)) {
-				emit_insn(ctx, ldbu, dst, src, off);
+				if (sign_extend)
+					emit_insn(ctx, ldb, dst, src, off);
+				else
+					emit_insn(ctx, ldbu, dst, src, off);
 			} else {
 				move_imm(ctx, t1, off, is32);
-				emit_insn(ctx, ldxbu, dst, src, t1);
+				if (sign_extend)
+					emit_insn(ctx, ldxb, dst, src, t1);
+				else
+					emit_insn(ctx, ldxbu, dst, src, t1);
 			}
 			break;
 		case BPF_H:
 			if (is_signed_imm12(off)) {
-				emit_insn(ctx, ldhu, dst, src, off);
+				if (sign_extend)
+					emit_insn(ctx, ldh, dst, src, off);
+				else
+					emit_insn(ctx, ldhu, dst, src, off);
 			} else {
 				move_imm(ctx, t1, off, is32);
-				emit_insn(ctx, ldxhu, dst, src, t1);
+				if (sign_extend)
+					emit_insn(ctx, ldxh, dst, src, t1);
+				else
+					emit_insn(ctx, ldxhu, dst, src, t1);
 			}
 			break;
 		case BPF_W:
 			if (is_signed_imm12(off)) {
-				emit_insn(ctx, ldwu, dst, src, off);
-			} else if (is_signed_imm14(off)) {
-				emit_insn(ctx, ldptrw, dst, src, off);
+				if (sign_extend)
+					emit_insn(ctx, ldw, dst, src, off);
+				else
+					emit_insn(ctx, ldwu, dst, src, off);
 			} else {
 				move_imm(ctx, t1, off, is32);
-				emit_insn(ctx, ldxwu, dst, src, t1);
+				if (sign_extend)
+					emit_insn(ctx, ldxw, dst, src, t1);
+				else
+					emit_insn(ctx, ldxwu, dst, src, t1);
 			}
 			break;
 		case BPF_DW:
-			if (is_signed_imm12(off)) {
-				emit_insn(ctx, ldd, dst, src, off);
-			} else if (is_signed_imm14(off)) {
-				emit_insn(ctx, ldptrd, dst, src, off);
-			} else {
-				move_imm(ctx, t1, off, is32);
-				emit_insn(ctx, ldxd, dst, src, t1);
-			}
+			move_imm(ctx, t1, off, is32);
+			emit_insn(ctx, ldxd, dst, src, t1);
 			break;
 		}
 
diff --git a/arch/m68k/include/asm/kexec.h b/arch/m68k/include/asm/kexec.h
index f5a8b2defa4bce..3b0b64f0a35317 100644
--- a/arch/m68k/include/asm/kexec.h
+++ b/arch/m68k/include/asm/kexec.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_M68K_KEXEC_H
 #define _ASM_M68K_KEXEC_H
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 /* Maximum physical address we can use pages from */
 #define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
@@ -25,6 +25,6 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
 #endif /* _ASM_M68K_KEXEC_H */
diff --git a/arch/m68k/kernel/Makefile b/arch/m68k/kernel/Makefile
index 01fb69a5095f43..f335bf3268a108 100644
--- a/arch/m68k/kernel/Makefile
+++ b/arch/m68k/kernel/Makefile
@@ -25,7 +25,7 @@ obj-$(CONFIG_PCI) += pcibios.o
 
 obj-$(CONFIG_M68K_NONCOHERENT_DMA) += dma.o
 
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_BOOTINFO_PROC)	+= bootinfo_proc.o
 obj-$(CONFIG_UBOOT)		+= uboot.o
 
diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms
index caad195ba5c196..a2311c4bce6a6a 100644
--- a/arch/mips/Kbuild.platforms
+++ b/arch/mips/Kbuild.platforms
@@ -2,7 +2,6 @@
 # All platforms listed in alphabetic order
 
 platform-$(CONFIG_MIPS_ALCHEMY)		+= alchemy/
-platform-$(CONFIG_AR7)			+= ar7/
 platform-$(CONFIG_ATH25)		+= ath25/
 platform-$(CONFIG_ATH79)		+= ath79/
 platform-$(CONFIG_BCM47XX)		+= bcm47xx/
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index bc8421859006fa..797ae590ebdba5 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -202,28 +202,6 @@ config MIPS_ALCHEMY
 	select SYS_SUPPORTS_ZBOOT
 	select COMMON_CLK
 
-config AR7
-	bool "Texas Instruments AR7"
-	select BOOT_ELF32
-	select COMMON_CLK
-	select DMA_NONCOHERENT
-	select CEVT_R4K
-	select CSRC_R4K
-	select IRQ_MIPS_CPU
-	select NO_EXCEPT_FILL
-	select SWAP_IO_SPACE
-	select SYS_HAS_CPU_MIPS32_R1
-	select SYS_HAS_EARLY_PRINTK
-	select SYS_SUPPORTS_32BIT_KERNEL
-	select SYS_SUPPORTS_LITTLE_ENDIAN
-	select SYS_SUPPORTS_MIPS16
-	select SYS_SUPPORTS_ZBOOT_UART16550
-	select GPIOLIB
-	select VLYNQ
-	help
-	  Support for the Texas Instruments AR7 System-on-a-Chip
-	  family: TNETD7100, 7200 and 7300.
-
 config ATH25
 	bool "Atheros AR231x/AR531x SoC support"
 	select CEVT_R4K
@@ -482,6 +460,7 @@ config MACH_LOONGSON2EF
 
 config MACH_LOONGSON64
 	bool "Loongson 64-bit family of machines"
+	select ARCH_DMA_DEFAULT_COHERENT
 	select ARCH_SPARSEMEM_ENABLE
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
@@ -1273,6 +1252,7 @@ config CPU_LOONGSON64
 	select CPU_SUPPORTS_MSA
 	select CPU_DIEI_BROKEN if !LOONGSON3_ENHANCEMENT
 	select CPU_MIPSR2_IRQ_VI
+	select DMA_NONCOHERENT
 	select WEAK_ORDERING
 	select WEAK_REORDERING_BEYOND_LLSC
 	select MIPS_ASID_BITS_VARIABLE
diff --git a/arch/mips/ar7/Makefile b/arch/mips/ar7/Makefile
deleted file mode 100644
index cd51c6c6e686e7..00000000000000
--- a/arch/mips/ar7/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-obj-y := \
-	prom.o \
-	setup.o \
-	memory.o \
-	irq.o \
-	time.o \
-	platform.o \
-	gpio.o \
-	clock.o
diff --git a/arch/mips/ar7/Platform b/arch/mips/ar7/Platform
deleted file mode 100644
index a9257cc01c3cbb..00000000000000
--- a/arch/mips/ar7/Platform
+++ /dev/null
@@ -1,5 +0,0 @@
-#
-# Texas Instruments AR7
-#
-cflags-$(CONFIG_AR7)		+= -I$(srctree)/arch/mips/include/asm/mach-ar7
-load-$(CONFIG_AR7)		+= 0xffffffff94100000
diff --git a/arch/mips/ar7/clock.c b/arch/mips/ar7/clock.c
deleted file mode 100644
index c717acbc5506c3..00000000000000
--- a/arch/mips/ar7/clock.c
+++ /dev/null
@@ -1,439 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2007 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2007 Eugene Konev <ejka@openwrt.org>
- * Copyright (C) 2009 Florian Fainelli <florian@openwrt.org>
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/export.h>
-#include <linux/delay.h>
-#include <linux/gcd.h>
-#include <linux/io.h>
-#include <linux/err.h>
-#include <linux/clkdev.h>
-#include <linux/clk.h>
-#include <linux/clk-provider.h>
-
-#include <asm/addrspace.h>
-#include <asm/mach-ar7/ar7.h>
-
-#define BOOT_PLL_SOURCE_MASK	0x3
-#define CPU_PLL_SOURCE_SHIFT	16
-#define BUS_PLL_SOURCE_SHIFT	14
-#define USB_PLL_SOURCE_SHIFT	18
-#define DSP_PLL_SOURCE_SHIFT	22
-#define BOOT_PLL_SOURCE_AFE	0
-#define BOOT_PLL_SOURCE_BUS	0
-#define BOOT_PLL_SOURCE_REF	1
-#define BOOT_PLL_SOURCE_XTAL	2
-#define BOOT_PLL_SOURCE_CPU	3
-#define BOOT_PLL_BYPASS		0x00000020
-#define BOOT_PLL_ASYNC_MODE	0x02000000
-#define BOOT_PLL_2TO1_MODE	0x00008000
-
-#define TNETD7200_CLOCK_ID_CPU	0
-#define TNETD7200_CLOCK_ID_DSP	1
-#define TNETD7200_CLOCK_ID_USB	2
-
-#define TNETD7200_DEF_CPU_CLK	211000000
-#define TNETD7200_DEF_DSP_CLK	125000000
-#define TNETD7200_DEF_USB_CLK	48000000
-
-struct tnetd7300_clock {
-	u32 ctrl;
-#define PREDIV_MASK	0x001f0000
-#define PREDIV_SHIFT	16
-#define POSTDIV_MASK	0x0000001f
-	u32 unused1[3];
-	u32 pll;
-#define MUL_MASK	0x0000f000
-#define MUL_SHIFT	12
-#define PLL_MODE_MASK	0x00000001
-#define PLL_NDIV	0x00000800
-#define PLL_DIV		0x00000002
-#define PLL_STATUS	0x00000001
-	u32 unused2[3];
-};
-
-struct tnetd7300_clocks {
-	struct tnetd7300_clock bus;
-	struct tnetd7300_clock cpu;
-	struct tnetd7300_clock usb;
-	struct tnetd7300_clock dsp;
-};
-
-struct tnetd7200_clock {
-	u32 ctrl;
-	u32 unused1[3];
-#define DIVISOR_ENABLE_MASK 0x00008000
-	u32 mul;
-	u32 prediv;
-	u32 postdiv;
-	u32 postdiv2;
-	u32 unused2[6];
-	u32 cmd;
-	u32 status;
-	u32 cmden;
-	u32 padding[15];
-};
-
-struct tnetd7200_clocks {
-	struct tnetd7200_clock cpu;
-	struct tnetd7200_clock dsp;
-	struct tnetd7200_clock usb;
-};
-
-struct clk_rate {
-	u32 rate;
-};
-static struct clk_rate bus_clk = {
-	.rate	= 125000000,
-};
-
-static struct clk_rate cpu_clk = {
-	.rate	= 150000000,
-};
-
-static void approximate(int base, int target, int *prediv,
-			int *postdiv, int *mul)
-{
-	int i, j, k, freq, res = target;
-	for (i = 1; i <= 16; i++)
-		for (j = 1; j <= 32; j++)
-			for (k = 1; k <= 32; k++) {
-				freq = abs(base / j * i / k - target);
-				if (freq < res) {
-					res = freq;
-					*mul = i;
-					*prediv = j;
-					*postdiv = k;
-				}
-			}
-}
-
-static void calculate(int base, int target, int *prediv, int *postdiv,
-	int *mul)
-{
-	int tmp_gcd, tmp_base, tmp_freq;
-
-	for (*prediv = 1; *prediv <= 32; (*prediv)++) {
-		tmp_base = base / *prediv;
-		tmp_gcd = gcd(target, tmp_base);
-		*mul = target / tmp_gcd;
-		*postdiv = tmp_base / tmp_gcd;
-		if ((*mul < 1) || (*mul >= 16))
-			continue;
-		if ((*postdiv > 0) & (*postdiv <= 32))
-			break;
-	}
-
-	if (base / *prediv * *mul / *postdiv != target) {
-		approximate(base, target, prediv, postdiv, mul);
-		tmp_freq = base / *prediv * *mul / *postdiv;
-		printk(KERN_WARNING
-		       "Adjusted requested frequency %d to %d\n",
-		       target, tmp_freq);
-	}
-
-	printk(KERN_DEBUG "Clocks: prediv: %d, postdiv: %d, mul: %d\n",
-	       *prediv, *postdiv, *mul);
-}
-
-static int tnetd7300_dsp_clock(void)
-{
-	u32 didr1, didr2;
-	u8 rev = ar7_chip_rev();
-	didr1 = readl((void *)KSEG1ADDR(AR7_REGS_GPIO + 0x18));
-	didr2 = readl((void *)KSEG1ADDR(AR7_REGS_GPIO + 0x1c));
-	if (didr2 & (1 << 23))
-		return 0;
-	if ((rev >= 0x23) && (rev != 0x57))
-		return 250000000;
-	if ((((didr2 & 0x1fff) << 10) | ((didr1 & 0xffc00000) >> 22))
-	    > 4208000)
-		return 250000000;
-	return 0;
-}
-
-static int tnetd7300_get_clock(u32 shift, struct tnetd7300_clock *clock,
-	u32 *bootcr, u32 bus_clock)
-{
-	int product;
-	int base_clock = AR7_REF_CLOCK;
-	u32 ctrl = readl(&clock->ctrl);
-	u32 pll = readl(&clock->pll);
-	int prediv = ((ctrl & PREDIV_MASK) >> PREDIV_SHIFT) + 1;
-	int postdiv = (ctrl & POSTDIV_MASK) + 1;
-	int divisor = prediv * postdiv;
-	int mul = ((pll & MUL_MASK) >> MUL_SHIFT) + 1;
-
-	switch ((*bootcr & (BOOT_PLL_SOURCE_MASK << shift)) >> shift) {
-	case BOOT_PLL_SOURCE_BUS:
-		base_clock = bus_clock;
-		break;
-	case BOOT_PLL_SOURCE_REF:
-		base_clock = AR7_REF_CLOCK;
-		break;
-	case BOOT_PLL_SOURCE_XTAL:
-		base_clock = AR7_XTAL_CLOCK;
-		break;
-	case BOOT_PLL_SOURCE_CPU:
-		base_clock = cpu_clk.rate;
-		break;
-	}
-
-	if (*bootcr & BOOT_PLL_BYPASS)
-		return base_clock / divisor;
-
-	if ((pll & PLL_MODE_MASK) == 0)
-		return (base_clock >> (mul / 16 + 1)) / divisor;
-
-	if ((pll & (PLL_NDIV | PLL_DIV)) == (PLL_NDIV | PLL_DIV)) {
-		product = (mul & 1) ?
-			(base_clock * mul) >> 1 :
-			(base_clock * (mul - 1)) >> 2;
-		return product / divisor;
-	}
-
-	if (mul == 16)
-		return base_clock / divisor;
-
-	return base_clock * mul / divisor;
-}
-
-static void tnetd7300_set_clock(u32 shift, struct tnetd7300_clock *clock,
-	u32 *bootcr, u32 frequency)
-{
-	int prediv, postdiv, mul;
-	int base_clock = bus_clk.rate;
-
-	switch ((*bootcr & (BOOT_PLL_SOURCE_MASK << shift)) >> shift) {
-	case BOOT_PLL_SOURCE_BUS:
-		base_clock = bus_clk.rate;
-		break;
-	case BOOT_PLL_SOURCE_REF:
-		base_clock = AR7_REF_CLOCK;
-		break;
-	case BOOT_PLL_SOURCE_XTAL:
-		base_clock = AR7_XTAL_CLOCK;
-		break;
-	case BOOT_PLL_SOURCE_CPU:
-		base_clock = cpu_clk.rate;
-		break;
-	}
-
-	calculate(base_clock, frequency, &prediv, &postdiv, &mul);
-
-	writel(((prediv - 1) << PREDIV_SHIFT) | (postdiv - 1), &clock->ctrl);
-	mdelay(1);
-	writel(4, &clock->pll);
-	while (readl(&clock->pll) & PLL_STATUS)
-		;
-	writel(((mul - 1) << MUL_SHIFT) | (0xff << 3) | 0x0e, &clock->pll);
-	mdelay(75);
-}
-
-static void __init tnetd7300_init_clocks(void)
-{
-	u32 *bootcr = (u32 *)ioremap(AR7_REGS_DCL, 4);
-	struct tnetd7300_clocks *clocks =
-					ioremap(UR8_REGS_CLOCKS,
-					sizeof(struct tnetd7300_clocks));
-	u32 dsp_clk;
-	struct clk *clk;
-
-	bus_clk.rate = tnetd7300_get_clock(BUS_PLL_SOURCE_SHIFT,
-		&clocks->bus, bootcr, AR7_AFE_CLOCK);
-
-	if (*bootcr & BOOT_PLL_ASYNC_MODE)
-		cpu_clk.rate = tnetd7300_get_clock(CPU_PLL_SOURCE_SHIFT,
-			&clocks->cpu, bootcr, AR7_AFE_CLOCK);
-	else
-		cpu_clk.rate = bus_clk.rate;
-
-	dsp_clk = tnetd7300_dsp_clock();
-	if (dsp_clk == 250000000)
-		tnetd7300_set_clock(DSP_PLL_SOURCE_SHIFT, &clocks->dsp,
-			bootcr, dsp_clk);
-
-	iounmap(clocks);
-	iounmap(bootcr);
-
-	clk = clk_register_fixed_rate(NULL, "cpu", NULL, 0, cpu_clk.rate);
-	clkdev_create(clk, "cpu", NULL);
-	clk = clk_register_fixed_rate(NULL, "dsp", NULL, 0, dsp_clk);
-	clkdev_create(clk, "dsp", NULL);
-}
-
-static void tnetd7200_set_clock(int base, struct tnetd7200_clock *clock,
-	int prediv, int postdiv, int postdiv2, int mul, u32 frequency)
-{
-	printk(KERN_INFO
-		"Clocks: base = %d, frequency = %u, prediv = %d, "
-		"postdiv = %d, postdiv2 = %d, mul = %d\n",
-		base, frequency, prediv, postdiv, postdiv2, mul);
-
-	writel(0, &clock->ctrl);
-	writel(DIVISOR_ENABLE_MASK | ((prediv - 1) & 0x1F), &clock->prediv);
-	writel((mul - 1) & 0xF, &clock->mul);
-
-	while (readl(&clock->status) & 0x1)
-		; /* nop */
-
-	writel(DIVISOR_ENABLE_MASK | ((postdiv - 1) & 0x1F), &clock->postdiv);
-
-	writel(readl(&clock->cmden) | 1, &clock->cmden);
-	writel(readl(&clock->cmd) | 1, &clock->cmd);
-
-	while (readl(&clock->status) & 0x1)
-		; /* nop */
-
-	writel(DIVISOR_ENABLE_MASK | ((postdiv2 - 1) & 0x1F), &clock->postdiv2);
-
-	writel(readl(&clock->cmden) | 1, &clock->cmden);
-	writel(readl(&clock->cmd) | 1, &clock->cmd);
-
-	while (readl(&clock->status) & 0x1)
-		; /* nop */
-
-	writel(readl(&clock->ctrl) | 1, &clock->ctrl);
-}
-
-static int tnetd7200_get_clock_base(int clock_id, u32 *bootcr)
-{
-	if (*bootcr & BOOT_PLL_ASYNC_MODE)
-		/* Async */
-		switch (clock_id) {
-		case TNETD7200_CLOCK_ID_DSP:
-			return AR7_REF_CLOCK;
-		default:
-			return AR7_AFE_CLOCK;
-		}
-	else
-		/* Sync */
-		if (*bootcr & BOOT_PLL_2TO1_MODE)
-			/* 2:1 */
-			switch (clock_id) {
-			case TNETD7200_CLOCK_ID_DSP:
-				return AR7_REF_CLOCK;
-			default:
-				return AR7_AFE_CLOCK;
-			}
-		else
-			/* 1:1 */
-			return AR7_REF_CLOCK;
-}
-
-
-static void __init tnetd7200_init_clocks(void)
-{
-	u32 *bootcr = (u32 *)ioremap(AR7_REGS_DCL, 4);
-	struct tnetd7200_clocks *clocks =
-					ioremap(AR7_REGS_CLOCKS,
-					sizeof(struct tnetd7200_clocks));
-	int cpu_base, cpu_mul, cpu_prediv, cpu_postdiv;
-	int dsp_base, dsp_mul, dsp_prediv, dsp_postdiv;
-	int usb_base, usb_mul, usb_prediv, usb_postdiv;
-	struct clk *clk;
-
-	cpu_base = tnetd7200_get_clock_base(TNETD7200_CLOCK_ID_CPU, bootcr);
-	dsp_base = tnetd7200_get_clock_base(TNETD7200_CLOCK_ID_DSP, bootcr);
-
-	if (*bootcr & BOOT_PLL_ASYNC_MODE) {
-		printk(KERN_INFO "Clocks: Async mode\n");
-
-		printk(KERN_INFO "Clocks: Setting DSP clock\n");
-		calculate(dsp_base, TNETD7200_DEF_DSP_CLK,
-			&dsp_prediv, &dsp_postdiv, &dsp_mul);
-		bus_clk.rate =
-			((dsp_base / dsp_prediv) * dsp_mul) / dsp_postdiv;
-		tnetd7200_set_clock(dsp_base, &clocks->dsp,
-			dsp_prediv, dsp_postdiv * 2, dsp_postdiv, dsp_mul * 2,
-			bus_clk.rate);
-
-		printk(KERN_INFO "Clocks: Setting CPU clock\n");
-		calculate(cpu_base, TNETD7200_DEF_CPU_CLK, &cpu_prediv,
-			&cpu_postdiv, &cpu_mul);
-		cpu_clk.rate =
-			((cpu_base / cpu_prediv) * cpu_mul) / cpu_postdiv;
-		tnetd7200_set_clock(cpu_base, &clocks->cpu,
-			cpu_prediv, cpu_postdiv, -1, cpu_mul,
-			cpu_clk.rate);
-
-	} else
-		if (*bootcr & BOOT_PLL_2TO1_MODE) {
-			printk(KERN_INFO "Clocks: Sync 2:1 mode\n");
-
-			printk(KERN_INFO "Clocks: Setting CPU clock\n");
-			calculate(cpu_base, TNETD7200_DEF_CPU_CLK, &cpu_prediv,
-				&cpu_postdiv, &cpu_mul);
-			cpu_clk.rate = ((cpu_base / cpu_prediv) * cpu_mul)
-								/ cpu_postdiv;
-			tnetd7200_set_clock(cpu_base, &clocks->cpu,
-				cpu_prediv, cpu_postdiv, -1, cpu_mul,
-				cpu_clk.rate);
-
-			printk(KERN_INFO "Clocks: Setting DSP clock\n");
-			calculate(dsp_base, TNETD7200_DEF_DSP_CLK, &dsp_prediv,
-				&dsp_postdiv, &dsp_mul);
-			bus_clk.rate = cpu_clk.rate / 2;
-			tnetd7200_set_clock(dsp_base, &clocks->dsp,
-				dsp_prediv, dsp_postdiv * 2, dsp_postdiv,
-				dsp_mul * 2, bus_clk.rate);
-		} else {
-			printk(KERN_INFO "Clocks: Sync 1:1 mode\n");
-
-			printk(KERN_INFO "Clocks: Setting DSP clock\n");
-			calculate(dsp_base, TNETD7200_DEF_DSP_CLK, &dsp_prediv,
-				&dsp_postdiv, &dsp_mul);
-			bus_clk.rate = ((dsp_base / dsp_prediv) * dsp_mul)
-								/ dsp_postdiv;
-			tnetd7200_set_clock(dsp_base, &clocks->dsp,
-				dsp_prediv, dsp_postdiv * 2, dsp_postdiv,
-				dsp_mul * 2, bus_clk.rate);
-
-			cpu_clk.rate = bus_clk.rate;
-		}
-
-	printk(KERN_INFO "Clocks: Setting USB clock\n");
-	usb_base = bus_clk.rate;
-	calculate(usb_base, TNETD7200_DEF_USB_CLK, &usb_prediv,
-		&usb_postdiv, &usb_mul);
-	tnetd7200_set_clock(usb_base, &clocks->usb,
-		usb_prediv, usb_postdiv, -1, usb_mul,
-		TNETD7200_DEF_USB_CLK);
-
-	iounmap(clocks);
-	iounmap(bootcr);
-
-	clk = clk_register_fixed_rate(NULL, "cpu", NULL, 0, cpu_clk.rate);
-	clkdev_create(clk, "cpu", NULL);
-	clkdev_create(clk, "dsp", NULL);
-}
-
-void __init ar7_init_clocks(void)
-{
-	struct clk *clk;
-
-	switch (ar7_chip_id()) {
-	case AR7_CHIP_7100:
-	case AR7_CHIP_7200:
-		tnetd7200_init_clocks();
-		break;
-	case AR7_CHIP_7300:
-		tnetd7300_init_clocks();
-		break;
-	default:
-		break;
-	}
-	clk = clk_register_fixed_rate(NULL, "bus", NULL, 0, bus_clk.rate);
-	clkdev_create(clk, "bus", NULL);
-	/* adjust vbus clock rate */
-	clk = clk_register_fixed_factor(NULL, "vbus", "bus", 0, 1, 2);
-	clkdev_create(clk, "vbus", NULL);
-	clkdev_create(clk, "cpmac", "cpmac.1");
-	clkdev_create(clk, "cpmac", "cpmac.1");
-}
diff --git a/arch/mips/ar7/gpio.c b/arch/mips/ar7/gpio.c
deleted file mode 100644
index 4ed833b9cc2f7b..00000000000000
--- a/arch/mips/ar7/gpio.c
+++ /dev/null
@@ -1,332 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2007 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2007 Eugene Konev <ejka@openwrt.org>
- * Copyright (C) 2009-2010 Florian Fainelli <florian@openwrt.org>
- */
-
-#include <linux/init.h>
-#include <linux/export.h>
-#include <linux/gpio/driver.h>
-
-#include <asm/mach-ar7/ar7.h>
-
-#define AR7_GPIO_MAX 32
-#define TITAN_GPIO_MAX 51
-
-struct ar7_gpio_chip {
-	void __iomem		*regs;
-	struct gpio_chip	chip;
-};
-
-static int ar7_gpio_get_value(struct gpio_chip *chip, unsigned gpio)
-{
-	struct ar7_gpio_chip *gpch = gpiochip_get_data(chip);
-	void __iomem *gpio_in = gpch->regs + AR7_GPIO_INPUT;
-
-	return !!(readl(gpio_in) & (1 << gpio));
-}
-
-static int titan_gpio_get_value(struct gpio_chip *chip, unsigned gpio)
-{
-	struct ar7_gpio_chip *gpch = gpiochip_get_data(chip);
-	void __iomem *gpio_in0 = gpch->regs + TITAN_GPIO_INPUT_0;
-	void __iomem *gpio_in1 = gpch->regs + TITAN_GPIO_INPUT_1;
-
-	return readl(gpio >> 5 ? gpio_in1 : gpio_in0) & (1 << (gpio & 0x1f));
-}
-
-static void ar7_gpio_set_value(struct gpio_chip *chip,
-				unsigned gpio, int value)
-{
-	struct ar7_gpio_chip *gpch = gpiochip_get_data(chip);
-	void __iomem *gpio_out = gpch->regs + AR7_GPIO_OUTPUT;
-	unsigned tmp;
-
-	tmp = readl(gpio_out) & ~(1 << gpio);
-	if (value)
-		tmp |= 1 << gpio;
-	writel(tmp, gpio_out);
-}
-
-static void titan_gpio_set_value(struct gpio_chip *chip,
-				unsigned gpio, int value)
-{
-	struct ar7_gpio_chip *gpch = gpiochip_get_data(chip);
-	void __iomem *gpio_out0 = gpch->regs + TITAN_GPIO_OUTPUT_0;
-	void __iomem *gpio_out1 = gpch->regs + TITAN_GPIO_OUTPUT_1;
-	unsigned tmp;
-
-	tmp = readl(gpio >> 5 ? gpio_out1 : gpio_out0) & ~(1 << (gpio & 0x1f));
-	if (value)
-		tmp |= 1 << (gpio & 0x1f);
-	writel(tmp, gpio >> 5 ? gpio_out1 : gpio_out0);
-}
-
-static int ar7_gpio_direction_input(struct gpio_chip *chip, unsigned gpio)
-{
-	struct ar7_gpio_chip *gpch = gpiochip_get_data(chip);
-	void __iomem *gpio_dir = gpch->regs + AR7_GPIO_DIR;
-
-	writel(readl(gpio_dir) | (1 << gpio), gpio_dir);
-
-	return 0;
-}
-
-static int titan_gpio_direction_input(struct gpio_chip *chip, unsigned gpio)
-{
-	struct ar7_gpio_chip *gpch = gpiochip_get_data(chip);
-	void __iomem *gpio_dir0 = gpch->regs + TITAN_GPIO_DIR_0;
-	void __iomem *gpio_dir1 = gpch->regs + TITAN_GPIO_DIR_1;
-
-	if (gpio >= TITAN_GPIO_MAX)
-		return -EINVAL;
-
-	writel(readl(gpio >> 5 ? gpio_dir1 : gpio_dir0) | (1 << (gpio & 0x1f)),
-			gpio >> 5 ? gpio_dir1 : gpio_dir0);
-	return 0;
-}
-
-static int ar7_gpio_direction_output(struct gpio_chip *chip,
-					unsigned gpio, int value)
-{
-	struct ar7_gpio_chip *gpch = gpiochip_get_data(chip);
-	void __iomem *gpio_dir = gpch->regs + AR7_GPIO_DIR;
-
-	ar7_gpio_set_value(chip, gpio, value);
-	writel(readl(gpio_dir) & ~(1 << gpio), gpio_dir);
-
-	return 0;
-}
-
-static int titan_gpio_direction_output(struct gpio_chip *chip,
-					unsigned gpio, int value)
-{
-	struct ar7_gpio_chip *gpch = gpiochip_get_data(chip);
-	void __iomem *gpio_dir0 = gpch->regs + TITAN_GPIO_DIR_0;
-	void __iomem *gpio_dir1 = gpch->regs + TITAN_GPIO_DIR_1;
-
-	if (gpio >= TITAN_GPIO_MAX)
-		return -EINVAL;
-
-	titan_gpio_set_value(chip, gpio, value);
-	writel(readl(gpio >> 5 ? gpio_dir1 : gpio_dir0) & ~(1 <<
-		(gpio & 0x1f)), gpio >> 5 ? gpio_dir1 : gpio_dir0);
-
-	return 0;
-}
-
-static struct ar7_gpio_chip ar7_gpio_chip = {
-	.chip = {
-		.label			= "ar7-gpio",
-		.direction_input	= ar7_gpio_direction_input,
-		.direction_output	= ar7_gpio_direction_output,
-		.set			= ar7_gpio_set_value,
-		.get			= ar7_gpio_get_value,
-		.base			= 0,
-		.ngpio			= AR7_GPIO_MAX,
-	}
-};
-
-static struct ar7_gpio_chip titan_gpio_chip = {
-	.chip = {
-		.label			= "titan-gpio",
-		.direction_input	= titan_gpio_direction_input,
-		.direction_output	= titan_gpio_direction_output,
-		.set			= titan_gpio_set_value,
-		.get			= titan_gpio_get_value,
-		.base			= 0,
-		.ngpio			= TITAN_GPIO_MAX,
-	}
-};
-
-static inline int ar7_gpio_enable_ar7(unsigned gpio)
-{
-	void __iomem *gpio_en = ar7_gpio_chip.regs + AR7_GPIO_ENABLE;
-
-	writel(readl(gpio_en) | (1 << gpio), gpio_en);
-
-	return 0;
-}
-
-static inline int ar7_gpio_enable_titan(unsigned gpio)
-{
-	void __iomem *gpio_en0 = titan_gpio_chip.regs  + TITAN_GPIO_ENBL_0;
-	void __iomem *gpio_en1 = titan_gpio_chip.regs  + TITAN_GPIO_ENBL_1;
-
-	writel(readl(gpio >> 5 ? gpio_en1 : gpio_en0) | (1 << (gpio & 0x1f)),
-		gpio >> 5 ? gpio_en1 : gpio_en0);
-
-	return 0;
-}
-
-int ar7_gpio_enable(unsigned gpio)
-{
-	return ar7_is_titan() ? ar7_gpio_enable_titan(gpio) :
-				ar7_gpio_enable_ar7(gpio);
-}
-EXPORT_SYMBOL(ar7_gpio_enable);
-
-static inline int ar7_gpio_disable_ar7(unsigned gpio)
-{
-	void __iomem *gpio_en = ar7_gpio_chip.regs + AR7_GPIO_ENABLE;
-
-	writel(readl(gpio_en) & ~(1 << gpio), gpio_en);
-
-	return 0;
-}
-
-static inline int ar7_gpio_disable_titan(unsigned gpio)
-{
-	void __iomem *gpio_en0 = titan_gpio_chip.regs + TITAN_GPIO_ENBL_0;
-	void __iomem *gpio_en1 = titan_gpio_chip.regs + TITAN_GPIO_ENBL_1;
-
-	writel(readl(gpio >> 5 ? gpio_en1 : gpio_en0) & ~(1 << (gpio & 0x1f)),
-			gpio >> 5 ? gpio_en1 : gpio_en0);
-
-	return 0;
-}
-
-int ar7_gpio_disable(unsigned gpio)
-{
-	return ar7_is_titan() ? ar7_gpio_disable_titan(gpio) :
-				ar7_gpio_disable_ar7(gpio);
-}
-EXPORT_SYMBOL(ar7_gpio_disable);
-
-struct titan_gpio_cfg {
-	u32 reg;
-	u32 shift;
-	u32 func;
-};
-
-static const struct titan_gpio_cfg titan_gpio_table[] = {
-	/* reg, start bit, mux value */
-	{4, 24, 1},
-	{4, 26, 1},
-	{4, 28, 1},
-	{4, 30, 1},
-	{5, 6, 1},
-	{5, 8, 1},
-	{5, 10, 1},
-	{5, 12, 1},
-	{7, 14, 3},
-	{7, 16, 3},
-	{7, 18, 3},
-	{7, 20, 3},
-	{7, 22, 3},
-	{7, 26, 3},
-	{7, 28, 3},
-	{7, 30, 3},
-	{8, 0, 3},
-	{8, 2, 3},
-	{8, 4, 3},
-	{8, 10, 3},
-	{8, 14, 3},
-	{8, 16, 3},
-	{8, 18, 3},
-	{8, 20, 3},
-	{9, 8, 3},
-	{9, 10, 3},
-	{9, 12, 3},
-	{9, 14, 3},
-	{9, 18, 3},
-	{9, 20, 3},
-	{9, 24, 3},
-	{9, 26, 3},
-	{9, 28, 3},
-	{9, 30, 3},
-	{10, 0, 3},
-	{10, 2, 3},
-	{10, 8, 3},
-	{10, 10, 3},
-	{10, 12, 3},
-	{10, 14, 3},
-	{13, 12, 3},
-	{13, 14, 3},
-	{13, 16, 3},
-	{13, 18, 3},
-	{13, 24, 3},
-	{13, 26, 3},
-	{13, 28, 3},
-	{13, 30, 3},
-	{14, 2, 3},
-	{14, 6, 3},
-	{14, 8, 3},
-	{14, 12, 3}
-};
-
-static int titan_gpio_pinsel(unsigned gpio)
-{
-	struct titan_gpio_cfg gpio_cfg;
-	u32 mux_status, pin_sel_reg, tmp;
-	void __iomem *pin_sel = (void __iomem *)KSEG1ADDR(AR7_REGS_PINSEL);
-
-	if (gpio >= ARRAY_SIZE(titan_gpio_table))
-		return -EINVAL;
-
-	gpio_cfg = titan_gpio_table[gpio];
-	pin_sel_reg = gpio_cfg.reg - 1;
-
-	mux_status = (readl(pin_sel + pin_sel_reg) >> gpio_cfg.shift) & 0x3;
-
-	/* Check the mux status */
-	if (!((mux_status == 0) || (mux_status == gpio_cfg.func)))
-		return 0;
-
-	/* Set the pin sel value */
-	tmp = readl(pin_sel + pin_sel_reg);
-	tmp |= ((gpio_cfg.func & 0x3) << gpio_cfg.shift);
-	writel(tmp, pin_sel + pin_sel_reg);
-
-	return 0;
-}
-
-/* Perform minimal Titan GPIO configuration */
-static void titan_gpio_init(void)
-{
-	unsigned i;
-
-	for (i = 44; i < 48; i++) {
-		titan_gpio_pinsel(i);
-		ar7_gpio_enable_titan(i);
-		titan_gpio_direction_input(&titan_gpio_chip.chip, i);
-	}
-}
-
-int __init ar7_gpio_init(void)
-{
-	int ret;
-	struct ar7_gpio_chip *gpch;
-	unsigned size;
-
-	if (!ar7_is_titan()) {
-		gpch = &ar7_gpio_chip;
-		size = 0x10;
-	} else {
-		gpch = &titan_gpio_chip;
-		size = 0x1f;
-	}
-
-	gpch->regs = ioremap(AR7_REGS_GPIO, size);
-	if (!gpch->regs) {
-		printk(KERN_ERR "%s: failed to ioremap regs\n",
-					gpch->chip.label);
-		return -ENOMEM;
-	}
-
-	ret = gpiochip_add_data(&gpch->chip, gpch);
-	if (ret) {
-		printk(KERN_ERR "%s: failed to add gpiochip\n",
-					gpch->chip.label);
-		iounmap(gpch->regs);
-		return ret;
-	}
-	printk(KERN_INFO "%s: registered %d GPIOs\n",
-				gpch->chip.label, gpch->chip.ngpio);
-
-	if (ar7_is_titan())
-		titan_gpio_init();
-
-	return ret;
-}
diff --git a/arch/mips/ar7/irq.c b/arch/mips/ar7/irq.c
deleted file mode 100644
index f0a7942d393edc..00000000000000
--- a/arch/mips/ar7/irq.c
+++ /dev/null
@@ -1,165 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2006,2007 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2006,2007 Eugene Konev <ejka@openwrt.org>
- */
-
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/irq.h>
-
-#include <asm/irq_cpu.h>
-#include <asm/mipsregs.h>
-#include <asm/mach-ar7/ar7.h>
-
-#define EXCEPT_OFFSET	0x80
-#define PACE_OFFSET	0xA0
-#define CHNLS_OFFSET	0x200
-
-#define REG_OFFSET(irq, reg)	((irq) / 32 * 0x4 + reg * 0x10)
-#define SEC_REG_OFFSET(reg)	(EXCEPT_OFFSET + reg * 0x8)
-#define SEC_SR_OFFSET		(SEC_REG_OFFSET(0))	/* 0x80 */
-#define CR_OFFSET(irq)		(REG_OFFSET(irq, 1))	/* 0x10 */
-#define SEC_CR_OFFSET		(SEC_REG_OFFSET(1))	/* 0x88 */
-#define ESR_OFFSET(irq)		(REG_OFFSET(irq, 2))	/* 0x20 */
-#define SEC_ESR_OFFSET		(SEC_REG_OFFSET(2))	/* 0x90 */
-#define ECR_OFFSET(irq)		(REG_OFFSET(irq, 3))	/* 0x30 */
-#define SEC_ECR_OFFSET		(SEC_REG_OFFSET(3))	/* 0x98 */
-#define PIR_OFFSET		(0x40)
-#define MSR_OFFSET		(0x44)
-#define PM_OFFSET(irq)		(REG_OFFSET(irq, 5))	/* 0x50 */
-#define TM_OFFSET(irq)		(REG_OFFSET(irq, 6))	/* 0x60 */
-
-#define REG(addr) ((u32 *)(KSEG1ADDR(AR7_REGS_IRQ) + addr))
-
-#define CHNL_OFFSET(chnl) (CHNLS_OFFSET + (chnl * 4))
-
-static int ar7_irq_base;
-
-static void ar7_unmask_irq(struct irq_data *d)
-{
-	writel(1 << ((d->irq - ar7_irq_base) % 32),
-	       REG(ESR_OFFSET(d->irq - ar7_irq_base)));
-}
-
-static void ar7_mask_irq(struct irq_data *d)
-{
-	writel(1 << ((d->irq - ar7_irq_base) % 32),
-	       REG(ECR_OFFSET(d->irq - ar7_irq_base)));
-}
-
-static void ar7_ack_irq(struct irq_data *d)
-{
-	writel(1 << ((d->irq - ar7_irq_base) % 32),
-	       REG(CR_OFFSET(d->irq - ar7_irq_base)));
-}
-
-static void ar7_unmask_sec_irq(struct irq_data *d)
-{
-	writel(1 << (d->irq - ar7_irq_base - 40), REG(SEC_ESR_OFFSET));
-}
-
-static void ar7_mask_sec_irq(struct irq_data *d)
-{
-	writel(1 << (d->irq - ar7_irq_base - 40), REG(SEC_ECR_OFFSET));
-}
-
-static void ar7_ack_sec_irq(struct irq_data *d)
-{
-	writel(1 << (d->irq - ar7_irq_base - 40), REG(SEC_CR_OFFSET));
-}
-
-static struct irq_chip ar7_irq_type = {
-	.name = "AR7",
-	.irq_unmask = ar7_unmask_irq,
-	.irq_mask = ar7_mask_irq,
-	.irq_ack = ar7_ack_irq
-};
-
-static struct irq_chip ar7_sec_irq_type = {
-	.name = "AR7",
-	.irq_unmask = ar7_unmask_sec_irq,
-	.irq_mask = ar7_mask_sec_irq,
-	.irq_ack = ar7_ack_sec_irq,
-};
-
-static void __init ar7_irq_init(int base)
-{
-	int i;
-	/*
-	 * Disable interrupts and clear pending
-	 */
-	writel(0xffffffff, REG(ECR_OFFSET(0)));
-	writel(0xff, REG(ECR_OFFSET(32)));
-	writel(0xffffffff, REG(SEC_ECR_OFFSET));
-	writel(0xffffffff, REG(CR_OFFSET(0)));
-	writel(0xff, REG(CR_OFFSET(32)));
-	writel(0xffffffff, REG(SEC_CR_OFFSET));
-
-	ar7_irq_base = base;
-
-	for (i = 0; i < 40; i++) {
-		writel(i, REG(CHNL_OFFSET(i)));
-		/* Primary IRQ's */
-		irq_set_chip_and_handler(base + i, &ar7_irq_type,
-					 handle_level_irq);
-		/* Secondary IRQ's */
-		if (i < 32)
-			irq_set_chip_and_handler(base + i + 40,
-						 &ar7_sec_irq_type,
-						 handle_level_irq);
-	}
-
-	if (request_irq(2, no_action, IRQF_NO_THREAD, "AR7 cascade interrupt",
-			NULL))
-		pr_err("Failed to request irq 2 (AR7 cascade interrupt)\n");
-	if (request_irq(ar7_irq_base, no_action, IRQF_NO_THREAD,
-			"AR7 cascade interrupt", NULL)) {
-		pr_err("Failed to request irq %d (AR7 cascade interrupt)\n",
-		       ar7_irq_base);
-	}
-	set_c0_status(IE_IRQ0);
-}
-
-void __init arch_init_irq(void)
-{
-	mips_cpu_irq_init();
-	ar7_irq_init(8);
-}
-
-static void ar7_cascade(void)
-{
-	u32 status;
-	int i, irq;
-
-	/* Primary IRQ's */
-	irq = readl(REG(PIR_OFFSET)) & 0x3f;
-	if (irq) {
-		do_IRQ(ar7_irq_base + irq);
-		return;
-	}
-
-	/* Secondary IRQ's are cascaded through primary '0' */
-	writel(1, REG(CR_OFFSET(irq)));
-	status = readl(REG(SEC_SR_OFFSET));
-	for (i = 0; i < 32; i++) {
-		if (status & 1) {
-			do_IRQ(ar7_irq_base + i + 40);
-			return;
-		}
-		status >>= 1;
-	}
-
-	spurious_interrupt();
-}
-
-asmlinkage void plat_irq_dispatch(void)
-{
-	unsigned int pending = read_c0_status() & read_c0_cause() & ST0_IM;
-	if (pending & STATUSF_IP7)		/* cpu timer */
-		do_IRQ(7);
-	else if (pending & STATUSF_IP2)		/* int0 hardware line */
-		ar7_cascade();
-	else
-		spurious_interrupt();
-}
diff --git a/arch/mips/ar7/memory.c b/arch/mips/ar7/memory.c
deleted file mode 100644
index ce8024c1a54e14..00000000000000
--- a/arch/mips/ar7/memory.c
+++ /dev/null
@@ -1,51 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2007 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2007 Eugene Konev <ejka@openwrt.org>
- */
-#include <linux/memblock.h>
-#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/pfn.h>
-#include <linux/proc_fs.h>
-#include <linux/string.h>
-#include <linux/swap.h>
-
-#include <asm/bootinfo.h>
-#include <asm/page.h>
-#include <asm/sections.h>
-
-#include <asm/mach-ar7/ar7.h>
-
-static int __init memsize(void)
-{
-	u32 size = (64 << 20);
-	u32 *addr = (u32 *)KSEG1ADDR(AR7_SDRAM_BASE + size - 4);
-	u32 *kernel_end = (u32 *)KSEG1ADDR(CPHYSADDR((u32)&_end));
-	u32 *tmpaddr = addr;
-
-	while (tmpaddr > kernel_end) {
-		*tmpaddr = (u32)tmpaddr;
-		size >>= 1;
-		tmpaddr -= size >> 2;
-	}
-
-	do {
-		tmpaddr += size >> 2;
-		if (*tmpaddr != (u32)tmpaddr)
-			break;
-		size <<= 1;
-	} while (size < (64 << 20));
-
-	writel((u32)tmpaddr, &addr);
-
-	return size;
-}
-
-void __init prom_meminit(void)
-{
-	unsigned long pages;
-
-	pages = memsize() >> PAGE_SHIFT;
-	memblock_add(PHYS_OFFSET, pages << PAGE_SHIFT);
-}
diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c
deleted file mode 100644
index 215149a85d83ba..00000000000000
--- a/arch/mips/ar7/platform.c
+++ /dev/null
@@ -1,722 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2006,2007 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2006,2007 Eugene Konev <ejka@openwrt.org>
- */
-
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/delay.h>
-#include <linux/dma-mapping.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/physmap.h>
-#include <linux/serial.h>
-#include <linux/serial_8250.h>
-#include <linux/ioport.h>
-#include <linux/io.h>
-#include <linux/vlynq.h>
-#include <linux/leds.h>
-#include <linux/string.h>
-#include <linux/etherdevice.h>
-#include <linux/phy.h>
-#include <linux/phy_fixed.h>
-#include <linux/gpio.h>
-#include <linux/clk.h>
-
-#include <asm/addrspace.h>
-#include <asm/mach-ar7/ar7.h>
-#include <asm/mach-ar7/prom.h>
-
-/*****************************************************************************
- * VLYNQ Bus
- ****************************************************************************/
-struct plat_vlynq_data {
-	struct plat_vlynq_ops ops;
-	int gpio_bit;
-	int reset_bit;
-};
-
-static int vlynq_on(struct vlynq_device *dev)
-{
-	int ret;
-	struct plat_vlynq_data *pdata = dev->dev.platform_data;
-
-	ret = gpio_request(pdata->gpio_bit, "vlynq");
-	if (ret)
-		goto out;
-
-	ar7_device_reset(pdata->reset_bit);
-
-	ret = ar7_gpio_disable(pdata->gpio_bit);
-	if (ret)
-		goto out_enabled;
-
-	ret = ar7_gpio_enable(pdata->gpio_bit);
-	if (ret)
-		goto out_enabled;
-
-	ret = gpio_direction_output(pdata->gpio_bit, 0);
-	if (ret)
-		goto out_gpio_enabled;
-
-	msleep(50);
-
-	gpio_set_value(pdata->gpio_bit, 1);
-
-	msleep(50);
-
-	return 0;
-
-out_gpio_enabled:
-	ar7_gpio_disable(pdata->gpio_bit);
-out_enabled:
-	ar7_device_disable(pdata->reset_bit);
-	gpio_free(pdata->gpio_bit);
-out:
-	return ret;
-}
-
-static void vlynq_off(struct vlynq_device *dev)
-{
-	struct plat_vlynq_data *pdata = dev->dev.platform_data;
-
-	ar7_gpio_disable(pdata->gpio_bit);
-	gpio_free(pdata->gpio_bit);
-	ar7_device_disable(pdata->reset_bit);
-}
-
-static struct resource vlynq_low_res[] = {
-	{
-		.name	= "regs",
-		.flags	= IORESOURCE_MEM,
-		.start	= AR7_REGS_VLYNQ0,
-		.end	= AR7_REGS_VLYNQ0 + 0xff,
-	},
-	{
-		.name	= "irq",
-		.flags	= IORESOURCE_IRQ,
-		.start	= 29,
-		.end	= 29,
-	},
-	{
-		.name	= "mem",
-		.flags	= IORESOURCE_MEM,
-		.start	= 0x04000000,
-		.end	= 0x04ffffff,
-	},
-	{
-		.name	= "devirq",
-		.flags	= IORESOURCE_IRQ,
-		.start	= 80,
-		.end	= 111,
-	},
-};
-
-static struct resource vlynq_high_res[] = {
-	{
-		.name	= "regs",
-		.flags	= IORESOURCE_MEM,
-		.start	= AR7_REGS_VLYNQ1,
-		.end	= AR7_REGS_VLYNQ1 + 0xff,
-	},
-	{
-		.name	= "irq",
-		.flags	= IORESOURCE_IRQ,
-		.start	= 33,
-		.end	= 33,
-	},
-	{
-		.name	= "mem",
-		.flags	= IORESOURCE_MEM,
-		.start	= 0x0c000000,
-		.end	= 0x0cffffff,
-	},
-	{
-		.name	= "devirq",
-		.flags	= IORESOURCE_IRQ,
-		.start	= 112,
-		.end	= 143,
-	},
-};
-
-static struct plat_vlynq_data vlynq_low_data = {
-	.ops = {
-		.on	= vlynq_on,
-		.off	= vlynq_off,
-	},
-	.reset_bit	= 20,
-	.gpio_bit	= 18,
-};
-
-static struct plat_vlynq_data vlynq_high_data = {
-	.ops = {
-		.on	= vlynq_on,
-		.off	= vlynq_off,
-	},
-	.reset_bit	= 16,
-	.gpio_bit	= 19,
-};
-
-static struct platform_device vlynq_low = {
-	.id		= 0,
-	.name		= "vlynq",
-	.dev = {
-		.platform_data	= &vlynq_low_data,
-	},
-	.resource	= vlynq_low_res,
-	.num_resources	= ARRAY_SIZE(vlynq_low_res),
-};
-
-static struct platform_device vlynq_high = {
-	.id		= 1,
-	.name		= "vlynq",
-	.dev = {
-		.platform_data	= &vlynq_high_data,
-	},
-	.resource	= vlynq_high_res,
-	.num_resources	= ARRAY_SIZE(vlynq_high_res),
-};
-
-/*****************************************************************************
- * Flash
- ****************************************************************************/
-static struct resource physmap_flash_resource = {
-	.name	= "mem",
-	.flags	= IORESOURCE_MEM,
-	.start	= 0x10000000,
-	.end	= 0x107fffff,
-};
-
-static const char *ar7_probe_types[] = { "ar7part", NULL };
-
-static struct physmap_flash_data physmap_flash_data = {
-	.width	= 2,
-	.part_probe_types = ar7_probe_types,
-};
-
-static struct platform_device physmap_flash = {
-	.name		= "physmap-flash",
-	.dev = {
-		.platform_data	= &physmap_flash_data,
-	},
-	.resource	= &physmap_flash_resource,
-	.num_resources	= 1,
-};
-
-/*****************************************************************************
- * Ethernet
- ****************************************************************************/
-static struct resource cpmac_low_res[] = {
-	{
-		.name	= "regs",
-		.flags	= IORESOURCE_MEM,
-		.start	= AR7_REGS_MAC0,
-		.end	= AR7_REGS_MAC0 + 0x7ff,
-	},
-	{
-		.name	= "irq",
-		.flags	= IORESOURCE_IRQ,
-		.start	= 27,
-		.end	= 27,
-	},
-};
-
-static struct resource cpmac_high_res[] = {
-	{
-		.name	= "regs",
-		.flags	= IORESOURCE_MEM,
-		.start	= AR7_REGS_MAC1,
-		.end	= AR7_REGS_MAC1 + 0x7ff,
-	},
-	{
-		.name	= "irq",
-		.flags	= IORESOURCE_IRQ,
-		.start	= 41,
-		.end	= 41,
-	},
-};
-
-static struct fixed_phy_status fixed_phy_status __initdata = {
-	.link		= 1,
-	.speed		= 100,
-	.duplex		= 1,
-};
-
-static struct plat_cpmac_data cpmac_low_data = {
-	.reset_bit	= 17,
-	.power_bit	= 20,
-	.phy_mask	= 0x80000000,
-};
-
-static struct plat_cpmac_data cpmac_high_data = {
-	.reset_bit	= 21,
-	.power_bit	= 22,
-	.phy_mask	= 0x7fffffff,
-};
-
-static u64 cpmac_dma_mask = DMA_BIT_MASK(32);
-
-static struct platform_device cpmac_low = {
-	.id		= 0,
-	.name		= "cpmac",
-	.dev = {
-		.dma_mask		= &cpmac_dma_mask,
-		.coherent_dma_mask	= DMA_BIT_MASK(32),
-		.platform_data		= &cpmac_low_data,
-	},
-	.resource	= cpmac_low_res,
-	.num_resources	= ARRAY_SIZE(cpmac_low_res),
-};
-
-static struct platform_device cpmac_high = {
-	.id		= 1,
-	.name		= "cpmac",
-	.dev = {
-		.dma_mask		= &cpmac_dma_mask,
-		.coherent_dma_mask	= DMA_BIT_MASK(32),
-		.platform_data		= &cpmac_high_data,
-	},
-	.resource	= cpmac_high_res,
-	.num_resources	= ARRAY_SIZE(cpmac_high_res),
-};
-
-static void __init cpmac_get_mac(int instance, unsigned char *dev_addr)
-{
-	char name[5], *mac;
-
-	sprintf(name, "mac%c", 'a' + instance);
-	mac = prom_getenv(name);
-	if (!mac && instance) {
-		sprintf(name, "mac%c", 'a');
-		mac = prom_getenv(name);
-	}
-
-	if (mac) {
-		if (!mac_pton(mac, dev_addr)) {
-			pr_warn("cannot parse mac address, using random address\n");
-			eth_random_addr(dev_addr);
-		}
-	} else
-		eth_random_addr(dev_addr);
-}
-
-/*****************************************************************************
- * USB
- ****************************************************************************/
-static struct resource usb_res[] = {
-	{
-		.name	= "regs",
-		.flags	= IORESOURCE_MEM,
-		.start	= AR7_REGS_USB,
-		.end	= AR7_REGS_USB + 0xff,
-	},
-	{
-		.name	= "irq",
-		.flags	= IORESOURCE_IRQ,
-		.start	= 32,
-		.end	= 32,
-	},
-	{
-		.name	= "mem",
-		.flags	= IORESOURCE_MEM,
-		.start	= 0x03400000,
-		.end	= 0x03401fff,
-	},
-};
-
-static struct platform_device ar7_udc = {
-	.name		= "ar7_udc",
-	.resource	= usb_res,
-	.num_resources	= ARRAY_SIZE(usb_res),
-};
-
-/*****************************************************************************
- * LEDs
- ****************************************************************************/
-static const struct gpio_led default_leds[] = {
-	{
-		.name			= "status",
-		.gpio			= 8,
-		.active_low		= 1,
-	},
-};
-
-static const struct gpio_led titan_leds[] = {
-	{ .name = "status", .gpio = 8, .active_low = 1, },
-	{ .name = "wifi", .gpio = 13, .active_low = 1, },
-};
-
-static const struct gpio_led dsl502t_leds[] = {
-	{
-		.name			= "status",
-		.gpio			= 9,
-		.active_low		= 1,
-	},
-	{
-		.name			= "ethernet",
-		.gpio			= 7,
-		.active_low		= 1,
-	},
-	{
-		.name			= "usb",
-		.gpio			= 12,
-		.active_low		= 1,
-	},
-};
-
-static const struct gpio_led dg834g_leds[] = {
-	{
-		.name			= "ppp",
-		.gpio			= 6,
-		.active_low		= 1,
-	},
-	{
-		.name			= "status",
-		.gpio			= 7,
-		.active_low		= 1,
-	},
-	{
-		.name			= "adsl",
-		.gpio			= 8,
-		.active_low		= 1,
-	},
-	{
-		.name			= "wifi",
-		.gpio			= 12,
-		.active_low		= 1,
-	},
-	{
-		.name			= "power",
-		.gpio			= 14,
-		.active_low		= 1,
-		.default_trigger	= "default-on",
-	},
-};
-
-static const struct gpio_led fb_sl_leds[] = {
-	{
-		.name			= "1",
-		.gpio			= 7,
-	},
-	{
-		.name			= "2",
-		.gpio			= 13,
-		.active_low		= 1,
-	},
-	{
-		.name			= "3",
-		.gpio			= 10,
-		.active_low		= 1,
-	},
-	{
-		.name			= "4",
-		.gpio			= 12,
-		.active_low		= 1,
-	},
-	{
-		.name			= "5",
-		.gpio			= 9,
-		.active_low		= 1,
-	},
-};
-
-static const struct gpio_led fb_fon_leds[] = {
-	{
-		.name			= "1",
-		.gpio			= 8,
-	},
-	{
-		.name			= "2",
-		.gpio			= 3,
-		.active_low		= 1,
-	},
-	{
-		.name			= "3",
-		.gpio			= 5,
-	},
-	{
-		.name			= "4",
-		.gpio			= 4,
-		.active_low		= 1,
-	},
-	{
-		.name			= "5",
-		.gpio			= 11,
-		.active_low		= 1,
-	},
-};
-
-static const struct gpio_led gt701_leds[] = {
-	{
-		.name			= "inet:green",
-		.gpio			= 13,
-		.active_low		= 1,
-	},
-	{
-		.name			= "usb",
-		.gpio			= 12,
-		.active_low		= 1,
-	},
-	{
-		.name			= "inet:red",
-		.gpio			= 9,
-		.active_low		= 1,
-	},
-	{
-		.name			= "power:red",
-		.gpio			= 7,
-		.active_low		= 1,
-	},
-	{
-		.name			= "power:green",
-		.gpio			= 8,
-		.active_low		= 1,
-		.default_trigger	= "default-on",
-	},
-	{
-		.name			= "ethernet",
-		.gpio			= 10,
-		.active_low		= 1,
-	},
-};
-
-static struct gpio_led_platform_data ar7_led_data;
-
-static struct platform_device ar7_gpio_leds = {
-	.name = "leds-gpio",
-	.dev = {
-		.platform_data = &ar7_led_data,
-	}
-};
-
-static void __init detect_leds(void)
-{
-	char *prid, *usb_prod;
-
-	/* Default LEDs */
-	ar7_led_data.num_leds = ARRAY_SIZE(default_leds);
-	ar7_led_data.leds = default_leds;
-
-	/* FIXME: the whole thing is unreliable */
-	prid = prom_getenv("ProductID");
-	usb_prod = prom_getenv("usb_prod");
-
-	/* If we can't get the product id from PROM, use the default LEDs */
-	if (!prid)
-		return;
-
-	if (strstr(prid, "Fritz_Box_FON")) {
-		ar7_led_data.num_leds = ARRAY_SIZE(fb_fon_leds);
-		ar7_led_data.leds = fb_fon_leds;
-	} else if (strstr(prid, "Fritz_Box_")) {
-		ar7_led_data.num_leds = ARRAY_SIZE(fb_sl_leds);
-		ar7_led_data.leds = fb_sl_leds;
-	} else if ((!strcmp(prid, "AR7RD") || !strcmp(prid, "AR7DB"))
-		&& usb_prod != NULL && strstr(usb_prod, "DSL-502T")) {
-		ar7_led_data.num_leds = ARRAY_SIZE(dsl502t_leds);
-		ar7_led_data.leds = dsl502t_leds;
-	} else if (strstr(prid, "DG834")) {
-		ar7_led_data.num_leds = ARRAY_SIZE(dg834g_leds);
-		ar7_led_data.leds = dg834g_leds;
-	} else if (strstr(prid, "CYWM") || strstr(prid, "CYWL")) {
-		ar7_led_data.num_leds = ARRAY_SIZE(titan_leds);
-		ar7_led_data.leds = titan_leds;
-	} else if (strstr(prid, "GT701")) {
-		ar7_led_data.num_leds = ARRAY_SIZE(gt701_leds);
-		ar7_led_data.leds = gt701_leds;
-	}
-}
-
-/*****************************************************************************
- * Watchdog
- ****************************************************************************/
-static struct resource ar7_wdt_res = {
-	.name		= "regs",
-	.flags		= IORESOURCE_MEM,
-	.start		= -1,	/* Filled at runtime */
-	.end		= -1,	/* Filled at runtime */
-};
-
-static struct platform_device ar7_wdt = {
-	.name		= "ar7_wdt",
-	.resource	= &ar7_wdt_res,
-	.num_resources	= 1,
-};
-
-/*****************************************************************************
- * Init
- ****************************************************************************/
-static int __init ar7_register_uarts(void)
-{
-#ifdef CONFIG_SERIAL_8250
-	static struct uart_port uart_port __initdata;
-	struct clk *bus_clk;
-	int res;
-
-	memset(&uart_port, 0, sizeof(struct uart_port));
-
-	bus_clk = clk_get(NULL, "bus");
-	if (IS_ERR(bus_clk))
-		panic("unable to get bus clk");
-
-	uart_port.type		= PORT_AR7;
-	uart_port.uartclk	= clk_get_rate(bus_clk) / 2;
-	uart_port.iotype	= UPIO_MEM32;
-	uart_port.flags		= UPF_FIXED_TYPE | UPF_BOOT_AUTOCONF;
-	uart_port.regshift	= 2;
-
-	uart_port.line		= 0;
-	uart_port.irq		= AR7_IRQ_UART0;
-	uart_port.mapbase	= AR7_REGS_UART0;
-	uart_port.membase	= ioremap(uart_port.mapbase, 256);
-
-	res = early_serial_setup(&uart_port);
-	if (res)
-		return res;
-
-	/* Only TNETD73xx have a second serial port */
-	if (ar7_has_second_uart()) {
-		uart_port.line		= 1;
-		uart_port.irq		= AR7_IRQ_UART1;
-		uart_port.mapbase	= UR8_REGS_UART1;
-		uart_port.membase	= ioremap(uart_port.mapbase, 256);
-
-		res = early_serial_setup(&uart_port);
-		if (res)
-			return res;
-	}
-#endif
-
-	return 0;
-}
-
-static void __init titan_fixup_devices(void)
-{
-	/* Set vlynq0 data */
-	vlynq_low_data.reset_bit = 15;
-	vlynq_low_data.gpio_bit = 14;
-
-	/* Set vlynq1 data */
-	vlynq_high_data.reset_bit = 16;
-	vlynq_high_data.gpio_bit = 7;
-
-	/* Set vlynq0 resources */
-	vlynq_low_res[0].start = TITAN_REGS_VLYNQ0;
-	vlynq_low_res[0].end = TITAN_REGS_VLYNQ0 + 0xff;
-	vlynq_low_res[1].start = 33;
-	vlynq_low_res[1].end = 33;
-	vlynq_low_res[2].start = 0x0c000000;
-	vlynq_low_res[2].end = 0x0fffffff;
-	vlynq_low_res[3].start = 80;
-	vlynq_low_res[3].end = 111;
-
-	/* Set vlynq1 resources */
-	vlynq_high_res[0].start = TITAN_REGS_VLYNQ1;
-	vlynq_high_res[0].end = TITAN_REGS_VLYNQ1 + 0xff;
-	vlynq_high_res[1].start = 34;
-	vlynq_high_res[1].end = 34;
-	vlynq_high_res[2].start = 0x40000000;
-	vlynq_high_res[2].end = 0x43ffffff;
-	vlynq_high_res[3].start = 112;
-	vlynq_high_res[3].end = 143;
-
-	/* Set cpmac0 data */
-	cpmac_low_data.phy_mask = 0x40000000;
-
-	/* Set cpmac1 data */
-	cpmac_high_data.phy_mask = 0x80000000;
-
-	/* Set cpmac0 resources */
-	cpmac_low_res[0].start = TITAN_REGS_MAC0;
-	cpmac_low_res[0].end = TITAN_REGS_MAC0 + 0x7ff;
-
-	/* Set cpmac1 resources */
-	cpmac_high_res[0].start = TITAN_REGS_MAC1;
-	cpmac_high_res[0].end = TITAN_REGS_MAC1 + 0x7ff;
-}
-
-static int __init ar7_register_devices(void)
-{
-	void __iomem *bootcr;
-	u32 val;
-	int res;
-
-	res = ar7_gpio_init();
-	if (res)
-		pr_warn("unable to register gpios: %d\n", res);
-
-	res = ar7_register_uarts();
-	if (res)
-		pr_err("unable to setup uart(s): %d\n", res);
-
-	res = platform_device_register(&physmap_flash);
-	if (res)
-		pr_warn("unable to register physmap-flash: %d\n", res);
-
-	if (ar7_is_titan())
-		titan_fixup_devices();
-
-	ar7_device_disable(vlynq_low_data.reset_bit);
-	res = platform_device_register(&vlynq_low);
-	if (res)
-		pr_warn("unable to register vlynq-low: %d\n", res);
-
-	if (ar7_has_high_vlynq()) {
-		ar7_device_disable(vlynq_high_data.reset_bit);
-		res = platform_device_register(&vlynq_high);
-		if (res)
-			pr_warn("unable to register vlynq-high: %d\n", res);
-	}
-
-	if (ar7_has_high_cpmac()) {
-		res = fixed_phy_add(PHY_POLL, cpmac_high.id,
-				    &fixed_phy_status);
-		if (!res) {
-			cpmac_get_mac(1, cpmac_high_data.dev_addr);
-
-			res = platform_device_register(&cpmac_high);
-			if (res)
-				pr_warn("unable to register cpmac-high: %d\n",
-					res);
-		} else
-			pr_warn("unable to add cpmac-high phy: %d\n", res);
-	} else
-		cpmac_low_data.phy_mask = 0xffffffff;
-
-	res = fixed_phy_add(PHY_POLL, cpmac_low.id, &fixed_phy_status);
-	if (!res) {
-		cpmac_get_mac(0, cpmac_low_data.dev_addr);
-		res = platform_device_register(&cpmac_low);
-		if (res)
-			pr_warn("unable to register cpmac-low: %d\n", res);
-	} else
-		pr_warn("unable to add cpmac-low phy: %d\n", res);
-
-	detect_leds();
-	res = platform_device_register(&ar7_gpio_leds);
-	if (res)
-		pr_warn("unable to register leds: %d\n", res);
-
-	res = platform_device_register(&ar7_udc);
-	if (res)
-		pr_warn("unable to register usb slave: %d\n", res);
-
-	/* Register watchdog only if enabled in hardware */
-	bootcr = ioremap(AR7_REGS_DCL, 4);
-	val = readl(bootcr);
-	iounmap(bootcr);
-	if (val & AR7_WDT_HW_ENA) {
-		if (ar7_has_high_vlynq())
-			ar7_wdt_res.start = UR8_REGS_WDT;
-		else
-			ar7_wdt_res.start = AR7_REGS_WDT;
-
-		ar7_wdt_res.end = ar7_wdt_res.start + 0x20;
-		res = platform_device_register(&ar7_wdt);
-		if (res)
-			pr_warn("unable to register watchdog: %d\n", res);
-	}
-
-	return 0;
-}
-device_initcall(ar7_register_devices);
diff --git a/arch/mips/ar7/prom.c b/arch/mips/ar7/prom.c
deleted file mode 100644
index 5810d3993fc65d..00000000000000
--- a/arch/mips/ar7/prom.c
+++ /dev/null
@@ -1,256 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Carsten Langgaard, carstenl@mips.com
- * Copyright (C) 1999,2000 MIPS Technologies, Inc.  All rights reserved.
- *
- * Putting things on the screen/serial line using YAMONs facilities.
- */
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/serial_reg.h>
-#include <linux/spinlock.h>
-#include <linux/export.h>
-#include <linux/string.h>
-#include <linux/io.h>
-#include <asm/bootinfo.h>
-#include <asm/setup.h>
-
-#include <asm/mach-ar7/ar7.h>
-#include <asm/mach-ar7/prom.h>
-
-#define MAX_ENTRY 80
-
-struct env_var {
-	char	*name;
-	char	*value;
-};
-
-static struct env_var adam2_env[MAX_ENTRY];
-
-char *prom_getenv(const char *name)
-{
-	int i;
-
-	for (i = 0; (i < MAX_ENTRY) && adam2_env[i].name; i++)
-		if (!strcmp(name, adam2_env[i].name))
-			return adam2_env[i].value;
-
-	return NULL;
-}
-EXPORT_SYMBOL(prom_getenv);
-
-static void  __init ar7_init_cmdline(int argc, char *argv[])
-{
-	int i;
-
-	for (i = 1; i < argc; i++) {
-		strlcat(arcs_cmdline, argv[i], COMMAND_LINE_SIZE);
-		if (i < (argc - 1))
-			strlcat(arcs_cmdline, " ", COMMAND_LINE_SIZE);
-	}
-}
-
-struct psbl_rec {
-	u32	psbl_size;
-	u32	env_base;
-	u32	env_size;
-	u32	ffs_base;
-	u32	ffs_size;
-};
-
-static const char psp_env_version[] __initconst = "TIENV0.8";
-
-struct psp_env_chunk {
-	u8	num;
-	u8	ctrl;
-	u16	csum;
-	u8	len;
-	char	data[11];
-} __packed;
-
-struct psp_var_map_entry {
-	u8	num;
-	char	*value;
-};
-
-static const struct psp_var_map_entry psp_var_map[] = {
-	{  1,	"cpufrequency" },
-	{  2,	"memsize" },
-	{  3,	"flashsize" },
-	{  4,	"modetty0" },
-	{  5,	"modetty1" },
-	{  8,	"maca" },
-	{  9,	"macb" },
-	{ 28,	"sysfrequency" },
-	{ 38,	"mipsfrequency" },
-};
-
-/*
-
-Well-known variable (num is looked up in table above for matching variable name)
-Example: cpufrequency=211968000
-+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+---
-| 01 |CTRL|CHECKSUM | 01 | _2 | _1 | _1 | _9 | _6 | _8 | _0 | _0 | _0 | \0 | FF
-+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+---
-
-Name=Value pair in a single chunk
-Example: NAME=VALUE
-+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+---
-| 00 |CTRL|CHECKSUM | 01 | _N | _A | _M | _E | _0 | _V | _A | _L | _U | _E | \0
-+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+---
-
-Name=Value pair in 2 chunks (len is the number of chunks)
-Example: bootloaderVersion=1.3.7.15
-+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+---
-| 00 |CTRL|CHECKSUM | 02 | _b | _o | _o | _t | _l | _o | _a | _d | _e | _r | _V
-+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+---
-| _e | _r | _s | _i | _o | _n | \0 | _1 | _. | _3 | _. | _7 | _. | _1 | _5 | \0
-+----+----+----+----+----+----+----+----+----+----+----+----+----+----+----+---
-
-Data is padded with 0xFF
-
-*/
-
-#define PSP_ENV_SIZE  4096
-
-static char psp_env_data[PSP_ENV_SIZE] = { 0, };
-
-static char * __init lookup_psp_var_map(u8 num)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(psp_var_map); i++)
-		if (psp_var_map[i].num == num)
-			return psp_var_map[i].value;
-
-	return NULL;
-}
-
-static void __init add_adam2_var(char *name, char *value)
-{
-	int i;
-
-	for (i = 0; i < MAX_ENTRY; i++) {
-		if (!adam2_env[i].name) {
-			adam2_env[i].name = name;
-			adam2_env[i].value = value;
-			return;
-		} else if (!strcmp(adam2_env[i].name, name)) {
-			adam2_env[i].value = value;
-			return;
-		}
-	}
-}
-
-static int __init parse_psp_env(void *psp_env_base)
-{
-	int i, n;
-	char *name, *value;
-	struct psp_env_chunk *chunks = (struct psp_env_chunk *)psp_env_data;
-
-	memcpy_fromio(chunks, psp_env_base, PSP_ENV_SIZE);
-
-	i = 1;
-	n = PSP_ENV_SIZE / sizeof(struct psp_env_chunk);
-	while (i < n) {
-		if ((chunks[i].num == 0xff) || ((i + chunks[i].len) > n))
-			break;
-		value = chunks[i].data;
-		if (chunks[i].num) {
-			name = lookup_psp_var_map(chunks[i].num);
-		} else {
-			name = value;
-			value += strlen(name) + 1;
-		}
-		if (name)
-			add_adam2_var(name, value);
-		i += chunks[i].len;
-	}
-	return 0;
-}
-
-static void __init ar7_init_env(struct env_var *env)
-{
-	int i;
-	struct psbl_rec *psbl = (struct psbl_rec *)(KSEG1ADDR(0x14000300));
-	void *psp_env = (void *)KSEG1ADDR(psbl->env_base);
-
-	if (strcmp(psp_env, psp_env_version) == 0) {
-		parse_psp_env(psp_env);
-	} else {
-		for (i = 0; i < MAX_ENTRY; i++, env++)
-			if (env->name)
-				add_adam2_var(env->name, env->value);
-	}
-}
-
-static void __init console_config(void)
-{
-#ifdef CONFIG_SERIAL_8250_CONSOLE
-	char console_string[40];
-	int baud = 0;
-	char parity = '\0', bits = '\0', flow = '\0';
-	char *s, *p;
-
-	if (strstr(arcs_cmdline, "console="))
-		return;
-
-	s = prom_getenv("modetty0");
-	if (s) {
-		baud = simple_strtoul(s, &p, 10);
-		s = p;
-		if (*s == ',')
-			s++;
-		if (*s)
-			parity = *s++;
-		if (*s == ',')
-			s++;
-		if (*s)
-			bits = *s++;
-		if (*s == ',')
-			s++;
-		if (*s == 'h')
-			flow = 'r';
-	}
-
-	if (baud == 0)
-		baud = 38400;
-	if (parity != 'n' && parity != 'o' && parity != 'e')
-		parity = 'n';
-	if (bits != '7' && bits != '8')
-		bits = '8';
-
-	if (flow == 'r')
-		sprintf(console_string, " console=ttyS0,%d%c%c%c", baud,
-			parity, bits, flow);
-	else
-		sprintf(console_string, " console=ttyS0,%d%c%c", baud, parity,
-			bits);
-	strlcat(arcs_cmdline, console_string, COMMAND_LINE_SIZE);
-#endif
-}
-
-void __init prom_init(void)
-{
-	ar7_init_cmdline(fw_arg0, (char **)fw_arg1);
-	ar7_init_env((struct env_var *)fw_arg2);
-	console_config();
-}
-
-#define PORT(offset) (KSEG1ADDR(AR7_REGS_UART0 + (offset * 4)))
-static inline unsigned int serial_in(int offset)
-{
-	return readl((void *)PORT(offset));
-}
-
-static inline void serial_out(int offset, int value)
-{
-	writel(value, (void *)PORT(offset));
-}
-
-void prom_putchar(char c)
-{
-	while ((serial_in(UART_LSR) & UART_LSR_TEMT) == 0)
-		;
-	serial_out(UART_TX, c);
-}
diff --git a/arch/mips/ar7/setup.c b/arch/mips/ar7/setup.c
deleted file mode 100644
index 352d5dbc777c39..00000000000000
--- a/arch/mips/ar7/setup.c
+++ /dev/null
@@ -1,93 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Carsten Langgaard, carstenl@mips.com
- * Copyright (C) 2000 MIPS Technologies, Inc.  All rights reserved.
- */
-#include <linux/init.h>
-#include <linux/ioport.h>
-#include <linux/pm.h>
-#include <linux/time.h>
-
-#include <asm/reboot.h>
-#include <asm/mach-ar7/ar7.h>
-#include <asm/mach-ar7/prom.h>
-
-static void ar7_machine_restart(char *command)
-{
-	u32 *softres_reg = ioremap(AR7_REGS_RESET + AR7_RESET_SOFTWARE, 1);
-
-	writel(1, softres_reg);
-}
-
-static void ar7_machine_halt(void)
-{
-	while (1)
-		;
-}
-
-static void ar7_machine_power_off(void)
-{
-	u32 *power_reg = (u32 *)ioremap(AR7_REGS_POWER, 1);
-	u32 power_state = readl(power_reg) | (3 << 30);
-
-	writel(power_state, power_reg);
-	ar7_machine_halt();
-}
-
-const char *get_system_type(void)
-{
-	u16 chip_id = ar7_chip_id();
-	u16 titan_variant_id = titan_chip_id();
-
-	switch (chip_id) {
-	case AR7_CHIP_7100:
-		return "TI AR7 (TNETD7100)";
-	case AR7_CHIP_7200:
-		return "TI AR7 (TNETD7200)";
-	case AR7_CHIP_7300:
-		return "TI AR7 (TNETD7300)";
-	case AR7_CHIP_TITAN:
-		switch (titan_variant_id) {
-		case TITAN_CHIP_1050:
-			return "TI AR7 (TNETV1050)";
-		case TITAN_CHIP_1055:
-			return "TI AR7 (TNETV1055)";
-		case TITAN_CHIP_1056:
-			return "TI AR7 (TNETV1056)";
-		case TITAN_CHIP_1060:
-			return "TI AR7 (TNETV1060)";
-		}
-		fallthrough;
-	default:
-		return "TI AR7 (unknown)";
-	}
-}
-
-static int __init ar7_init_console(void)
-{
-	return 0;
-}
-console_initcall(ar7_init_console);
-
-/*
- * Initializes basic routines and structures pointers, memory size (as
- * given by the bios and saves the command line.
- */
-void __init plat_mem_setup(void)
-{
-	unsigned long io_base;
-
-	_machine_restart = ar7_machine_restart;
-	_machine_halt = ar7_machine_halt;
-	pm_power_off = ar7_machine_power_off;
-
-	io_base = (unsigned long)ioremap(AR7_REGS_BASE, 0x10000);
-	if (!io_base)
-		panic("Can't remap IO base!");
-	set_io_port_base(io_base);
-
-	prom_meminit();
-
-	printk(KERN_INFO "%s, ID: 0x%04x, Revision: 0x%02x\n",
-			get_system_type(), ar7_chip_id(), ar7_chip_rev());
-}
diff --git a/arch/mips/ar7/time.c b/arch/mips/ar7/time.c
deleted file mode 100644
index 72aa77d7087b00..00000000000000
--- a/arch/mips/ar7/time.c
+++ /dev/null
@@ -1,31 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Carsten Langgaard, carstenl@mips.com
- * Copyright (C) 1999,2000 MIPS Technologies, Inc.  All rights reserved.
- *
- * Setting up the clock on the MIPS boards.
- */
-
-#include <linux/init.h>
-#include <linux/time.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-
-#include <asm/time.h>
-#include <asm/mach-ar7/ar7.h>
-
-void __init plat_time_init(void)
-{
-	struct clk *cpu_clk;
-
-	/* Initialize ar7 clocks so the CPU clock frequency is correct */
-	ar7_init_clocks();
-
-	cpu_clk = clk_get(NULL, "cpu");
-	if (IS_ERR(cpu_clk)) {
-		printk(KERN_ERR "unable to get cpu clock\n");
-		return;
-	}
-
-	mips_hpt_frequency = clk_get_rate(cpu_clk) / 2;
-}
diff --git a/arch/mips/boot/compressed/uart-16550.c b/arch/mips/boot/compressed/uart-16550.c
index 96d28f21112196..09dcd2c561d9af 100644
--- a/arch/mips/boot/compressed/uart-16550.c
+++ b/arch/mips/boot/compressed/uart-16550.c
@@ -13,11 +13,6 @@
 #define PORT(offset) (CKSEG1ADDR(UART_BASE) + (offset))
 #endif
 
-#ifdef CONFIG_AR7
-#include <ar7.h>
-#define PORT(offset) (CKSEG1ADDR(AR7_REGS_UART0) + (4 * offset))
-#endif
-
 #ifdef CONFIG_MACH_INGENIC
 #define INGENIC_UART_BASE_ADDR	(0x10030000 + 0x1000 * CONFIG_ZBOOT_INGENIC_UART)
 #define PORT(offset) (CKSEG1ADDR(INGENIC_UART_BASE_ADDR) + (4 * offset))
diff --git a/arch/mips/boot/dts/ingenic/jz4725b.dtsi b/arch/mips/boot/dts/ingenic/jz4725b.dtsi
index acbbe8c4664c11..c5c5a094c37d2e 100644
--- a/arch/mips/boot/dts/ingenic/jz4725b.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4725b.dtsi
@@ -366,7 +366,6 @@
 
 	rom: memory@1fc00000 {
 		compatible = "mtd-rom";
-		probe-type = "map_rom";
 		reg = <0x1fc00000 0x2000>;
 
 		bank-width = <4>;
diff --git a/arch/mips/boot/dts/ingenic/jz4770.dtsi b/arch/mips/boot/dts/ingenic/jz4770.dtsi
index 9c0099919db7ab..504e895e916e57 100644
--- a/arch/mips/boot/dts/ingenic/jz4770.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4770.dtsi
@@ -461,7 +461,6 @@
 
 	rom: memory@1fc00000 {
 		compatible = "mtd-rom";
-		probe-type = "map_rom";
 		reg = <0x1fc00000 0x2000>;
 
 		bank-width = <4>;
diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
index f878f47e4501bc..ee3e2153dd13fb 100644
--- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
+++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
@@ -130,8 +130,7 @@
 				compatible = "pci0014,7a03.0",
 						   "pci0014,7a03",
 						   "pciclass0c0320",
-						   "pciclass0c03",
-						   "loongson, pci-gmac";
+						   "pciclass0c03";
 
 				reg = <0x1800 0x0 0x0 0x0 0x0>;
 				interrupts = <12 IRQ_TYPE_LEVEL_LOW>,
diff --git a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
index 7c69e8245c2f10..cce9428afc41fc 100644
--- a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
+++ b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
@@ -193,8 +193,7 @@
 				compatible = "pci0014,7a03.0",
 						   "pci0014,7a03",
 						   "pciclass020000",
-						   "pciclass0200",
-						   "loongson, pci-gmac";
+						   "pciclass0200";
 
 				reg = <0x1800 0x0 0x0 0x0 0x0>;
 				interrupts = <12 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc1.dts b/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc1.dts
index 129b6710b699df..f9c262cc2e96bf 100644
--- a/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc1.dts
+++ b/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc1.dts
@@ -8,7 +8,7 @@
 
 / {
 	compatible = "gnubee,gb-pc1", "mediatek,mt7621-soc";
-	model = "GB-PC1";
+	model = "GnuBee GB-PC1";
 
 	memory@0 {
 		device_type = "memory";
diff --git a/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc2.dts b/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc2.dts
index f810cd10f4f4fc..b281e13f22ed26 100644
--- a/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc2.dts
+++ b/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc2.dts
@@ -8,7 +8,7 @@
 
 / {
 	compatible = "gnubee,gb-pc2", "mediatek,mt7621-soc";
-	model = "GB-PC2";
+	model = "GnuBee GB-PC2";
 
 	memory@0 {
 		device_type = "memory";
diff --git a/arch/mips/boot/dts/ralink/mt7621.dtsi b/arch/mips/boot/dts/ralink/mt7621.dtsi
index 7caed0d14f11a6..35a10258f2357b 100644
--- a/arch/mips/boot/dts/ralink/mt7621.dtsi
+++ b/arch/mips/boot/dts/ralink/mt7621.dtsi
@@ -300,14 +300,13 @@
 		compatible = "mediatek,mt7621-eth";
 		reg = <0x1e100000 0x10000>;
 
-		clocks = <&sysc MT7621_CLK_FE>,
-			 <&sysc MT7621_CLK_ETH>;
+		clocks = <&sysc MT7621_CLK_FE>, <&sysc MT7621_CLK_ETH>;
 		clock-names = "fe", "ethif";
 
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		resets = <&sysc MT7621_RST_FE &sysc MT7621_RST_ETH>;
+		resets = <&sysc MT7621_RST_FE>, <&sysc MT7621_RST_ETH>;
 		reset-names = "fe", "eth";
 
 		interrupt-parent = <&gic>;
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 33c09688210fff..08ea2cde1eb5b3 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -422,7 +422,7 @@ static const struct plat_smp_ops octeon_smp_ops = {
 	.cpu_disable		= octeon_cpu_disable,
 	.cpu_die		= octeon_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
@@ -502,7 +502,7 @@ static const struct plat_smp_ops octeon_78xx_smp_ops = {
 	.cpu_disable		= octeon_cpu_disable,
 	.cpu_die		= octeon_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
diff --git a/arch/mips/configs/ar7_defconfig b/arch/mips/configs/ar7_defconfig
deleted file mode 100644
index 329c60aa570ab4..00000000000000
--- a/arch/mips/configs/ar7_defconfig
+++ /dev/null
@@ -1,119 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_KERNEL_LZMA=y
-CONFIG_SYSVIPC=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-# CONFIG_ELF_CORE is not set
-# CONFIG_KALLSYMS is not set
-# CONFIG_VM_EVENT_COUNTERS is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_AR7=y
-CONFIG_HZ_100=y
-CONFIG_KEXEC=y
-# CONFIG_SECCOMP is not set
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_ROUTE_MULTIPATH=y
-CONFIG_IP_ROUTE_VERBOSE=y
-CONFIG_IP_MROUTE=y
-CONFIG_SYN_COOKIES=y
-# CONFIG_INET_DIAG is not set
-CONFIG_TCP_CONG_ADVANCED=y
-# CONFIG_TCP_CONG_BIC is not set
-# CONFIG_TCP_CONG_CUBIC is not set
-CONFIG_TCP_CONG_WESTWOOD=y
-# CONFIG_TCP_CONG_HTCP is not set
-# CONFIG_IPV6 is not set
-CONFIG_NETFILTER=y
-# CONFIG_BRIDGE_NETFILTER is not set
-CONFIG_NF_CONNTRACK=m
-CONFIG_NF_CONNTRACK_MARK=y
-CONFIG_NF_CONNTRACK_FTP=m
-CONFIG_NF_CONNTRACK_IRC=m
-CONFIG_NF_CONNTRACK_TFTP=m
-CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
-CONFIG_NETFILTER_XT_MATCH_LIMIT=m
-CONFIG_NETFILTER_XT_MATCH_MAC=m
-CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
-CONFIG_NETFILTER_XT_MATCH_STATE=m
-CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_FILTER=m
-CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_RAW=m
-CONFIG_ATM=m
-CONFIG_ATM_BR2684=m
-CONFIG_ATM_BR2684_IPFILTER=y
-CONFIG_BRIDGE=y
-CONFIG_VLAN_8021Q=y
-CONFIG_NET_SCHED=y
-CONFIG_NET_CLS_ACT=y
-CONFIG_NET_ACT_POLICE=y
-CONFIG_HAMRADIO=y
-CONFIG_CFG80211=m
-CONFIG_MAC80211=m
-CONFIG_MTD=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_CFI_STAA=y
-CONFIG_MTD_COMPLEX_MAPPINGS=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_NETDEVICES=y
-CONFIG_CPMAC=y
-CONFIG_FIXED_PHY=y
-CONFIG_PPP=m
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_MULTILINK=y
-CONFIG_PPPOATM=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_NR_UARTS=2
-CONFIG_SERIAL_8250_RUNTIME_UARTS=2
-CONFIG_HW_RANDOM=y
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AR7_WDT=y
-# CONFIG_USB_SUPPORT is not set
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
-# CONFIG_DNOTIFY is not set
-CONFIG_PROC_KCORE=y
-# CONFIG_PROC_PAGE_MONITOR is not set
-CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=y
-CONFIG_JFFS2_SUMMARY=y
-CONFIG_JFFS2_COMPRESSION_OPTIONS=y
-CONFIG_SQUASHFS=y
-# CONFIG_CRYPTO_HW is not set
-CONFIG_STRIP_ASM_SYMS=y
-CONFIG_DEBUG_FS=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="rootfstype=squashfs,jffs2"
diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig
index 1843468f84a30d..00329bb5de5ab0 100644
--- a/arch/mips/configs/fuloong2e_defconfig
+++ b/arch/mips/configs/fuloong2e_defconfig
@@ -177,7 +177,6 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
-CONFIG_REISERFS_FS=m
 CONFIG_AUTOFS_FS=y
 CONFIG_FUSE_FS=y
 CONFIG_ISO9660_FS=m
diff --git a/arch/mips/configs/jazz_defconfig b/arch/mips/configs/jazz_defconfig
index fdf37457410547..65adb538030d02 100644
--- a/arch/mips/configs/jazz_defconfig
+++ b/arch/mips/configs/jazz_defconfig
@@ -70,10 +70,6 @@ CONFIG_FRAMEBUFFER_CONSOLE=y
 # CONFIG_HWMON is not set
 CONFIG_EXT2_FS=m
 CONFIG_EXT3_FS=y
-CONFIG_REISERFS_FS=m
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_QUOTA=y
 CONFIG_AUTOFS_FS=m
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index 83d9a8ff427082..38f17b65842187 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -229,9 +229,6 @@ CONFIG_EXT2_FS=m
 CONFIG_EXT3_FS=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT3_FS_SECURITY=y
-CONFIG_REISERFS_FS=m
-CONFIG_REISERFS_PROC_INFO=y
-CONFIG_REISERFS_FS_XATTR=y
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
 CONFIG_XFS_FS=m
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index ae1a7793e810f8..6f80460245573e 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -317,11 +317,6 @@ CONFIG_UIO=m
 CONFIG_UIO_CIF=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
-CONFIG_REISERFS_FS=m
-CONFIG_REISERFS_PROC_INFO=y
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
 CONFIG_JFS_SECURITY=y
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index c07e30f63d8bc6..16a91eeff67fe9 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -323,11 +323,6 @@ CONFIG_UIO=m
 CONFIG_UIO_CIF=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
-CONFIG_REISERFS_FS=m
-CONFIG_REISERFS_PROC_INFO=y
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
 CONFIG_JFS_SECURITY=y
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 0a5701020d3f25..264aba29ea4fea 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -323,11 +323,6 @@ CONFIG_UIO=m
 CONFIG_UIO_CIF=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
-CONFIG_REISERFS_FS=m
-CONFIG_REISERFS_PROC_INFO=y
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
 CONFIG_JFS_FS=m
 CONFIG_JFS_POSIX_ACL=y
 CONFIG_JFS_SECURITY=y
diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig
index 5c5e2186210cfd..08e1c1f2f4debf 100644
--- a/arch/mips/configs/rm200_defconfig
+++ b/arch/mips/configs/rm200_defconfig
@@ -310,10 +310,6 @@ CONFIG_USB_LD=m
 CONFIG_USB_TEST=m
 CONFIG_EXT2_FS=m
 CONFIG_EXT3_FS=y
-CONFIG_REISERFS_FS=m
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_QUOTA=y
 CONFIG_AUTOFS_FS=m
diff --git a/arch/mips/include/asm/kexec.h b/arch/mips/include/asm/kexec.h
index d6d5fa5cc31dd7..69e579e41e6623 100644
--- a/arch/mips/include/asm/kexec.h
+++ b/arch/mips/include/asm/kexec.h
@@ -31,7 +31,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 		prepare_frametrace(newregs);
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 struct kimage;
 extern unsigned long kexec_args[4];
 extern int (*_machine_kexec_prepare)(struct kimage *);
diff --git a/arch/mips/include/asm/kprobes.h b/arch/mips/include/asm/kprobes.h
index 68b1e5d458cfb6..bc27d99c943634 100644
--- a/arch/mips/include/asm/kprobes.h
+++ b/arch/mips/include/asm/kprobes.h
@@ -71,8 +71,6 @@ struct kprobe_ctlblk {
 	struct prev_kprobe prev_kprobe;
 };
 
-extern int kprobe_exceptions_notify(struct notifier_block *self,
-				    unsigned long val, void *data);
 
 #endif /* CONFIG_KPROBES */
 #endif /* _ASM_KPROBES_H */
diff --git a/arch/mips/include/asm/mach-ar7/ar7.h b/arch/mips/include/asm/mach-ar7/ar7.h
deleted file mode 100644
index 1e8621a6afa310..00000000000000
--- a/arch/mips/include/asm/mach-ar7/ar7.h
+++ /dev/null
@@ -1,191 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2006,2007 Felix Fietkau <nbd@openwrt.org>
- * Copyright (C) 2006,2007 Eugene Konev <ejka@openwrt.org>
- */
-
-#ifndef __AR7_H__
-#define __AR7_H__
-
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <linux/errno.h>
-
-#include <asm/addrspace.h>
-
-#define AR7_SDRAM_BASE	0x14000000
-
-#define AR7_REGS_BASE	0x08610000
-
-#define AR7_REGS_MAC0	(AR7_REGS_BASE + 0x0000)
-#define AR7_REGS_GPIO	(AR7_REGS_BASE + 0x0900)
-/* 0x08610A00 - 0x08610BFF (512 bytes, 128 bytes / clock) */
-#define AR7_REGS_POWER	(AR7_REGS_BASE + 0x0a00)
-#define AR7_REGS_CLOCKS (AR7_REGS_POWER + 0x80)
-#define UR8_REGS_CLOCKS (AR7_REGS_POWER + 0x20)
-#define AR7_REGS_UART0	(AR7_REGS_BASE + 0x0e00)
-#define AR7_REGS_USB	(AR7_REGS_BASE + 0x1200)
-#define AR7_REGS_RESET	(AR7_REGS_BASE + 0x1600)
-#define AR7_REGS_PINSEL (AR7_REGS_BASE + 0x160C)
-#define AR7_REGS_VLYNQ0 (AR7_REGS_BASE + 0x1800)
-#define AR7_REGS_DCL	(AR7_REGS_BASE + 0x1a00)
-#define AR7_REGS_VLYNQ1 (AR7_REGS_BASE + 0x1c00)
-#define AR7_REGS_MDIO	(AR7_REGS_BASE + 0x1e00)
-#define AR7_REGS_IRQ	(AR7_REGS_BASE + 0x2400)
-#define AR7_REGS_MAC1	(AR7_REGS_BASE + 0x2800)
-
-#define AR7_REGS_WDT	(AR7_REGS_BASE + 0x1f00)
-#define UR8_REGS_WDT	(AR7_REGS_BASE + 0x0b00)
-#define UR8_REGS_UART1	(AR7_REGS_BASE + 0x0f00)
-
-/* Titan registers */
-#define TITAN_REGS_ESWITCH_BASE (0x08640000)
-#define TITAN_REGS_MAC0		(TITAN_REGS_ESWITCH_BASE)
-#define TITAN_REGS_MAC1		(TITAN_REGS_ESWITCH_BASE + 0x0800)
-#define TITAN_REGS_MDIO		(TITAN_REGS_ESWITCH_BASE + 0x02000)
-#define TITAN_REGS_VLYNQ0	(AR7_REGS_BASE + 0x1c00)
-#define TITAN_REGS_VLYNQ1	(AR7_REGS_BASE + 0x1300)
-
-#define AR7_RESET_PERIPHERAL	0x0
-#define AR7_RESET_SOFTWARE	0x4
-#define AR7_RESET_STATUS	0x8
-
-#define AR7_RESET_BIT_CPMAC_LO	17
-#define AR7_RESET_BIT_CPMAC_HI	21
-#define AR7_RESET_BIT_MDIO	22
-#define AR7_RESET_BIT_EPHY	26
-
-#define TITAN_RESET_BIT_EPHY1	28
-
-/* GPIO control registers */
-#define AR7_GPIO_INPUT	0x0
-#define AR7_GPIO_OUTPUT 0x4
-#define AR7_GPIO_DIR	0x8
-#define AR7_GPIO_ENABLE 0xc
-#define TITAN_GPIO_INPUT_0	0x0
-#define TITAN_GPIO_INPUT_1	0x4
-#define TITAN_GPIO_OUTPUT_0	0x8
-#define TITAN_GPIO_OUTPUT_1	0xc
-#define TITAN_GPIO_DIR_0	0x10
-#define TITAN_GPIO_DIR_1	0x14
-#define TITAN_GPIO_ENBL_0	0x18
-#define TITAN_GPIO_ENBL_1	0x1c
-
-#define AR7_CHIP_7100	0x18
-#define AR7_CHIP_7200	0x2b
-#define AR7_CHIP_7300	0x05
-#define AR7_CHIP_TITAN	0x07
-#define TITAN_CHIP_1050 0x0f
-#define TITAN_CHIP_1055 0x0e
-#define TITAN_CHIP_1056 0x0d
-#define TITAN_CHIP_1060 0x07
-
-/* Interrupts */
-#define AR7_IRQ_UART0	15
-#define AR7_IRQ_UART1	16
-
-/* Clocks */
-#define AR7_AFE_CLOCK	35328000
-#define AR7_REF_CLOCK	25000000
-#define AR7_XTAL_CLOCK	24000000
-
-/* DCL */
-#define AR7_WDT_HW_ENA	0x10
-
-struct plat_cpmac_data {
-	int reset_bit;
-	int power_bit;
-	u32 phy_mask;
-	char dev_addr[6];
-};
-
-struct plat_dsl_data {
-	int reset_bit_dsl;
-	int reset_bit_sar;
-};
-
-static inline int ar7_is_titan(void)
-{
-	return (readl((void *)KSEG1ADDR(AR7_REGS_GPIO + 0x24)) & 0xffff) ==
-		AR7_CHIP_TITAN;
-}
-
-static inline u16 ar7_chip_id(void)
-{
-	return ar7_is_titan() ? AR7_CHIP_TITAN : (readl((void *)
-		KSEG1ADDR(AR7_REGS_GPIO + 0x14)) & 0xffff);
-}
-
-static inline u16 titan_chip_id(void)
-{
-	unsigned int val = readl((void *)KSEG1ADDR(AR7_REGS_GPIO +
-						TITAN_GPIO_INPUT_1));
-	return ((val >> 12) & 0x0f);
-}
-
-static inline u8 ar7_chip_rev(void)
-{
-	return (readl((void *)KSEG1ADDR(AR7_REGS_GPIO + (ar7_is_titan() ? 0x24 :
-		0x14))) >> 16) & 0xff;
-}
-
-static inline int ar7_has_high_cpmac(void)
-{
-	u16 chip_id = ar7_chip_id();
-	switch (chip_id) {
-	case AR7_CHIP_7100:
-	case AR7_CHIP_7200:
-		return 0;
-	case AR7_CHIP_7300:
-		return 1;
-	default:
-		return -ENXIO;
-	}
-}
-#define ar7_has_high_vlynq ar7_has_high_cpmac
-#define ar7_has_second_uart ar7_has_high_cpmac
-
-static inline void ar7_device_enable(u32 bit)
-{
-	void *reset_reg =
-		(void *)KSEG1ADDR(AR7_REGS_RESET + AR7_RESET_PERIPHERAL);
-	writel(readl(reset_reg) | (1 << bit), reset_reg);
-	msleep(20);
-}
-
-static inline void ar7_device_disable(u32 bit)
-{
-	void *reset_reg =
-		(void *)KSEG1ADDR(AR7_REGS_RESET + AR7_RESET_PERIPHERAL);
-	writel(readl(reset_reg) & ~(1 << bit), reset_reg);
-	msleep(20);
-}
-
-static inline void ar7_device_reset(u32 bit)
-{
-	ar7_device_disable(bit);
-	ar7_device_enable(bit);
-}
-
-static inline void ar7_device_on(u32 bit)
-{
-	void *power_reg = (void *)KSEG1ADDR(AR7_REGS_POWER);
-	writel(readl(power_reg) | (1 << bit), power_reg);
-	msleep(20);
-}
-
-static inline void ar7_device_off(u32 bit)
-{
-	void *power_reg = (void *)KSEG1ADDR(AR7_REGS_POWER);
-	writel(readl(power_reg) & ~(1 << bit), power_reg);
-	msleep(20);
-}
-
-int __init ar7_gpio_init(void);
-void __init ar7_init_clocks(void);
-
-/* Board specific GPIO functions */
-int ar7_gpio_enable(unsigned gpio);
-int ar7_gpio_disable(unsigned gpio);
-
-#endif /* __AR7_H__ */
diff --git a/arch/mips/include/asm/mach-ar7/irq.h b/arch/mips/include/asm/mach-ar7/irq.h
deleted file mode 100644
index 46bb730ea970c6..00000000000000
--- a/arch/mips/include/asm/mach-ar7/irq.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Shamelessly copied from asm-mips/mach-emma2rh/
- * Copyright (C) 2003 by Ralf Baechle
- */
-#ifndef __ASM_AR7_IRQ_H
-#define __ASM_AR7_IRQ_H
-
-#define NR_IRQS 256
-
-#include <asm/mach-generic/irq.h>
-
-#endif /* __ASM_AR7_IRQ_H */
diff --git a/arch/mips/include/asm/mach-ar7/prom.h b/arch/mips/include/asm/mach-ar7/prom.h
deleted file mode 100644
index 9e1d20b06f5766..00000000000000
--- a/arch/mips/include/asm/mach-ar7/prom.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2006, 2007 Florian Fainelli <florian@openwrt.org>
- */
-
-#ifndef __PROM_H__
-#define __PROM_H__
-
-extern char *prom_getenv(const char *name);
-extern void prom_meminit(void);
-
-#endif /* __PROM_H__ */
diff --git a/arch/mips/include/asm/mach-ar7/spaces.h b/arch/mips/include/asm/mach-ar7/spaces.h
deleted file mode 100644
index a004d94dfbddcb..00000000000000
--- a/arch/mips/include/asm/mach-ar7/spaces.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1994 - 1999, 2000, 03, 04 Ralf Baechle
- * Copyright (C) 2000, 2002  Maciej W. Rozycki
- * Copyright (C) 1990, 1999, 2000 Silicon Graphics, Inc.
- */
-#ifndef _ASM_AR7_SPACES_H
-#define _ASM_AR7_SPACES_H
-
-/*
- * This handles the memory map.
- * We handle pages at KSEG0 for kernels with 32 bit address space.
- */
-#define PAGE_OFFSET	_AC(0x94000000, UL)
-#define PHYS_OFFSET	_AC(0x14000000, UL)
-
-#include <asm/mach-generic/spaces.h>
-
-#endif /* __ASM_AR7_SPACES_H */
diff --git a/arch/mips/include/asm/mach-loongson32/dma.h b/arch/mips/include/asm/mach-loongson32/dma.h
deleted file mode 100644
index e917b3ccb2c2d6..00000000000000
--- a/arch/mips/include/asm/mach-loongson32/dma.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (c) 2015 Zhang, Keguang <keguang.zhang@gmail.com>
- *
- * Loongson 1 NAND platform support.
- */
-
-#ifndef __ASM_MACH_LOONGSON32_DMA_H
-#define __ASM_MACH_LOONGSON32_DMA_H
-
-#define LS1X_DMA_CHANNEL0	0
-#define LS1X_DMA_CHANNEL1	1
-#define LS1X_DMA_CHANNEL2	2
-
-struct plat_ls1x_dma {
-	int nr_channels;
-};
-
-extern struct plat_ls1x_dma ls1b_dma_pdata;
-
-#endif /* __ASM_MACH_LOONGSON32_DMA_H */
diff --git a/arch/mips/include/asm/mach-loongson32/nand.h b/arch/mips/include/asm/mach-loongson32/nand.h
deleted file mode 100644
index aaf5ed19d78d41..00000000000000
--- a/arch/mips/include/asm/mach-loongson32/nand.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (c) 2015 Zhang, Keguang <keguang.zhang@gmail.com>
- *
- * Loongson 1 NAND platform support.
- */
-
-#ifndef __ASM_MACH_LOONGSON32_NAND_H
-#define __ASM_MACH_LOONGSON32_NAND_H
-
-#include <linux/dmaengine.h>
-#include <linux/mtd/partitions.h>
-
-struct plat_ls1x_nand {
-	struct mtd_partition *parts;
-	unsigned int nr_parts;
-
-	int hold_cycle;
-	int wait_cycle;
-};
-
-extern struct plat_ls1x_nand ls1b_nand_pdata;
-
-bool ls1x_dma_filter_fn(struct dma_chan *chan, void *param);
-
-#endif /* __ASM_MACH_LOONGSON32_NAND_H */
diff --git a/arch/mips/include/asm/mach-loongson32/platform.h b/arch/mips/include/asm/mach-loongson32/platform.h
index 2cdcfb5f6012d4..f74292b13bc3ba 100644
--- a/arch/mips/include/asm/mach-loongson32/platform.h
+++ b/arch/mips/include/asm/mach-loongson32/platform.h
@@ -8,9 +8,6 @@
 
 #include <linux/platform_device.h>
 
-#include <dma.h>
-#include <nand.h>
-
 extern struct platform_device ls1x_uart_pdev;
 extern struct platform_device ls1x_eth0_pdev;
 extern struct platform_device ls1x_eth1_pdev;
diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h
index 035b1a69e2d00d..e007edd6b60a7e 100644
--- a/arch/mips/include/asm/mach-loongson64/boot_param.h
+++ b/arch/mips/include/asm/mach-loongson64/boot_param.h
@@ -14,7 +14,11 @@
 #define ADAPTER_ROM		8
 #define ACPI_TABLE		9
 #define SMBIOS_TABLE		10
-#define MAX_MEMORY_TYPE		11
+#define UMA_VIDEO_RAM		11
+#define VUMA_VIDEO_RAM		12
+#define MAX_MEMORY_TYPE		13
+
+#define MEM_SIZE_IS_IN_BYTES	(1 << 31)
 
 #define LOONGSON3_BOOT_MEM_MAP_MAX 128
 struct efi_memory_map_loongson {
@@ -117,7 +121,8 @@ struct irq_source_routing_table {
 	u64 pci_io_start_addr;
 	u64 pci_io_end_addr;
 	u64 pci_config_addr;
-	u32 dma_mask_bits;
+	u16 dma_mask_bits;
+	u16 dma_noncoherent;
 } __packed;
 
 struct interface_info {
diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h
index 5719ff49eff1c8..0c59e168f8008c 100644
--- a/arch/mips/include/asm/smp-ops.h
+++ b/arch/mips/include/asm/smp-ops.h
@@ -35,7 +35,7 @@ struct plat_smp_ops {
 	void (*cpu_die)(unsigned int cpu);
 	void (*cleanup_dead_cpu)(unsigned cpu);
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	void (*kexec_nonboot_cpu)(void);
 #endif
 };
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index a40d8c0e4b879b..901bc61fa7ae92 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -93,7 +93,7 @@ static inline void __cpu_die(unsigned int cpu)
 extern void __noreturn play_dead(void);
 #endif
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 static inline void kexec_nonboot_cpu(void)
 {
 	extern const struct plat_smp_ops *mp_ops;	/* private */
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 853a43ee4b446e..ecf3278a32f707 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -90,7 +90,7 @@ obj-$(CONFIG_GPIO_TXX9)		+= gpio_txx9.o
 
 obj-$(CONFIG_RELOCATABLE)	+= relocate.o
 
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o crash.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_EARLY_PRINTK_8250)	+= early_printk_8250.o
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 5387ed0a51862b..b630604c577f9f 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -121,6 +121,19 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	/*  Put the stack after the struct pt_regs.  */
 	childksp = (unsigned long) childregs;
 	p->thread.cp0_status = (read_c0_status() & ~(ST0_CU2|ST0_CU1)) | ST0_KERNEL_CUMASK;
+
+	/*
+	 * New tasks lose permission to use the fpu. This accelerates context
+	 * switching for most programs since they don't use the fpu.
+	 */
+	clear_tsk_thread_flag(p, TIF_USEDFPU);
+	clear_tsk_thread_flag(p, TIF_USEDMSA);
+	clear_tsk_thread_flag(p, TIF_MSA_CTX_LIVE);
+
+#ifdef CONFIG_MIPS_MT_FPAFF
+	clear_tsk_thread_flag(p, TIF_FPUBOUND);
+#endif /* CONFIG_MIPS_MT_FPAFF */
+
 	if (unlikely(args->fn)) {
 		/* kernel thread */
 		unsigned long status = p->thread.cp0_status;
@@ -149,20 +162,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	p->thread.reg29 = (unsigned long) childregs;
 	p->thread.reg31 = (unsigned long) ret_from_fork;
 
-	/*
-	 * New tasks lose permission to use the fpu. This accelerates context
-	 * switching for most programs since they don't use the fpu.
-	 */
 	childregs->cp0_status &= ~(ST0_CU2|ST0_CU1);
 
-	clear_tsk_thread_flag(p, TIF_USEDFPU);
-	clear_tsk_thread_flag(p, TIF_USEDMSA);
-	clear_tsk_thread_flag(p, TIF_MSA_CTX_LIVE);
-
-#ifdef CONFIG_MIPS_MT_FPAFF
-	clear_tsk_thread_flag(p, TIF_FPUBOUND);
-#endif /* CONFIG_MIPS_MT_FPAFF */
-
 #ifdef CONFIG_MIPS_FP_SUPPORT
 	atomic_set(&p->thread.bd_emu_frame, BD_EMUFRAME_NONE);
 #endif
diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S
index f5b2ef979b4378..8f0a7263a9d61f 100644
--- a/arch/mips/kernel/relocate_kernel.S
+++ b/arch/mips/kernel/relocate_kernel.S
@@ -66,7 +66,6 @@ copy_word:
 	LONG_ADDIU	s6, s6, -1
 	beq		s6, zero, process_entry
 	b		copy_word
-	b		process_entry
 
 done:
 #ifdef CONFIG_SMP
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index c074ecce3fbf29..b3dbf9ecb0d63e 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -434,7 +434,7 @@ const struct plat_smp_ops bmips43xx_smp_ops = {
 	.cpu_disable		= bmips_cpu_disable,
 	.cpu_die		= bmips_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
@@ -451,7 +451,7 @@ const struct plat_smp_ops bmips5000_smp_ops = {
 	.cpu_disable		= bmips_cpu_disable,
 	.cpu_die		= bmips_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index dd55d59b88db34..f6c37d407f365f 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -392,7 +392,7 @@ static void cps_smp_finish(void)
 	local_irq_enable();
 }
 
-#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC)
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC_CORE)
 
 enum cpu_death {
 	CPU_DEATH_HALT,
@@ -429,7 +429,7 @@ static void cps_shutdown_this_cpu(enum cpu_death death)
 	}
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 static void cps_kexec_nonboot_cpu(void)
 {
@@ -439,9 +439,9 @@ static void cps_kexec_nonboot_cpu(void)
 		cps_shutdown_this_cpu(CPU_DEATH_POWER);
 }
 
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
-#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC */
+#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC_CORE */
 
 #ifdef CONFIG_HOTPLUG_CPU
 
@@ -610,7 +610,7 @@ static const struct plat_smp_ops cps_smp_ops = {
 	.cpu_die		= cps_cpu_die,
 	.cleanup_dead_cpu	= cps_cleanup_dead_cpu,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= cps_kexec_nonboot_cpu,
 #endif
 };
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 8fbef537fb8859..82e2e051b4161c 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -351,10 +351,11 @@ early_initcall(mips_smp_ipi_init);
  */
 asmlinkage void start_secondary(void)
 {
-	unsigned int cpu;
+	unsigned int cpu = raw_smp_processor_id();
 
 	cpu_probe();
 	per_cpu_trap_init(false);
+	rcutree_report_cpu_starting(cpu);
 	mips_clockevent_init();
 	mp_ops->init_secondary();
 	cpu_report();
@@ -366,7 +367,6 @@ asmlinkage void start_secondary(void)
 	 */
 
 	calibrate_delay();
-	cpu = smp_processor_id();
 	cpu_data[cpu].udelay_val = loops_per_jiffy;
 
 	set_cpu_sibling_map(cpu);
diff --git a/arch/mips/loongson32/common/platform.c b/arch/mips/loongson32/common/platform.c
index 8075590a9f8346..623eb4bc7b41ea 100644
--- a/arch/mips/loongson32/common/platform.c
+++ b/arch/mips/loongson32/common/platform.c
@@ -15,8 +15,6 @@
 
 #include <platform.h>
 #include <loongson1.h>
-#include <dma.h>
-#include <nand.h>
 
 /* 8250/16550 compatible UART */
 #define LS1X_UART(_id)						\
diff --git a/arch/mips/loongson32/ls1b/board.c b/arch/mips/loongson32/ls1b/board.c
index fed8d432ef2068..fe115bdcb22ce9 100644
--- a/arch/mips/loongson32/ls1b/board.c
+++ b/arch/mips/loongson32/ls1b/board.c
@@ -8,8 +8,6 @@
 #include <linux/sizes.h>
 
 #include <loongson1.h>
-#include <dma.h>
-#include <nand.h>
 #include <platform.h>
 
 static const struct gpio_led ls1x_gpio_leds[] __initconst = {
diff --git a/arch/mips/loongson64/env.c b/arch/mips/loongson64/env.c
index c961e2999f15ac..ef3750a6ffacf8 100644
--- a/arch/mips/loongson64/env.c
+++ b/arch/mips/loongson64/env.c
@@ -13,6 +13,8 @@
  * Copyright (C) 2009 Lemote Inc.
  * Author: Wu Zhangjin, wuzhangjin@gmail.com
  */
+
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <linux/pci_ids.h>
 #include <asm/bootinfo.h>
@@ -147,8 +149,14 @@ void __init prom_lefi_init_env(void)
 
 	loongson_sysconf.dma_mask_bits = eirq_source->dma_mask_bits;
 	if (loongson_sysconf.dma_mask_bits < 32 ||
-		loongson_sysconf.dma_mask_bits > 64)
+			loongson_sysconf.dma_mask_bits > 64) {
 		loongson_sysconf.dma_mask_bits = 32;
+		dma_default_coherent = true;
+	} else {
+		dma_default_coherent = !eirq_source->dma_noncoherent;
+	}
+
+	pr_info("Firmware: Coherent DMA: %s\n", dma_default_coherent ? "on" : "off");
 
 	loongson_sysconf.restart_addr = boot_p->reset_system.ResetWarm;
 	loongson_sysconf.poweroff_addr = boot_p->reset_system.Shutdown;
diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c
index ee8de1735b7c04..f25caa6aa9d306 100644
--- a/arch/mips/loongson64/init.c
+++ b/arch/mips/loongson64/init.c
@@ -49,8 +49,7 @@ void virtual_early_config(void)
 void __init szmem(unsigned int node)
 {
 	u32 i, mem_type;
-	static unsigned long num_physpages;
-	u64 node_id, node_psize, start_pfn, end_pfn, mem_start, mem_size;
+	phys_addr_t node_id, mem_start, mem_size;
 
 	/* Otherwise come from DTB */
 	if (loongson_sysconf.fw_interface != LOONGSON_LEFI)
@@ -64,30 +63,46 @@ void __init szmem(unsigned int node)
 
 		mem_type = loongson_memmap->map[i].mem_type;
 		mem_size = loongson_memmap->map[i].mem_size;
-		mem_start = loongson_memmap->map[i].mem_start;
+
+		/* Memory size comes in MB if MEM_SIZE_IS_IN_BYTES not set */
+		if (mem_size & MEM_SIZE_IS_IN_BYTES)
+			mem_size &= ~MEM_SIZE_IS_IN_BYTES;
+		else
+			mem_size = mem_size << 20;
+
+		mem_start = (node_id << 44) | loongson_memmap->map[i].mem_start;
 
 		switch (mem_type) {
 		case SYSTEM_RAM_LOW:
 		case SYSTEM_RAM_HIGH:
-			start_pfn = ((node_id << 44) + mem_start) >> PAGE_SHIFT;
-			node_psize = (mem_size << 20) >> PAGE_SHIFT;
-			end_pfn  = start_pfn + node_psize;
-			num_physpages += node_psize;
-			pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
-				(u32)node_id, mem_type, mem_start, mem_size);
-			pr_info("       start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
-				start_pfn, end_pfn, num_physpages);
-			memblock_add_node(PFN_PHYS(start_pfn),
-					  PFN_PHYS(node_psize), node,
+		case UMA_VIDEO_RAM:
+			pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes usable\n",
+				(u32)node_id, mem_type, &mem_start, &mem_size);
+			memblock_add_node(mem_start, mem_size, node,
 					  MEMBLOCK_NONE);
 			break;
 		case SYSTEM_RAM_RESERVED:
-			pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
-				(u32)node_id, mem_type, mem_start, mem_size);
-			memblock_reserve(((node_id << 44) + mem_start), mem_size << 20);
+		case VIDEO_ROM:
+		case ADAPTER_ROM:
+		case ACPI_TABLE:
+		case SMBIOS_TABLE:
+			pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes reserved\n",
+				(u32)node_id, mem_type, &mem_start, &mem_size);
+			memblock_reserve(mem_start, mem_size);
+			break;
+		/* We should not reserve VUMA_VIDEO_RAM as it overlaps with MMIO */
+		case VUMA_VIDEO_RAM:
+		default:
+			pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes unhandled\n",
+				(u32)node_id, mem_type, &mem_start, &mem_size);
 			break;
 		}
 	}
+
+	/* Reserve vgabios if it comes from firmware */
+	if (loongson_sysconf.vgabios_addr)
+		memblock_reserve(virt_to_phys((void *)loongson_sysconf.vgabios_addr),
+				SZ_256K);
 }
 
 #ifndef CONFIG_NUMA
diff --git a/arch/mips/loongson64/reset.c b/arch/mips/loongson64/reset.c
index e420800043b089..e01c8d4a805a91 100644
--- a/arch/mips/loongson64/reset.c
+++ b/arch/mips/loongson64/reset.c
@@ -53,7 +53,7 @@ static void loongson_halt(void)
 	}
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 /* 0X80000000~0X80200000 is safe */
 #define MAX_ARGS	64
@@ -158,7 +158,7 @@ static int __init mips_reboot_setup(void)
 	_machine_halt = loongson_halt;
 	pm_power_off = loongson_poweroff;
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	kexec_argv = kmalloc(KEXEC_ARGV_SIZE, GFP_KERNEL);
 	if (WARN_ON(!kexec_argv))
 		return -ENOMEM;
diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c
index e015a26a40f7a5..498bdc1bb0ede8 100644
--- a/arch/mips/loongson64/smp.c
+++ b/arch/mips/loongson64/smp.c
@@ -864,7 +864,7 @@ const struct plat_smp_ops loongson3_smp_ops = {
 	.cpu_disable = loongson3_cpu_disable,
 	.cpu_die = loongson3_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu = kexec_nonboot_cpu_jump,
 #endif
 };
diff --git a/arch/mips/pci/fixup-lantiq.c b/arch/mips/pci/fixup-lantiq.c
index 105569c1b7127b..13009666204f94 100644
--- a/arch/mips/pci/fixup-lantiq.c
+++ b/arch/mips/pci/fixup-lantiq.c
@@ -4,8 +4,8 @@
  *  Copyright (C) 2012 John Crispin <john@phrozen.org>
  */
 
-#include <linux/of_irq.h>
 #include <linux/of_pci.h>
+#include <linux/pci.h>
 
 int (*ltq_pci_plat_arch_init)(struct pci_dev *dev) = NULL;
 int (*ltq_pci_plat_dev_init)(struct pci_dev *dev) = NULL;
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index fd69dfa0cdabbe..d14ccc948a29b9 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -115,9 +115,12 @@ config ARCH_HAS_ILOG2_U64
 	default n
 
 config GENERIC_BUG
-	bool
-	default y
+	def_bool y
 	depends on BUG
+	select GENERIC_BUG_RELATIVE_POINTERS if 64BIT
+
+config GENERIC_BUG_RELATIVE_POINTERS
+	bool
 
 config GENERIC_HWEIGHT
 	bool
@@ -140,11 +143,11 @@ config ARCH_MMAP_RND_COMPAT_BITS_MIN
 	default 8
 
 config ARCH_MMAP_RND_BITS_MAX
-	default 24 if 64BIT
-	default 17
+	default 18 if 64BIT
+	default 13
 
 config ARCH_MMAP_RND_COMPAT_BITS_MAX
-	default 17
+	default 13
 
 # unless you want to implement ACPI on PA-RISC ... ;-)
 config PM
diff --git a/arch/parisc/include/asm/alternative.h b/arch/parisc/include/asm/alternative.h
index 1ed45fd085d3b8..1eb488f25b8380 100644
--- a/arch/parisc/include/asm/alternative.h
+++ b/arch/parisc/include/asm/alternative.h
@@ -34,7 +34,8 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
 
 /* Alternative SMP implementation. */
 #define ALTERNATIVE(cond, replacement)		"!0:"	\
-	".section .altinstructions, \"aw\"	!"	\
+	".section .altinstructions, \"a\"	!"	\
+	".align 4				!"	\
 	".word (0b-4-.)				!"	\
 	".hword 1, " __stringify(cond) "	!"	\
 	".word " __stringify(replacement) "	!"	\
@@ -44,7 +45,8 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
 
 /* to replace one single instructions by a new instruction */
 #define ALTERNATIVE(from, to, cond, replacement)\
-	.section .altinstructions, "aw"	!	\
+	.section .altinstructions, "a"	!	\
+	.align 4			!	\
 	.word (from - .)		!	\
 	.hword (to - from)/4, cond	!	\
 	.word replacement		!	\
@@ -52,7 +54,8 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
 
 /* to replace multiple instructions by new code */
 #define ALTERNATIVE_CODE(from, num_instructions, cond, new_instr_ptr)\
-	.section .altinstructions, "aw"	!	\
+	.section .altinstructions, "a"	!	\
+	.align 4			!	\
 	.word (from - .)		!	\
 	.hword -num_instructions, cond	!	\
 	.word (new_instr_ptr - .)	!	\
diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h
index 75677b526b2bb7..74d17d7e759da9 100644
--- a/arch/parisc/include/asm/assembly.h
+++ b/arch/parisc/include/asm/assembly.h
@@ -574,6 +574,7 @@
 	 */
 #define ASM_EXCEPTIONTABLE_ENTRY(fault_addr, except_addr)	\
 	.section __ex_table,"aw"			!	\
+	.align 4					!	\
 	.word (fault_addr - .), (except_addr - .)	!	\
 	.previous
 
diff --git a/arch/parisc/include/asm/bug.h b/arch/parisc/include/asm/bug.h
index 4b6d60b941247e..833555f74ffa72 100644
--- a/arch/parisc/include/asm/bug.h
+++ b/arch/parisc/include/asm/bug.h
@@ -17,24 +17,27 @@
 #define	PARISC_BUG_BREAK_ASM	"break 0x1f, 0x1fff"
 #define	PARISC_BUG_BREAK_INSN	0x03ffe01f  /* PARISC_BUG_BREAK_ASM */
 
-#if defined(CONFIG_64BIT)
-#define ASM_WORD_INSN		".dword\t"
+#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
+# define __BUG_REL(val) ".word " __stringify(val) " - ."
 #else
-#define ASM_WORD_INSN		".word\t"
+# define __BUG_REL(val) ".word " __stringify(val)
 #endif
 
+
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 #define BUG()								\
 	do {								\
 		asm volatile("\n"					\
 			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
-			     "\t.pushsection __bug_table,\"aw\"\n"	\
-			     "2:\t" ASM_WORD_INSN "1b, %c0\n"		\
-			     "\t.short %c1, %c2\n"			\
-			     "\t.org 2b+%c3\n"				\
+			     "\t.pushsection __bug_table,\"a\"\n"	\
+			     "\t.align 4\n"				\
+			     "2:\t" __BUG_REL(1b) "\n"			\
+			     "\t" __BUG_REL(%c0)  "\n"			\
+			     "\t.short %1, %2\n"			\
+			     "\t.blockz %3-2*4-2*2\n"			\
 			     "\t.popsection"				\
 			     : : "i" (__FILE__), "i" (__LINE__),	\
-			     "i" (0), "i" (sizeof(struct bug_entry)) ); \
+			     "i" (0), "i" (sizeof(struct bug_entry)) );	\
 		unreachable();						\
 	} while(0)
 
@@ -51,10 +54,12 @@
 	do {								\
 		asm volatile("\n"					\
 			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
-			     "\t.pushsection __bug_table,\"aw\"\n"	\
-			     "2:\t" ASM_WORD_INSN "1b, %c0\n"		\
-			     "\t.short %c1, %c2\n"			\
-			     "\t.org 2b+%c3\n"				\
+			     "\t.pushsection __bug_table,\"a\"\n"	\
+			     "\t.align 4\n"				\
+			     "2:\t" __BUG_REL(1b) "\n"			\
+			     "\t" __BUG_REL(%c0)  "\n"			\
+			     "\t.short %1, %2\n"			\
+			     "\t.blockz %3-2*4-2*2\n"			\
 			     "\t.popsection"				\
 			     : : "i" (__FILE__), "i" (__LINE__),	\
 			     "i" (BUGFLAG_WARNING|(flags)),		\
@@ -65,10 +70,11 @@
 	do {								\
 		asm volatile("\n"					\
 			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
-			     "\t.pushsection __bug_table,\"aw\"\n"	\
-			     "2:\t" ASM_WORD_INSN "1b\n"		\
-			     "\t.short %c0\n"				\
-			     "\t.org 2b+%c1\n"				\
+			     "\t.pushsection __bug_table,\"a\"\n"	\
+			     "\t.align 4\n"				\
+			     "2:\t" __BUG_REL(1b) "\n"			\
+			     "\t.short %0\n"				\
+			     "\t.blockz %1-4-2\n"			\
 			     "\t.popsection"				\
 			     : : "i" (BUGFLAG_WARNING|(flags)),		\
 			     "i" (sizeof(struct bug_entry)) );		\
diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h
index 140eaa97bf215d..2d73d3c3cd37f8 100644
--- a/arch/parisc/include/asm/elf.h
+++ b/arch/parisc/include/asm/elf.h
@@ -349,15 +349,7 @@ struct pt_regs;	/* forward declaration... */
 
 #define ELF_HWCAP	0
 
-/* Masks for stack and mmap randomization */
-#define BRK_RND_MASK	(is_32bit_task() ? 0x07ffUL : 0x3ffffUL)
-#define MMAP_RND_MASK	(is_32bit_task() ? 0x1fffUL : 0x3ffffUL)
-#define STACK_RND_MASK	MMAP_RND_MASK
-
-struct mm_struct;
-extern unsigned long arch_randomize_brk(struct mm_struct *);
-#define arch_randomize_brk arch_randomize_brk
-
+#define STACK_RND_MASK	0x7ff	/* 8MB of VA */
 
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
 struct linux_binprm;
diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h
index af2a598bc0f819..94428798b6aa63 100644
--- a/arch/parisc/include/asm/jump_label.h
+++ b/arch/parisc/include/asm/jump_label.h
@@ -15,10 +15,12 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran
 	asm_volatile_goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".align %1\n\t"
 		 ".word 1b - ., %l[l_yes] - .\n\t"
 		 __stringify(ASM_ULONG_INSN) " %c0 - .\n\t"
 		 ".popsection\n\t"
-		 : :  "i" (&((char *)key)[branch]) :  : l_yes);
+		 : : "i" (&((char *)key)[branch]), "i" (sizeof(long))
+		 : : l_yes);
 
 	return false;
 l_yes:
@@ -30,10 +32,12 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, bool
 	asm_volatile_goto("1:\n\t"
 		 "b,n %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".align %1\n\t"
 		 ".word 1b - ., %l[l_yes] - .\n\t"
 		 __stringify(ASM_ULONG_INSN) " %c0 - .\n\t"
 		 ".popsection\n\t"
-		 : :  "i" (&((char *)key)[branch]) :  : l_yes);
+		 : : "i" (&((char *)key)[branch]), "i" (sizeof(long))
+		 : : l_yes);
 
 	return false;
 l_yes:
diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h
index ee9e071859b2f4..47ebc4c91eaff3 100644
--- a/arch/parisc/include/asm/ldcw.h
+++ b/arch/parisc/include/asm/ldcw.h
@@ -55,7 +55,7 @@
 })
 
 #ifdef CONFIG_SMP
-# define __lock_aligned __section(".data..lock_aligned")
+# define __lock_aligned __section(".data..lock_aligned") __aligned(16)
 #endif
 
 #endif /* __PARISC_LDCW_H */
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index c05d121cf5d0f2..982aca20f56f53 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -47,6 +47,8 @@
 
 #ifndef __ASSEMBLY__
 
+struct rlimit;
+unsigned long mmap_upper_limit(struct rlimit *rlim_stack);
 unsigned long calc_max_stack_size(unsigned long stack_max);
 
 /*
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 2bf660eabe421e..4165079898d9e7 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -41,6 +41,7 @@ struct exception_table_entry {
 
 #define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\
 	".section __ex_table,\"aw\"\n"			   \
+	".align 4\n"					   \
 	".word (" #fault_addr " - .), (" #except_addr " - .)\n\t" \
 	".previous\n"
 
diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h
index 87245c584784ec..8d94739d75c67c 100644
--- a/arch/parisc/include/uapi/asm/errno.h
+++ b/arch/parisc/include/uapi/asm/errno.h
@@ -75,7 +75,6 @@
 
 /* We now return you to your regularly scheduled HPUX. */
 
-#define ENOSYM		215	/* symbol does not exist in executable */
 #define	ENOTSOCK	216	/* Socket operation on non-socket */
 #define	EDESTADDRREQ	217	/* Destination address required */
 #define	EMSGSIZE	218	/* Message too long */
@@ -101,7 +100,6 @@
 #define	ETIMEDOUT	238	/* Connection timed out */
 #define	ECONNREFUSED	239	/* Connection refused */
 #define	EREFUSED	ECONNREFUSED	/* for HP's NFS apparently */
-#define	EREMOTERELEASE	240	/* Remote peer released connection */
 #define	EHOSTDOWN	241	/* Host is down */
 #define	EHOSTUNREACH	242	/* No route to host */
 
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index cab1ec23e0d7a8..ab23e61a6f016a 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -475,13 +475,13 @@
 	 * to a CPU TLB 4k PFN (4k => 12 bits to shift) */
 	#define PAGE_ADD_SHIFT		(PAGE_SHIFT-12)
 	#define PAGE_ADD_HUGE_SHIFT	(REAL_HPAGE_SHIFT-12)
+	#define PFN_START_BIT	(63-ASM_PFN_PTE_SHIFT+(63-58)-PAGE_ADD_SHIFT)
 
 	/* Drop prot bits and convert to page addr for iitlbt and idtlbt */
 	.macro		convert_for_tlb_insert20 pte,tmp
 #ifdef CONFIG_HUGETLB_PAGE
 	copy		\pte,\tmp
-	extrd,u		\tmp,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\
-				64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte
+	extrd,u		\tmp,PFN_START_BIT,PFN_START_BIT+1,\pte
 
 	depdi		_PAGE_SIZE_ENCODING_DEFAULT,63,\
 				(63-58)+PAGE_ADD_SHIFT,\pte
@@ -489,8 +489,7 @@
 	depdi		_HUGE_PAGE_SIZE_ENCODING_DEFAULT,63,\
 				(63-58)+PAGE_ADD_HUGE_SHIFT,\pte
 #else /* Huge pages disabled */
-	extrd,u		\pte,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\
-				64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte
+	extrd,u		\pte,PFN_START_BIT,PFN_START_BIT+1,\pte
 	depdi		_PAGE_SIZE_ENCODING_DEFAULT,63,\
 				(63-58)+PAGE_ADD_SHIFT,\pte
 #endif
diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index a171bf3c6b318d..96e0264ac96163 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -70,9 +70,8 @@ $bss_loop:
 	stw,ma          %arg2,4(%r1)
 	stw,ma          %arg3,4(%r1)
 
-#if !defined(CONFIG_64BIT) && defined(CONFIG_PA20)
-	/* This 32-bit kernel was compiled for PA2.0 CPUs. Check current CPU
-	 * and halt kernel if we detect a PA1.x CPU. */
+#if defined(CONFIG_PA20)
+	/* check for 64-bit capable CPU as required by current kernel */
 	ldi		32,%r10
 	mtctl		%r10,%cr11
 	.level 2.0
diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index 29e2750f86a410..e95a977ba5f376 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -383,7 +383,7 @@ show_cpuinfo (struct seq_file *m, void *v)
 	char cpu_name[60], *p;
 
 	/* strip PA path from CPU name to not confuse lscpu */
-	strlcpy(cpu_name, per_cpu(cpu_data, 0).dev->name, sizeof(cpu_name));
+	strscpy(cpu_name, per_cpu(cpu_data, 0).dev->name, sizeof(cpu_name));
 	p = strrchr(cpu_name, '[');
 	if (p)
 		*(--p) = 0;
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index ab896eff7a1de9..98af719d5f85b2 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -77,7 +77,7 @@ unsigned long calc_max_stack_size(unsigned long stack_max)
  * indicating that "current" should be used instead of a passed-in
  * value from the exec bprm as done with arch_pick_mmap_layout().
  */
-static unsigned long mmap_upper_limit(struct rlimit *rlim_stack)
+unsigned long mmap_upper_limit(struct rlimit *rlim_stack)
 {
 	unsigned long stack_base;
 
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 58694d1989c233..548051b0b4aff6 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -130,6 +130,7 @@ SECTIONS
 	RO_DATA(8)
 
 	/* unwind info */
+	. = ALIGN(4);
 	.PARISC.unwind : {
 		__start___unwind = .;
 		*(.PARISC.unwind)
diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 8d3eacb50d5601..9d44e6630908d2 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -301,7 +301,6 @@ CONFIG_WQ_WATCHDOG=y
 CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
 CONFIG_BUG_ON_DATA_CORRUPTION=y
-CONFIG_DEBUG_CREDENTIALS=y
 # CONFIG_FTRACE is not set
 CONFIG_XMON=y
 # CONFIG_RUNTIME_TESTING_MENU is not set
diff --git a/arch/powerpc/include/asm/fb.h b/arch/powerpc/include/asm/fb.h
index 3cecf14d51de86..c0c5d1df7ad1ec 100644
--- a/arch/powerpc/include/asm/fb.h
+++ b/arch/powerpc/include/asm/fb.h
@@ -8,12 +8,7 @@ static inline pgprot_t pgprot_framebuffer(pgprot_t prot,
 					  unsigned long vm_start, unsigned long vm_end,
 					  unsigned long offset)
 {
-	/*
-	 * PowerPC's implementation of phys_mem_access_prot() does
-	 * not use the file argument. Set it to NULL in preparation
-	 * of later updates to the interface.
-	 */
-	return phys_mem_access_prot(NULL, PHYS_PFN(offset), vm_end - vm_start, prot);
+	return __phys_mem_access_prot(PHYS_PFN(offset), vm_end - vm_start, prot);
 }
 #define pgprot_framebuffer pgprot_framebuffer
 
diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index c8e4b4fd4e3302..4525a9c68260d9 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -84,8 +84,6 @@ struct arch_optimized_insn {
 	kprobe_opcode_t *insn;
 };
 
-extern int kprobe_exceptions_notify(struct notifier_block *self,
-					unsigned long val, void *data);
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 extern int kprobe_handler(struct pt_regs *regs);
 extern int kprobe_post_handler(struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 4f6e7d7ee3883c..d31a5ec1550d4b 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -10,7 +10,7 @@
 #include <linux/export.h>
 
 struct pt_regs;
-struct pci_bus;	
+struct pci_bus;
 struct device_node;
 struct iommu_table;
 struct rtc_time;
@@ -78,8 +78,8 @@ struct machdep_calls {
 	unsigned char 	(*nvram_read_val)(int addr);
 	void		(*nvram_write_val)(int addr, unsigned char val);
 	ssize_t		(*nvram_write)(char *buf, size_t count, loff_t *index);
-	ssize_t		(*nvram_read)(char *buf, size_t count, loff_t *index);	
-	ssize_t		(*nvram_size)(void);		
+	ssize_t		(*nvram_read)(char *buf, size_t count, loff_t *index);
+	ssize_t		(*nvram_size)(void);
 	void		(*nvram_sync)(void);
 
 	/* Exception handlers */
@@ -102,12 +102,11 @@ struct machdep_calls {
 	 */
 	long	 	(*feature_call)(unsigned int feature, ...);
 
-	/* Get legacy PCI/IDE interrupt mapping */ 
+	/* Get legacy PCI/IDE interrupt mapping */
 	int		(*pci_get_legacy_ide_irq)(struct pci_dev *dev, int channel);
-	
+
 	/* Get access protection for /dev/mem */
-	pgprot_t	(*phys_mem_access_prot)(struct file *file,
-						unsigned long pfn,
+	pgprot_t	(*phys_mem_access_prot)(unsigned long pfn,
 						unsigned long size,
 						pgprot_t vma_prot);
 
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index f5078a7dd85a52..46a9c4491ed0cb 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -105,9 +105,7 @@ extern void of_scan_pci_bridge(struct pci_dev *dev);
 extern void of_scan_bus(struct device_node *node, struct pci_bus *bus);
 extern void of_rescan_bus(struct device_node *node, struct pci_bus *bus);
 
-struct file;
-extern pgprot_t	pci_phys_mem_access_prot(struct file *file,
-					 unsigned long pfn,
+extern pgprot_t	pci_phys_mem_access_prot(unsigned long pfn,
 					 unsigned long size,
 					 pgprot_t prot);
 
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 2bfb7dd3b49e6c..9224f23065fff9 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -120,9 +120,15 @@ static inline void mark_initmem_nx(void) { }
 int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 			  pte_t *ptep, pte_t entry, int dirty);
 
+pgprot_t __phys_mem_access_prot(unsigned long pfn, unsigned long size,
+				pgprot_t vma_prot);
+
 struct file;
-pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-			      unsigned long size, pgprot_t vma_prot);
+static inline pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+					    unsigned long size, pgprot_t vma_prot)
+{
+	return __phys_mem_access_prot(pfn, size, vma_prot);
+}
 #define __HAVE_PHYS_MEM_ACCESS_PROT
 
 void __update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep);
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 6a9acfb690c9f5..2f8f3f93cbb67e 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -23,6 +23,15 @@
 #include <asm/feature-fixups.h>
 
 #ifdef CONFIG_VSX
+#define __REST_1FPVSR(n,c,base)						\
+BEGIN_FTR_SECTION							\
+	b	2f;							\
+END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
+	REST_FPR(n,base);						\
+	b	3f;							\
+2:	REST_VSR(n,c,base);						\
+3:
+
 #define __REST_32FPVSRS(n,c,base)					\
 BEGIN_FTR_SECTION							\
 	b	2f;							\
@@ -41,9 +50,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
 2:	SAVE_32VSRS(n,c,base);						\
 3:
 #else
+#define __REST_1FPVSR(n,b,base)		REST_FPR(n, base)
 #define __REST_32FPVSRS(n,b,base)	REST_32FPRS(n, base)
 #define __SAVE_32FPVSRS(n,b,base)	SAVE_32FPRS(n, base)
 #endif
+#define REST_1FPVSR(n,c,base)   __REST_1FPVSR(n,__REG_##c,__REG_##base)
 #define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base)
 #define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base)
 
@@ -67,6 +78,7 @@ _GLOBAL(store_fp_state)
 	SAVE_32FPVSRS(0, R4, R3)
 	mffs	fr0
 	stfd	fr0,FPSTATE_FPSCR(r3)
+	REST_1FPVSR(0, R4, R3)
 	blr
 EXPORT_SYMBOL(store_fp_state)
 
@@ -138,4 +150,5 @@ _GLOBAL(save_fpu)
 2:	SAVE_32FPVSRS(0, R4, R6)
 	mffs	fr0
 	stfd	fr0,FPSTATE_FPSCR(r6)
+	REST_1FPVSR(0, R4, R6)
 	blr
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 040255ddb5697d..d95a48eff412ee 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -521,8 +521,7 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma)
  * PCI device, it tries to find the PCI device first and calls the
  * above routine
  */
-pgprot_t pci_phys_mem_access_prot(struct file *file,
-				  unsigned long pfn,
+pgprot_t pci_phys_mem_access_prot(unsigned long pfn,
 				  unsigned long size,
 				  pgprot_t prot)
 {
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 392404688cec35..9452a54d356c97 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1198,11 +1198,11 @@ void kvmppc_save_user_regs(void)
 
 	usermsr = current->thread.regs->msr;
 
+	/* Caller has enabled FP/VEC/VSX/TM in MSR */
 	if (usermsr & MSR_FP)
-		save_fpu(current);
-
+		__giveup_fpu(current);
 	if (usermsr & MSR_VEC)
-		save_altivec(current);
+		__giveup_altivec(current);
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (usermsr & MSR_TM) {
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index 9454b8395b6ac9..f38df72e64b877 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -752,6 +752,8 @@ static int ppc_rtas_tone_volume_show(struct seq_file *m, void *v)
 
 /**
  * ppc_rtas_rmo_buf_show() - Describe RTAS-addressable region for user space.
+ * @m: seq_file output target.
+ * @v: Unused.
  *
  * Base + size description of a range of RTAS-addressable memory set
  * aside for user space to use as work area(s) for certain RTAS
diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S
index 90701885762cf1..40677416d7b262 100644
--- a/arch/powerpc/kernel/trace/ftrace_entry.S
+++ b/arch/powerpc/kernel/trace/ftrace_entry.S
@@ -62,7 +62,7 @@
 	.endif
 
 	/* Save previous stack pointer (r1) */
-	addi	r8, r1, SWITCH_FRAME_SIZE
+	addi	r8, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
 	PPC_STL	r8, GPR1(r1)
 
 	.if \allregs == 1
@@ -182,7 +182,7 @@ ftrace_no_trace:
 	mflr	r3
 	mtctr	r3
 	REST_GPR(3, r1)
-	addi	r1, r1, SWITCH_FRAME_SIZE
+	addi	r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
 	mtlr	r0
 	bctr
 #endif
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 4094e4c4c77a77..80b3f6e476b66b 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -33,6 +33,7 @@ _GLOBAL(store_vr_state)
 	mfvscr	v0
 	li	r4, VRSTATE_VSCR
 	stvx	v0, r4, r3
+	lvx	v0, 0, r3
 	blr
 EXPORT_SYMBOL(store_vr_state)
 
@@ -109,6 +110,7 @@ _GLOBAL(save_altivec)
 	mfvscr	v0
 	li	r4,VRSTATE_VSCR
 	stvx	v0,r4,r7
+	lvx	v0,0,r7
 	blr
 
 #ifdef CONFIG_VSX
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 1717554b04b108..3a440004b97d2b 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -35,18 +35,18 @@ unsigned long long memory_limit;
 unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
 EXPORT_SYMBOL(empty_zero_page);
 
-pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-			      unsigned long size, pgprot_t vma_prot)
+pgprot_t __phys_mem_access_prot(unsigned long pfn, unsigned long size,
+				pgprot_t vma_prot)
 {
 	if (ppc_md.phys_mem_access_prot)
-		return ppc_md.phys_mem_access_prot(file, pfn, size, vma_prot);
+		return ppc_md.phys_mem_access_prot(pfn, size, vma_prot);
 
 	if (!page_is_ram(pfn))
 		vma_prot = pgprot_noncached(vma_prot);
 
 	return vma_prot;
 }
-EXPORT_SYMBOL(phys_mem_access_prot);
+EXPORT_SYMBOL(__phys_mem_access_prot);
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 static DEFINE_MUTEX(linear_mapping_mutex);
diff --git a/arch/powerpc/platforms/pseries/rtas-work-area.c b/arch/powerpc/platforms/pseries/rtas-work-area.c
index b37d52f40360e0..7fe34bee84d894 100644
--- a/arch/powerpc/platforms/pseries/rtas-work-area.c
+++ b/arch/powerpc/platforms/pseries/rtas-work-area.c
@@ -184,6 +184,7 @@ machine_arch_initcall(pseries, rtas_work_area_allocator_init);
 
 /**
  * rtas_work_area_reserve_arena() - Reserve memory suitable for RTAS work areas.
+ * @limit: Upper limit for memblock allocation.
  */
 void __init rtas_work_area_reserve_arena(const phys_addr_t limit)
 {
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index b1f25bac280b4e..71d52a670d951b 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -385,11 +385,15 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
 	 * same fault IRQ is not freed by the OS before.
 	 */
 	mutex_lock(&vas_pseries_mutex);
-	if (migration_in_progress)
+	if (migration_in_progress) {
 		rc = -EBUSY;
-	else
+	} else {
 		rc = allocate_setup_window(txwin, (u64 *)&domain[0],
 				   cop_feat_caps->win_type);
+		if (!rc)
+			caps->nr_open_wins_progress++;
+	}
+
 	mutex_unlock(&vas_pseries_mutex);
 	if (rc)
 		goto out;
@@ -404,8 +408,17 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
 		goto out_free;
 
 	txwin->win_type = cop_feat_caps->win_type;
-	mutex_lock(&vas_pseries_mutex);
+
 	/*
+	 * The migration SUSPEND thread sets migration_in_progress and
+	 * closes all open windows from the list. But the window is
+	 * added to the list after open and modify HCALLs. So possible
+	 * that migration_in_progress is set before modify HCALL which
+	 * may cause some windows are still open when the hypervisor
+	 * initiates the migration.
+	 * So checks the migration_in_progress flag again and close all
+	 * open windows.
+	 *
 	 * Possible to lose the acquired credit with DLPAR core
 	 * removal after the window is opened. So if there are any
 	 * closed windows (means with lost credits), do not give new
@@ -413,9 +426,11 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
 	 * after the existing windows are reopened when credits are
 	 * available.
 	 */
-	if (!caps->nr_close_wins) {
+	mutex_lock(&vas_pseries_mutex);
+	if (!caps->nr_close_wins && !migration_in_progress) {
 		list_add(&txwin->win_list, &caps->list);
 		caps->nr_open_windows++;
+		caps->nr_open_wins_progress--;
 		mutex_unlock(&vas_pseries_mutex);
 		vas_user_win_add_mm_context(&txwin->vas_win.task_ref);
 		return &txwin->vas_win;
@@ -433,6 +448,12 @@ out_free:
 	 */
 	free_irq_setup(txwin);
 	h_deallocate_vas_window(txwin->vas_win.winid);
+	/*
+	 * Hold mutex and reduce nr_open_wins_progress counter.
+	 */
+	mutex_lock(&vas_pseries_mutex);
+	caps->nr_open_wins_progress--;
+	mutex_unlock(&vas_pseries_mutex);
 out:
 	atomic_dec(&cop_feat_caps->nr_used_credits);
 	kfree(txwin);
@@ -937,14 +958,14 @@ int vas_migration_handler(int action)
 	struct vas_caps *vcaps;
 	int i, rc = 0;
 
+	pr_info("VAS migration event %d\n", action);
+
 	/*
 	 * NX-GZIP is not enabled. Nothing to do for migration.
 	 */
 	if (!copypaste_feat)
 		return rc;
 
-	mutex_lock(&vas_pseries_mutex);
-
 	if (action == VAS_SUSPEND)
 		migration_in_progress = true;
 	else
@@ -990,12 +1011,27 @@ int vas_migration_handler(int action)
 
 		switch (action) {
 		case VAS_SUSPEND:
+			mutex_lock(&vas_pseries_mutex);
 			rc = reconfig_close_windows(vcaps, vcaps->nr_open_windows,
 							true);
+			/*
+			 * Windows are included in the list after successful
+			 * open. So wait for closing these in-progress open
+			 * windows in vas_allocate_window() which will be
+			 * done if the migration_in_progress is set.
+			 */
+			while (vcaps->nr_open_wins_progress) {
+				mutex_unlock(&vas_pseries_mutex);
+				msleep(10);
+				mutex_lock(&vas_pseries_mutex);
+			}
+			mutex_unlock(&vas_pseries_mutex);
 			break;
 		case VAS_RESUME:
+			mutex_lock(&vas_pseries_mutex);
 			atomic_set(&caps->nr_total_credits, new_nr_creds);
 			rc = reconfig_open_windows(vcaps, new_nr_creds, true);
+			mutex_unlock(&vas_pseries_mutex);
 			break;
 		default:
 			/* should not happen */
@@ -1011,8 +1047,9 @@ int vas_migration_handler(int action)
 			goto out;
 	}
 
+	pr_info("VAS migration event (%d) successful\n", action);
+
 out:
-	mutex_unlock(&vas_pseries_mutex);
 	return rc;
 }
 
diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h
index 7115043ec48830..45567cd1317837 100644
--- a/arch/powerpc/platforms/pseries/vas.h
+++ b/arch/powerpc/platforms/pseries/vas.h
@@ -91,6 +91,8 @@ struct vas_cop_feat_caps {
 struct vas_caps {
 	struct vas_cop_feat_caps caps;
 	struct list_head list;	/* List of open windows */
+	int nr_open_wins_progress;	/* Number of open windows in */
+					/* progress. Used in migration */
 	int nr_close_wins;	/* closed windows in the hypervisor for DLPAR */
 	int nr_open_windows;	/* Number of successful open windows */
 	u8 feat;		/* Feature type */
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 18b03ad0e6b973..24c1799e2ec490 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -642,6 +642,15 @@ config THREAD_SIZE_ORDER
 	  Specify the Pages of thread stack size (from 4KB to 64KB), which also
 	  affects irq stack size, which is equal to thread stack size.
 
+config RISCV_MISALIGNED
+	bool "Support misaligned load/store traps for kernel and userspace"
+	select SYSCTL_ARCH_UNALIGN_ALLOW
+	default y
+	help
+	  Say Y here if you want the kernel to embed support for misaligned
+	  load/store for both kernel and userspace. When disable, misaligned
+	  accesses will generate SIGBUS in userspace and panic in kernel.
+
 endmenu # "Platform type"
 
 menu "Kernel features"
@@ -676,7 +685,7 @@ config RISCV_BOOT_SPINWAIT
 	  If unsure what to do here, say N.
 
 config ARCH_SUPPORTS_KEXEC
-	def_bool MMU
+	def_bool y
 
 config ARCH_SELECTS_KEXEC
 	def_bool y
@@ -684,7 +693,7 @@ config ARCH_SELECTS_KEXEC
 	select HOTPLUG_CPU if SMP
 
 config ARCH_SUPPORTS_KEXEC_FILE
-	def_bool 64BIT && MMU
+	def_bool 64BIT
 
 config ARCH_SELECTS_KEXEC_FILE
 	def_bool y
@@ -909,6 +918,9 @@ config PORTABLE
 	select MMU
 	select OF
 
+config ARCH_PROC_KCORE_TEXT
+	def_bool y
+
 menu "Power management options"
 
 source "kernel/power/Kconfig"
diff --git a/arch/riscv/Kconfig.debug b/arch/riscv/Kconfig.debug
index e69de29bb2d1d6..eafe17ebf7102c 100644
--- a/arch/riscv/Kconfig.debug
+++ b/arch/riscv/Kconfig.debug
@@ -0,0 +1 @@
+source "arch/riscv/kernel/tests/Kconfig.debug"
diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile
index 22b13947bd131e..8e7fc0edf21d3e 100644
--- a/arch/riscv/boot/Makefile
+++ b/arch/riscv/boot/Makefile
@@ -17,6 +17,7 @@
 KCOV_INSTRUMENT := n
 
 OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
+OBJCOPYFLAGS_loader.bin :=-O binary
 OBJCOPYFLAGS_xipImage :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
 
 targets := Image Image.* loader loader.o loader.lds loader.bin
diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts
index 90b26111476375..dce96f27cc89a4 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts
+++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts
@@ -8,9 +8,6 @@
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/leds/common.h>
 
-/* Clock frequency (in Hz) of the rtcclk */
-#define RTCCLK_FREQ		1000000
-
 / {
 	model = "Microchip PolarFire-SoC Icicle Kit";
 	compatible = "microchip,mpfs-icicle-reference-rtlv2210", "microchip,mpfs-icicle-kit",
@@ -29,10 +26,6 @@
 		stdout-path = "serial1:115200n8";
 	};
 
-	cpus {
-		timebase-frequency = <RTCCLK_FREQ>;
-	};
-
 	leds {
 		compatible = "gpio-leds";
 
diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts
index 184cb36a175e40..a8d623ee9fa4ce 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts
+++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts
@@ -10,9 +10,6 @@
 #include "mpfs.dtsi"
 #include "mpfs-m100pfs-fabric.dtsi"
 
-/* Clock frequency (in Hz) of the rtcclk */
-#define MTIMER_FREQ	1000000
-
 / {
 	model = "Aries Embedded M100PFEVPS";
 	compatible = "aries,m100pfsevp", "microchip,mpfs";
@@ -33,10 +30,6 @@
 		stdout-path = "serial1:115200n8";
 	};
 
-	cpus {
-		timebase-frequency = <MTIMER_FREQ>;
-	};
-
 	ddrc_cache_lo: memory@80000000 {
 		device_type = "memory";
 		reg = <0x0 0x80000000 0x0 0x40000000>;
diff --git a/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts b/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts
index c87cc2d8fe29fa..ea0808ab104255 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts
+++ b/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts
@@ -6,9 +6,6 @@
 #include "mpfs.dtsi"
 #include "mpfs-polarberry-fabric.dtsi"
 
-/* Clock frequency (in Hz) of the rtcclk */
-#define MTIMER_FREQ	1000000
-
 / {
 	model = "Sundance PolarBerry";
 	compatible = "sundance,polarberry", "microchip,mpfs";
@@ -22,10 +19,6 @@
 		stdout-path = "serial0:115200n8";
 	};
 
-	cpus {
-		timebase-frequency = <MTIMER_FREQ>;
-	};
-
 	ddrc_cache_lo: memory@80000000 {
 		device_type = "memory";
 		reg = <0x0 0x80000000 0x0 0x2e000000>;
diff --git a/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts
index 013cb666c72da8..f9a89057943834 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts
+++ b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts
@@ -6,9 +6,6 @@
 #include "mpfs.dtsi"
 #include "mpfs-sev-kit-fabric.dtsi"
 
-/* Clock frequency (in Hz) of the rtcclk */
-#define MTIMER_FREQ		1000000
-
 / {
 	#address-cells = <2>;
 	#size-cells = <2>;
@@ -28,10 +25,6 @@
 		stdout-path = "serial1:115200n8";
 	};
 
-	cpus {
-		timebase-frequency = <MTIMER_FREQ>;
-	};
-
 	reserved-memory {
 		#address-cells = <2>;
 		#size-cells = <2>;
diff --git a/arch/riscv/boot/dts/microchip/mpfs-tysom-m.dts b/arch/riscv/boot/dts/microchip/mpfs-tysom-m.dts
index e0797c7e1b3553..d1120f5f2c0153 100644
--- a/arch/riscv/boot/dts/microchip/mpfs-tysom-m.dts
+++ b/arch/riscv/boot/dts/microchip/mpfs-tysom-m.dts
@@ -11,9 +11,6 @@
 #include "mpfs.dtsi"
 #include "mpfs-tysom-m-fabric.dtsi"
 
-/* Clock frequency (in Hz) of the rtcclk */
-#define MTIMER_FREQ		1000000
-
 / {
 	model = "Aldec TySOM-M-MPFS250T-REV2";
 	compatible = "aldec,tysom-m-mpfs250t-rev2", "microchip,mpfs";
@@ -34,10 +31,6 @@
 		stdout-path = "serial1:115200n8";
 	};
 
-	cpus {
-		timebase-frequency = <MTIMER_FREQ>;
-	};
-
 	ddrc_cache_lo: memory@80000000 {
 		device_type = "memory";
 		reg = <0x0 0x80000000 0x0 0x30000000>;
diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi
index a6faf24f1dbaf6..266489d43912fc 100644
--- a/arch/riscv/boot/dts/microchip/mpfs.dtsi
+++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi
@@ -13,6 +13,7 @@
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
+		timebase-frequency = <1000000>;
 
 		cpu0: cpu@0 {
 			compatible = "sifive,e51", "sifive,rocket0", "riscv";
diff --git a/arch/riscv/boot/dts/sophgo/cv1800b.dtsi b/arch/riscv/boot/dts/sophgo/cv1800b.dtsi
index df40e87ee06329..aec6401a467b02 100644
--- a/arch/riscv/boot/dts/sophgo/cv1800b.dtsi
+++ b/arch/riscv/boot/dts/sophgo/cv1800b.dtsi
@@ -34,7 +34,6 @@
 			cpu0_intc: interrupt-controller {
 				compatible = "riscv,cpu-intc";
 				interrupt-controller;
-				#address-cells = <0>;
 				#interrupt-cells = <1>;
 			};
 		};
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 938fa07ddf7734..905881282a7cd1 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -215,6 +215,8 @@ CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_CADENCE=y
 CONFIG_MMC_SPI=y
+CONFIG_MMC_DW=y
+CONFIG_MMC_DW_STARFIVE=y
 CONFIG_MMC_SDHI=y
 CONFIG_MMC_SUNXI=y
 CONFIG_RTC_CLASS=y
diff --git a/arch/riscv/errata/andes/errata.c b/arch/riscv/errata/andes/errata.c
index 197db68cc8daf7..17a90486972468 100644
--- a/arch/riscv/errata/andes/errata.c
+++ b/arch/riscv/errata/andes/errata.c
@@ -38,29 +38,35 @@ static long ax45mp_iocp_sw_workaround(void)
 	return ret.error ? 0 : ret.value;
 }
 
-static bool errata_probe_iocp(unsigned int stage, unsigned long arch_id, unsigned long impid)
+static void errata_probe_iocp(unsigned int stage, unsigned long arch_id, unsigned long impid)
 {
+	static bool done;
+
 	if (!IS_ENABLED(CONFIG_ERRATA_ANDES_CMO))
-		return false;
+		return;
+
+	if (done)
+		return;
+
+	done = true;
 
 	if (arch_id != ANDESTECH_AX45MP_MARCHID || impid != ANDESTECH_AX45MP_MIMPID)
-		return false;
+		return;
 
 	if (!ax45mp_iocp_sw_workaround())
-		return false;
+		return;
 
 	/* Set this just to make core cbo code happy */
 	riscv_cbom_block_size = 1;
 	riscv_noncoherent_supported();
-
-	return true;
 }
 
 void __init_or_module andes_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
 					      unsigned long archid, unsigned long impid,
 					      unsigned int stage)
 {
-	errata_probe_iocp(stage, archid, impid);
+	if (stage == RISCV_ALTERNATIVES_BOOT)
+		errata_probe_iocp(stage, archid, impid);
 
 	/* we have nothing to patch here ATM so just return back */
 }
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 65f6eee4ab8d77..224b4dc02b50bc 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -15,13 +15,261 @@
 #include <asm/barrier.h>
 #include <asm/bitsperlong.h>
 
+#if !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE)
 #include <asm-generic/bitops/__ffs.h>
-#include <asm-generic/bitops/ffz.h>
-#include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/ffs.h>
+#include <asm-generic/bitops/fls.h>
+
+#else
+#include <asm/alternative-macros.h>
+#include <asm/hwcap.h>
+
+#if (BITS_PER_LONG == 64)
+#define CTZW	"ctzw "
+#define CLZW	"clzw "
+#elif (BITS_PER_LONG == 32)
+#define CTZW	"ctz "
+#define CLZW	"clz "
+#else
+#error "Unexpected BITS_PER_LONG"
+#endif
+
+static __always_inline unsigned long variable__ffs(unsigned long word)
+{
+	int num;
+
+	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm volatile (".option push\n"
+		      ".option arch,+zbb\n"
+		      "ctz %0, %1\n"
+		      ".option pop\n"
+		      : "=r" (word) : "r" (word) :);
+
+	return word;
+
+legacy:
+	num = 0;
+#if BITS_PER_LONG == 64
+	if ((word & 0xffffffff) == 0) {
+		num += 32;
+		word >>= 32;
+	}
+#endif
+	if ((word & 0xffff) == 0) {
+		num += 16;
+		word >>= 16;
+	}
+	if ((word & 0xff) == 0) {
+		num += 8;
+		word >>= 8;
+	}
+	if ((word & 0xf) == 0) {
+		num += 4;
+		word >>= 4;
+	}
+	if ((word & 0x3) == 0) {
+		num += 2;
+		word >>= 2;
+	}
+	if ((word & 0x1) == 0)
+		num += 1;
+	return num;
+}
+
+/**
+ * __ffs - find first set bit in a long word
+ * @word: The word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+#define __ffs(word)				\
+	(__builtin_constant_p(word) ?		\
+	 (unsigned long)__builtin_ctzl(word) :	\
+	 variable__ffs(word))
+
+static __always_inline unsigned long variable__fls(unsigned long word)
+{
+	int num;
+
+	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm volatile (".option push\n"
+		      ".option arch,+zbb\n"
+		      "clz %0, %1\n"
+		      ".option pop\n"
+		      : "=r" (word) : "r" (word) :);
+
+	return BITS_PER_LONG - 1 - word;
+
+legacy:
+	num = BITS_PER_LONG - 1;
+#if BITS_PER_LONG == 64
+	if (!(word & (~0ul << 32))) {
+		num -= 32;
+		word <<= 32;
+	}
+#endif
+	if (!(word & (~0ul << (BITS_PER_LONG - 16)))) {
+		num -= 16;
+		word <<= 16;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG - 8)))) {
+		num -= 8;
+		word <<= 8;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG - 4)))) {
+		num -= 4;
+		word <<= 4;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG - 2)))) {
+		num -= 2;
+		word <<= 2;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG - 1))))
+		num -= 1;
+	return num;
+}
+
+/**
+ * __fls - find last set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+#define __fls(word)							\
+	(__builtin_constant_p(word) ?					\
+	 (unsigned long)(BITS_PER_LONG - 1 - __builtin_clzl(word)) :	\
+	 variable__fls(word))
+
+static __always_inline int variable_ffs(int x)
+{
+	int r;
+
+	if (!x)
+		return 0;
+
+	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm volatile (".option push\n"
+		      ".option arch,+zbb\n"
+		      CTZW "%0, %1\n"
+		      ".option pop\n"
+		      : "=r" (r) : "r" (x) :);
+
+	return r + 1;
+
+legacy:
+	r = 1;
+	if (!(x & 0xffff)) {
+		x >>= 16;
+		r += 16;
+	}
+	if (!(x & 0xff)) {
+		x >>= 8;
+		r += 8;
+	}
+	if (!(x & 0xf)) {
+		x >>= 4;
+		r += 4;
+	}
+	if (!(x & 3)) {
+		x >>= 2;
+		r += 2;
+	}
+	if (!(x & 1)) {
+		x >>= 1;
+		r += 1;
+	}
+	return r;
+}
+
+/**
+ * ffs - find first set bit in a word
+ * @x: the word to search
+ *
+ * This is defined the same way as the libc and compiler builtin ffs routines.
+ *
+ * ffs(value) returns 0 if value is 0 or the position of the first set bit if
+ * value is nonzero. The first (least significant) bit is at position 1.
+ */
+#define ffs(x) (__builtin_constant_p(x) ? __builtin_ffs(x) : variable_ffs(x))
+
+static __always_inline int variable_fls(unsigned int x)
+{
+	int r;
+
+	if (!x)
+		return 0;
+
+	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm volatile (".option push\n"
+		      ".option arch,+zbb\n"
+		      CLZW "%0, %1\n"
+		      ".option pop\n"
+		      : "=r" (r) : "r" (x) :);
+
+	return 32 - r;
+
+legacy:
+	r = 32;
+	if (!(x & 0xffff0000u)) {
+		x <<= 16;
+		r -= 16;
+	}
+	if (!(x & 0xff000000u)) {
+		x <<= 8;
+		r -= 8;
+	}
+	if (!(x & 0xf0000000u)) {
+		x <<= 4;
+		r -= 4;
+	}
+	if (!(x & 0xc0000000u)) {
+		x <<= 2;
+		r -= 2;
+	}
+	if (!(x & 0x80000000u)) {
+		x <<= 1;
+		r -= 1;
+	}
+	return r;
+}
+
+/**
+ * fls - find last set bit in a word
+ * @x: the word to search
+ *
+ * This is defined in a similar way as ffs, but returns the position of the most
+ * significant set bit.
+ *
+ * fls(value) returns 0 if value is 0 or the position of the last set bit if
+ * value is nonzero. The last (most significant) bit is at position 32.
+ */
+#define fls(x)							\
+({								\
+	typeof(x) x_ = (x);					\
+	__builtin_constant_p(x_) ?				\
+	 (int)((x_ != 0) ? (32 - __builtin_clz(x_)) : 0)	\
+	 :							\
+	 variable_fls(x_);					\
+})
+
+#endif /* !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE) */
+
+#include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/ffs.h>
 
 #include <asm-generic/bitops/hweight.h>
 
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 13b7d35648a9c5..a418c3112cd60c 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -7,7 +7,10 @@
 #define _ASM_CPUFEATURE_H
 
 #include <linux/bitmap.h>
+#include <linux/jump_label.h>
 #include <asm/hwcap.h>
+#include <asm/alternative-macros.h>
+#include <asm/errno.h>
 
 /*
  * These are probed via a device_initcall(), via either the SBI or directly
@@ -30,7 +33,104 @@ DECLARE_PER_CPU(long, misaligned_access_speed);
 /* Per-cpu ISA extensions. */
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
-void check_unaligned_access(int cpu);
 void riscv_user_isa_enable(void);
 
+#ifdef CONFIG_RISCV_MISALIGNED
+bool unaligned_ctl_available(void);
+bool check_unaligned_access_emulated(int cpu);
+void unaligned_emulation_finish(void);
+#else
+static inline bool unaligned_ctl_available(void)
+{
+	return false;
+}
+
+static inline bool check_unaligned_access_emulated(int cpu)
+{
+	return false;
+}
+
+static inline void unaligned_emulation_finish(void) {}
+#endif
+
+unsigned long riscv_get_elf_hwcap(void);
+
+struct riscv_isa_ext_data {
+	const unsigned int id;
+	const char *name;
+	const char *property;
+};
+
+extern const struct riscv_isa_ext_data riscv_isa_ext[];
+extern const size_t riscv_isa_ext_count;
+extern bool riscv_isa_fallback;
+
+unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
+
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit);
+#define riscv_isa_extension_available(isa_bitmap, ext)	\
+	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
+
+static __always_inline bool
+riscv_has_extension_likely(const unsigned long ext)
+{
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX,
+			   "ext must be < RISCV_ISA_EXT_MAX");
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+		asm_volatile_goto(
+		ALTERNATIVE("j	%l[l_no]", "nop", 0, %[ext], 1)
+		:
+		: [ext] "i" (ext)
+		:
+		: l_no);
+	} else {
+		if (!__riscv_isa_extension_available(NULL, ext))
+			goto l_no;
+	}
+
+	return true;
+l_no:
+	return false;
+}
+
+static __always_inline bool
+riscv_has_extension_unlikely(const unsigned long ext)
+{
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX,
+			   "ext must be < RISCV_ISA_EXT_MAX");
+
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
+		asm_volatile_goto(
+		ALTERNATIVE("nop", "j	%l[l_yes]", 0, %[ext], 1)
+		:
+		: [ext] "i" (ext)
+		:
+		: l_yes);
+	} else {
+		if (__riscv_isa_extension_available(NULL, ext))
+			goto l_yes;
+	}
+
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_likely(ext))
+		return true;
+
+	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
+}
+
+static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_unlikely(ext))
+		return true;
+
+	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
+}
+
 #endif
diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
index b3b2dfbdf945ef..06c236bfab53b3 100644
--- a/arch/riscv/include/asm/elf.h
+++ b/arch/riscv/include/asm/elf.h
@@ -14,7 +14,7 @@
 #include <asm/auxvec.h>
 #include <asm/byteorder.h>
 #include <asm/cacheinfo.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 
 /*
  * These are used to set parameters in the core dumps.
diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h
index 6e4dee49d84b98..7ab5e34318c85f 100644
--- a/arch/riscv/include/asm/entry-common.h
+++ b/arch/riscv/include/asm/entry-common.h
@@ -8,4 +8,18 @@
 void handle_page_fault(struct pt_regs *regs);
 void handle_break(struct pt_regs *regs);
 
+#ifdef CONFIG_RISCV_MISALIGNED
+int handle_misaligned_load(struct pt_regs *regs);
+int handle_misaligned_store(struct pt_regs *regs);
+#else
+static inline int handle_misaligned_load(struct pt_regs *regs)
+{
+	return -1;
+}
+static inline int handle_misaligned_store(struct pt_regs *regs)
+{
+	return -1;
+}
+#endif
+
 #endif /* _ASM_RISCV_ENTRY_COMMON_H */
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index 0ac18a4135be7d..83ed25e4355343 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -117,9 +117,9 @@ asm volatile(ALTERNATIVE(						\
  * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
  *   0000000    11001     00000      000      00000  0001011
  */
-#define THEAD_inval_A0	".long 0x0265000b"
-#define THEAD_clean_A0	".long 0x0255000b"
-#define THEAD_flush_A0	".long 0x0275000b"
+#define THEAD_INVAL_A0	".long 0x0265000b"
+#define THEAD_CLEAN_A0	".long 0x0255000b"
+#define THEAD_FLUSH_A0	".long 0x0275000b"
 #define THEAD_SYNC_S	".long 0x0190000b"
 
 #define ALT_CMO_OP(_op, _start, _size, _cachesize)			\
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index fe6656af967af9..06d30526ef3b83 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -8,9 +8,6 @@
 #ifndef _ASM_RISCV_HWCAP_H
 #define _ASM_RISCV_HWCAP_H
 
-#include <asm/alternative-macros.h>
-#include <asm/errno.h>
-#include <linux/bits.h>
 #include <uapi/asm/hwcap.h>
 
 #define RISCV_ISA_EXT_a		('a' - 'a')
@@ -69,92 +66,4 @@
 #define RISCV_ISA_EXT_SxAIA		RISCV_ISA_EXT_SSAIA
 #endif
 
-#ifndef __ASSEMBLY__
-
-#include <linux/jump_label.h>
-#include <asm/cpufeature.h>
-
-unsigned long riscv_get_elf_hwcap(void);
-
-struct riscv_isa_ext_data {
-	const unsigned int id;
-	const char *name;
-	const char *property;
-};
-
-extern const struct riscv_isa_ext_data riscv_isa_ext[];
-extern const size_t riscv_isa_ext_count;
-extern bool riscv_isa_fallback;
-
-unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
-
-#define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext)
-
-bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit);
-#define riscv_isa_extension_available(isa_bitmap, ext)	\
-	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
-
-static __always_inline bool
-riscv_has_extension_likely(const unsigned long ext)
-{
-	compiletime_assert(ext < RISCV_ISA_EXT_MAX,
-			   "ext must be < RISCV_ISA_EXT_MAX");
-
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
-		ALTERNATIVE("j	%l[l_no]", "nop", 0, %[ext], 1)
-		:
-		: [ext] "i" (ext)
-		:
-		: l_no);
-	} else {
-		if (!__riscv_isa_extension_available(NULL, ext))
-			goto l_no;
-	}
-
-	return true;
-l_no:
-	return false;
-}
-
-static __always_inline bool
-riscv_has_extension_unlikely(const unsigned long ext)
-{
-	compiletime_assert(ext < RISCV_ISA_EXT_MAX,
-			   "ext must be < RISCV_ISA_EXT_MAX");
-
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
-		ALTERNATIVE("nop", "j	%l[l_yes]", 0, %[ext], 1)
-		:
-		: [ext] "i" (ext)
-		:
-		: l_yes);
-	} else {
-		if (__riscv_isa_extension_available(NULL, ext))
-			goto l_yes;
-	}
-
-	return false;
-l_yes:
-	return true;
-}
-
-static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext)
-{
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_likely(ext))
-		return true;
-
-	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
-}
-
-static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext)
-{
-	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_unlikely(ext))
-		return true;
-
-	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
-}
-#endif
-
 #endif /* _ASM_RISCV_HWCAP_H */
diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h
index 6960beb75f3294..e27179b26086b3 100644
--- a/arch/riscv/include/asm/insn-def.h
+++ b/arch/riscv/include/asm/insn-def.h
@@ -180,19 +180,19 @@
 	INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(51),		\
 	       __RD(0), RS1(gaddr), RS2(vmid))
 
-#define CBO_inval(base)						\
+#define CBO_INVAL(base)						\
 	INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0),		\
 	       RS1(base), SIMM12(0))
 
-#define CBO_clean(base)						\
+#define CBO_CLEAN(base)						\
 	INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0),		\
 	       RS1(base), SIMM12(1))
 
-#define CBO_flush(base)						\
+#define CBO_FLUSH(base)						\
 	INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0),		\
 	       RS1(base), SIMM12(2))
 
-#define CBO_zero(base)						\
+#define CBO_ZERO(base)						\
 	INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0),		\
 	       RS1(base), SIMM12(4))
 
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 7a5097202e1570..9a2c780a11e953 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -126,14 +126,18 @@ enum napot_cont_order {
 
 /*
  * [63:59] T-Head Memory Type definitions:
- *
- * 00000 - NC   Weakly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable
+ * bit[63] SO - Strong Order
+ * bit[62] C - Cacheable
+ * bit[61] B - Bufferable
+ * bit[60] SH - Shareable
+ * bit[59] Sec - Trustable
+ * 00110 - NC   Weakly-ordered, Non-cacheable, Bufferable, Shareable, Non-trustable
  * 01110 - PMA  Weakly-ordered, Cacheable, Bufferable, Shareable, Non-trustable
- * 10000 - IO   Strongly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable
+ * 10010 - IO   Strongly-ordered, Non-cacheable, Non-bufferable, Shareable, Non-trustable
  */
 #define _PAGE_PMA_THEAD		((1UL << 62) | (1UL << 61) | (1UL << 60))
-#define _PAGE_NOCACHE_THEAD	0UL
-#define _PAGE_IO_THEAD		(1UL << 63)
+#define _PAGE_NOCACHE_THEAD	((1UL < 61) | (1UL << 60))
+#define _PAGE_IO_THEAD		((1UL << 63) | (1UL << 60))
 #define _PAGE_MTMASK_THEAD	(_PAGE_PMA_THEAD | _PAGE_IO_THEAD | (1UL << 59))
 
 static inline u64 riscv_page_mtmask(void)
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
index f896708e833127..179bd4afece46a 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -16,9 +16,9 @@
 #define _PAGE_GLOBAL    (1 << 5)    /* Global */
 #define _PAGE_ACCESSED  (1 << 6)    /* Set by hardware on any access */
 #define _PAGE_DIRTY     (1 << 7)    /* Set by hardware on any write */
-#define _PAGE_SOFT      (1 << 8)    /* Reserved for software */
+#define _PAGE_SOFT      (3 << 8)    /* Reserved for software */
 
-#define _PAGE_SPECIAL   _PAGE_SOFT
+#define _PAGE_SPECIAL   (1 << 8)    /* RSW: 0x1 */
 #define _PAGE_TABLE     _PAGE_PRESENT
 
 /*
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index c8e8867c42f6a9..ab00235b018f89 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -291,6 +291,7 @@ static inline pte_t pud_pte(pud_t pud)
 }
 
 #ifdef CONFIG_RISCV_ISA_SVNAPOT
+#include <asm/cpufeature.h>
 
 static __always_inline bool has_svnapot(void)
 {
@@ -898,7 +899,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 #define PAGE_KERNEL		__pgprot(0)
 #define swapper_pg_dir		NULL
 #define TASK_SIZE		0xffffffffUL
-#define VMALLOC_START		0
+#define VMALLOC_START		_AC(0, UL)
 #define VMALLOC_END		TASK_SIZE
 
 #endif /* !CONFIG_MMU */
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 441da1839c9478..f19f861cda5490 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -8,6 +8,7 @@
 
 #include <linux/const.h>
 #include <linux/cache.h>
+#include <linux/prctl.h>
 
 #include <vdso/processor.h>
 
@@ -82,6 +83,7 @@ struct thread_struct {
 	unsigned long bad_cause;
 	unsigned long vstate_ctrl;
 	struct __riscv_v_ext_state vstate;
+	unsigned long align_ctl;
 };
 
 /* Whitelist the fstate from the task_struct for hardened usercopy */
@@ -94,6 +96,7 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset,
 
 #define INIT_THREAD {					\
 	.sp = sizeof(init_stack) + (long)&init_stack,	\
+	.align_ctl = PR_UNALIGN_NOPRINT,		\
 }
 
 #define task_pt_regs(tsk)						\
@@ -136,6 +139,12 @@ extern long riscv_v_vstate_ctrl_set_current(unsigned long arg);
 extern long riscv_v_vstate_ctrl_get_current(void);
 #endif /* CONFIG_RISCV_ISA_V */
 
+extern int get_unalign_ctl(struct task_struct *tsk, unsigned long addr);
+extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
+
+#define GET_UNALIGN_CTL(tsk, addr)	get_unalign_ctl((tsk), (addr))
+#define SET_UNALIGN_CTL(tsk, val)	set_unalign_ctl((tsk), (val))
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_RISCV_PROCESSOR_H */
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index 12dfda6bb9242f..0892f4421bc4a5 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -280,9 +280,6 @@ void sbi_set_timer(uint64_t stime_value);
 void sbi_shutdown(void);
 void sbi_send_ipi(unsigned int cpu);
 int sbi_remote_fence_i(const struct cpumask *cpu_mask);
-int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
-			   unsigned long start,
-			   unsigned long size);
 
 int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
 				unsigned long start,
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index a727be723c5610..f90d8e42f3c791 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -9,7 +9,7 @@
 #include <linux/jump_label.h>
 #include <linux/sched/task_stack.h>
 #include <asm/vector.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/csr.h>
diff --git a/arch/riscv/include/asm/syscall_wrapper.h b/arch/riscv/include/asm/syscall_wrapper.h
index 1d7942c8a6cbae..eeec04b7dae67b 100644
--- a/arch/riscv/include/asm/syscall_wrapper.h
+++ b/arch/riscv/include/asm/syscall_wrapper.h
@@ -46,9 +46,6 @@ asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *);
 		return sys_ni_syscall();						\
 	}
 
-#define COMPAT_SYS_NI(name) \
-	SYSCALL_ALIAS(__riscv_compat_sys_##name, sys_ni_posix_timers);
-
 #endif /* CONFIG_COMPAT */
 
 #define __SYSCALL_DEFINEx(x, name, ...)						\
@@ -82,6 +79,4 @@ asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *);
 		return sys_ni_syscall();					\
 	}
 
-#define SYS_NI(name) SYSCALL_ALIAS(__riscv_sys_##name, sys_ni_posix_timers);
-
 #endif /* __ASM_SYSCALL_WRAPPER_H */
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index 120bcf2ed8a878..1eb5682b2af606 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -15,7 +15,13 @@ static void tlb_flush(struct mmu_gather *tlb);
 
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
-	flush_tlb_mm(tlb->mm);
+#ifdef CONFIG_MMU
+	if (tlb->fullmm || tlb->need_flush_all)
+		flush_tlb_mm(tlb->mm);
+	else
+		flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end,
+				   tlb_get_unmap_size(tlb));
+#endif
 }
 
 #endif /* _ASM_RISCV_TLB_H */
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index a09196f8de688e..8f3418c5f1724b 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -11,6 +11,9 @@
 #include <asm/smp.h>
 #include <asm/errata_list.h>
 
+#define FLUSH_TLB_MAX_SIZE      ((unsigned long)-1)
+#define FLUSH_TLB_NO_ASID       ((unsigned long)-1)
+
 #ifdef CONFIG_MMU
 extern unsigned long asid_mask;
 
@@ -32,9 +35,12 @@ static inline void local_flush_tlb_page(unsigned long addr)
 #if defined(CONFIG_SMP) && defined(CONFIG_MMU)
 void flush_tlb_all(void);
 void flush_tlb_mm(struct mm_struct *mm);
+void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
+			unsigned long end, unsigned int page_size);
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end);
+void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
@@ -51,14 +57,15 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 	local_flush_tlb_all();
 }
 
-#define flush_tlb_mm(mm) flush_tlb_all()
-#endif /* !CONFIG_SMP || !CONFIG_MMU */
-
 /* Flush a range of kernel pages */
 static inline void flush_tlb_kernel_range(unsigned long start,
 	unsigned long end)
 {
-	flush_tlb_all();
+	local_flush_tlb_all();
 }
 
+#define flush_tlb_mm(mm) flush_tlb_all()
+#define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
+#endif /* !CONFIG_SMP || !CONFIG_MMU */
+
 #endif /* _ASM_RISCV_TLBFLUSH_H */
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index c5ee07b3df071d..87aaef656257cb 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -15,7 +15,7 @@
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 #include <asm/ptrace.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/csr.h>
 #include <asm/asm.h>
 
diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h
index d696d6610231dd..11a71b8533d575 100644
--- a/arch/riscv/include/uapi/asm/elf.h
+++ b/arch/riscv/include/uapi/asm/elf.h
@@ -49,6 +49,7 @@ typedef union __riscv_fp_state elf_fpregset_t;
 #define R_RISCV_TLS_DTPREL64	9
 #define R_RISCV_TLS_TPREL32	10
 #define R_RISCV_TLS_TPREL64	11
+#define R_RISCV_IRELATIVE	58
 
 /* Relocation types not used by the dynamic linker */
 #define R_RISCV_BRANCH		16
@@ -81,7 +82,6 @@ typedef union __riscv_fp_state elf_fpregset_t;
 #define R_RISCV_ALIGN		43
 #define R_RISCV_RVC_BRANCH	44
 #define R_RISCV_RVC_JUMP	45
-#define R_RISCV_LUI		46
 #define R_RISCV_GPREL_I		47
 #define R_RISCV_GPREL_S		48
 #define R_RISCV_TPREL_I		49
@@ -93,6 +93,9 @@ typedef union __riscv_fp_state elf_fpregset_t;
 #define R_RISCV_SET16		55
 #define R_RISCV_SET32		56
 #define R_RISCV_32_PCREL	57
+#define R_RISCV_PLT32		59
+#define R_RISCV_SET_ULEB128	60
+#define R_RISCV_SUB_ULEB128	61
 
 
 #endif /* _UAPI_ASM_RISCV_ELF_H */
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 95cf25d484052e..fee22a3d1b5346 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -57,9 +57,10 @@ obj-y	+= stacktrace.o
 obj-y	+= cacheinfo.o
 obj-y	+= patch.o
 obj-y	+= probes/
+obj-y	+= tests/
 obj-$(CONFIG_MMU) += vdso.o vdso/
 
-obj-$(CONFIG_RISCV_M_MODE)	+= traps_misaligned.o
+obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o
diff --git a/arch/riscv/kernel/copy-unaligned.S b/arch/riscv/kernel/copy-unaligned.S
index cfdecfbaad6271..2b3d9398c113fb 100644
--- a/arch/riscv/kernel/copy-unaligned.S
+++ b/arch/riscv/kernel/copy-unaligned.S
@@ -9,7 +9,7 @@
 /* void __riscv_copy_words_unaligned(void *, const void *, size_t) */
 /* Performs a memcpy without aligning buffers, using word loads and stores. */
 /* Note: The size is truncated to a multiple of 8 * SZREG */
-ENTRY(__riscv_copy_words_unaligned)
+SYM_FUNC_START(__riscv_copy_words_unaligned)
 	andi  a4, a2, ~((8*SZREG)-1)
 	beqz  a4, 2f
 	add   a3, a1, a4
@@ -36,12 +36,12 @@ ENTRY(__riscv_copy_words_unaligned)
 
 2:
 	ret
-END(__riscv_copy_words_unaligned)
+SYM_FUNC_END(__riscv_copy_words_unaligned)
 
 /* void __riscv_copy_bytes_unaligned(void *, const void *, size_t) */
 /* Performs a memcpy without aligning buffers, using only byte accesses. */
 /* Note: The size is truncated to a multiple of 8 */
-ENTRY(__riscv_copy_bytes_unaligned)
+SYM_FUNC_START(__riscv_copy_bytes_unaligned)
 	andi a4, a2, ~(8-1)
 	beqz a4, 2f
 	add  a3, a1, a4
@@ -68,4 +68,4 @@ ENTRY(__riscv_copy_bytes_unaligned)
 
 2:
 	ret
-END(__riscv_copy_bytes_unaligned)
+SYM_FUNC_END(__riscv_copy_bytes_unaligned)
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index c17dacb1141cb3..d11d6320fb0d2d 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -125,13 +125,14 @@ old_interface:
  */
 int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid)
 {
-	int rc;
-
 	for (; node; node = node->parent) {
 		if (of_device_is_compatible(node, "riscv")) {
-			rc = riscv_of_processor_hartid(node, hartid);
-			if (!rc)
-				return 0;
+			*hartid = (unsigned long)of_get_cpu_hwid(node, 0);
+			if (*hartid == ~0UL) {
+				pr_warn("Found CPU without hart ID\n");
+				return -ENODEV;
+			}
+			return 0;
 		}
 	}
 
@@ -202,9 +203,8 @@ arch_initcall(riscv_cpuinfo_init);
 
 #ifdef CONFIG_PROC_FS
 
-static void print_isa(struct seq_file *f)
+static void print_isa(struct seq_file *f, const unsigned long *isa_bitmap)
 {
-	seq_puts(f, "isa\t\t: ");
 
 	if (IS_ENABLED(CONFIG_32BIT))
 		seq_write(f, "rv32", 4);
@@ -212,7 +212,7 @@ static void print_isa(struct seq_file *f)
 		seq_write(f, "rv64", 4);
 
 	for (int i = 0; i < riscv_isa_ext_count; i++) {
-		if (!__riscv_isa_extension_available(NULL, riscv_isa_ext[i].id))
+		if (!__riscv_isa_extension_available(isa_bitmap, riscv_isa_ext[i].id))
 			continue;
 
 		/* Only multi-letter extensions are split by underscores */
@@ -276,7 +276,15 @@ static int c_show(struct seq_file *m, void *v)
 
 	seq_printf(m, "processor\t: %lu\n", cpu_id);
 	seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id));
-	print_isa(m);
+
+	/*
+	 * For historical raisins, the isa: line is limited to the lowest common
+	 * denominator of extensions supported across all harts. A true list of
+	 * extensions supported on this hart is printed later in the hart isa:
+	 * line.
+	 */
+	seq_puts(m, "isa\t\t: ");
+	print_isa(m, NULL);
 	print_mmu(m);
 
 	if (acpi_disabled) {
@@ -292,6 +300,13 @@ static int c_show(struct seq_file *m, void *v)
 	seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid);
 	seq_printf(m, "marchid\t\t: 0x%lx\n", ci->marchid);
 	seq_printf(m, "mimpid\t\t: 0x%lx\n", ci->mimpid);
+
+	/*
+	 * Print the ISA extensions specific to this hart, which may show
+	 * additional extensions not present across all harts.
+	 */
+	seq_puts(m, "hart isa\t: ");
+	print_isa(m, hart_isa[cpu_id].isa);
 	seq_puts(m, "\n");
 
 	return 0;
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 7aeba01dcfd408..b3785ffc15703c 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -8,6 +8,7 @@
 
 #include <linux/acpi.h>
 #include <linux/bitmap.h>
+#include <linux/cpuhotplug.h>
 #include <linux/ctype.h>
 #include <linux/log2.h>
 #include <linux/memory.h>
@@ -29,6 +30,7 @@
 
 #define MISALIGNED_ACCESS_JIFFIES_LG2 1
 #define MISALIGNED_BUFFER_SIZE 0x4000
+#define MISALIGNED_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE)
 #define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80)
 
 unsigned long elf_hwcap __read_mostly;
@@ -559,23 +561,21 @@ unsigned long riscv_get_elf_hwcap(void)
 	return hwcap;
 }
 
-void check_unaligned_access(int cpu)
+static int check_unaligned_access(void *param)
 {
+	int cpu = smp_processor_id();
 	u64 start_cycles, end_cycles;
 	u64 word_cycles;
 	u64 byte_cycles;
 	int ratio;
 	unsigned long start_jiffies, now;
-	struct page *page;
+	struct page *page = param;
 	void *dst;
 	void *src;
 	long speed = RISCV_HWPROBE_MISALIGNED_SLOW;
 
-	page = alloc_pages(GFP_NOWAIT, get_order(MISALIGNED_BUFFER_SIZE));
-	if (!page) {
-		pr_warn("Can't alloc pages to measure memcpy performance");
-		return;
-	}
+	if (check_unaligned_access_emulated(cpu))
+		return 0;
 
 	/* Make an unaligned destination buffer. */
 	dst = (void *)((unsigned long)page_address(page) | 0x1);
@@ -629,7 +629,7 @@ void check_unaligned_access(int cpu)
 		pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n",
 			cpu);
 
-		goto out;
+		return 0;
 	}
 
 	if (word_cycles < byte_cycles)
@@ -643,18 +643,84 @@ void check_unaligned_access(int cpu)
 		(speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
 
 	per_cpu(misaligned_access_speed, cpu) = speed;
+	return 0;
+}
 
-out:
-	__free_pages(page, get_order(MISALIGNED_BUFFER_SIZE));
+static void check_unaligned_access_nonboot_cpu(void *param)
+{
+	unsigned int cpu = smp_processor_id();
+	struct page **pages = param;
+
+	if (smp_processor_id() != 0)
+		check_unaligned_access(pages[cpu]);
+}
+
+static int riscv_online_cpu(unsigned int cpu)
+{
+	static struct page *buf;
+
+	/* We are already set since the last check */
+	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
+		return 0;
+
+	buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
+	if (!buf) {
+		pr_warn("Allocation failure, not measuring misaligned performance\n");
+		return -ENOMEM;
+	}
+
+	check_unaligned_access(buf);
+	__free_pages(buf, MISALIGNED_BUFFER_ORDER);
+	return 0;
 }
 
-static int check_unaligned_access_boot_cpu(void)
+/* Measure unaligned access on all CPUs present at boot in parallel. */
+static int check_unaligned_access_all_cpus(void)
 {
-	check_unaligned_access(0);
+	unsigned int cpu;
+	unsigned int cpu_count = num_possible_cpus();
+	struct page **bufs = kzalloc(cpu_count * sizeof(struct page *),
+				     GFP_KERNEL);
+
+	if (!bufs) {
+		pr_warn("Allocation failure, not measuring misaligned performance\n");
+		return 0;
+	}
+
+	/*
+	 * Allocate separate buffers for each CPU so there's no fighting over
+	 * cache lines.
+	 */
+	for_each_cpu(cpu, cpu_online_mask) {
+		bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
+		if (!bufs[cpu]) {
+			pr_warn("Allocation failure, not measuring misaligned performance\n");
+			goto out;
+		}
+	}
+
+	/* Check everybody except 0, who stays behind to tend jiffies. */
+	on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1);
+
+	/* Check core 0. */
+	smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
+
+	/* Setup hotplug callback for any new CPUs that come online. */
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
+				  riscv_online_cpu, NULL);
+
+out:
+	unaligned_emulation_finish();
+	for_each_cpu(cpu, cpu_online_mask) {
+		if (bufs[cpu])
+			__free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER);
+	}
+
+	kfree(bufs);
 	return 0;
 }
 
-arch_initcall(check_unaligned_access_boot_cpu);
+arch_initcall(check_unaligned_access_all_cpus);
 
 void riscv_user_isa_enable(void)
 {
diff --git a/arch/riscv/kernel/crash_core.c b/arch/riscv/kernel/crash_core.c
index 55f1d7856b5448..8706736fd4e2dc 100644
--- a/arch/riscv/kernel/crash_core.c
+++ b/arch/riscv/kernel/crash_core.c
@@ -5,18 +5,20 @@
 
 void arch_crash_save_vmcoreinfo(void)
 {
-	VMCOREINFO_NUMBER(VA_BITS);
 	VMCOREINFO_NUMBER(phys_ram_base);
 
 	vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET);
 	vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", VMALLOC_START);
 	vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END);
+#ifdef CONFIG_MMU
+	VMCOREINFO_NUMBER(VA_BITS);
 	vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START);
 	vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END);
 #ifdef CONFIG_64BIT
 	vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR);
 	vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END);
 #endif
+#endif
 	vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR);
 	vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n",
 						kernel_map.va_kernel_pa_offset);
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 9f92c067f7e1e8..54ca4564a92631 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -26,9 +26,9 @@ SYM_CODE_START(handle_exception)
 	 * register will contain 0, and we should continue on the current TP.
 	 */
 	csrrw tp, CSR_SCRATCH, tp
-	bnez tp, _save_context
+	bnez tp, .Lsave_context
 
-_restore_kernel_tpsp:
+.Lrestore_kernel_tpsp:
 	csrr tp, CSR_SCRATCH
 	REG_S sp, TASK_TI_KERNEL_SP(tp)
 
@@ -40,7 +40,7 @@ _restore_kernel_tpsp:
 	REG_L sp, TASK_TI_KERNEL_SP(tp)
 #endif
 
-_save_context:
+.Lsave_context:
 	REG_S sp, TASK_TI_USER_SP(tp)
 	REG_L sp, TASK_TI_KERNEL_SP(tp)
 	addi sp, sp, -(PT_SIZE_ON_STACK)
@@ -322,7 +322,7 @@ SYM_FUNC_END(__switch_to)
 	.section ".rodata"
 	.align LGREG
 	/* Exception vector table */
-SYM_CODE_START(excp_vect_table)
+SYM_DATA_START_LOCAL(excp_vect_table)
 	RISCV_PTR do_trap_insn_misaligned
 	ALT_INSN_FAULT(RISCV_PTR do_trap_insn_fault)
 	RISCV_PTR do_trap_insn_illegal
@@ -340,12 +340,11 @@ SYM_CODE_START(excp_vect_table)
 	RISCV_PTR do_page_fault   /* load page fault */
 	RISCV_PTR do_trap_unknown
 	RISCV_PTR do_page_fault   /* store page fault */
-excp_vect_table_end:
-SYM_CODE_END(excp_vect_table)
+SYM_DATA_END_LABEL(excp_vect_table, SYM_L_LOCAL, excp_vect_table_end)
 
 #ifndef CONFIG_MMU
-SYM_CODE_START(__user_rt_sigreturn)
+SYM_DATA_START(__user_rt_sigreturn)
 	li a7, __NR_rt_sigreturn
 	ecall
-SYM_CODE_END(__user_rt_sigreturn)
+SYM_DATA_END(__user_rt_sigreturn)
 #endif
diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S
index dd2205473de785..2c543f130f9389 100644
--- a/arch/riscv/kernel/fpu.S
+++ b/arch/riscv/kernel/fpu.S
@@ -19,7 +19,7 @@
 #include <asm/csr.h>
 #include <asm/asm-offsets.h>
 
-ENTRY(__fstate_save)
+SYM_FUNC_START(__fstate_save)
 	li  a2,  TASK_THREAD_F0
 	add a0, a0, a2
 	li t1, SR_FS
@@ -60,9 +60,9 @@ ENTRY(__fstate_save)
 	sw t0, TASK_THREAD_FCSR_F0(a0)
 	csrc CSR_STATUS, t1
 	ret
-ENDPROC(__fstate_save)
+SYM_FUNC_END(__fstate_save)
 
-ENTRY(__fstate_restore)
+SYM_FUNC_START(__fstate_restore)
 	li  a2,  TASK_THREAD_F0
 	add a0, a0, a2
 	li t1, SR_FS
@@ -103,4 +103,125 @@ ENTRY(__fstate_restore)
 	fscsr t0
 	csrc CSR_STATUS, t1
 	ret
-ENDPROC(__fstate_restore)
+SYM_FUNC_END(__fstate_restore)
+
+#define get_f32(which) fmv.x.s a0, which; j 2f
+#define put_f32(which) fmv.s.x which, a1; j 2f
+#if __riscv_xlen == 64
+# define get_f64(which) fmv.x.d a0, which; j 2f
+# define put_f64(which) fmv.d.x which, a1; j 2f
+#else
+# define get_f64(which) fsd which, 0(a1); j 2f
+# define put_f64(which) fld which, 0(a1); j 2f
+#endif
+
+.macro fp_access_prologue
+	/*
+	 * Compute jump offset to store the correct FP register since we don't
+	 * have indirect FP register access
+	 */
+	sll t0, a0, 3
+	la t2, 1f
+	add t0, t0, t2
+	li t1, SR_FS
+	csrs CSR_STATUS, t1
+	jr t0
+1:
+.endm
+
+.macro fp_access_epilogue
+2:
+	csrc CSR_STATUS, t1
+	ret
+.endm
+
+#define fp_access_body(__access_func) \
+	__access_func(f0); \
+	__access_func(f1); \
+	__access_func(f2); \
+	__access_func(f3); \
+	__access_func(f4); \
+	__access_func(f5); \
+	__access_func(f6); \
+	__access_func(f7); \
+	__access_func(f8); \
+	__access_func(f9); \
+	__access_func(f10); \
+	__access_func(f11); \
+	__access_func(f12); \
+	__access_func(f13); \
+	__access_func(f14); \
+	__access_func(f15); \
+	__access_func(f16); \
+	__access_func(f17); \
+	__access_func(f18); \
+	__access_func(f19); \
+	__access_func(f20); \
+	__access_func(f21); \
+	__access_func(f22); \
+	__access_func(f23); \
+	__access_func(f24); \
+	__access_func(f25); \
+	__access_func(f26); \
+	__access_func(f27); \
+	__access_func(f28); \
+	__access_func(f29); \
+	__access_func(f30); \
+	__access_func(f31)
+
+
+#ifdef CONFIG_RISCV_MISALIGNED
+
+/*
+ * Disable compressed instructions set to keep a constant offset between FP
+ * load/store/move instructions
+ */
+.option norvc
+/*
+ * put_f32_reg - Set a FP register from a register containing the value
+ * a0 = FP register index to be set
+ * a1 = value to be loaded in the FP register
+ */
+SYM_FUNC_START(put_f32_reg)
+	fp_access_prologue
+	fp_access_body(put_f32)
+	fp_access_epilogue
+SYM_FUNC_END(put_f32_reg)
+
+/*
+ * get_f32_reg - Get a FP register value and return it
+ * a0 = FP register index to be retrieved
+ */
+SYM_FUNC_START(get_f32_reg)
+	fp_access_prologue
+	fp_access_body(get_f32)
+	fp_access_epilogue
+SYM_FUNC_END(get_f32_reg)
+
+/*
+ * put_f64_reg - Set a 64 bits FP register from a value or a pointer.
+ * a0 = FP register index to be set
+ * a1 = value/pointer to be loaded in the FP register (when xlen == 32 bits, we
+ * load the value to a pointer).
+ */
+SYM_FUNC_START(put_f64_reg)
+	fp_access_prologue
+	fp_access_body(put_f64)
+	fp_access_epilogue
+SYM_FUNC_END(put_f64_reg)
+
+/*
+ * put_f64_reg - Get a 64 bits FP register value and returned it or store it to
+ *	 	 a pointer.
+ * a0 = FP register index to be retrieved
+ * a1 = If xlen == 32, pointer which should be loaded with the FP register value
+ *	or unused if xlen == 64. In which case the FP register value is returned
+ *	through a0
+ */
+SYM_FUNC_START(get_f64_reg)
+	fp_access_prologue
+	fp_access_body(get_f64)
+	fp_access_epilogue
+SYM_FUNC_END(get_f64_reg)
+
+#endif /* CONFIG_RISCV_MISALIGNED */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 18f97ec0f7ed5e..76ace1e0b46f62 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -19,7 +19,7 @@
 #include "efi-header.S"
 
 __HEAD
-ENTRY(_start)
+SYM_CODE_START(_start)
 	/*
 	 * Image header expected by Linux boot-loaders. The image header data
 	 * structure is described in asm/image.h.
@@ -154,7 +154,6 @@ secondary_start_sbi:
 	XIP_FIXUP_OFFSET a3
 	add a3, a3, a1
 	REG_L sp, (a3)
-	scs_load_current
 
 .Lsecondary_start_common:
 
@@ -164,12 +163,13 @@ secondary_start_sbi:
 	XIP_FIXUP_OFFSET a0
 	call relocate_enable_mmu
 #endif
-	call setup_trap_vector
+	call .Lsetup_trap_vector
+	scs_load_current
 	tail smp_callin
 #endif /* CONFIG_SMP */
 
 .align 2
-setup_trap_vector:
+.Lsetup_trap_vector:
 	/* Set trap vector to exception handler */
 	la a0, handle_exception
 	csrw CSR_TVEC, a0
@@ -187,9 +187,9 @@ setup_trap_vector:
 	wfi
 	j .Lsecondary_park
 
-END(_start)
+SYM_CODE_END(_start)
 
-ENTRY(_start_kernel)
+SYM_CODE_START(_start_kernel)
 	/* Mask all interrupts */
 	csrw CSR_IE, zero
 	csrw CSR_IP, zero
@@ -206,7 +206,7 @@ ENTRY(_start_kernel)
 	 * not implement PMPs, so we set up a quick trap handler to just skip
 	 * touching the PMPs on any trap.
 	 */
-	la a0, pmp_done
+	la a0, .Lpmp_done
 	csrw CSR_TVEC, a0
 
 	li a0, -1
@@ -214,7 +214,7 @@ ENTRY(_start_kernel)
 	li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X)
 	csrw CSR_PMPCFG0, a0
 .align 2
-pmp_done:
+.Lpmp_done:
 
 	/*
 	 * The hartid in a0 is expected later on, and we have no firmware
@@ -275,12 +275,12 @@ pmp_done:
 	/* Clear BSS for flat non-ELF images */
 	la a3, __bss_start
 	la a4, __bss_stop
-	ble a4, a3, clear_bss_done
-clear_bss:
+	ble a4, a3, .Lclear_bss_done
+.Lclear_bss:
 	REG_S zero, (a3)
 	add a3, a3, RISCV_SZPTR
-	blt a3, a4, clear_bss
-clear_bss_done:
+	blt a3, a4, .Lclear_bss
+.Lclear_bss_done:
 #endif
 	la a2, boot_cpu_hartid
 	XIP_FIXUP_OFFSET a2
@@ -305,7 +305,7 @@ clear_bss_done:
 	call relocate_enable_mmu
 #endif /* CONFIG_MMU */
 
-	call setup_trap_vector
+	call .Lsetup_trap_vector
 	/* Restore C environment */
 	la tp, init_task
 	la sp, init_thread_union + THREAD_SIZE
@@ -348,10 +348,10 @@ clear_bss_done:
 	tail .Lsecondary_start_common
 #endif /* CONFIG_RISCV_BOOT_SPINWAIT */
 
-END(_start_kernel)
+SYM_CODE_END(_start_kernel)
 
 #ifdef CONFIG_RISCV_M_MODE
-ENTRY(reset_regs)
+SYM_CODE_START_LOCAL(reset_regs)
 	li	sp, 0
 	li	gp, 0
 	li	tp, 0
@@ -449,5 +449,5 @@ ENTRY(reset_regs)
 .Lreset_regs_done_vector:
 #endif /* CONFIG_RISCV_ISA_V */
 	ret
-END(reset_regs)
+SYM_CODE_END(reset_regs)
 #endif /* CONFIG_RISCV_M_MODE */
diff --git a/arch/riscv/kernel/hibernate-asm.S b/arch/riscv/kernel/hibernate-asm.S
index d698dd7df637ba..d040dcf4add453 100644
--- a/arch/riscv/kernel/hibernate-asm.S
+++ b/arch/riscv/kernel/hibernate-asm.S
@@ -21,7 +21,7 @@
  *
  * Always returns 0
  */
-ENTRY(__hibernate_cpu_resume)
+SYM_FUNC_START(__hibernate_cpu_resume)
 	/* switch to hibernated image's page table. */
 	csrw CSR_SATP, s0
 	sfence.vma
@@ -34,7 +34,7 @@ ENTRY(__hibernate_cpu_resume)
 	mv	a0, zero
 
 	ret
-END(__hibernate_cpu_resume)
+SYM_FUNC_END(__hibernate_cpu_resume)
 
 /*
  * Prepare to restore the image.
@@ -42,7 +42,7 @@ END(__hibernate_cpu_resume)
  * a1: satp of temporary page tables.
  * a2: cpu_resume.
  */
-ENTRY(hibernate_restore_image)
+SYM_FUNC_START(hibernate_restore_image)
 	mv	s0, a0
 	mv	s1, a1
 	mv	s2, a2
@@ -50,7 +50,7 @@ ENTRY(hibernate_restore_image)
 	REG_L	a1, relocated_restore_code
 
 	jr	a1
-END(hibernate_restore_image)
+SYM_FUNC_END(hibernate_restore_image)
 
 /*
  * The below code will be executed from a 'safe' page.
@@ -58,7 +58,7 @@ END(hibernate_restore_image)
  * back to the original memory location. Finally, it jumps to __hibernate_cpu_resume()
  * to restore the CPU context.
  */
-ENTRY(hibernate_core_restore_code)
+SYM_FUNC_START(hibernate_core_restore_code)
 	/* switch to temp page table. */
 	csrw satp, s1
 	sfence.vma
@@ -73,4 +73,4 @@ ENTRY(hibernate_core_restore_code)
 	bnez	s4, .Lcopy
 
 	jr	s2
-END(hibernate_core_restore_code)
+SYM_FUNC_END(hibernate_core_restore_code)
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index 669b8697aa38a5..58dd96a2a15340 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -82,7 +82,7 @@
 	.endm
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
-ENTRY(ftrace_caller)
+SYM_FUNC_START(ftrace_caller)
 	SAVE_ABI
 
 	addi	a0, t0, -FENTRY_RA_OFFSET
@@ -91,8 +91,7 @@ ENTRY(ftrace_caller)
 	mv	a1, ra
 	mv	a3, sp
 
-ftrace_call:
-	.global ftrace_call
+SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -102,16 +101,15 @@ ftrace_call:
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	mv	a2, s0
 #endif
-ftrace_graph_call:
-	.global ftrace_graph_call
+SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 #endif
 	RESTORE_ABI
 	jr t0
-ENDPROC(ftrace_caller)
+SYM_FUNC_END(ftrace_caller)
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-ENTRY(ftrace_regs_caller)
+SYM_FUNC_START(ftrace_regs_caller)
 	SAVE_ALL
 
 	addi	a0, t0, -FENTRY_RA_OFFSET
@@ -120,8 +118,7 @@ ENTRY(ftrace_regs_caller)
 	mv	a1, ra
 	mv	a3, sp
 
-ftrace_regs_call:
-	.global ftrace_regs_call
+SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -131,12 +128,11 @@ ftrace_regs_call:
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	mv	a2, s0
 #endif
-ftrace_graph_regs_call:
-	.global ftrace_graph_regs_call
+SYM_INNER_LABEL(ftrace_graph_regs_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 #endif
 
 	RESTORE_ALL
 	jr t0
-ENDPROC(ftrace_regs_caller)
+SYM_FUNC_END(ftrace_regs_caller)
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index 8818a8fa9ff3af..b4dd9ed6849e30 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -61,7 +61,7 @@ SYM_TYPED_FUNC_START(ftrace_stub_graph)
 	ret
 SYM_FUNC_END(ftrace_stub_graph)
 
-ENTRY(return_to_handler)
+SYM_FUNC_START(return_to_handler)
 /*
  * On implementing the frame point test, the ideal way is to compare the
  * s0 (frame pointer, if enabled) on entry and the sp (stack pointer) on return.
@@ -76,25 +76,25 @@ ENTRY(return_to_handler)
 	mv	a2, a0
 	RESTORE_RET_ABI_STATE
 	jalr	a2
-ENDPROC(return_to_handler)
+SYM_FUNC_END(return_to_handler)
 #endif
 
 #ifndef CONFIG_DYNAMIC_FTRACE
-ENTRY(MCOUNT_NAME)
+SYM_FUNC_START(MCOUNT_NAME)
 	la	t4, ftrace_stub
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	la	t0, ftrace_graph_return
 	REG_L	t1, 0(t0)
-	bne	t1, t4, do_ftrace_graph_caller
+	bne	t1, t4, .Ldo_ftrace_graph_caller
 
 	la	t3, ftrace_graph_entry
 	REG_L	t2, 0(t3)
 	la	t6, ftrace_graph_entry_stub
-	bne	t2, t6, do_ftrace_graph_caller
+	bne	t2, t6, .Ldo_ftrace_graph_caller
 #endif
 	la	t3, ftrace_trace_function
 	REG_L	t5, 0(t3)
-	bne	t5, t4, do_trace
+	bne	t5, t4, .Ldo_trace
 	ret
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -102,7 +102,7 @@ ENTRY(MCOUNT_NAME)
  * A pseudo representation for the function graph tracer:
  * prepare_to_return(&ra_to_caller_of_caller, ra_to_caller)
  */
-do_ftrace_graph_caller:
+.Ldo_ftrace_graph_caller:
 	addi	a0, s0, -SZREG
 	mv	a1, ra
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
@@ -118,7 +118,7 @@ do_ftrace_graph_caller:
  * A pseudo representation for the function tracer:
  * (*ftrace_trace_function)(ra_to_caller, ra_to_caller_of_caller)
  */
-do_trace:
+.Ldo_trace:
 	REG_L	a1, -SZREG(s0)
 	mv	a0, ra
 
@@ -126,6 +126,6 @@ do_trace:
 	jalr	t5
 	RESTORE_ABI_STATE
 	ret
-ENDPROC(MCOUNT_NAME)
+SYM_FUNC_END(MCOUNT_NAME)
 #endif
 EXPORT_SYMBOL(MCOUNT_NAME)
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 7c651d55fcbd2f..aac019ed63b1bd 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -7,6 +7,9 @@
 #include <linux/elf.h>
 #include <linux/err.h>
 #include <linux/errno.h>
+#include <linux/hashtable.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
 #include <linux/moduleloader.h>
 #include <linux/vmalloc.h>
 #include <linux/sizes.h>
@@ -14,6 +17,29 @@
 #include <asm/alternative.h>
 #include <asm/sections.h>
 
+struct used_bucket {
+	struct list_head head;
+	struct hlist_head *bucket;
+};
+
+struct relocation_head {
+	struct hlist_node node;
+	struct list_head *rel_entry;
+	void *location;
+};
+
+struct relocation_entry {
+	struct list_head head;
+	Elf_Addr value;
+	unsigned int type;
+};
+
+struct relocation_handlers {
+	int (*reloc_handler)(struct module *me, void *location, Elf_Addr v);
+	int (*accumulate_handler)(struct module *me, void *location,
+				  long buffer);
+};
+
 /*
  * The auipc+jalr instruction pair can reach any PC-relative offset
  * in the range [-2^31 - 2^11, 2^31 - 2^11)
@@ -27,68 +53,90 @@ static bool riscv_insn_valid_32bit_offset(ptrdiff_t val)
 #endif
 }
 
-static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v)
+static int riscv_insn_rmw(void *location, u32 keep, u32 set)
+{
+	__le16 *parcel = location;
+	u32 insn = (u32)le16_to_cpu(parcel[0]) | (u32)le16_to_cpu(parcel[1]) << 16;
+
+	insn &= keep;
+	insn |= set;
+
+	parcel[0] = cpu_to_le16(insn);
+	parcel[1] = cpu_to_le16(insn >> 16);
+	return 0;
+}
+
+static int riscv_insn_rvc_rmw(void *location, u16 keep, u16 set)
+{
+	__le16 *parcel = location;
+	u16 insn = le16_to_cpu(*parcel);
+
+	insn &= keep;
+	insn |= set;
+
+	*parcel = cpu_to_le16(insn);
+	return 0;
+}
+
+static int apply_r_riscv_32_rela(struct module *me, void *location, Elf_Addr v)
 {
 	if (v != (u32)v) {
 		pr_err("%s: value %016llx out of range for 32-bit field\n",
 		       me->name, (long long)v);
 		return -EINVAL;
 	}
-	*location = v;
+	*(u32 *)location = v;
 	return 0;
 }
 
-static int apply_r_riscv_64_rela(struct module *me, u32 *location, Elf_Addr v)
+static int apply_r_riscv_64_rela(struct module *me, void *location, Elf_Addr v)
 {
 	*(u64 *)location = v;
 	return 0;
 }
 
-static int apply_r_riscv_branch_rela(struct module *me, u32 *location,
+static int apply_r_riscv_branch_rela(struct module *me, void *location,
 				     Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - location;
 	u32 imm12 = (offset & 0x1000) << (31 - 12);
 	u32 imm11 = (offset & 0x800) >> (11 - 7);
 	u32 imm10_5 = (offset & 0x7e0) << (30 - 10);
 	u32 imm4_1 = (offset & 0x1e) << (11 - 4);
 
-	*location = (*location & 0x1fff07f) | imm12 | imm11 | imm10_5 | imm4_1;
-	return 0;
+	return riscv_insn_rmw(location, 0x1fff07f, imm12 | imm11 | imm10_5 | imm4_1);
 }
 
-static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
+static int apply_r_riscv_jal_rela(struct module *me, void *location,
 				  Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - location;
 	u32 imm20 = (offset & 0x100000) << (31 - 20);
 	u32 imm19_12 = (offset & 0xff000);
 	u32 imm11 = (offset & 0x800) << (20 - 11);
 	u32 imm10_1 = (offset & 0x7fe) << (30 - 10);
 
-	*location = (*location & 0xfff) | imm20 | imm19_12 | imm11 | imm10_1;
-	return 0;
+	return riscv_insn_rmw(location, 0xfff, imm20 | imm19_12 | imm11 | imm10_1);
 }
 
-static int apply_r_riscv_rvc_branch_rela(struct module *me, u32 *location,
+static int apply_r_riscv_rvc_branch_rela(struct module *me, void *location,
 					 Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - location;
 	u16 imm8 = (offset & 0x100) << (12 - 8);
 	u16 imm7_6 = (offset & 0xc0) >> (6 - 5);
 	u16 imm5 = (offset & 0x20) >> (5 - 2);
 	u16 imm4_3 = (offset & 0x18) << (12 - 5);
 	u16 imm2_1 = (offset & 0x6) << (12 - 10);
 
-	*(u16 *)location = (*(u16 *)location & 0xe383) |
-		    imm8 | imm7_6 | imm5 | imm4_3 | imm2_1;
-	return 0;
+	return riscv_insn_rvc_rmw(location, 0xe383,
+			imm8 | imm7_6 | imm5 | imm4_3 | imm2_1);
 }
 
-static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location,
+static int apply_r_riscv_rvc_jump_rela(struct module *me, void *location,
 				       Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - location;
 	u16 imm11 = (offset & 0x800) << (12 - 11);
 	u16 imm10 = (offset & 0x400) >> (10 - 8);
 	u16 imm9_8 = (offset & 0x300) << (12 - 11);
@@ -98,16 +146,14 @@ static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location,
 	u16 imm4 = (offset & 0x10) << (12 - 5);
 	u16 imm3_1 = (offset & 0xe) << (12 - 10);
 
-	*(u16 *)location = (*(u16 *)location & 0xe003) |
-		    imm11 | imm10 | imm9_8 | imm7 | imm6 | imm5 | imm4 | imm3_1;
-	return 0;
+	return riscv_insn_rvc_rmw(location, 0xe003,
+			imm11 | imm10 | imm9_8 | imm7 | imm6 | imm5 | imm4 | imm3_1);
 }
 
-static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
+static int apply_r_riscv_pcrel_hi20_rela(struct module *me, void *location,
 					 Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
-	s32 hi20;
+	ptrdiff_t offset = (void *)v - location;
 
 	if (!riscv_insn_valid_32bit_offset(offset)) {
 		pr_err(
@@ -116,23 +162,20 @@ static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
 		return -EINVAL;
 	}
 
-	hi20 = (offset + 0x800) & 0xfffff000;
-	*location = (*location & 0xfff) | hi20;
-	return 0;
+	return riscv_insn_rmw(location, 0xfff, (offset + 0x800) & 0xfffff000);
 }
 
-static int apply_r_riscv_pcrel_lo12_i_rela(struct module *me, u32 *location,
+static int apply_r_riscv_pcrel_lo12_i_rela(struct module *me, void *location,
 					   Elf_Addr v)
 {
 	/*
 	 * v is the lo12 value to fill. It is calculated before calling this
 	 * handler.
 	 */
-	*location = (*location & 0xfffff) | ((v & 0xfff) << 20);
-	return 0;
+	return riscv_insn_rmw(location, 0xfffff, (v & 0xfff) << 20);
 }
 
-static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, u32 *location,
+static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, void *location,
 					   Elf_Addr v)
 {
 	/*
@@ -142,15 +185,12 @@ static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, u32 *location,
 	u32 imm11_5 = (v & 0xfe0) << (31 - 11);
 	u32 imm4_0 = (v & 0x1f) << (11 - 4);
 
-	*location = (*location & 0x1fff07f) | imm11_5 | imm4_0;
-	return 0;
+	return riscv_insn_rmw(location, 0x1fff07f, imm11_5 | imm4_0);
 }
 
-static int apply_r_riscv_hi20_rela(struct module *me, u32 *location,
+static int apply_r_riscv_hi20_rela(struct module *me, void *location,
 				   Elf_Addr v)
 {
-	s32 hi20;
-
 	if (IS_ENABLED(CONFIG_CMODEL_MEDLOW)) {
 		pr_err(
 		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
@@ -158,22 +198,20 @@ static int apply_r_riscv_hi20_rela(struct module *me, u32 *location,
 		return -EINVAL;
 	}
 
-	hi20 = ((s32)v + 0x800) & 0xfffff000;
-	*location = (*location & 0xfff) | hi20;
-	return 0;
+	return riscv_insn_rmw(location, 0xfff, ((s32)v + 0x800) & 0xfffff000);
 }
 
-static int apply_r_riscv_lo12_i_rela(struct module *me, u32 *location,
+static int apply_r_riscv_lo12_i_rela(struct module *me, void *location,
 				     Elf_Addr v)
 {
 	/* Skip medlow checking because of filtering by HI20 already */
 	s32 hi20 = ((s32)v + 0x800) & 0xfffff000;
 	s32 lo12 = ((s32)v - hi20);
-	*location = (*location & 0xfffff) | ((lo12 & 0xfff) << 20);
-	return 0;
+
+	return riscv_insn_rmw(location, 0xfffff, (lo12 & 0xfff) << 20);
 }
 
-static int apply_r_riscv_lo12_s_rela(struct module *me, u32 *location,
+static int apply_r_riscv_lo12_s_rela(struct module *me, void *location,
 				     Elf_Addr v)
 {
 	/* Skip medlow checking because of filtering by HI20 already */
@@ -181,20 +219,18 @@ static int apply_r_riscv_lo12_s_rela(struct module *me, u32 *location,
 	s32 lo12 = ((s32)v - hi20);
 	u32 imm11_5 = (lo12 & 0xfe0) << (31 - 11);
 	u32 imm4_0 = (lo12 & 0x1f) << (11 - 4);
-	*location = (*location & 0x1fff07f) | imm11_5 | imm4_0;
-	return 0;
+
+	return riscv_insn_rmw(location, 0x1fff07f, imm11_5 | imm4_0);
 }
 
-static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location,
+static int apply_r_riscv_got_hi20_rela(struct module *me, void *location,
 				       Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
-	s32 hi20;
+	ptrdiff_t offset = (void *)v - location;
 
 	/* Always emit the got entry */
 	if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) {
-		offset = module_emit_got_entry(me, v);
-		offset = (void *)offset - (void *)location;
+		offset = (void *)module_emit_got_entry(me, v) - location;
 	} else {
 		pr_err(
 		  "%s: can not generate the GOT entry for symbol = %016llx from PC = %p\n",
@@ -202,22 +238,19 @@ static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location,
 		return -EINVAL;
 	}
 
-	hi20 = (offset + 0x800) & 0xfffff000;
-	*location = (*location & 0xfff) | hi20;
-	return 0;
+	return riscv_insn_rmw(location, 0xfff, (offset + 0x800) & 0xfffff000);
 }
 
-static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
+static int apply_r_riscv_call_plt_rela(struct module *me, void *location,
 				       Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - location;
 	u32 hi20, lo12;
 
 	if (!riscv_insn_valid_32bit_offset(offset)) {
 		/* Only emit the plt entry if offset over 32-bit range */
 		if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) {
-			offset = module_emit_plt_entry(me, v);
-			offset = (void *)offset - (void *)location;
+			offset = (void *)module_emit_plt_entry(me, v) - location;
 		} else {
 			pr_err(
 			  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
@@ -228,15 +261,14 @@ static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
 
 	hi20 = (offset + 0x800) & 0xfffff000;
 	lo12 = (offset - hi20) & 0xfff;
-	*location = (*location & 0xfff) | hi20;
-	*(location + 1) = (*(location + 1) & 0xfffff) | (lo12 << 20);
-	return 0;
+	riscv_insn_rmw(location, 0xfff, hi20);
+	return riscv_insn_rmw(location + 4, 0xfffff, lo12 << 20);
 }
 
-static int apply_r_riscv_call_rela(struct module *me, u32 *location,
+static int apply_r_riscv_call_rela(struct module *me, void *location,
 				   Elf_Addr v)
 {
-	ptrdiff_t offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - location;
 	u32 hi20, lo12;
 
 	if (!riscv_insn_valid_32bit_offset(offset)) {
@@ -248,18 +280,17 @@ static int apply_r_riscv_call_rela(struct module *me, u32 *location,
 
 	hi20 = (offset + 0x800) & 0xfffff000;
 	lo12 = (offset - hi20) & 0xfff;
-	*location = (*location & 0xfff) | hi20;
-	*(location + 1) = (*(location + 1) & 0xfffff) | (lo12 << 20);
-	return 0;
+	riscv_insn_rmw(location, 0xfff, hi20);
+	return riscv_insn_rmw(location + 4, 0xfffff, lo12 << 20);
 }
 
-static int apply_r_riscv_relax_rela(struct module *me, u32 *location,
+static int apply_r_riscv_relax_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	return 0;
 }
 
-static int apply_r_riscv_align_rela(struct module *me, u32 *location,
+static int apply_r_riscv_align_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	pr_err(
@@ -268,91 +299,505 @@ static int apply_r_riscv_align_rela(struct module *me, u32 *location,
 	return -EINVAL;
 }
 
-static int apply_r_riscv_add16_rela(struct module *me, u32 *location,
+static int apply_r_riscv_add8_rela(struct module *me, void *location, Elf_Addr v)
+{
+	*(u8 *)location += (u8)v;
+	return 0;
+}
+
+static int apply_r_riscv_add16_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	*(u16 *)location += (u16)v;
 	return 0;
 }
 
-static int apply_r_riscv_add32_rela(struct module *me, u32 *location,
+static int apply_r_riscv_add32_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	*(u32 *)location += (u32)v;
 	return 0;
 }
 
-static int apply_r_riscv_add64_rela(struct module *me, u32 *location,
+static int apply_r_riscv_add64_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	*(u64 *)location += (u64)v;
 	return 0;
 }
 
-static int apply_r_riscv_sub16_rela(struct module *me, u32 *location,
+static int apply_r_riscv_sub8_rela(struct module *me, void *location, Elf_Addr v)
+{
+	*(u8 *)location -= (u8)v;
+	return 0;
+}
+
+static int apply_r_riscv_sub16_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	*(u16 *)location -= (u16)v;
 	return 0;
 }
 
-static int apply_r_riscv_sub32_rela(struct module *me, u32 *location,
+static int apply_r_riscv_sub32_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	*(u32 *)location -= (u32)v;
 	return 0;
 }
 
-static int apply_r_riscv_sub64_rela(struct module *me, u32 *location,
+static int apply_r_riscv_sub64_rela(struct module *me, void *location,
 				    Elf_Addr v)
 {
 	*(u64 *)location -= (u64)v;
 	return 0;
 }
 
-static int (*reloc_handlers_rela[]) (struct module *me, u32 *location,
-				Elf_Addr v) = {
-	[R_RISCV_32]			= apply_r_riscv_32_rela,
-	[R_RISCV_64]			= apply_r_riscv_64_rela,
-	[R_RISCV_BRANCH]		= apply_r_riscv_branch_rela,
-	[R_RISCV_JAL]			= apply_r_riscv_jal_rela,
-	[R_RISCV_RVC_BRANCH]		= apply_r_riscv_rvc_branch_rela,
-	[R_RISCV_RVC_JUMP]		= apply_r_riscv_rvc_jump_rela,
-	[R_RISCV_PCREL_HI20]		= apply_r_riscv_pcrel_hi20_rela,
-	[R_RISCV_PCREL_LO12_I]		= apply_r_riscv_pcrel_lo12_i_rela,
-	[R_RISCV_PCREL_LO12_S]		= apply_r_riscv_pcrel_lo12_s_rela,
-	[R_RISCV_HI20]			= apply_r_riscv_hi20_rela,
-	[R_RISCV_LO12_I]		= apply_r_riscv_lo12_i_rela,
-	[R_RISCV_LO12_S]		= apply_r_riscv_lo12_s_rela,
-	[R_RISCV_GOT_HI20]		= apply_r_riscv_got_hi20_rela,
-	[R_RISCV_CALL_PLT]		= apply_r_riscv_call_plt_rela,
-	[R_RISCV_CALL]			= apply_r_riscv_call_rela,
-	[R_RISCV_RELAX]			= apply_r_riscv_relax_rela,
-	[R_RISCV_ALIGN]			= apply_r_riscv_align_rela,
-	[R_RISCV_ADD16]			= apply_r_riscv_add16_rela,
-	[R_RISCV_ADD32]			= apply_r_riscv_add32_rela,
-	[R_RISCV_ADD64]			= apply_r_riscv_add64_rela,
-	[R_RISCV_SUB16]			= apply_r_riscv_sub16_rela,
-	[R_RISCV_SUB32]			= apply_r_riscv_sub32_rela,
-	[R_RISCV_SUB64]			= apply_r_riscv_sub64_rela,
+static int dynamic_linking_not_supported(struct module *me, void *location,
+					 Elf_Addr v)
+{
+	pr_err("%s: Dynamic linking not supported in kernel modules PC = %p\n",
+	       me->name, location);
+	return -EINVAL;
+}
+
+static int tls_not_supported(struct module *me, void *location, Elf_Addr v)
+{
+	pr_err("%s: Thread local storage not supported in kernel modules PC = %p\n",
+	       me->name, location);
+	return -EINVAL;
+}
+
+static int apply_r_riscv_sub6_rela(struct module *me, void *location, Elf_Addr v)
+{
+	u8 *byte = location;
+	u8 value = v;
+
+	*byte = (*byte - (value & 0x3f)) & 0x3f;
+	return 0;
+}
+
+static int apply_r_riscv_set6_rela(struct module *me, void *location, Elf_Addr v)
+{
+	u8 *byte = location;
+	u8 value = v;
+
+	*byte = (*byte & 0xc0) | (value & 0x3f);
+	return 0;
+}
+
+static int apply_r_riscv_set8_rela(struct module *me, void *location, Elf_Addr v)
+{
+	*(u8 *)location = (u8)v;
+	return 0;
+}
+
+static int apply_r_riscv_set16_rela(struct module *me, void *location,
+				    Elf_Addr v)
+{
+	*(u16 *)location = (u16)v;
+	return 0;
+}
+
+static int apply_r_riscv_set32_rela(struct module *me, void *location,
+				    Elf_Addr v)
+{
+	*(u32 *)location = (u32)v;
+	return 0;
+}
+
+static int apply_r_riscv_32_pcrel_rela(struct module *me, void *location,
+				       Elf_Addr v)
+{
+	*(u32 *)location = v - (uintptr_t)location;
+	return 0;
+}
+
+static int apply_r_riscv_plt32_rela(struct module *me, void *location,
+				    Elf_Addr v)
+{
+	ptrdiff_t offset = (void *)v - location;
+
+	if (!riscv_insn_valid_32bit_offset(offset)) {
+		/* Only emit the plt entry if offset over 32-bit range */
+		if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) {
+			offset = (void *)module_emit_plt_entry(me, v) - location;
+		} else {
+			pr_err("%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
+			       me->name, (long long)v, location);
+			return -EINVAL;
+		}
+	}
+
+	*(u32 *)location = (u32)offset;
+	return 0;
+}
+
+static int apply_r_riscv_set_uleb128(struct module *me, void *location, Elf_Addr v)
+{
+	*(long *)location = v;
+	return 0;
+}
+
+static int apply_r_riscv_sub_uleb128(struct module *me, void *location, Elf_Addr v)
+{
+	*(long *)location -= v;
+	return 0;
+}
+
+static int apply_6_bit_accumulation(struct module *me, void *location, long buffer)
+{
+	u8 *byte = location;
+	u8 value = buffer;
+
+	if (buffer > 0x3f) {
+		pr_err("%s: value %ld out of range for 6-bit relocation.\n",
+		       me->name, buffer);
+		return -EINVAL;
+	}
+
+	*byte = (*byte & 0xc0) | (value & 0x3f);
+	return 0;
+}
+
+static int apply_8_bit_accumulation(struct module *me, void *location, long buffer)
+{
+	if (buffer > U8_MAX) {
+		pr_err("%s: value %ld out of range for 8-bit relocation.\n",
+		       me->name, buffer);
+		return -EINVAL;
+	}
+	*(u8 *)location = (u8)buffer;
+	return 0;
+}
+
+static int apply_16_bit_accumulation(struct module *me, void *location, long buffer)
+{
+	if (buffer > U16_MAX) {
+		pr_err("%s: value %ld out of range for 16-bit relocation.\n",
+		       me->name, buffer);
+		return -EINVAL;
+	}
+	*(u16 *)location = (u16)buffer;
+	return 0;
+}
+
+static int apply_32_bit_accumulation(struct module *me, void *location, long buffer)
+{
+	if (buffer > U32_MAX) {
+		pr_err("%s: value %ld out of range for 32-bit relocation.\n",
+		       me->name, buffer);
+		return -EINVAL;
+	}
+	*(u32 *)location = (u32)buffer;
+	return 0;
+}
+
+static int apply_64_bit_accumulation(struct module *me, void *location, long buffer)
+{
+	*(u64 *)location = (u64)buffer;
+	return 0;
+}
+
+static int apply_uleb128_accumulation(struct module *me, void *location, long buffer)
+{
+	/*
+	 * ULEB128 is a variable length encoding. Encode the buffer into
+	 * the ULEB128 data format.
+	 */
+	u8 *p = location;
+
+	while (buffer != 0) {
+		u8 value = buffer & 0x7f;
+
+		buffer >>= 7;
+		value |= (!!buffer) << 7;
+
+		*p++ = value;
+	}
+	return 0;
+}
+
+/*
+ * Relocations defined in the riscv-elf-psabi-doc.
+ * This handles static linking only.
+ */
+static const struct relocation_handlers reloc_handlers[] = {
+	[R_RISCV_32]		= { .reloc_handler = apply_r_riscv_32_rela },
+	[R_RISCV_64]		= { .reloc_handler = apply_r_riscv_64_rela },
+	[R_RISCV_RELATIVE]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_COPY]		= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_JUMP_SLOT]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_TLS_DTPMOD32]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_TLS_DTPMOD64]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_TLS_DTPREL32]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_TLS_DTPREL64]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_TLS_TPREL32]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_TLS_TPREL64]	= { .reloc_handler = dynamic_linking_not_supported },
+	/* 12-15 undefined */
+	[R_RISCV_BRANCH]	= { .reloc_handler = apply_r_riscv_branch_rela },
+	[R_RISCV_JAL]		= { .reloc_handler = apply_r_riscv_jal_rela },
+	[R_RISCV_CALL]		= { .reloc_handler = apply_r_riscv_call_rela },
+	[R_RISCV_CALL_PLT]	= { .reloc_handler = apply_r_riscv_call_plt_rela },
+	[R_RISCV_GOT_HI20]	= { .reloc_handler = apply_r_riscv_got_hi20_rela },
+	[R_RISCV_TLS_GOT_HI20]	= { .reloc_handler = tls_not_supported },
+	[R_RISCV_TLS_GD_HI20]	= { .reloc_handler = tls_not_supported },
+	[R_RISCV_PCREL_HI20]	= { .reloc_handler = apply_r_riscv_pcrel_hi20_rela },
+	[R_RISCV_PCREL_LO12_I]	= { .reloc_handler = apply_r_riscv_pcrel_lo12_i_rela },
+	[R_RISCV_PCREL_LO12_S]	= { .reloc_handler = apply_r_riscv_pcrel_lo12_s_rela },
+	[R_RISCV_HI20]		= { .reloc_handler = apply_r_riscv_hi20_rela },
+	[R_RISCV_LO12_I]	= { .reloc_handler = apply_r_riscv_lo12_i_rela },
+	[R_RISCV_LO12_S]	= { .reloc_handler = apply_r_riscv_lo12_s_rela },
+	[R_RISCV_TPREL_HI20]	= { .reloc_handler = tls_not_supported },
+	[R_RISCV_TPREL_LO12_I]	= { .reloc_handler = tls_not_supported },
+	[R_RISCV_TPREL_LO12_S]	= { .reloc_handler = tls_not_supported },
+	[R_RISCV_TPREL_ADD]	= { .reloc_handler = tls_not_supported },
+	[R_RISCV_ADD8]		= { .reloc_handler = apply_r_riscv_add8_rela,
+				    .accumulate_handler = apply_8_bit_accumulation },
+	[R_RISCV_ADD16]		= { .reloc_handler = apply_r_riscv_add16_rela,
+				    .accumulate_handler = apply_16_bit_accumulation },
+	[R_RISCV_ADD32]		= { .reloc_handler = apply_r_riscv_add32_rela,
+				    .accumulate_handler = apply_32_bit_accumulation },
+	[R_RISCV_ADD64]		= { .reloc_handler = apply_r_riscv_add64_rela,
+				    .accumulate_handler = apply_64_bit_accumulation },
+	[R_RISCV_SUB8]		= { .reloc_handler = apply_r_riscv_sub8_rela,
+				    .accumulate_handler = apply_8_bit_accumulation },
+	[R_RISCV_SUB16]		= { .reloc_handler = apply_r_riscv_sub16_rela,
+				    .accumulate_handler = apply_16_bit_accumulation },
+	[R_RISCV_SUB32]		= { .reloc_handler = apply_r_riscv_sub32_rela,
+				    .accumulate_handler = apply_32_bit_accumulation },
+	[R_RISCV_SUB64]		= { .reloc_handler = apply_r_riscv_sub64_rela,
+				    .accumulate_handler = apply_64_bit_accumulation },
+	/* 41-42 reserved for future standard use */
+	[R_RISCV_ALIGN]		= { .reloc_handler = apply_r_riscv_align_rela },
+	[R_RISCV_RVC_BRANCH]	= { .reloc_handler = apply_r_riscv_rvc_branch_rela },
+	[R_RISCV_RVC_JUMP]	= { .reloc_handler = apply_r_riscv_rvc_jump_rela },
+	/* 46-50 reserved for future standard use */
+	[R_RISCV_RELAX]		= { .reloc_handler = apply_r_riscv_relax_rela },
+	[R_RISCV_SUB6]		= { .reloc_handler = apply_r_riscv_sub6_rela,
+				    .accumulate_handler = apply_6_bit_accumulation },
+	[R_RISCV_SET6]		= { .reloc_handler = apply_r_riscv_set6_rela,
+				    .accumulate_handler = apply_6_bit_accumulation },
+	[R_RISCV_SET8]		= { .reloc_handler = apply_r_riscv_set8_rela,
+				    .accumulate_handler = apply_8_bit_accumulation },
+	[R_RISCV_SET16]		= { .reloc_handler = apply_r_riscv_set16_rela,
+				    .accumulate_handler = apply_16_bit_accumulation },
+	[R_RISCV_SET32]		= { .reloc_handler = apply_r_riscv_set32_rela,
+				    .accumulate_handler = apply_32_bit_accumulation },
+	[R_RISCV_32_PCREL]	= { .reloc_handler = apply_r_riscv_32_pcrel_rela },
+	[R_RISCV_IRELATIVE]	= { .reloc_handler = dynamic_linking_not_supported },
+	[R_RISCV_PLT32]		= { .reloc_handler = apply_r_riscv_plt32_rela },
+	[R_RISCV_SET_ULEB128]	= { .reloc_handler = apply_r_riscv_set_uleb128,
+				    .accumulate_handler = apply_uleb128_accumulation },
+	[R_RISCV_SUB_ULEB128]	= { .reloc_handler = apply_r_riscv_sub_uleb128,
+				    .accumulate_handler = apply_uleb128_accumulation },
+	/* 62-191 reserved for future standard use */
+	/* 192-255 nonstandard ABI extensions  */
 };
 
+static void
+process_accumulated_relocations(struct module *me,
+				struct hlist_head **relocation_hashtable,
+				struct list_head *used_buckets_list)
+{
+	/*
+	 * Only ADD/SUB/SET/ULEB128 should end up here.
+	 *
+	 * Each bucket may have more than one relocation location. All
+	 * relocations for a location are stored in a list in a bucket.
+	 *
+	 * Relocations are applied to a temp variable before being stored to the
+	 * provided location to check for overflow. This also allows ULEB128 to
+	 * properly decide how many entries are needed before storing to
+	 * location. The final value is stored into location using the handler
+	 * for the last relocation to an address.
+	 *
+	 * Three layers of indexing:
+	 *	- Each of the buckets in use
+	 *	- Groups of relocations in each bucket by location address
+	 *	- Each relocation entry for a location address
+	 */
+	struct used_bucket *bucket_iter;
+	struct used_bucket *bucket_iter_tmp;
+	struct relocation_head *rel_head_iter;
+	struct hlist_node *rel_head_iter_tmp;
+	struct relocation_entry *rel_entry_iter;
+	struct relocation_entry *rel_entry_iter_tmp;
+	int curr_type;
+	void *location;
+	long buffer;
+
+	list_for_each_entry_safe(bucket_iter, bucket_iter_tmp,
+				 used_buckets_list, head) {
+		hlist_for_each_entry_safe(rel_head_iter, rel_head_iter_tmp,
+					  bucket_iter->bucket, node) {
+			buffer = 0;
+			location = rel_head_iter->location;
+			list_for_each_entry_safe(rel_entry_iter,
+						 rel_entry_iter_tmp,
+						 rel_head_iter->rel_entry,
+						 head) {
+				curr_type = rel_entry_iter->type;
+				reloc_handlers[curr_type].reloc_handler(
+					me, &buffer, rel_entry_iter->value);
+				kfree(rel_entry_iter);
+			}
+			reloc_handlers[curr_type].accumulate_handler(
+				me, location, buffer);
+			kfree(rel_head_iter);
+		}
+		kfree(bucket_iter);
+	}
+
+	kfree(*relocation_hashtable);
+}
+
+static int add_relocation_to_accumulate(struct module *me, int type,
+					void *location,
+					unsigned int hashtable_bits, Elf_Addr v,
+					struct hlist_head *relocation_hashtable,
+					struct list_head *used_buckets_list)
+{
+	struct relocation_entry *entry;
+	struct relocation_head *rel_head;
+	struct hlist_head *current_head;
+	struct used_bucket *bucket;
+	unsigned long hash;
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+
+	if (!entry)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&entry->head);
+	entry->type = type;
+	entry->value = v;
+
+	hash = hash_min((uintptr_t)location, hashtable_bits);
+
+	current_head = &relocation_hashtable[hash];
+
+	/*
+	 * Search for the relocation_head for the relocations that happen at the
+	 * provided location
+	 */
+	bool found = false;
+	struct relocation_head *rel_head_iter;
+
+	hlist_for_each_entry(rel_head_iter, current_head, node) {
+		if (rel_head_iter->location == location) {
+			found = true;
+			rel_head = rel_head_iter;
+			break;
+		}
+	}
+
+	/*
+	 * If there has not yet been any relocations at the provided location,
+	 * create a relocation_head for that location and populate it with this
+	 * relocation_entry.
+	 */
+	if (!found) {
+		rel_head = kmalloc(sizeof(*rel_head), GFP_KERNEL);
+
+		if (!rel_head) {
+			kfree(entry);
+			return -ENOMEM;
+		}
+
+		rel_head->rel_entry =
+			kmalloc(sizeof(struct list_head), GFP_KERNEL);
+
+		if (!rel_head->rel_entry) {
+			kfree(entry);
+			kfree(rel_head);
+			return -ENOMEM;
+		}
+
+		INIT_LIST_HEAD(rel_head->rel_entry);
+		rel_head->location = location;
+		INIT_HLIST_NODE(&rel_head->node);
+		if (!current_head->first) {
+			bucket =
+				kmalloc(sizeof(struct used_bucket), GFP_KERNEL);
+
+			if (!bucket) {
+				kfree(entry);
+				kfree(rel_head);
+				kfree(rel_head->rel_entry);
+				return -ENOMEM;
+			}
+
+			INIT_LIST_HEAD(&bucket->head);
+			bucket->bucket = current_head;
+			list_add(&bucket->head, used_buckets_list);
+		}
+		hlist_add_head(&rel_head->node, current_head);
+	}
+
+	/* Add relocation to head of discovered rel_head */
+	list_add_tail(&entry->head, rel_head->rel_entry);
+
+	return 0;
+}
+
+static unsigned int
+initialize_relocation_hashtable(unsigned int num_relocations,
+				struct hlist_head **relocation_hashtable)
+{
+	/* Can safely assume that bits is not greater than sizeof(long) */
+	unsigned long hashtable_size = roundup_pow_of_two(num_relocations);
+	unsigned int hashtable_bits = ilog2(hashtable_size);
+
+	/*
+	 * Double size of hashtable if num_relocations * 1.25 is greater than
+	 * hashtable_size.
+	 */
+	int should_double_size = ((num_relocations + (num_relocations >> 2)) > (hashtable_size));
+
+	hashtable_bits += should_double_size;
+
+	hashtable_size <<= should_double_size;
+
+	*relocation_hashtable = kmalloc_array(hashtable_size,
+					      sizeof(*relocation_hashtable),
+					      GFP_KERNEL);
+	if (!*relocation_hashtable)
+		return -ENOMEM;
+
+	__hash_init(*relocation_hashtable, hashtable_size);
+
+	return hashtable_bits;
+}
+
 int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 		       unsigned int symindex, unsigned int relsec,
 		       struct module *me)
 {
 	Elf_Rela *rel = (void *) sechdrs[relsec].sh_addr;
-	int (*handler)(struct module *me, u32 *location, Elf_Addr v);
+	int (*handler)(struct module *me, void *location, Elf_Addr v);
 	Elf_Sym *sym;
-	u32 *location;
+	void *location;
 	unsigned int i, type;
 	Elf_Addr v;
 	int res;
+	unsigned int num_relocations = sechdrs[relsec].sh_size / sizeof(*rel);
+	struct hlist_head *relocation_hashtable;
+	struct list_head used_buckets_list;
+	unsigned int hashtable_bits;
+
+	hashtable_bits = initialize_relocation_hashtable(num_relocations,
+							 &relocation_hashtable);
+
+	if (hashtable_bits < 0)
+		return hashtable_bits;
+
+	INIT_LIST_HEAD(&used_buckets_list);
 
 	pr_debug("Applying relocate section %u to %u\n", relsec,
 	       sechdrs[relsec].sh_info);
 
-	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
+	for (i = 0; i < num_relocations; i++) {
 		/* This is where to make the change */
 		location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
 			+ rel[i].r_offset;
@@ -370,8 +815,8 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 
 		type = ELF_RISCV_R_TYPE(rel[i].r_info);
 
-		if (type < ARRAY_SIZE(reloc_handlers_rela))
-			handler = reloc_handlers_rela[type];
+		if (type < ARRAY_SIZE(reloc_handlers))
+			handler = reloc_handlers[type].reloc_handler;
 		else
 			handler = NULL;
 
@@ -427,11 +872,20 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 			}
 		}
 
-		res = handler(me, location, v);
+		if (reloc_handlers[type].accumulate_handler)
+			res = add_relocation_to_accumulate(me, type, location,
+							   hashtable_bits, v,
+							   relocation_hashtable,
+							   &used_buckets_list);
+		else
+			res = handler(me, location, v);
 		if (res)
 			return res;
 	}
 
+	process_accumulated_relocations(me, &relocation_hashtable,
+					&used_buckets_list);
+
 	return 0;
 }
 
diff --git a/arch/riscv/kernel/probes/rethook_trampoline.S b/arch/riscv/kernel/probes/rethook_trampoline.S
index 21bac92a170a9b..f2cd83d9b0f004 100644
--- a/arch/riscv/kernel/probes/rethook_trampoline.S
+++ b/arch/riscv/kernel/probes/rethook_trampoline.S
@@ -75,7 +75,7 @@
 	REG_L x31, PT_T6(sp)
 	.endm
 
-ENTRY(arch_rethook_trampoline)
+SYM_CODE_START(arch_rethook_trampoline)
 	addi sp, sp, -(PT_SIZE_ON_STACK)
 	save_all_base_regs
 
@@ -90,4 +90,4 @@ ENTRY(arch_rethook_trampoline)
 	addi sp, sp, PT_SIZE_ON_STACK
 
 	ret
-ENDPROC(arch_rethook_trampoline)
+SYM_CODE_END(arch_rethook_trampoline)
diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c
index d3099d67816d05..6c166029079c42 100644
--- a/arch/riscv/kernel/probes/simulate-insn.c
+++ b/arch/riscv/kernel/probes/simulate-insn.c
@@ -24,7 +24,7 @@ static inline bool rv_insn_reg_set_val(struct pt_regs *regs, u32 index,
 				       unsigned long val)
 {
 	if (index == 0)
-		return false;
+		return true;
 	else if (index <= 31)
 		*((unsigned long *)regs + index) = val;
 	else
diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c
index 194f166b2cc40e..4b3dc8beaf77d3 100644
--- a/arch/riscv/kernel/probes/uprobes.c
+++ b/arch/riscv/kernel/probes/uprobes.c
@@ -3,6 +3,7 @@
 #include <linux/highmem.h>
 #include <linux/ptrace.h>
 #include <linux/uprobes.h>
+#include <asm/insn.h>
 
 #include "decode-insn.h"
 
@@ -17,6 +18,11 @@ bool is_swbp_insn(uprobe_opcode_t *insn)
 #endif
 }
 
+bool is_trap_insn(uprobe_opcode_t *insn)
+{
+	return riscv_insn_is_ebreak(*insn) || riscv_insn_is_c_ebreak(*insn);
+}
+
 unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
 {
 	return instruction_pointer(regs);
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index e32d737e039fd4..4f21d970a1292b 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -25,6 +25,7 @@
 #include <asm/thread_info.h>
 #include <asm/cpuidle.h>
 #include <asm/vector.h>
+#include <asm/cpufeature.h>
 
 register unsigned long gp_in_global __asm__("gp");
 
@@ -41,6 +42,23 @@ void arch_cpu_idle(void)
 	cpu_do_idle();
 }
 
+int set_unalign_ctl(struct task_struct *tsk, unsigned int val)
+{
+	if (!unaligned_ctl_available())
+		return -EINVAL;
+
+	tsk->thread.align_ctl = val;
+	return 0;
+}
+
+int get_unalign_ctl(struct task_struct *tsk, unsigned long adr)
+{
+	if (!unaligned_ctl_available())
+		return -EINVAL;
+
+	return put_user(tsk->thread.align_ctl, (unsigned long __user *)adr);
+}
+
 void __show_regs(struct pt_regs *regs)
 {
 	show_regs_print_info(KERN_DEFAULT);
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index c672c8ba9a2a6b..5a62ed1da45332 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -11,6 +11,7 @@
 #include <linux/reboot.h>
 #include <asm/sbi.h>
 #include <asm/smp.h>
+#include <asm/tlbflush.h>
 
 /* default SBI version is 0.1 */
 unsigned long sbi_spec_version __ro_after_init = SBI_SPEC_VERSION_DEFAULT;
@@ -377,31 +378,14 @@ int sbi_remote_fence_i(const struct cpumask *cpu_mask)
 EXPORT_SYMBOL(sbi_remote_fence_i);
 
 /**
- * sbi_remote_sfence_vma() - Execute SFENCE.VMA instructions on given remote
- *			     harts for the specified virtual address range.
- * @cpu_mask: A cpu mask containing all the target harts.
- * @start: Start of the virtual address
- * @size: Total size of the virtual address range.
- *
- * Return: 0 on success, appropriate linux error code otherwise.
- */
-int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
-			   unsigned long start,
-			   unsigned long size)
-{
-	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
-			    cpu_mask, start, size, 0, 0);
-}
-EXPORT_SYMBOL(sbi_remote_sfence_vma);
-
-/**
  * sbi_remote_sfence_vma_asid() - Execute SFENCE.VMA instructions on given
- * remote harts for a virtual address range belonging to a specific ASID.
+ * remote harts for a virtual address range belonging to a specific ASID or not.
  *
  * @cpu_mask: A cpu mask containing all the target harts.
  * @start: Start of the virtual address
  * @size: Total size of the virtual address range.
- * @asid: The value of address space identifier (ASID).
+ * @asid: The value of address space identifier (ASID), or FLUSH_TLB_NO_ASID
+ * for flushing all address spaces.
  *
  * Return: 0 on success, appropriate linux error code otherwise.
  */
@@ -410,8 +394,12 @@ int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
 				unsigned long size,
 				unsigned long asid)
 {
-	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
-			    cpu_mask, start, size, asid, 0);
+	if (asid == FLUSH_TLB_NO_ASID)
+		return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
+				    cpu_mask, start, size, 0, 0);
+	else
+		return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
+				    cpu_mask, start, size, asid, 0);
 }
 EXPORT_SYMBOL(sbi_remote_sfence_vma_asid);
 
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 21a4d0e111bc5f..88b6220b260879 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -384,30 +384,6 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	sigset_t *oldset = sigmask_to_save();
 	int ret;
 
-	/* Are we from a system call? */
-	if (regs->cause == EXC_SYSCALL) {
-		/* Avoid additional syscall restarting via ret_from_exception */
-		regs->cause = -1UL;
-		/* If so, check system call restarting.. */
-		switch (regs->a0) {
-		case -ERESTART_RESTARTBLOCK:
-		case -ERESTARTNOHAND:
-			regs->a0 = -EINTR;
-			break;
-
-		case -ERESTARTSYS:
-			if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
-				regs->a0 = -EINTR;
-				break;
-			}
-			fallthrough;
-		case -ERESTARTNOINTR:
-                        regs->a0 = regs->orig_a0;
-			regs->epc -= 0x4;
-			break;
-		}
-	}
-
 	rseq_signal_deliver(ksig, regs);
 
 	/* Set up the stack frame */
@@ -421,36 +397,67 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 
 void arch_do_signal_or_restart(struct pt_regs *regs)
 {
+	unsigned long continue_addr = 0, restart_addr = 0;
+	int retval = 0;
 	struct ksignal ksig;
+	bool syscall = (regs->cause == EXC_SYSCALL);
 
-	if (get_signal(&ksig)) {
-		/* Actually deliver the signal */
-		handle_signal(&ksig, regs);
-		return;
-	}
+	/* If we were from a system call, check for system call restarting */
+	if (syscall) {
+		continue_addr = regs->epc;
+		restart_addr = continue_addr - 4;
+		retval = regs->a0;
 
-	/* Did we come from a system call? */
-	if (regs->cause == EXC_SYSCALL) {
 		/* Avoid additional syscall restarting via ret_from_exception */
 		regs->cause = -1UL;
 
-		/* Restart the system call - no handlers present */
-		switch (regs->a0) {
+		/*
+		 * Prepare for system call restart. We do this here so that a
+		 * debugger will see the already changed PC.
+		 */
+		switch (retval) {
 		case -ERESTARTNOHAND:
 		case -ERESTARTSYS:
 		case -ERESTARTNOINTR:
-                        regs->a0 = regs->orig_a0;
-			regs->epc -= 0x4;
-			break;
 		case -ERESTART_RESTARTBLOCK:
-                        regs->a0 = regs->orig_a0;
-			regs->a7 = __NR_restart_syscall;
-			regs->epc -= 0x4;
+			regs->a0 = regs->orig_a0;
+			regs->epc = restart_addr;
 			break;
 		}
 	}
 
 	/*
+	 * Get the signal to deliver. When running under ptrace, at this point
+	 * the debugger may change all of our registers.
+	 */
+	if (get_signal(&ksig)) {
+		/*
+		 * Depending on the signal settings, we may need to revert the
+		 * decision to restart the system call, but skip this if a
+		 * debugger has chosen to restart at a different PC.
+		 */
+		if (regs->epc == restart_addr &&
+		    (retval == -ERESTARTNOHAND ||
+		     retval == -ERESTART_RESTARTBLOCK ||
+		     (retval == -ERESTARTSYS &&
+		      !(ksig.ka.sa.sa_flags & SA_RESTART)))) {
+			regs->a0 = -EINTR;
+			regs->epc = continue_addr;
+		}
+
+		/* Actually deliver the signal */
+		handle_signal(&ksig, regs);
+		return;
+	}
+
+	/*
+	 * Handle restarting a different system call. As above, if a debugger
+	 * has chosen to restart at a different PC, ignore the restart.
+	 */
+	if (syscall && regs->epc == restart_addr && retval == -ERESTART_RESTARTBLOCK)
+		regs->a7 = __NR_restart_syscall;
+
+	/*
 	 * If there is no signal to deliver, we just put the saved
 	 * sigmask back.
 	 */
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index d1b0a6fc3adfc7..d162bf339beb16 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -248,7 +248,6 @@ asmlinkage __visible void smp_callin(void)
 
 	numa_add_cpu(curr_cpuid);
 	set_cpu_online(curr_cpuid, 1);
-	check_unaligned_access(curr_cpuid);
 
 	if (has_vector()) {
 		if (riscv_v_setup_vsize())
diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S
index d5cf8b57577739..2d54f309c14059 100644
--- a/arch/riscv/kernel/suspend_entry.S
+++ b/arch/riscv/kernel/suspend_entry.S
@@ -16,7 +16,7 @@
 	.altmacro
 	.option norelax
 
-ENTRY(__cpu_suspend_enter)
+SYM_FUNC_START(__cpu_suspend_enter)
 	/* Save registers (except A0 and T0-T6) */
 	REG_S	ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0)
 	REG_S	sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0)
@@ -57,7 +57,7 @@ ENTRY(__cpu_suspend_enter)
 
 	/* Return to C code */
 	ret
-END(__cpu_suspend_enter)
+SYM_FUNC_END(__cpu_suspend_enter)
 
 SYM_TYPED_FUNC_START(__cpu_resume_enter)
 	/* Load the global pointer */
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index c712037dbe10ec..a2ca5b7756a5b0 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -169,7 +169,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
 	pair->value &= ~missing;
 }
 
-static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
+static bool hwprobe_ext0_has(const struct cpumask *cpus, u64 ext)
 {
 	struct riscv_hwprobe pair;
 
diff --git a/arch/riscv/kernel/tests/Kconfig.debug b/arch/riscv/kernel/tests/Kconfig.debug
new file mode 100644
index 00000000000000..5dba64e8e977cd
--- /dev/null
+++ b/arch/riscv/kernel/tests/Kconfig.debug
@@ -0,0 +1,35 @@
+# SPDX-License-Identifier: GPL-2.0-only
+menu "arch/riscv/kernel Testing and Coverage"
+
+config AS_HAS_ULEB128
+	def_bool $(as-instr,.reloc label$(comma) R_RISCV_SET_ULEB128$(comma) 127\n.reloc label$(comma) R_RISCV_SUB_ULEB128$(comma) 127\nlabel:\n.word 0)
+
+menuconfig RUNTIME_KERNEL_TESTING_MENU
+       bool "arch/riscv/kernel runtime Testing"
+       def_bool y
+       help
+         Enable riscv kernel runtime testing.
+
+if RUNTIME_KERNEL_TESTING_MENU
+
+config RISCV_MODULE_LINKING_KUNIT
+       bool "KUnit test riscv module linking at runtime" if !KUNIT_ALL_TESTS
+       depends on KUNIT
+       default KUNIT_ALL_TESTS
+       help
+         Enable this option to test riscv module linking at boot. This will
+	 enable a module called "test_module_linking".
+
+         KUnit tests run during boot and output the results to the debug log
+         in TAP format (http://testanything.org/). Only useful for kernel devs
+         running the KUnit test harness, and not intended for inclusion into a
+         production build.
+
+         For more information on KUnit and unit tests in general please refer
+         to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+         If unsure, say N.
+
+endif # RUNTIME_TESTING_MENU
+
+endmenu # "arch/riscv/kernel runtime Testing"
diff --git a/arch/riscv/kernel/tests/Makefile b/arch/riscv/kernel/tests/Makefile
new file mode 100644
index 00000000000000..7d6c76cffe2067
--- /dev/null
+++ b/arch/riscv/kernel/tests/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_RISCV_MODULE_LINKING_KUNIT)	+= module_test/
diff --git a/arch/riscv/kernel/tests/module_test/Makefile b/arch/riscv/kernel/tests/module_test/Makefile
new file mode 100644
index 00000000000000..d7a6fd8943de25
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/Makefile
@@ -0,0 +1,15 @@
+obj-m += test_module_linking.o
+
+test_sub := test_sub6.o test_sub8.o test_sub16.o test_sub32.o test_sub64.o
+
+test_set := test_set6.o test_set8.o test_set16.o test_set32.o
+
+test_module_linking-objs += $(test_sub)
+
+test_module_linking-objs += $(test_set)
+
+ifeq ($(CONFIG_AS_HAS_ULEB128),y)
+test_module_linking-objs += test_uleb128.o
+endif
+
+test_module_linking-objs += test_module_linking_main.o
diff --git a/arch/riscv/kernel/tests/module_test/test_module_linking_main.c b/arch/riscv/kernel/tests/module_test/test_module_linking_main.c
new file mode 100644
index 00000000000000..8df5fa5b834e68
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_module_linking_main.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <kunit/test.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Test module linking");
+
+extern int test_set32(void);
+extern int test_set16(void);
+extern int test_set8(void);
+extern int test_set6(void);
+extern long test_sub64(void);
+extern int test_sub32(void);
+extern int test_sub16(void);
+extern int test_sub8(void);
+extern int test_sub6(void);
+
+#ifdef CONFIG_AS_HAS_ULEB128
+extern int test_uleb_basic(void);
+extern int test_uleb_large(void);
+#endif
+
+#define CHECK_EQ(lhs, rhs) KUNIT_ASSERT_EQ(test, lhs, rhs)
+
+void run_test_set(struct kunit *test);
+void run_test_sub(struct kunit *test);
+void run_test_uleb(struct kunit *test);
+
+void run_test_set(struct kunit *test)
+{
+	int val32 = test_set32();
+	int val16 = test_set16();
+	int val8 = test_set8();
+	int val6 = test_set6();
+
+	CHECK_EQ(val32, 0);
+	CHECK_EQ(val16, 0);
+	CHECK_EQ(val8, 0);
+	CHECK_EQ(val6, 0);
+}
+
+void run_test_sub(struct kunit *test)
+{
+	int val64 = test_sub64();
+	int val32 = test_sub32();
+	int val16 = test_sub16();
+	int val8 = test_sub8();
+	int val6 = test_sub6();
+
+	CHECK_EQ(val64, 0);
+	CHECK_EQ(val32, 0);
+	CHECK_EQ(val16, 0);
+	CHECK_EQ(val8, 0);
+	CHECK_EQ(val6, 0);
+}
+
+#ifdef CONFIG_AS_HAS_ULEB128
+void run_test_uleb(struct kunit *test)
+{
+	int val_uleb = test_uleb_basic();
+	int val_uleb2 = test_uleb_large();
+
+	CHECK_EQ(val_uleb, 0);
+	CHECK_EQ(val_uleb2, 0);
+}
+#endif
+
+static struct kunit_case __refdata riscv_module_linking_test_cases[] = {
+	KUNIT_CASE(run_test_set),
+	KUNIT_CASE(run_test_sub),
+#ifdef CONFIG_AS_HAS_ULEB128
+	KUNIT_CASE(run_test_uleb),
+#endif
+	{}
+};
+
+static struct kunit_suite riscv_module_linking_test_suite = {
+	.name = "riscv_checksum",
+	.test_cases = riscv_module_linking_test_cases,
+};
+
+kunit_test_suites(&riscv_module_linking_test_suite);
diff --git a/arch/riscv/kernel/tests/module_test/test_set16.S b/arch/riscv/kernel/tests/module_test/test_set16.S
new file mode 100644
index 00000000000000..2be0e441a12eb4
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_set16.S
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_set16
+test_set16:
+	lw	a0, set16
+	la	t0, set16
+#ifdef CONFIG_32BIT
+	slli	t0, t0, 16
+	srli	t0, t0, 16
+#else
+	slli	t0, t0, 48
+	srli	t0, t0, 48
+#endif
+	sub	a0, a0, t0
+	ret
+.data
+set16:
+	.reloc set16, R_RISCV_SET16, set16
+	.word 0
diff --git a/arch/riscv/kernel/tests/module_test/test_set32.S b/arch/riscv/kernel/tests/module_test/test_set32.S
new file mode 100644
index 00000000000000..de0444537e672f
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_set32.S
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_set32
+test_set32:
+	lw	a0, set32
+	la	t0, set32
+#ifndef CONFIG_32BIT
+	slli	t0, t0, 32
+	srli	t0, t0, 32
+#endif
+	sub	a0, a0, t0
+	ret
+.data
+set32:
+	.reloc set32, R_RISCV_SET32, set32
+	.word 0
diff --git a/arch/riscv/kernel/tests/module_test/test_set6.S b/arch/riscv/kernel/tests/module_test/test_set6.S
new file mode 100644
index 00000000000000..c39ce4c219eb2e
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_set6.S
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_set6
+test_set6:
+	lw	a0, set6
+	la	t0, set6
+#ifdef CONFIG_32BIT
+	slli	t0, t0, 26
+	srli	t0, t0, 26
+#else
+	slli	t0, t0, 58
+	srli	t0, t0, 58
+#endif
+	sub	a0, a0, t0
+	ret
+.data
+set6:
+	.reloc set6, R_RISCV_SET6, set6
+	.word 0
diff --git a/arch/riscv/kernel/tests/module_test/test_set8.S b/arch/riscv/kernel/tests/module_test/test_set8.S
new file mode 100644
index 00000000000000..a656173f6f991f
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_set8.S
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_set8
+test_set8:
+	lw	a0, set8
+	la	t0, set8
+#ifdef CONFIG_32BIT
+	slli	t0, t0, 24
+	srli	t0, t0, 24
+#else
+	slli	t0, t0, 56
+	srli	t0, t0, 56
+#endif
+	sub	a0, a0, t0
+	ret
+.data
+set8:
+	.reloc set8, R_RISCV_SET8, set8
+	.word 0
diff --git a/arch/riscv/kernel/tests/module_test/test_sub16.S b/arch/riscv/kernel/tests/module_test/test_sub16.S
new file mode 100644
index 00000000000000..80f731d599ba13
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_sub16.S
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_sub16
+test_sub16:
+	lh	a0, sub16
+	addi	a0, a0, -32
+	ret
+first:
+	.space 32
+second:
+
+.data
+sub16:
+	.reloc		sub16, R_RISCV_ADD16, second
+	.reloc		sub16, R_RISCV_SUB16, first
+	.half		0
diff --git a/arch/riscv/kernel/tests/module_test/test_sub32.S b/arch/riscv/kernel/tests/module_test/test_sub32.S
new file mode 100644
index 00000000000000..a341686e12df2c
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_sub32.S
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_sub32
+test_sub32:
+	lw	a0, sub32
+	addi	a0, a0, -32
+	ret
+first:
+	.space 32
+second:
+
+.data
+sub32:
+	.reloc		sub32, R_RISCV_ADD32, second
+	.reloc		sub32, R_RISCV_SUB32, first
+	.word		0
diff --git a/arch/riscv/kernel/tests/module_test/test_sub6.S b/arch/riscv/kernel/tests/module_test/test_sub6.S
new file mode 100644
index 00000000000000..e8b61c1ec527a0
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_sub6.S
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_sub6
+test_sub6:
+	lb	a0, sub6
+	addi	a0, a0, -32
+	ret
+first:
+	.space 32
+second:
+
+.data
+sub6:
+	.reloc		sub6, R_RISCV_SET6, second
+	.reloc		sub6, R_RISCV_SUB6, first
+	.byte		0
diff --git a/arch/riscv/kernel/tests/module_test/test_sub64.S b/arch/riscv/kernel/tests/module_test/test_sub64.S
new file mode 100644
index 00000000000000..a59e8afa88fd0e
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_sub64.S
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_sub64
+test_sub64:
+#ifdef CONFIG_32BIT
+	lw	a0, sub64
+#else
+	ld	a0, sub64
+#endif
+	addi	a0, a0, -32
+	ret
+first:
+	.space 32
+second:
+
+.data
+sub64:
+	.reloc		sub64, R_RISCV_ADD64, second
+	.reloc		sub64, R_RISCV_SUB64, first
+	.word		0
+	.word		0
diff --git a/arch/riscv/kernel/tests/module_test/test_sub8.S b/arch/riscv/kernel/tests/module_test/test_sub8.S
new file mode 100644
index 00000000000000..ac5d0ec98de327
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_sub8.S
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_sub8
+test_sub8:
+	lb	a0, sub8
+	addi	a0, a0, -32
+	ret
+first:
+	.space 32
+second:
+
+.data
+sub8:
+	.reloc		sub8, R_RISCV_ADD8, second
+	.reloc		sub8, R_RISCV_SUB8, first
+	.byte		0
diff --git a/arch/riscv/kernel/tests/module_test/test_uleb128.S b/arch/riscv/kernel/tests/module_test/test_uleb128.S
new file mode 100644
index 00000000000000..8515ed7cd8c120
--- /dev/null
+++ b/arch/riscv/kernel/tests/module_test/test_uleb128.S
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+.text
+.global test_uleb_basic
+test_uleb_basic:
+	lw	a0, second
+	addi	a0, a0, -127
+	ret
+
+.global test_uleb_large
+test_uleb_large:
+	lw	a0, fourth
+	addi	a0, a0, -0x07e8
+	ret
+
+.data
+first:
+	.space 127
+second:
+	.reloc second, R_RISCV_SET_ULEB128, second
+	.reloc second, R_RISCV_SUB_ULEB128, first
+	.word 0
+third:
+	.space 1000
+fourth:
+	.reloc fourth, R_RISCV_SET_ULEB128, fourth
+	.reloc fourth, R_RISCV_SUB_ULEB128, third
+	.word 0
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index c9d698518bae19..a1b9be3c4332d9 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -36,7 +36,21 @@ int show_unhandled_signals = 1;
 
 static DEFINE_SPINLOCK(die_lock);
 
-static void dump_kernel_instr(const char *loglvl, struct pt_regs *regs)
+static int copy_code(struct pt_regs *regs, u16 *val, const u16 *insns)
+{
+	const void __user *uaddr = (__force const void __user *)insns;
+
+	if (!user_mode(regs))
+		return get_kernel_nofault(*val, insns);
+
+	/* The user space code from other tasks cannot be accessed. */
+	if (regs != task_pt_regs(current))
+		return -EPERM;
+
+	return copy_from_user_nofault(val, uaddr, sizeof(*val));
+}
+
+static void dump_instr(const char *loglvl, struct pt_regs *regs)
 {
 	char str[sizeof("0000 ") * 12 + 2 + 1], *p = str;
 	const u16 *insns = (u16 *)instruction_pointer(regs);
@@ -45,7 +59,7 @@ static void dump_kernel_instr(const char *loglvl, struct pt_regs *regs)
 	int i;
 
 	for (i = -10; i < 2; i++) {
-		bad = get_kernel_nofault(val, &insns[i]);
+		bad = copy_code(regs, &val, &insns[i]);
 		if (!bad) {
 			p += sprintf(p, i == 0 ? "(%04hx) " : "%04hx ", val);
 		} else {
@@ -74,7 +88,7 @@ void die(struct pt_regs *regs, const char *str)
 	print_modules();
 	if (regs) {
 		show_regs(regs);
-		dump_kernel_instr(KERN_EMERG, regs);
+		dump_instr(KERN_EMERG, regs);
 	}
 
 	cause = regs ? regs->cause : -1;
@@ -107,6 +121,7 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr)
 		print_vma_addr(KERN_CONT " in ", instruction_pointer(regs));
 		pr_cont("\n");
 		__show_regs(regs);
+		dump_instr(KERN_EMERG, regs);
 	}
 
 	force_sig_fault(signo, code, (void __user *)addr);
@@ -181,14 +196,6 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re
 
 DO_ERROR_INFO(do_trap_load_fault,
 	SIGSEGV, SEGV_ACCERR, "load access fault");
-#ifndef CONFIG_RISCV_M_MODE
-DO_ERROR_INFO(do_trap_load_misaligned,
-	SIGBUS, BUS_ADRALN, "Oops - load address misaligned");
-DO_ERROR_INFO(do_trap_store_misaligned,
-	SIGBUS, BUS_ADRALN, "Oops - store (or AMO) address misaligned");
-#else
-int handle_misaligned_load(struct pt_regs *regs);
-int handle_misaligned_store(struct pt_regs *regs);
 
 asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs)
 {
@@ -231,7 +238,6 @@ asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs
 		irqentry_nmi_exit(regs, state);
 	}
 }
-#endif
 DO_ERROR_INFO(do_trap_store_fault,
 	SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault");
 DO_ERROR_INFO(do_trap_ecall_s,
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 378f5b15144356..5255f8134aeff5 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -6,12 +6,16 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/perf_event.h>
 #include <linux/irq.h>
 #include <linux/stringify.h>
 
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/csr.h>
+#include <asm/entry-common.h>
+#include <asm/hwprobe.h>
+#include <asm/cpufeature.h>
 
 #define INSN_MATCH_LB			0x3
 #define INSN_MASK_LB			0x707f
@@ -151,53 +155,134 @@
 #define PRECISION_S 0
 #define PRECISION_D 1
 
-#define DECLARE_UNPRIVILEGED_LOAD_FUNCTION(type, insn)			\
-static inline type load_##type(const type *addr)			\
-{									\
-	type val;							\
-	asm (#insn " %0, %1"						\
-	: "=&r" (val) : "m" (*addr));					\
-	return val;							\
+#ifdef CONFIG_FPU
+
+#define FP_GET_RD(insn)		(insn >> 7 & 0x1F)
+
+extern void put_f32_reg(unsigned long fp_reg, unsigned long value);
+
+static int set_f32_rd(unsigned long insn, struct pt_regs *regs,
+		      unsigned long val)
+{
+	unsigned long fp_reg = FP_GET_RD(insn);
+
+	put_f32_reg(fp_reg, val);
+	regs->status |= SR_FS_DIRTY;
+
+	return 0;
 }
 
-#define DECLARE_UNPRIVILEGED_STORE_FUNCTION(type, insn)			\
-static inline void store_##type(type *addr, type val)			\
-{									\
-	asm volatile (#insn " %0, %1\n"					\
-	: : "r" (val), "m" (*addr));					\
+extern void put_f64_reg(unsigned long fp_reg, unsigned long value);
+
+static int set_f64_rd(unsigned long insn, struct pt_regs *regs, u64 val)
+{
+	unsigned long fp_reg = FP_GET_RD(insn);
+	unsigned long value;
+
+#if __riscv_xlen == 32
+	value = (unsigned long) &val;
+#else
+	value = val;
+#endif
+	put_f64_reg(fp_reg, value);
+	regs->status |= SR_FS_DIRTY;
+
+	return 0;
 }
 
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u8, lbu)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u16, lhu)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s8, lb)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s16, lh)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s32, lw)
-DECLARE_UNPRIVILEGED_STORE_FUNCTION(u8, sb)
-DECLARE_UNPRIVILEGED_STORE_FUNCTION(u16, sh)
-DECLARE_UNPRIVILEGED_STORE_FUNCTION(u32, sw)
-#if defined(CONFIG_64BIT)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lwu)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u64, ld)
-DECLARE_UNPRIVILEGED_STORE_FUNCTION(u64, sd)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, ld)
+#if __riscv_xlen == 32
+extern void get_f64_reg(unsigned long fp_reg, u64 *value);
+
+static u64 get_f64_rs(unsigned long insn, u8 fp_reg_offset,
+		      struct pt_regs *regs)
+{
+	unsigned long fp_reg = (insn >> fp_reg_offset) & 0x1F;
+	u64 val;
+
+	get_f64_reg(fp_reg, &val);
+	regs->status |= SR_FS_DIRTY;
+
+	return val;
+}
 #else
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lw)
-DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, lw)
 
-static inline u64 load_u64(const u64 *addr)
+extern unsigned long get_f64_reg(unsigned long fp_reg);
+
+static unsigned long get_f64_rs(unsigned long insn, u8 fp_reg_offset,
+				struct pt_regs *regs)
+{
+	unsigned long fp_reg = (insn >> fp_reg_offset) & 0x1F;
+	unsigned long val;
+
+	val = get_f64_reg(fp_reg);
+	regs->status |= SR_FS_DIRTY;
+
+	return val;
+}
+
+#endif
+
+extern unsigned long get_f32_reg(unsigned long fp_reg);
+
+static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset,
+				struct pt_regs *regs)
 {
-	return load_u32((u32 *)addr)
-		+ ((u64)load_u32((u32 *)addr + 1) << 32);
+	unsigned long fp_reg = (insn >> fp_reg_offset) & 0x1F;
+	unsigned long val;
+
+	val = get_f32_reg(fp_reg);
+	regs->status |= SR_FS_DIRTY;
+
+	return val;
+}
+
+#else /* CONFIG_FPU */
+static void set_f32_rd(unsigned long insn, struct pt_regs *regs,
+		       unsigned long val) {}
+
+static void set_f64_rd(unsigned long insn, struct pt_regs *regs, u64 val) {}
+
+static unsigned long get_f64_rs(unsigned long insn, u8 fp_reg_offset,
+				struct pt_regs *regs)
+{
+	return 0;
 }
 
-static inline void store_u64(u64 *addr, u64 val)
+static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset,
+				struct pt_regs *regs)
 {
-	store_u32((u32 *)addr, val);
-	store_u32((u32 *)addr + 1, val >> 32);
+	return 0;
 }
+
 #endif
 
-static inline ulong get_insn(ulong mepc)
+#define GET_F64_RS2(insn, regs) (get_f64_rs(insn, 20, regs))
+#define GET_F64_RS2C(insn, regs) (get_f64_rs(insn, 2, regs))
+#define GET_F64_RS2S(insn, regs) (get_f64_rs(RVC_RS2S(insn), 0, regs))
+
+#define GET_F32_RS2(insn, regs) (get_f32_rs(insn, 20, regs))
+#define GET_F32_RS2C(insn, regs) (get_f32_rs(insn, 2, regs))
+#define GET_F32_RS2S(insn, regs) (get_f32_rs(RVC_RS2S(insn), 0, regs))
+
+#ifdef CONFIG_RISCV_M_MODE
+static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val)
+{
+	u8 val;
+
+	asm volatile("lbu %0, %1" : "=&r" (val) : "m" (*addr));
+	*r_val = val;
+
+	return 0;
+}
+
+static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val)
+{
+	asm volatile ("sb %0, %1\n" : : "r" (val), "m" (*addr));
+
+	return 0;
+}
+
+static inline int get_insn(struct pt_regs *regs, ulong mepc, ulong *r_insn)
 {
 	register ulong __mepc asm ("a2") = mepc;
 	ulong val, rvc_mask = 3, tmp;
@@ -226,8 +311,86 @@ static inline ulong get_insn(ulong mepc)
 	: [addr] "r" (__mepc), [rvc_mask] "r" (rvc_mask),
 	  [xlen_minus_16] "i" (XLEN_MINUS_16));
 
-	return val;
+	*r_insn = val;
+
+	return 0;
 }
+#else
+static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val)
+{
+	if (user_mode(regs)) {
+		return __get_user(*r_val, addr);
+	} else {
+		*r_val = *addr;
+		return 0;
+	}
+}
+
+static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val)
+{
+	if (user_mode(regs)) {
+		return __put_user(val, addr);
+	} else {
+		*addr = val;
+		return 0;
+	}
+}
+
+#define __read_insn(regs, insn, insn_addr)		\
+({							\
+	int __ret;					\
+							\
+	if (user_mode(regs)) {				\
+		__ret = __get_user(insn, insn_addr);	\
+	} else {					\
+		insn = *insn_addr;			\
+		__ret = 0;				\
+	}						\
+							\
+	__ret;						\
+})
+
+static inline int get_insn(struct pt_regs *regs, ulong epc, ulong *r_insn)
+{
+	ulong insn = 0;
+
+	if (epc & 0x2) {
+		ulong tmp = 0;
+		u16 __user *insn_addr = (u16 __user *)epc;
+
+		if (__read_insn(regs, insn, insn_addr))
+			return -EFAULT;
+		/* __get_user() uses regular "lw" which sign extend the loaded
+		 * value make sure to clear higher order bits in case we "or" it
+		 * below with the upper 16 bits half.
+		 */
+		insn &= GENMASK(15, 0);
+		if ((insn & __INSN_LENGTH_MASK) != __INSN_LENGTH_32) {
+			*r_insn = insn;
+			return 0;
+		}
+		insn_addr++;
+		if (__read_insn(regs, tmp, insn_addr))
+			return -EFAULT;
+		*r_insn = (tmp << 16) | insn;
+
+		return 0;
+	} else {
+		u32 __user *insn_addr = (u32 __user *)epc;
+
+		if (__read_insn(regs, insn, insn_addr))
+			return -EFAULT;
+		if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) {
+			*r_insn = insn;
+			return 0;
+		}
+		insn &= GENMASK(15, 0);
+		*r_insn = insn;
+
+		return 0;
+	}
+}
+#endif
 
 union reg_data {
 	u8 data_bytes[8];
@@ -235,14 +398,32 @@ union reg_data {
 	u64 data_u64;
 };
 
+static bool unaligned_ctl __read_mostly;
+
+/* sysctl hooks */
+int unaligned_enabled __read_mostly = 1;	/* Enabled by default */
+
 int handle_misaligned_load(struct pt_regs *regs)
 {
 	union reg_data val;
 	unsigned long epc = regs->epc;
-	unsigned long insn = get_insn(epc);
-	unsigned long addr = csr_read(mtval);
+	unsigned long insn;
+	unsigned long addr = regs->badaddr;
 	int i, fp = 0, shift = 0, len = 0;
 
+	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
+
+	*this_cpu_ptr(&misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_EMULATED;
+
+	if (!unaligned_enabled)
+		return -1;
+
+	if (user_mode(regs) && (current->thread.align_ctl & PR_UNALIGN_SIGBUS))
+		return -1;
+
+	if (get_insn(regs, epc, &insn))
+		return -1;
+
 	regs->epc = 0;
 
 	if ((insn & INSN_MASK_LW) == INSN_MATCH_LW) {
@@ -305,13 +486,21 @@ int handle_misaligned_load(struct pt_regs *regs)
 		return -1;
 	}
 
+	if (!IS_ENABLED(CONFIG_FPU) && fp)
+		return -EOPNOTSUPP;
+
 	val.data_u64 = 0;
-	for (i = 0; i < len; i++)
-		val.data_bytes[i] = load_u8((void *)(addr + i));
+	for (i = 0; i < len; i++) {
+		if (load_u8(regs, (void *)(addr + i), &val.data_bytes[i]))
+			return -1;
+	}
 
-	if (fp)
-		return -1;
-	SET_RD(insn, regs, val.data_ulong << shift >> shift);
+	if (!fp)
+		SET_RD(insn, regs, val.data_ulong << shift >> shift);
+	else if (len == 8)
+		set_f64_rd(insn, regs, val.data_u64);
+	else
+		set_f32_rd(insn, regs, val.data_ulong);
 
 	regs->epc = epc + INSN_LEN(insn);
 
@@ -322,9 +511,20 @@ int handle_misaligned_store(struct pt_regs *regs)
 {
 	union reg_data val;
 	unsigned long epc = regs->epc;
-	unsigned long insn = get_insn(epc);
-	unsigned long addr = csr_read(mtval);
-	int i, len = 0;
+	unsigned long insn;
+	unsigned long addr = regs->badaddr;
+	int i, len = 0, fp = 0;
+
+	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
+
+	if (!unaligned_enabled)
+		return -1;
+
+	if (user_mode(regs) && (current->thread.align_ctl & PR_UNALIGN_SIGBUS))
+		return -1;
+
+	if (get_insn(regs, epc, &insn))
+		return -1;
 
 	regs->epc = 0;
 
@@ -336,33 +536,112 @@ int handle_misaligned_store(struct pt_regs *regs)
 	} else if ((insn & INSN_MASK_SD) == INSN_MATCH_SD) {
 		len = 8;
 #endif
+	} else if ((insn & INSN_MASK_FSD) == INSN_MATCH_FSD) {
+		fp = 1;
+		len = 8;
+		val.data_u64 = GET_F64_RS2(insn, regs);
+	} else if ((insn & INSN_MASK_FSW) == INSN_MATCH_FSW) {
+		fp = 1;
+		len = 4;
+		val.data_ulong = GET_F32_RS2(insn, regs);
 	} else if ((insn & INSN_MASK_SH) == INSN_MATCH_SH) {
 		len = 2;
 #if defined(CONFIG_64BIT)
 	} else if ((insn & INSN_MASK_C_SD) == INSN_MATCH_C_SD) {
 		len = 8;
 		val.data_ulong = GET_RS2S(insn, regs);
-	} else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP &&
-		   ((insn >> SH_RD) & 0x1f)) {
+	} else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP) {
 		len = 8;
 		val.data_ulong = GET_RS2C(insn, regs);
 #endif
 	} else if ((insn & INSN_MASK_C_SW) == INSN_MATCH_C_SW) {
 		len = 4;
 		val.data_ulong = GET_RS2S(insn, regs);
-	} else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP &&
-		   ((insn >> SH_RD) & 0x1f)) {
+	} else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP) {
 		len = 4;
 		val.data_ulong = GET_RS2C(insn, regs);
+	} else if ((insn & INSN_MASK_C_FSD) == INSN_MATCH_C_FSD) {
+		fp = 1;
+		len = 8;
+		val.data_u64 = GET_F64_RS2S(insn, regs);
+	} else if ((insn & INSN_MASK_C_FSDSP) == INSN_MATCH_C_FSDSP) {
+		fp = 1;
+		len = 8;
+		val.data_u64 = GET_F64_RS2C(insn, regs);
+#if !defined(CONFIG_64BIT)
+	} else if ((insn & INSN_MASK_C_FSW) == INSN_MATCH_C_FSW) {
+		fp = 1;
+		len = 4;
+		val.data_ulong = GET_F32_RS2S(insn, regs);
+	} else if ((insn & INSN_MASK_C_FSWSP) == INSN_MATCH_C_FSWSP) {
+		fp = 1;
+		len = 4;
+		val.data_ulong = GET_F32_RS2C(insn, regs);
+#endif
 	} else {
 		regs->epc = epc;
 		return -1;
 	}
 
-	for (i = 0; i < len; i++)
-		store_u8((void *)(addr + i), val.data_bytes[i]);
+	if (!IS_ENABLED(CONFIG_FPU) && fp)
+		return -EOPNOTSUPP;
+
+	for (i = 0; i < len; i++) {
+		if (store_u8(regs, (void *)(addr + i), val.data_bytes[i]))
+			return -1;
+	}
 
 	regs->epc = epc + INSN_LEN(insn);
 
 	return 0;
 }
+
+bool check_unaligned_access_emulated(int cpu)
+{
+	long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu);
+	unsigned long tmp_var, tmp_val;
+	bool misaligned_emu_detected;
+
+	*mas_ptr = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+
+	__asm__ __volatile__ (
+		"       "REG_L" %[tmp], 1(%[ptr])\n"
+		: [tmp] "=r" (tmp_val) : [ptr] "r" (&tmp_var) : "memory");
+
+	misaligned_emu_detected = (*mas_ptr == RISCV_HWPROBE_MISALIGNED_EMULATED);
+	/*
+	 * If unaligned_ctl is already set, this means that we detected that all
+	 * CPUS uses emulated misaligned access at boot time. If that changed
+	 * when hotplugging the new cpu, this is something we don't handle.
+	 */
+	if (unlikely(unaligned_ctl && !misaligned_emu_detected)) {
+		pr_crit("CPU misaligned accesses non homogeneous (expected all emulated)\n");
+		while (true)
+			cpu_relax();
+	}
+
+	return misaligned_emu_detected;
+}
+
+void unaligned_emulation_finish(void)
+{
+	int cpu;
+
+	/*
+	 * We can only support PR_UNALIGN controls if all CPUs have misaligned
+	 * accesses emulated since tasks requesting such control can run on any
+	 * CPU.
+	 */
+	for_each_present_cpu(cpu) {
+		if (per_cpu(misaligned_access_speed, cpu) !=
+					RISCV_HWPROBE_MISALIGNED_EMULATED) {
+			return;
+		}
+	}
+	unaligned_ctl = true;
+}
+
+bool unaligned_ctl_available(void)
+{
+	return unaligned_ctl;
+}
diff --git a/arch/riscv/kernel/vdso/flush_icache.S b/arch/riscv/kernel/vdso/flush_icache.S
index 82f97d67c23e9b..8f884227e8bca7 100644
--- a/arch/riscv/kernel/vdso/flush_icache.S
+++ b/arch/riscv/kernel/vdso/flush_icache.S
@@ -8,7 +8,7 @@
 
 	.text
 /* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */
-ENTRY(__vdso_flush_icache)
+SYM_FUNC_START(__vdso_flush_icache)
 	.cfi_startproc
 #ifdef CONFIG_SMP
 	li a7, __NR_riscv_flush_icache
@@ -19,4 +19,4 @@ ENTRY(__vdso_flush_icache)
 #endif
 	ret
 	.cfi_endproc
-ENDPROC(__vdso_flush_icache)
+SYM_FUNC_END(__vdso_flush_icache)
diff --git a/arch/riscv/kernel/vdso/getcpu.S b/arch/riscv/kernel/vdso/getcpu.S
index bb0c05e2ffbae3..9c1bd531907f2f 100644
--- a/arch/riscv/kernel/vdso/getcpu.S
+++ b/arch/riscv/kernel/vdso/getcpu.S
@@ -8,11 +8,11 @@
 
 	.text
 /* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */
-ENTRY(__vdso_getcpu)
+SYM_FUNC_START(__vdso_getcpu)
 	.cfi_startproc
 	/* For now, just do the syscall. */
 	li a7, __NR_getcpu
 	ecall
 	ret
 	.cfi_endproc
-ENDPROC(__vdso_getcpu)
+SYM_FUNC_END(__vdso_getcpu)
diff --git a/arch/riscv/kernel/vdso/rt_sigreturn.S b/arch/riscv/kernel/vdso/rt_sigreturn.S
index 10438c7c626acc..3dc022aa8931ad 100644
--- a/arch/riscv/kernel/vdso/rt_sigreturn.S
+++ b/arch/riscv/kernel/vdso/rt_sigreturn.S
@@ -7,10 +7,10 @@
 #include <asm/unistd.h>
 
 	.text
-ENTRY(__vdso_rt_sigreturn)
+SYM_FUNC_START(__vdso_rt_sigreturn)
 	.cfi_startproc
 	.cfi_signal_frame
 	li a7, __NR_rt_sigreturn
 	ecall
 	.cfi_endproc
-ENDPROC(__vdso_rt_sigreturn)
+SYM_FUNC_END(__vdso_rt_sigreturn)
diff --git a/arch/riscv/kernel/vdso/sys_hwprobe.S b/arch/riscv/kernel/vdso/sys_hwprobe.S
index 4e704146c77a09..77e57f8305216c 100644
--- a/arch/riscv/kernel/vdso/sys_hwprobe.S
+++ b/arch/riscv/kernel/vdso/sys_hwprobe.S
@@ -5,11 +5,11 @@
 #include <asm/unistd.h>
 
 .text
-ENTRY(riscv_hwprobe)
+SYM_FUNC_START(riscv_hwprobe)
 	.cfi_startproc
 	li a7, __NR_riscv_hwprobe
 	ecall
 	ret
 
 	.cfi_endproc
-ENDPROC(riscv_hwprobe)
+SYM_FUNC_END(riscv_hwprobe)
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index 82ce64900f3d7e..cbe2a179331d25 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -23,35 +23,31 @@ SECTIONS
 	.gnu.version_d	: { *(.gnu.version_d) }
 	.gnu.version_r	: { *(.gnu.version_r) }
 
-	.note		: { *(.note.*) }		:text	:note
 	.dynamic	: { *(.dynamic) }		:text	:dynamic
 
+	.rodata		: {
+		*(.rodata .rodata.* .gnu.linkonce.r.*)
+		*(.got.plt) *(.got)
+		*(.data .data.* .gnu.linkonce.d.*)
+		*(.dynbss)
+		*(.bss .bss.* .gnu.linkonce.b.*)
+	}
+
+	.note		: { *(.note.*) }		:text	:note
+
 	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
 	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
 
-	.rodata		: { *(.rodata .rodata.* .gnu.linkonce.r.*) }
-
 	/*
-	 * This linker script is used both with -r and with -shared.
-	 * For the layouts to match, we need to skip more than enough
-	 * space for the dynamic symbol table, etc. If this amount is
-	 * insufficient, ld -shared will error; simply increase it here.
+	 * Text is well-separated from actual data: there's plenty of
+	 * stuff that isn't used at runtime in between.
 	 */
-	. = 0x800;
+	. = ALIGN(16);
 	.text		: { *(.text .text.*) }		:text
 
 	. = ALIGN(4);
 	.alternative : {
-		__alt_start = .;
 		*(.alternative)
-		__alt_end = .;
-	}
-
-	.data		: {
-		*(.got.plt) *(.got)
-		*(.data .data.* .gnu.linkonce.d.*)
-		*(.dynbss)
-		*(.bss .bss.* .gnu.linkonce.b.*)
 	}
 }
 
diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c
index 74bb27440527b3..a944294f6f23a7 100644
--- a/arch/riscv/kvm/aia.c
+++ b/arch/riscv/kvm/aia.c
@@ -14,7 +14,7 @@
 #include <linux/kvm_host.h>
 #include <linux/percpu.h>
 #include <linux/spinlock.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/kvm_aia_imsic.h>
 
 struct aia_hgei_control {
diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index 6cf23b8adb7129..e808723a85f1b1 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -55,6 +55,7 @@ struct imsic {
 	/* IMSIC SW-file */
 	struct imsic_mrif *swfile;
 	phys_addr_t swfile_pa;
+	spinlock_t swfile_extirq_lock;
 };
 
 #define imsic_vs_csr_read(__c)			\
@@ -613,12 +614,23 @@ static void imsic_swfile_extirq_update(struct kvm_vcpu *vcpu)
 {
 	struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
 	struct imsic_mrif *mrif = imsic->swfile;
+	unsigned long flags;
+
+	/*
+	 * The critical section is necessary during external interrupt
+	 * updates to avoid the risk of losing interrupts due to potential
+	 * interruptions between reading topei and updating pending status.
+	 */
+
+	spin_lock_irqsave(&imsic->swfile_extirq_lock, flags);
 
 	if (imsic_mrif_atomic_read(mrif, &mrif->eidelivery) &&
 	    imsic_mrif_topei(mrif, imsic->nr_eix, imsic->nr_msis))
 		kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_VS_EXT);
 	else
 		kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT);
+
+	spin_unlock_irqrestore(&imsic->swfile_extirq_lock, flags);
 }
 
 static void imsic_swfile_read(struct kvm_vcpu *vcpu, bool clear,
@@ -1039,6 +1051,7 @@ int kvm_riscv_vcpu_aia_imsic_init(struct kvm_vcpu *vcpu)
 	}
 	imsic->swfile = page_to_virt(swfile_page);
 	imsic->swfile_pa = page_to_phys(swfile_page);
+	spin_lock_init(&imsic->swfile_extirq_lock);
 
 	/* Setup IO device */
 	kvm_iodevice_init(&imsic->iodev, &imsic_iodoev_ops);
diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c
index 48ae0d4b393245..225a435d9c9a9c 100644
--- a/arch/riscv/kvm/main.c
+++ b/arch/riscv/kvm/main.c
@@ -11,7 +11,7 @@
 #include <linux/module.h>
 #include <linux/kvm_host.h>
 #include <asm/csr.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/sbi.h>
 
 long kvm_arch_dev_ioctl(struct file *filp,
diff --git a/arch/riscv/kvm/tlb.c b/arch/riscv/kvm/tlb.c
index 44bc324aeeb08d..23c0e82b5103cd 100644
--- a/arch/riscv/kvm/tlb.c
+++ b/arch/riscv/kvm/tlb.c
@@ -12,7 +12,7 @@
 #include <linux/kvm_host.h>
 #include <asm/cacheflush.h>
 #include <asm/csr.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/insn-def.h>
 
 #define has_svinval()	riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL)
diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c
index 08ba48a395aa2a..030904d82b583e 100644
--- a/arch/riscv/kvm/vcpu_fp.c
+++ b/arch/riscv/kvm/vcpu_fp.c
@@ -11,7 +11,7 @@
 #include <linux/err.h>
 #include <linux/kvm_host.h>
 #include <linux/uaccess.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 
 #ifdef CONFIG_FPU
 void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu)
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index c6ebce6126b550..f8c9fa0c03c5ab 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -13,7 +13,7 @@
 #include <linux/uaccess.h>
 #include <linux/kvm_host.h>
 #include <asm/cacheflush.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/kvm_vcpu_vector.h>
 #include <asm/vector.h>
 
diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c
index b430cbb695214d..b339a2682f252b 100644
--- a/arch/riscv/kvm/vcpu_vector.c
+++ b/arch/riscv/kvm/vcpu_vector.c
@@ -11,7 +11,7 @@
 #include <linux/err.h>
 #include <linux/kvm_host.h>
 #include <linux/uaccess.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/kvm_vcpu_vector.h>
 #include <asm/vector.h>
 
diff --git a/arch/riscv/lib/clear_page.S b/arch/riscv/lib/clear_page.S
index d7a256eb53f404..b22de1231144c2 100644
--- a/arch/riscv/lib/clear_page.S
+++ b/arch/riscv/lib/clear_page.S
@@ -29,41 +29,41 @@ SYM_FUNC_START(clear_page)
 	lw	a1, riscv_cboz_block_size
 	add	a2, a0, a2
 .Lzero_loop:
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
 	CBOZ_ALT(11, "bltu a0, a2, .Lzero_loop; ret", "nop; nop")
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
 	CBOZ_ALT(10, "bltu a0, a2, .Lzero_loop; ret", "nop; nop")
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
 	CBOZ_ALT(9, "bltu a0, a2, .Lzero_loop; ret", "nop; nop")
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
 	CBOZ_ALT(8, "bltu a0, a2, .Lzero_loop; ret", "nop; nop")
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
-	CBO_zero(a0)
+	CBO_ZERO(a0)
 	add	a0, a0, a1
 	bltu	a0, a2, .Lzero_loop
 	ret
diff --git a/arch/riscv/lib/memcpy.S b/arch/riscv/lib/memcpy.S
index 1a40d01a95439e..44e009ec5fef68 100644
--- a/arch/riscv/lib/memcpy.S
+++ b/arch/riscv/lib/memcpy.S
@@ -7,8 +7,7 @@
 #include <asm/asm.h>
 
 /* void *memcpy(void *, const void *, size_t) */
-ENTRY(__memcpy)
-WEAK(memcpy)
+SYM_FUNC_START(__memcpy)
 	move t6, a0  /* Preserve return value */
 
 	/* Defer to byte-oriented copy for small sizes */
@@ -105,6 +104,7 @@ WEAK(memcpy)
 	bltu a1, a3, 5b
 6:
 	ret
-END(__memcpy)
+SYM_FUNC_END(__memcpy)
+SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy)
 SYM_FUNC_ALIAS(__pi_memcpy, __memcpy)
 SYM_FUNC_ALIAS(__pi___memcpy, __memcpy)
diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S
index 838ff2022fe32d..cb3e2e7ef0baa2 100644
--- a/arch/riscv/lib/memmove.S
+++ b/arch/riscv/lib/memmove.S
@@ -7,7 +7,6 @@
 #include <asm/asm.h>
 
 SYM_FUNC_START(__memmove)
-SYM_FUNC_START_WEAK(memmove)
 	/*
 	 * Returns
 	 *   a0 - dest
@@ -26,8 +25,8 @@ SYM_FUNC_START_WEAK(memmove)
 	 */
 
 	/* Return if nothing to do */
-	beq a0, a1, return_from_memmove
-	beqz a2, return_from_memmove
+	beq a0, a1, .Lreturn_from_memmove
+	beqz a2, .Lreturn_from_memmove
 
 	/*
 	 * Register Uses
@@ -60,7 +59,7 @@ SYM_FUNC_START_WEAK(memmove)
 	 * small enough not to bother.
 	 */
 	andi t0, a2, -(2 * SZREG)
-	beqz t0, byte_copy
+	beqz t0, .Lbyte_copy
 
 	/*
 	 * Now solve for t5 and t6.
@@ -87,14 +86,14 @@ SYM_FUNC_START_WEAK(memmove)
 	 */
 	xor  t0, a0, a1
 	andi t1, t0, (SZREG - 1)
-	beqz t1, coaligned_copy
+	beqz t1, .Lcoaligned_copy
 	/* Fall through to misaligned fixup copy */
 
-misaligned_fixup_copy:
-	bltu a1, a0, misaligned_fixup_copy_reverse
+.Lmisaligned_fixup_copy:
+	bltu a1, a0, .Lmisaligned_fixup_copy_reverse
 
-misaligned_fixup_copy_forward:
-	jal  t0, byte_copy_until_aligned_forward
+.Lmisaligned_fixup_copy_forward:
+	jal  t0, .Lbyte_copy_until_aligned_forward
 
 	andi a5, a1, (SZREG - 1) /* Find the alignment offset of src (a1) */
 	slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */
@@ -153,10 +152,10 @@ misaligned_fixup_copy_forward:
 	mv    t3, t6 /* Fix the dest pointer in case the loop was broken */
 
 	add  a1, t3, a5 /* Restore the src pointer */
-	j byte_copy_forward /* Copy any remaining bytes */
+	j .Lbyte_copy_forward /* Copy any remaining bytes */
 
-misaligned_fixup_copy_reverse:
-	jal  t0, byte_copy_until_aligned_reverse
+.Lmisaligned_fixup_copy_reverse:
+	jal  t0, .Lbyte_copy_until_aligned_reverse
 
 	andi a5, a4, (SZREG - 1) /* Find the alignment offset of src (a4) */
 	slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */
@@ -215,18 +214,18 @@ misaligned_fixup_copy_reverse:
 	mv    t4, t5 /* Fix the dest pointer in case the loop was broken */
 
 	add  a4, t4, a5 /* Restore the src pointer */
-	j byte_copy_reverse /* Copy any remaining bytes */
+	j .Lbyte_copy_reverse /* Copy any remaining bytes */
 
 /*
  * Simple copy loops for SZREG co-aligned memory locations.
  * These also make calls to do byte copies for any unaligned
  * data at their terminations.
  */
-coaligned_copy:
-	bltu a1, a0, coaligned_copy_reverse
+.Lcoaligned_copy:
+	bltu a1, a0, .Lcoaligned_copy_reverse
 
-coaligned_copy_forward:
-	jal t0, byte_copy_until_aligned_forward
+.Lcoaligned_copy_forward:
+	jal t0, .Lbyte_copy_until_aligned_forward
 
 	1:
 	REG_L t1, ( 0 * SZREG)(a1)
@@ -235,10 +234,10 @@ coaligned_copy_forward:
 	REG_S t1, (-1 * SZREG)(t3)
 	bne   t3, t6, 1b
 
-	j byte_copy_forward /* Copy any remaining bytes */
+	j .Lbyte_copy_forward /* Copy any remaining bytes */
 
-coaligned_copy_reverse:
-	jal t0, byte_copy_until_aligned_reverse
+.Lcoaligned_copy_reverse:
+	jal t0, .Lbyte_copy_until_aligned_reverse
 
 	1:
 	REG_L t1, (-1 * SZREG)(a4)
@@ -247,7 +246,7 @@ coaligned_copy_reverse:
 	REG_S t1, ( 0 * SZREG)(t4)
 	bne   t4, t5, 1b
 
-	j byte_copy_reverse /* Copy any remaining bytes */
+	j .Lbyte_copy_reverse /* Copy any remaining bytes */
 
 /*
  * These are basically sub-functions within the function.  They
@@ -258,7 +257,7 @@ coaligned_copy_reverse:
  * up from where they were left and we avoid code duplication
  * without any overhead except the call in and return jumps.
  */
-byte_copy_until_aligned_forward:
+.Lbyte_copy_until_aligned_forward:
 	beq  t3, t5, 2f
 	1:
 	lb   t1,  0(a1)
@@ -269,7 +268,7 @@ byte_copy_until_aligned_forward:
 	2:
 	jalr zero, 0x0(t0) /* Return to multibyte copy loop */
 
-byte_copy_until_aligned_reverse:
+.Lbyte_copy_until_aligned_reverse:
 	beq  t4, t6, 2f
 	1:
 	lb   t1, -1(a4)
@@ -285,10 +284,10 @@ byte_copy_until_aligned_reverse:
  * These will byte copy until they reach the end of data to copy.
  * At that point, they will call to return from memmove.
  */
-byte_copy:
-	bltu a1, a0, byte_copy_reverse
+.Lbyte_copy:
+	bltu a1, a0, .Lbyte_copy_reverse
 
-byte_copy_forward:
+.Lbyte_copy_forward:
 	beq  t3, t4, 2f
 	1:
 	lb   t1,  0(a1)
@@ -299,7 +298,7 @@ byte_copy_forward:
 	2:
 	ret
 
-byte_copy_reverse:
+.Lbyte_copy_reverse:
 	beq  t4, t3, 2f
 	1:
 	lb   t1, -1(a4)
@@ -309,10 +308,10 @@ byte_copy_reverse:
 	bne  t4, t3, 1b
 	2:
 
-return_from_memmove:
+.Lreturn_from_memmove:
 	ret
 
-SYM_FUNC_END(memmove)
 SYM_FUNC_END(__memmove)
+SYM_FUNC_ALIAS_WEAK(memmove, __memmove)
 SYM_FUNC_ALIAS(__pi_memmove, __memmove)
 SYM_FUNC_ALIAS(__pi___memmove, __memmove)
diff --git a/arch/riscv/lib/memset.S b/arch/riscv/lib/memset.S
index 34c5360c6705c5..35f358e70bdb6b 100644
--- a/arch/riscv/lib/memset.S
+++ b/arch/riscv/lib/memset.S
@@ -8,8 +8,7 @@
 #include <asm/asm.h>
 
 /* void *memset(void *, int, size_t) */
-ENTRY(__memset)
-WEAK(memset)
+SYM_FUNC_START(__memset)
 	move t0, a0  /* Preserve return value */
 
 	/* Defer to byte-oriented fill for small sizes */
@@ -110,4 +109,5 @@ WEAK(memset)
 	bltu t0, a3, 5b
 6:
 	ret
-END(__memset)
+SYM_FUNC_END(__memset)
+SYM_FUNC_ALIAS_WEAK(memset, __memset)
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index 09b47ebacf2e87..3ab438f30d1328 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -10,8 +10,7 @@
 	_asm_extable	100b, \lbl
 	.endm
 
-ENTRY(__asm_copy_to_user)
-ENTRY(__asm_copy_from_user)
+SYM_FUNC_START(__asm_copy_to_user)
 
 	/* Enable access to user memory */
 	li t6, SR_SUM
@@ -181,13 +180,13 @@ ENTRY(__asm_copy_from_user)
 	csrc CSR_STATUS, t6
 	sub a0, t5, a0
 	ret
-ENDPROC(__asm_copy_to_user)
-ENDPROC(__asm_copy_from_user)
+SYM_FUNC_END(__asm_copy_to_user)
 EXPORT_SYMBOL(__asm_copy_to_user)
+SYM_FUNC_ALIAS(__asm_copy_from_user, __asm_copy_to_user)
 EXPORT_SYMBOL(__asm_copy_from_user)
 
 
-ENTRY(__clear_user)
+SYM_FUNC_START(__clear_user)
 
 	/* Enable access to user memory */
 	li t6, SR_SUM
@@ -233,5 +232,5 @@ ENTRY(__clear_user)
 	csrc CSR_STATUS, t6
 	sub a0, a3, a0
 	ret
-ENDPROC(__clear_user)
+SYM_FUNC_END(__clear_user)
 EXPORT_SYMBOL(__clear_user)
diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index 9c454f90fd3da2..3a4dfc8babcf8c 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -36,3 +36,4 @@ endif
 
 obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o
 obj-$(CONFIG_RISCV_DMA_NONCOHERENT) += dma-noncoherent.o
+obj-$(CONFIG_RISCV_NONSTANDARD_CACHE_OPS) += cache-ops.o
diff --git a/arch/riscv/mm/cache-ops.c b/arch/riscv/mm/cache-ops.c
new file mode 100644
index 00000000000000..a993ad11d0eca9
--- /dev/null
+++ b/arch/riscv/mm/cache-ops.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <asm/dma-noncoherent.h>
+
+struct riscv_nonstd_cache_ops noncoherent_cache_ops __ro_after_init;
+
+void
+riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops)
+{
+	if (!ops)
+		return;
+	noncoherent_cache_ops = *ops;
+}
+EXPORT_SYMBOL_GPL(riscv_noncoherent_register_cache_ops);
diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
index b76e7e192eb183..4e4e469b8dd66c 100644
--- a/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -15,12 +15,6 @@ static bool noncoherent_supported __ro_after_init;
 int dma_cache_alignment __ro_after_init = ARCH_DMA_MINALIGN;
 EXPORT_SYMBOL_GPL(dma_cache_alignment);
 
-struct riscv_nonstd_cache_ops noncoherent_cache_ops __ro_after_init = {
-	.wback = NULL,
-	.inv = NULL,
-	.wback_inv = NULL,
-};
-
 static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size)
 {
 	void *vaddr = phys_to_virt(paddr);
@@ -31,7 +25,7 @@ static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size)
 		return;
 	}
 #endif
-	ALT_CMO_OP(clean, vaddr, size, riscv_cbom_block_size);
+	ALT_CMO_OP(CLEAN, vaddr, size, riscv_cbom_block_size);
 }
 
 static inline void arch_dma_cache_inv(phys_addr_t paddr, size_t size)
@@ -45,7 +39,7 @@ static inline void arch_dma_cache_inv(phys_addr_t paddr, size_t size)
 	}
 #endif
 
-	ALT_CMO_OP(inval, vaddr, size, riscv_cbom_block_size);
+	ALT_CMO_OP(INVAL, vaddr, size, riscv_cbom_block_size);
 }
 
 static inline void arch_dma_cache_wback_inv(phys_addr_t paddr, size_t size)
@@ -59,7 +53,7 @@ static inline void arch_dma_cache_wback_inv(phys_addr_t paddr, size_t size)
 	}
 #endif
 
-	ALT_CMO_OP(flush, vaddr, size, riscv_cbom_block_size);
+	ALT_CMO_OP(FLUSH, vaddr, size, riscv_cbom_block_size);
 }
 
 static inline bool arch_sync_dma_clean_before_fromdevice(void)
@@ -131,7 +125,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 	}
 #endif
 
-	ALT_CMO_OP(flush, flush_addr, size, riscv_cbom_block_size);
+	ALT_CMO_OP(FLUSH, flush_addr, size, riscv_cbom_block_size);
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
@@ -162,12 +156,3 @@ void __init riscv_set_dma_cache_alignment(void)
 	if (!noncoherent_supported)
 		dma_cache_alignment = 1;
 }
-
-void riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops)
-{
-	if (!ops)
-		return;
-
-	noncoherent_cache_ops = *ops;
-}
-EXPORT_SYMBOL_GPL(riscv_noncoherent_register_cache_ops);
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index b128ed3c5a372a..2e011cbddf3af3 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -666,16 +666,16 @@ void __init create_pgd_mapping(pgd_t *pgdp,
 static uintptr_t __init best_map_size(phys_addr_t pa, uintptr_t va,
 				      phys_addr_t size)
 {
-	if (!(pa & (PGDIR_SIZE - 1)) && !(va & (PGDIR_SIZE - 1)) && size >= PGDIR_SIZE)
-		return PGDIR_SIZE;
-
-	if (!(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE)
+	if (pgtable_l5_enabled &&
+	    !(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE)
 		return P4D_SIZE;
 
-	if (!(pa & (PUD_SIZE - 1)) && !(va & (PUD_SIZE - 1)) && size >= PUD_SIZE)
+	if (pgtable_l4_enabled &&
+	    !(pa & (PUD_SIZE - 1)) && !(va & (PUD_SIZE - 1)) && size >= PUD_SIZE)
 		return PUD_SIZE;
 
-	if (!(pa & (PMD_SIZE - 1)) && !(va & (PMD_SIZE - 1)) && size >= PMD_SIZE)
+	if (IS_ENABLED(CONFIG_64BIT) &&
+	    !(pa & (PMD_SIZE - 1)) && !(va & (PMD_SIZE - 1)) && size >= PMD_SIZE)
 		return PMD_SIZE;
 
 	return PAGE_SIZE;
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index 161d0b34c2cb28..fc5fc4f785c481 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -5,6 +5,7 @@
 
 #include <linux/pagewalk.h>
 #include <linux/pgtable.h>
+#include <linux/vmalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/bitops.h>
 #include <asm/set_memory.h>
@@ -25,19 +26,6 @@ static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk)
 	return new_val;
 }
 
-static int pageattr_pgd_entry(pgd_t *pgd, unsigned long addr,
-			      unsigned long next, struct mm_walk *walk)
-{
-	pgd_t val = READ_ONCE(*pgd);
-
-	if (pgd_leaf(val)) {
-		val = __pgd(set_pageattr_masks(pgd_val(val), walk));
-		set_pgd(pgd, val);
-	}
-
-	return 0;
-}
-
 static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
@@ -96,7 +84,6 @@ static int pageattr_pte_hole(unsigned long addr, unsigned long next,
 }
 
 static const struct mm_walk_ops pageattr_ops = {
-	.pgd_entry = pageattr_pgd_entry,
 	.p4d_entry = pageattr_p4d_entry,
 	.pud_entry = pageattr_pud_entry,
 	.pmd_entry = pageattr_pmd_entry,
@@ -105,12 +92,181 @@ static const struct mm_walk_ops pageattr_ops = {
 	.walk_lock = PGWALK_RDLOCK,
 };
 
+#ifdef CONFIG_64BIT
+static int __split_linear_mapping_pmd(pud_t *pudp,
+				      unsigned long vaddr, unsigned long end)
+{
+	pmd_t *pmdp;
+	unsigned long next;
+
+	pmdp = pmd_offset(pudp, vaddr);
+
+	do {
+		next = pmd_addr_end(vaddr, end);
+
+		if (next - vaddr >= PMD_SIZE &&
+		    vaddr <= (vaddr & PMD_MASK) && end >= next)
+			continue;
+
+		if (pmd_leaf(*pmdp)) {
+			struct page *pte_page;
+			unsigned long pfn = _pmd_pfn(*pmdp);
+			pgprot_t prot = __pgprot(pmd_val(*pmdp) & ~_PAGE_PFN_MASK);
+			pte_t *ptep_new;
+			int i;
+
+			pte_page = alloc_page(GFP_KERNEL);
+			if (!pte_page)
+				return -ENOMEM;
+
+			ptep_new = (pte_t *)page_address(pte_page);
+			for (i = 0; i < PTRS_PER_PTE; ++i, ++ptep_new)
+				set_pte(ptep_new, pfn_pte(pfn + i, prot));
+
+			smp_wmb();
+
+			set_pmd(pmdp, pfn_pmd(page_to_pfn(pte_page), PAGE_TABLE));
+		}
+	} while (pmdp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_pud(p4d_t *p4dp,
+				      unsigned long vaddr, unsigned long end)
+{
+	pud_t *pudp;
+	unsigned long next;
+	int ret;
+
+	pudp = pud_offset(p4dp, vaddr);
+
+	do {
+		next = pud_addr_end(vaddr, end);
+
+		if (next - vaddr >= PUD_SIZE &&
+		    vaddr <= (vaddr & PUD_MASK) && end >= next)
+			continue;
+
+		if (pud_leaf(*pudp)) {
+			struct page *pmd_page;
+			unsigned long pfn = _pud_pfn(*pudp);
+			pgprot_t prot = __pgprot(pud_val(*pudp) & ~_PAGE_PFN_MASK);
+			pmd_t *pmdp_new;
+			int i;
+
+			pmd_page = alloc_page(GFP_KERNEL);
+			if (!pmd_page)
+				return -ENOMEM;
+
+			pmdp_new = (pmd_t *)page_address(pmd_page);
+			for (i = 0; i < PTRS_PER_PMD; ++i, ++pmdp_new)
+				set_pmd(pmdp_new,
+					pfn_pmd(pfn + ((i * PMD_SIZE) >> PAGE_SHIFT), prot));
+
+			smp_wmb();
+
+			set_pud(pudp, pfn_pud(page_to_pfn(pmd_page), PAGE_TABLE));
+		}
+
+		ret = __split_linear_mapping_pmd(pudp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (pudp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_p4d(pgd_t *pgdp,
+				      unsigned long vaddr, unsigned long end)
+{
+	p4d_t *p4dp;
+	unsigned long next;
+	int ret;
+
+	p4dp = p4d_offset(pgdp, vaddr);
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+
+		/*
+		 * If [vaddr; end] contains [vaddr & P4D_MASK; next], we don't
+		 * need to split, we'll change the protections on the whole P4D.
+		 */
+		if (next - vaddr >= P4D_SIZE &&
+		    vaddr <= (vaddr & P4D_MASK) && end >= next)
+			continue;
+
+		if (p4d_leaf(*p4dp)) {
+			struct page *pud_page;
+			unsigned long pfn = _p4d_pfn(*p4dp);
+			pgprot_t prot = __pgprot(p4d_val(*p4dp) & ~_PAGE_PFN_MASK);
+			pud_t *pudp_new;
+			int i;
+
+			pud_page = alloc_page(GFP_KERNEL);
+			if (!pud_page)
+				return -ENOMEM;
+
+			/*
+			 * Fill the pud level with leaf puds that have the same
+			 * protections as the leaf p4d.
+			 */
+			pudp_new = (pud_t *)page_address(pud_page);
+			for (i = 0; i < PTRS_PER_PUD; ++i, ++pudp_new)
+				set_pud(pudp_new,
+					pfn_pud(pfn + ((i * PUD_SIZE) >> PAGE_SHIFT), prot));
+
+			/*
+			 * Make sure the pud filling is not reordered with the
+			 * p4d store which could result in seeing a partially
+			 * filled pud level.
+			 */
+			smp_wmb();
+
+			set_p4d(p4dp, pfn_p4d(page_to_pfn(pud_page), PAGE_TABLE));
+		}
+
+		ret = __split_linear_mapping_pud(p4dp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (p4dp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_pgd(pgd_t *pgdp,
+				      unsigned long vaddr,
+				      unsigned long end)
+{
+	unsigned long next;
+	int ret;
+
+	do {
+		next = pgd_addr_end(vaddr, end);
+		/* We never use PGD mappings for the linear mapping */
+		ret = __split_linear_mapping_p4d(pgdp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (pgdp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int split_linear_mapping(unsigned long start, unsigned long end)
+{
+	return __split_linear_mapping_pgd(pgd_offset_k(start), start, end);
+}
+#endif	/* CONFIG_64BIT */
+
 static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 			pgprot_t clear_mask)
 {
 	int ret;
 	unsigned long start = addr;
 	unsigned long end = start + PAGE_SIZE * numpages;
+	unsigned long __maybe_unused lm_start;
+	unsigned long __maybe_unused lm_end;
 	struct pageattr_masks masks = {
 		.set_mask = set_mask,
 		.clear_mask = clear_mask
@@ -120,11 +276,67 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 		return 0;
 
 	mmap_write_lock(&init_mm);
+
+#ifdef CONFIG_64BIT
+	/*
+	 * We are about to change the permissions of a kernel mapping, we must
+	 * apply the same changes to its linear mapping alias, which may imply
+	 * splitting a huge mapping.
+	 */
+
+	if (is_vmalloc_or_module_addr((void *)start)) {
+		struct vm_struct *area = NULL;
+		int i, page_start;
+
+		area = find_vm_area((void *)start);
+		page_start = (start - (unsigned long)area->addr) >> PAGE_SHIFT;
+
+		for (i = page_start; i < page_start + numpages; ++i) {
+			lm_start = (unsigned long)page_address(area->pages[i]);
+			lm_end = lm_start + PAGE_SIZE;
+
+			ret = split_linear_mapping(lm_start, lm_end);
+			if (ret)
+				goto unlock;
+
+			ret = walk_page_range_novma(&init_mm, lm_start, lm_end,
+						    &pageattr_ops, NULL, &masks);
+			if (ret)
+				goto unlock;
+		}
+	} else if (is_kernel_mapping(start) || is_linear_mapping(start)) {
+		lm_start = (unsigned long)lm_alias(start);
+		lm_end = (unsigned long)lm_alias(end);
+
+		ret = split_linear_mapping(lm_start, lm_end);
+		if (ret)
+			goto unlock;
+
+		ret = walk_page_range_novma(&init_mm, lm_start, lm_end,
+					    &pageattr_ops, NULL, &masks);
+		if (ret)
+			goto unlock;
+	}
+
 	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
 				     &masks);
+
+unlock:
+	mmap_write_unlock(&init_mm);
+
+	/*
+	 * We can't use flush_tlb_kernel_range() here as we may have split a
+	 * hugepage that is larger than that, so let's flush everything.
+	 */
+	flush_tlb_all();
+#else
+	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
+				     &masks);
+
 	mmap_write_unlock(&init_mm);
 
 	flush_tlb_kernel_range(start, end);
+#endif
 
 	return ret;
 }
@@ -159,36 +371,14 @@ int set_memory_nx(unsigned long addr, int numpages)
 
 int set_direct_map_invalid_noflush(struct page *page)
 {
-	int ret;
-	unsigned long start = (unsigned long)page_address(page);
-	unsigned long end = start + PAGE_SIZE;
-	struct pageattr_masks masks = {
-		.set_mask = __pgprot(0),
-		.clear_mask = __pgprot(_PAGE_PRESENT)
-	};
-
-	mmap_read_lock(&init_mm);
-	ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
-	mmap_read_unlock(&init_mm);
-
-	return ret;
+	return __set_memory((unsigned long)page_address(page), 1,
+			    __pgprot(0), __pgprot(_PAGE_PRESENT));
 }
 
 int set_direct_map_default_noflush(struct page *page)
 {
-	int ret;
-	unsigned long start = (unsigned long)page_address(page);
-	unsigned long end = start + PAGE_SIZE;
-	struct pageattr_masks masks = {
-		.set_mask = PAGE_KERNEL,
-		.clear_mask = __pgprot(0)
-	};
-
-	mmap_read_lock(&init_mm);
-	ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
-	mmap_read_unlock(&init_mm);
-
-	return ret;
+	return __set_memory((unsigned long)page_address(page), 1,
+			    PAGE_KERNEL, __pgprot(0));
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
diff --git a/arch/riscv/mm/pmem.c b/arch/riscv/mm/pmem.c
index c5fc5ec96f6d4b..370a422ede1101 100644
--- a/arch/riscv/mm/pmem.c
+++ b/arch/riscv/mm/pmem.c
@@ -17,7 +17,7 @@ void arch_wb_cache_pmem(void *addr, size_t size)
 		return;
 	}
 #endif
-	ALT_CMO_OP(clean, addr, size, riscv_cbom_block_size);
+	ALT_CMO_OP(CLEAN, addr, size, riscv_cbom_block_size);
 }
 EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
 
@@ -29,6 +29,6 @@ void arch_invalidate_pmem(void *addr, size_t size)
 		return;
 	}
 #endif
-	ALT_CMO_OP(inval, addr, size, riscv_cbom_block_size);
+	ALT_CMO_OP(INVAL, addr, size, riscv_cbom_block_size);
 }
 EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c
index e9090b38f8117c..657c27bc07a769 100644
--- a/arch/riscv/mm/ptdump.c
+++ b/arch/riscv/mm/ptdump.c
@@ -129,55 +129,55 @@ static struct ptd_mm_info efi_ptd_info = {
 /* Page Table Entry */
 struct prot_bits {
 	u64 mask;
-	u64 val;
 	const char *set;
 	const char *clear;
 };
 
 static const struct prot_bits pte_bits[] = {
 	{
+#ifdef CONFIG_64BIT
+		.mask = _PAGE_NAPOT,
+		.set = "N",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_MTMASK_SVPBMT,
+		.set = "MT(%s)",
+		.clear = "  ..  ",
+	}, {
+#endif
 		.mask = _PAGE_SOFT,
-		.val = _PAGE_SOFT,
-		.set = "RSW",
-		.clear = "   ",
+		.set = "RSW(%d)",
+		.clear = "  ..  ",
 	}, {
 		.mask = _PAGE_DIRTY,
-		.val = _PAGE_DIRTY,
 		.set = "D",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_ACCESSED,
-		.val = _PAGE_ACCESSED,
 		.set = "A",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_GLOBAL,
-		.val = _PAGE_GLOBAL,
 		.set = "G",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_USER,
-		.val = _PAGE_USER,
 		.set = "U",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_EXEC,
-		.val = _PAGE_EXEC,
 		.set = "X",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_WRITE,
-		.val = _PAGE_WRITE,
 		.set = "W",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_READ,
-		.val = _PAGE_READ,
 		.set = "R",
 		.clear = ".",
 	}, {
 		.mask = _PAGE_PRESENT,
-		.val = _PAGE_PRESENT,
 		.set = "V",
 		.clear = ".",
 	}
@@ -208,15 +208,30 @@ static void dump_prot(struct pg_state *st)
 	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(pte_bits); i++) {
-		const char *s;
+		char s[7];
+		unsigned long val;
 
-		if ((st->current_prot & pte_bits[i].mask) == pte_bits[i].val)
-			s = pte_bits[i].set;
-		else
-			s = pte_bits[i].clear;
+		val = st->current_prot & pte_bits[i].mask;
+		if (val) {
+			if (pte_bits[i].mask == _PAGE_SOFT)
+				sprintf(s, pte_bits[i].set, val >> 8);
+#ifdef CONFIG_64BIT
+			else if (pte_bits[i].mask == _PAGE_MTMASK_SVPBMT) {
+				if (val == _PAGE_NOCACHE_SVPBMT)
+					sprintf(s, pte_bits[i].set, "NC");
+				else if (val == _PAGE_IO_SVPBMT)
+					sprintf(s, pte_bits[i].set, "IO");
+				else
+					sprintf(s, pte_bits[i].set, "??");
+			}
+#endif
+			else
+				sprintf(s, "%s", pte_bits[i].set);
+		} else {
+			sprintf(s, "%s", pte_bits[i].clear);
+		}
 
-		if (s)
-			pt_dump_seq_printf(st->seq, " %s", s);
+		pt_dump_seq_printf(st->seq, " %s", s);
 	}
 }
 
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 77be59aadc735e..e6659d7368b354 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -3,33 +3,56 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
+#include <linux/hugetlb.h>
 #include <asm/sbi.h>
 #include <asm/mmu_context.h>
 
 static inline void local_flush_tlb_all_asid(unsigned long asid)
 {
-	__asm__ __volatile__ ("sfence.vma x0, %0"
-			:
-			: "r" (asid)
-			: "memory");
+	if (asid != FLUSH_TLB_NO_ASID)
+		__asm__ __volatile__ ("sfence.vma x0, %0"
+				:
+				: "r" (asid)
+				: "memory");
+	else
+		local_flush_tlb_all();
 }
 
 static inline void local_flush_tlb_page_asid(unsigned long addr,
 		unsigned long asid)
 {
-	__asm__ __volatile__ ("sfence.vma %0, %1"
-			:
-			: "r" (addr), "r" (asid)
-			: "memory");
+	if (asid != FLUSH_TLB_NO_ASID)
+		__asm__ __volatile__ ("sfence.vma %0, %1"
+				:
+				: "r" (addr), "r" (asid)
+				: "memory");
+	else
+		local_flush_tlb_page(addr);
 }
 
-static inline void local_flush_tlb_range(unsigned long start,
-		unsigned long size, unsigned long stride)
+/*
+ * Flush entire TLB if number of entries to be flushed is greater
+ * than the threshold below.
+ */
+static unsigned long tlb_flush_all_threshold __read_mostly = 64;
+
+static void local_flush_tlb_range_threshold_asid(unsigned long start,
+						 unsigned long size,
+						 unsigned long stride,
+						 unsigned long asid)
 {
-	if (size <= stride)
-		local_flush_tlb_page(start);
-	else
-		local_flush_tlb_all();
+	unsigned long nr_ptes_in_range = DIV_ROUND_UP(size, stride);
+	int i;
+
+	if (nr_ptes_in_range > tlb_flush_all_threshold) {
+		local_flush_tlb_all_asid(asid);
+		return;
+	}
+
+	for (i = 0; i < nr_ptes_in_range; ++i) {
+		local_flush_tlb_page_asid(start, asid);
+		start += stride;
+	}
 }
 
 static inline void local_flush_tlb_range_asid(unsigned long start,
@@ -37,8 +60,10 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
 {
 	if (size <= stride)
 		local_flush_tlb_page_asid(start, asid);
-	else
+	else if (size == FLUSH_TLB_MAX_SIZE)
 		local_flush_tlb_all_asid(asid);
+	else
+		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
 }
 
 static void __ipi_flush_tlb_all(void *info)
@@ -51,7 +76,7 @@ void flush_tlb_all(void)
 	if (riscv_use_ipi_for_rfence())
 		on_each_cpu(__ipi_flush_tlb_all, NULL, 1);
 	else
-		sbi_remote_sfence_vma(NULL, 0, -1);
+		sbi_remote_sfence_vma_asid(NULL, 0, FLUSH_TLB_MAX_SIZE, FLUSH_TLB_NO_ASID);
 }
 
 struct flush_tlb_range_data {
@@ -68,68 +93,62 @@ static void __ipi_flush_tlb_range_asid(void *info)
 	local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
 }
 
-static void __ipi_flush_tlb_range(void *info)
-{
-	struct flush_tlb_range_data *d = info;
-
-	local_flush_tlb_range(d->start, d->size, d->stride);
-}
-
 static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
 			      unsigned long size, unsigned long stride)
 {
 	struct flush_tlb_range_data ftd;
-	struct cpumask *cmask = mm_cpumask(mm);
-	unsigned int cpuid;
+	const struct cpumask *cmask;
+	unsigned long asid = FLUSH_TLB_NO_ASID;
 	bool broadcast;
 
-	if (cpumask_empty(cmask))
-		return;
+	if (mm) {
+		unsigned int cpuid;
 
-	cpuid = get_cpu();
-	/* check if the tlbflush needs to be sent to other CPUs */
-	broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
-	if (static_branch_unlikely(&use_asid_allocator)) {
-		unsigned long asid = atomic_long_read(&mm->context.id) & asid_mask;
-
-		if (broadcast) {
-			if (riscv_use_ipi_for_rfence()) {
-				ftd.asid = asid;
-				ftd.start = start;
-				ftd.size = size;
-				ftd.stride = stride;
-				on_each_cpu_mask(cmask,
-						 __ipi_flush_tlb_range_asid,
-						 &ftd, 1);
-			} else
-				sbi_remote_sfence_vma_asid(cmask,
-							   start, size, asid);
-		} else {
-			local_flush_tlb_range_asid(start, size, stride, asid);
-		}
+		cmask = mm_cpumask(mm);
+		if (cpumask_empty(cmask))
+			return;
+
+		cpuid = get_cpu();
+		/* check if the tlbflush needs to be sent to other CPUs */
+		broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
+
+		if (static_branch_unlikely(&use_asid_allocator))
+			asid = atomic_long_read(&mm->context.id) & asid_mask;
 	} else {
-		if (broadcast) {
-			if (riscv_use_ipi_for_rfence()) {
-				ftd.asid = 0;
-				ftd.start = start;
-				ftd.size = size;
-				ftd.stride = stride;
-				on_each_cpu_mask(cmask,
-						 __ipi_flush_tlb_range,
-						 &ftd, 1);
-			} else
-				sbi_remote_sfence_vma(cmask, start, size);
-		} else {
-			local_flush_tlb_range(start, size, stride);
-		}
+		cmask = cpu_online_mask;
+		broadcast = true;
 	}
 
-	put_cpu();
+	if (broadcast) {
+		if (riscv_use_ipi_for_rfence()) {
+			ftd.asid = asid;
+			ftd.start = start;
+			ftd.size = size;
+			ftd.stride = stride;
+			on_each_cpu_mask(cmask,
+					 __ipi_flush_tlb_range_asid,
+					 &ftd, 1);
+		} else
+			sbi_remote_sfence_vma_asid(cmask,
+						   start, size, asid);
+	} else {
+		local_flush_tlb_range_asid(start, size, stride, asid);
+	}
+
+	if (mm)
+		put_cpu();
 }
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	__flush_tlb_range(mm, 0, -1, PAGE_SIZE);
+	__flush_tlb_range(mm, 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+}
+
+void flush_tlb_mm_range(struct mm_struct *mm,
+			unsigned long start, unsigned long end,
+			unsigned int page_size)
+{
+	__flush_tlb_range(mm, start, end - start, page_size);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
@@ -140,8 +159,40 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end)
 {
-	__flush_tlb_range(vma->vm_mm, start, end - start, PAGE_SIZE);
+	unsigned long stride_size;
+
+	if (!is_vm_hugetlb_page(vma)) {
+		stride_size = PAGE_SIZE;
+	} else {
+		stride_size = huge_page_size(hstate_vma(vma));
+
+		/*
+		 * As stated in the privileged specification, every PTE in a
+		 * NAPOT region must be invalidated, so reset the stride in that
+		 * case.
+		 */
+		if (has_svnapot()) {
+			if (stride_size >= PGDIR_SIZE)
+				stride_size = PGDIR_SIZE;
+			else if (stride_size >= P4D_SIZE)
+				stride_size = P4D_SIZE;
+			else if (stride_size >= PUD_SIZE)
+				stride_size = PUD_SIZE;
+			else if (stride_size >= PMD_SIZE)
+				stride_size = PMD_SIZE;
+			else
+				stride_size = PAGE_SIZE;
+		}
+	}
+
+	__flush_tlb_range(vma->vm_mm, start, end - start, stride_size);
+}
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	__flush_tlb_range(NULL, start, end - start, PAGE_SIZE);
 }
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end)
diff --git a/arch/riscv/purgatory/entry.S b/arch/riscv/purgatory/entry.S
index 0194f4554130ae..5bcf3af903daa2 100644
--- a/arch/riscv/purgatory/entry.S
+++ b/arch/riscv/purgatory/entry.S
@@ -7,15 +7,11 @@
  * Author: Li Zhengyu (lizhengyu3@huawei.com)
  *
  */
-
-.macro	size, sym:req
-	.size \sym, . - \sym
-.endm
+#include <linux/linkage.h>
 
 .text
 
-.globl purgatory_start
-purgatory_start:
+SYM_CODE_START(purgatory_start)
 
 	lla	sp, .Lstack
 	mv	s0, a0	/* The hartid of the current hart */
@@ -28,8 +24,7 @@ purgatory_start:
 	mv	a1, s1
 	ld	a2, riscv_kernel_entry
 	jr	a2
-
-size purgatory_start
+SYM_CODE_END(purgatory_start)
 
 .align 4
 	.rept	256
@@ -39,9 +34,6 @@ size purgatory_start
 
 .data
 
-.globl riscv_kernel_entry
-riscv_kernel_entry:
-	.quad	0
-size riscv_kernel_entry
+SYM_DATA(riscv_kernel_entry, .quad 0)
 
 .end
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 438cd92e60801b..6de44ede4e14dd 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -44,8 +44,7 @@ CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
 CONFIG_CRASH_DUMP=y
 CONFIG_LIVEPATCH=y
-CONFIG_MARCH_ZEC12=y
-CONFIG_TUNE_ZEC12=y
+CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
@@ -76,7 +75,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_MODULE_SIG_SHA256=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
@@ -93,6 +91,7 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_IOSCHED_BFQ=y
 CONFIG_BINFMT_MISC=m
 CONFIG_ZSWAP=y
+CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_SLUB_STATS=y
 # CONFIG_COMPAT_BRK is not set
@@ -619,6 +618,9 @@ CONFIG_BTRFS_FS_POSIX_ACL=y
 CONFIG_BTRFS_DEBUG=y
 CONFIG_BTRFS_ASSERT=y
 CONFIG_NILFS2_FS=m
+CONFIG_BCACHEFS_FS=y
+CONFIG_BCACHEFS_QUOTA=y
+CONFIG_BCACHEFS_POSIX_ACL=y
 CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
@@ -691,7 +693,6 @@ CONFIG_PERSISTENT_KEYRINGS=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_KEY_NOTIFICATIONS=y
 CONFIG_SECURITY=y
-CONFIG_SECURITY_NETWORK=y
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_FORTIFY_SOURCE=y
 CONFIG_SECURITY_SELINUX=y
@@ -834,7 +835,6 @@ CONFIG_DEBUG_IRQFLAGS=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
-CONFIG_DEBUG_CREDENTIALS=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_RCU_REF_SCALE_TEST=m
 CONFIG_RCU_CPU_STALL_TIMEOUT=300
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 1b8150e50f6a65..bcae47da6b7cd2 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -42,8 +42,7 @@ CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
 CONFIG_CRASH_DUMP=y
 CONFIG_LIVEPATCH=y
-CONFIG_MARCH_ZEC12=y
-CONFIG_TUNE_ZEC12=y
+CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
@@ -71,7 +70,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_MODULE_SIG_SHA256=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
@@ -88,6 +86,7 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_IOSCHED_BFQ=y
 CONFIG_BINFMT_MISC=m
 CONFIG_ZSWAP=y
+CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y
 CONFIG_ZSMALLOC_STAT=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_MEMORY_HOTPLUG=y
@@ -605,6 +604,9 @@ CONFIG_OCFS2_FS=m
 CONFIG_BTRFS_FS=y
 CONFIG_BTRFS_FS_POSIX_ACL=y
 CONFIG_NILFS2_FS=m
+CONFIG_BCACHEFS_FS=m
+CONFIG_BCACHEFS_QUOTA=y
+CONFIG_BCACHEFS_POSIX_ACL=y
 CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
@@ -677,7 +679,6 @@ CONFIG_PERSISTENT_KEYRINGS=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_KEY_NOTIFICATIONS=y
 CONFIG_SECURITY=y
-CONFIG_SECURITY_NETWORK=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_LOCKDOWN_LSM=y
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index b831083b4edd8b..47028450eee157 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -9,8 +9,7 @@ CONFIG_BPF_SYSCALL=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_CRASH_DUMP=y
-CONFIG_MARCH_ZEC12=y
-CONFIG_TUNE_ZEC12=y
+CONFIG_MARCH_Z13=y
 # CONFIG_COMPAT is not set
 CONFIG_NR_CPUS=2
 CONFIG_HZ_100=y
diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h
index b714ed0ef68853..9acf48e53a87fb 100644
--- a/arch/s390/include/asm/fpu/api.h
+++ b/arch/s390/include/asm/fpu/api.h
@@ -79,7 +79,7 @@ static inline int test_fp_ctl(u32 fpc)
 #define KERNEL_VXR_HIGH		(KERNEL_VXR_V16V23|KERNEL_VXR_V24V31)
 
 #define KERNEL_VXR		(KERNEL_VXR_LOW|KERNEL_VXR_HIGH)
-#define KERNEL_FPR		(KERNEL_FPC|KERNEL_VXR_V0V7)
+#define KERNEL_FPR		(KERNEL_FPC|KERNEL_VXR_LOW)
 
 struct kernel_fpu;
 
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 21b9e5290c0488..01f1682a73b761 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -73,8 +73,6 @@ struct kprobe_ctlblk {
 void arch_remove_kprobe(struct kprobe *p);
 
 int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
-int kprobe_exceptions_notify(struct notifier_block *self,
-	unsigned long val, void *data);
 
 #define flush_insn_slot(p)	do { } while (0)
 
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index dc17896a001a92..c15eadbb998343 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -228,7 +228,6 @@ typedef struct thread_struct thread_struct;
 	execve_tail();							\
 } while (0)
 
-/* Forward declaration, a strange C thing */
 struct task_struct;
 struct mm_struct;
 struct seq_file;
diff --git a/arch/s390/include/asm/syscall_wrapper.h b/arch/s390/include/asm/syscall_wrapper.h
index 9286430fe7290b..35c1d1b860d88a 100644
--- a/arch/s390/include/asm/syscall_wrapper.h
+++ b/arch/s390/include/asm/syscall_wrapper.h
@@ -63,10 +63,6 @@
 	cond_syscall(__s390x_sys_##name);				\
 	cond_syscall(__s390_sys_##name)
 
-#define SYS_NI(name)							\
-	SYSCALL_ALIAS(__s390x_sys_##name, sys_ni_posix_timers);		\
-	SYSCALL_ALIAS(__s390_sys_##name, sys_ni_posix_timers)
-
 #define COMPAT_SYSCALL_DEFINEx(x, name, ...)						\
 	long __s390_compat_sys##name(struct pt_regs *regs);				\
 	ALLOW_ERROR_INJECTION(__s390_compat_sys##name, ERRNO);				\
@@ -85,15 +81,11 @@
 
 /*
  * As some compat syscalls may not be implemented, we need to expand
- * COND_SYSCALL_COMPAT in kernel/sys_ni.c and COMPAT_SYS_NI in
- * kernel/time/posix-stubs.c to cover this case as well.
+ * COND_SYSCALL_COMPAT in kernel/sys_ni.c to cover this case as well.
  */
 #define COND_SYSCALL_COMPAT(name)					\
 	cond_syscall(__s390_compat_sys_##name)
 
-#define COMPAT_SYS_NI(name)						\
-	SYSCALL_ALIAS(__s390_compat_sys_##name, sys_ni_posix_timers)
-
 #define __S390_SYS_STUBx(x, name, ...)						\
 	long __s390_sys##name(struct pt_regs *regs);				\
 	ALLOW_ERROR_INJECTION(__s390_sys##name, ERRNO);				\
@@ -124,9 +116,6 @@
 #define COND_SYSCALL(name)						\
 	cond_syscall(__s390x_sys_##name)
 
-#define SYS_NI(name)							\
-	SYSCALL_ALIAS(__s390x_sys_##name, sys_ni_posix_timers)
-
 #define __S390_SYS_STUBx(x, fullname, name, ...)
 
 #endif /* CONFIG_COMPAT */
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index cc364fce6aa96b..ba75f6bee77423 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -666,6 +666,7 @@ static int __init ipl_init(void)
 						&ipl_ccw_attr_group_lpar);
 		break;
 	case IPL_TYPE_ECKD:
+	case IPL_TYPE_ECKD_DUMP:
 		rc = sysfs_create_group(&ipl_kset->kobj, &ipl_eckd_attr_group);
 		break;
 	case IPL_TYPE_FCP:
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index 77fd24e6cbb643..39a91b00438a7f 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -279,12 +279,6 @@ static int paicrypt_event_init(struct perf_event *event)
 	if (IS_ERR(cpump))
 		return PTR_ERR(cpump);
 
-	/* Event initialization sets last_tag to 0. When later on the events
-	 * are deleted and re-added, do not reset the event count value to zero.
-	 * Events are added, deleted and re-added when 2 or more events
-	 * are active at the same time.
-	 */
-	event->hw.last_tag = 0;
 	event->destroy = paicrypt_event_destroy;
 
 	if (a->sample_period) {
@@ -318,6 +312,11 @@ static void paicrypt_start(struct perf_event *event, int flags)
 {
 	u64 sum;
 
+	/* Event initialization sets last_tag to 0. When later on the events
+	 * are deleted and re-added, do not reset the event count value to zero.
+	 * Events are added, deleted and re-added when 2 or more events
+	 * are active at the same time.
+	 */
 	if (!event->hw.last_tag) {
 		event->hw.last_tag = 1;
 		sum = paicrypt_getall(event);		/* Get current value */
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index 8ba0f1a3a39dc0..e7013a2e896050 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -260,7 +260,6 @@ static int paiext_event_init(struct perf_event *event)
 	rc = paiext_alloc(a, event);
 	if (rc)
 		return rc;
-	event->hw.last_tag = 0;
 	event->destroy = paiext_event_destroy;
 
 	if (a->sample_period) {
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 02dcbe82a8e512..8207a892bbe22f 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -587,10 +587,6 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start,
 
 	if (!gmap_is_shadow(gmap))
 		return;
-	if (start >= 1UL << 31)
-		/* We are only interested in prefix pages */
-		return;
-
 	/*
 	 * Only new shadow blocks are added to the list during runtime,
 	 * therefore we can safely reference them all the time.
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 3bd2ab2a9a3449..5cb92941540b32 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -756,7 +756,7 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
 		pte_clear(mm, addr, ptep);
 	}
 	if (reset)
-		pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
+		pgste_val(pgste) &= ~(_PGSTE_GPS_USAGE_MASK | _PGSTE_GPS_NODAT);
 	pgste_set_unlock(ptep, pgste);
 	preempt_enable();
 }
diff --git a/arch/sh/include/asm/kexec.h b/arch/sh/include/asm/kexec.h
index 927d80ba2332a7..76631714673ca8 100644
--- a/arch/sh/include/asm/kexec.h
+++ b/arch/sh/include/asm/kexec.h
@@ -28,7 +28,7 @@
 /* The native architecture */
 #define KEXEC_ARCH KEXEC_ARCH_SH
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 /* arch/sh/kernel/machine_kexec.c */
 void reserve_crashkernel(void);
 
@@ -67,6 +67,6 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 }
 #else
 static inline void reserve_crashkernel(void) { }
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
 #endif /* __ASM_SH_KEXEC_H */
diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h
index eeba83e0a7d294..65d4c3316a5bd2 100644
--- a/arch/sh/include/asm/kprobes.h
+++ b/arch/sh/include/asm/kprobes.h
@@ -46,8 +46,6 @@ struct kprobe_ctlblk {
 };
 
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
-extern int kprobe_exceptions_notify(struct notifier_block *self,
-				    unsigned long val, void *data);
 extern int kprobe_handle_illslot(unsigned long pc);
 #else
 
diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile
index 69cd9ac4b2ab8a..2d7e70537de04c 100644
--- a/arch/sh/kernel/Makefile
+++ b/arch/sh/kernel/Makefile
@@ -33,7 +33,7 @@ obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SH_STANDARD_BIOS)	+= sh_bios.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_MODULES)		+= sh_ksyms_32.o module.o
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_IO_TRAPPED)	+= io_trapped.o
diff --git a/arch/sh/kernel/reboot.c b/arch/sh/kernel/reboot.c
index e8eeedc9b1822d..1de006b1c33934 100644
--- a/arch/sh/kernel/reboot.c
+++ b/arch/sh/kernel/reboot.c
@@ -63,7 +63,7 @@ struct machine_ops machine_ops = {
 	.shutdown	= native_machine_shutdown,
 	.restart	= native_machine_restart,
 	.halt		= native_machine_halt,
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.crash_shutdown = native_machine_crash_shutdown,
 #endif
 };
@@ -88,7 +88,7 @@ void machine_halt(void)
 	machine_ops.halt();
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 void machine_crash_shutdown(struct pt_regs *regs)
 {
 	machine_ops.crash_shutdown(regs);
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index 3d80515298d268..d3175f09b3aad9 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -220,7 +220,7 @@ void __init __add_active_range(unsigned int nid, unsigned long start_pfn,
 	request_resource(res, &code_resource);
 	request_resource(res, &data_resource);
 	request_resource(res, &bss_resource);
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	request_resource(res, &crashk_res);
 #endif
 
diff --git a/arch/sparc/include/asm/kprobes.h b/arch/sparc/include/asm/kprobes.h
index 06c2bc767ef751..aec742cd898f27 100644
--- a/arch/sparc/include/asm/kprobes.h
+++ b/arch/sparc/include/asm/kprobes.h
@@ -47,8 +47,6 @@ struct kprobe_ctlblk {
 	struct prev_kprobe prev_kprobe;
 };
 
-int kprobe_exceptions_notify(struct notifier_block *self,
-			     unsigned long val, void *data);
 int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 asmlinkage void __kprobes kprobe_trap(unsigned long trap_level,
 				      struct pt_regs *regs);
diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c
index 55c98fdd67d2b7..18d15d1ce87d59 100644
--- a/arch/x86/boot/compressed/acpi.c
+++ b/arch/x86/boot/compressed/acpi.c
@@ -178,7 +178,7 @@ static unsigned long get_cmdline_acpi_rsdp(void)
 {
 	unsigned long addr = 0;
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	char val[MAX_ADDR_LEN] = { };
 	int ret;
 
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 1b5d17a9f70dde..cf1f13c8217569 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -10,6 +10,7 @@
 #include <asm/coco.h>
 #include <asm/tdx.h>
 #include <asm/vmx.h>
+#include <asm/ia32.h>
 #include <asm/insn.h>
 #include <asm/insn-eval.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index d813160b14d851..6356060caaf311 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -26,6 +26,7 @@
 #include <xen/events.h>
 #endif
 
+#include <asm/apic.h>
 #include <asm/desc.h>
 #include <asm/traps.h>
 #include <asm/vdso.h>
@@ -167,7 +168,96 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
 	}
 }
 
-/* Handles int $0x80 */
+#ifdef CONFIG_IA32_EMULATION
+static __always_inline bool int80_is_external(void)
+{
+	const unsigned int offs = (0x80 / 32) * 0x10;
+	const u32 bit = BIT(0x80 % 32);
+
+	/* The local APIC on XENPV guests is fake */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/*
+	 * If vector 0x80 is set in the APIC ISR then this is an external
+	 * interrupt. Either from broken hardware or injected by a VMM.
+	 *
+	 * Note: In guest mode this is only valid for secure guests where
+	 * the secure module fully controls the vAPIC exposed to the guest.
+	 */
+	return apic_read(APIC_ISR + offs) & bit;
+}
+
+/**
+ * int80_emulation - 32-bit legacy syscall entry
+ *
+ * This entry point can be used by 32-bit and 64-bit programs to perform
+ * 32-bit system calls.  Instances of INT $0x80 can be found inline in
+ * various programs and libraries.  It is also used by the vDSO's
+ * __kernel_vsyscall fallback for hardware that doesn't support a faster
+ * entry method.  Restarted 32-bit system calls also fall back to INT
+ * $0x80 regardless of what instruction was originally used to do the
+ * system call.
+ *
+ * This is considered a slow path.  It is not used by most libc
+ * implementations on modern hardware except during process startup.
+ *
+ * The arguments for the INT $0x80 based syscall are on stack in the
+ * pt_regs structure:
+ *   eax:				system call number
+ *   ebx, ecx, edx, esi, edi, ebp:	arg1 - arg 6
+ */
+DEFINE_IDTENTRY_RAW(int80_emulation)
+{
+	int nr;
+
+	/* Kernel does not use INT $0x80! */
+	if (unlikely(!user_mode(regs))) {
+		irqentry_enter(regs);
+		instrumentation_begin();
+		panic("Unexpected external interrupt 0x80\n");
+	}
+
+	/*
+	 * Establish kernel context for instrumentation, including for
+	 * int80_is_external() below which calls into the APIC driver.
+	 * Identical for soft and external interrupts.
+	 */
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	add_random_kstack_offset();
+
+	/* Validate that this is a soft interrupt to the extent possible */
+	if (unlikely(int80_is_external()))
+		panic("Unexpected external interrupt 0x80\n");
+
+	/*
+	 * The low level idtentry code pushed -1 into regs::orig_ax
+	 * and regs::ax contains the syscall number.
+	 *
+	 * User tracing code (ptrace or signal handlers) might assume
+	 * that the regs::orig_ax contains a 32-bit number on invoking
+	 * a 32-bit syscall.
+	 *
+	 * Establish the syscall convention by saving the 32bit truncated
+	 * syscall number in regs::orig_ax and by invalidating regs::ax.
+	 */
+	regs->orig_ax = regs->ax & GENMASK(31, 0);
+	regs->ax = -ENOSYS;
+
+	nr = syscall_32_enter(regs);
+
+	local_irq_enable();
+	nr = syscall_enter_from_user_mode_work(regs, nr);
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+}
+#else /* CONFIG_IA32_EMULATION */
+
+/* Handles int $0x80 on a 32bit kernel */
 __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 {
 	int nr = syscall_32_enter(regs);
@@ -186,6 +276,7 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 	instrumentation_end();
 	syscall_exit_to_user_mode(regs);
 }
+#endif /* !CONFIG_IA32_EMULATION */
 
 static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 {
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 27c05d08558aaa..de94e2e84ecca9 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -275,80 +275,3 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	int3
 SYM_CODE_END(entry_SYSCALL_compat)
-
-/*
- * 32-bit legacy system call entry.
- *
- * 32-bit x86 Linux system calls traditionally used the INT $0x80
- * instruction.  INT $0x80 lands here.
- *
- * This entry point can be used by 32-bit and 64-bit programs to perform
- * 32-bit system calls.  Instances of INT $0x80 can be found inline in
- * various programs and libraries.  It is also used by the vDSO's
- * __kernel_vsyscall fallback for hardware that doesn't support a faster
- * entry method.  Restarted 32-bit system calls also fall back to INT
- * $0x80 regardless of what instruction was originally used to do the
- * system call.
- *
- * This is considered a slow path.  It is not used by most libc
- * implementations on modern hardware except during process startup.
- *
- * Arguments:
- * eax  system call number
- * ebx  arg1
- * ecx  arg2
- * edx  arg3
- * esi  arg4
- * edi  arg5
- * ebp  arg6
- */
-SYM_CODE_START(entry_INT80_compat)
-	UNWIND_HINT_ENTRY
-	ENDBR
-	/*
-	 * Interrupts are off on entry.
-	 */
-	ASM_CLAC			/* Do this early to minimize exposure */
-	ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV
-
-	/*
-	 * User tracing code (ptrace or signal handlers) might assume that
-	 * the saved RAX contains a 32-bit number when we're invoking a 32-bit
-	 * syscall.  Just in case the high bits are nonzero, zero-extend
-	 * the syscall number.  (This could almost certainly be deleted
-	 * with no ill effects.)
-	 */
-	movl	%eax, %eax
-
-	/* switch to thread stack expects orig_ax and rdi to be pushed */
-	pushq	%rax			/* pt_regs->orig_ax */
-
-	/* Need to switch before accessing the thread stack. */
-	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
-
-	/* In the Xen PV case we already run on the thread stack. */
-	ALTERNATIVE "", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV
-
-	movq	%rsp, %rax
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
-
-	pushq	5*8(%rax)		/* regs->ss */
-	pushq	4*8(%rax)		/* regs->rsp */
-	pushq	3*8(%rax)		/* regs->eflags */
-	pushq	2*8(%rax)		/* regs->cs */
-	pushq	1*8(%rax)		/* regs->ip */
-	pushq	0*8(%rax)		/* regs->orig_ax */
-.Lint80_keep_stack:
-
-	PUSH_AND_CLEAR_REGS rax=$-ENOSYS
-	UNWIND_HINT_REGS
-
-	cld
-
-	IBRS_ENTER
-	UNTRAIN_RET
-
-	movq	%rsp, %rdi
-	call	do_int80_syscall_32
-	jmp	swapgs_restore_regs_and_return_to_usermode
-SYM_CODE_END(entry_INT80_compat)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a08f794a0e79ac..ce1c777227b4ef 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4660,7 +4660,7 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 	if (pmu->intel_cap.pebs_output_pt_available)
 		pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
 	else
-		pmu->pmu.capabilities |= ~PERF_PMU_CAP_AUX_OUTPUT;
+		pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT;
 
 	intel_pmu_check_event_constraints(pmu->event_constraints,
 					  pmu->num_counters,
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 21556ad87f4ba8..8f3a4d16bb791f 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -15,6 +15,7 @@
 #include <linux/io.h>
 #include <asm/apic.h>
 #include <asm/desc.h>
+#include <asm/e820/api.h>
 #include <asm/sev.h>
 #include <asm/ibt.h>
 #include <asm/hypervisor.h>
@@ -286,15 +287,31 @@ static int hv_cpu_die(unsigned int cpu)
 
 static int __init hv_pci_init(void)
 {
-	int gen2vm = efi_enabled(EFI_BOOT);
+	bool gen2vm = efi_enabled(EFI_BOOT);
 
 	/*
-	 * For Generation-2 VM, we exit from pci_arch_init() by returning 0.
-	 * The purpose is to suppress the harmless warning:
+	 * A Generation-2 VM doesn't support legacy PCI/PCIe, so both
+	 * raw_pci_ops and raw_pci_ext_ops are NULL, and pci_subsys_init() ->
+	 * pcibios_init() doesn't call pcibios_resource_survey() ->
+	 * e820__reserve_resources_late(); as a result, any emulated persistent
+	 * memory of E820_TYPE_PRAM (12) via the kernel parameter
+	 * memmap=nn[KMG]!ss is not added into iomem_resource and hence can't be
+	 * detected by register_e820_pmem(). Fix this by directly calling
+	 * e820__reserve_resources_late() here: e820__reserve_resources_late()
+	 * depends on e820__reserve_resources(), which has been called earlier
+	 * from setup_arch(). Note: e820__reserve_resources_late() also adds
+	 * any memory of E820_TYPE_PMEM (7) into iomem_resource, and
+	 * acpi_nfit_register_region() -> acpi_nfit_insert_resource() ->
+	 * region_intersects() returns REGION_INTERSECTS, so the memory of
+	 * E820_TYPE_PMEM won't get added twice.
+	 *
+	 * We return 0 here so that pci_arch_init() won't print the warning:
 	 * "PCI: Fatal: No config space access function found"
 	 */
-	if (gen2vm)
+	if (gen2vm) {
+		e820__reserve_resources_late();
 		return 0;
+	}
 
 	/* For Generation-1 VM, we'll proceed in pci_arch_init().  */
 	return 1;
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index c8a7fc23f63c67..f896eed4516c7e 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -16,6 +16,9 @@
 #include <asm/x86_init.h>
 #include <asm/cpufeature.h>
 #include <asm/irq_vectors.h>
+#include <asm/xen/hypervisor.h>
+
+#include <xen/xen.h>
 
 #ifdef CONFIG_ACPI_APEI
 # include <asm/pgtable_types.h>
@@ -127,6 +130,17 @@ static inline void arch_acpi_set_proc_cap_bits(u32 *cap)
 	if (!cpu_has(c, X86_FEATURE_MWAIT) ||
 	    boot_option_idle_override == IDLE_NOMWAIT)
 		*cap &= ~(ACPI_PROC_CAP_C_C1_FFH | ACPI_PROC_CAP_C_C2C3_FFH);
+
+	if (xen_initial_domain()) {
+		/*
+		 * When Linux is running as Xen dom0, the hypervisor is the
+		 * entity in charge of the processor power management, and so
+		 * Xen needs to check the OS capabilities reported in the
+		 * processor capabilities buffer matches what the hypervisor
+		 * driver supports.
+		 */
+		xen_sanitize_proc_cap_bits(cap);
+	}
 }
 
 static inline bool acpi_has_cpu_in_madt(void)
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 5a2ae24b1204f9..9805629479d968 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -75,6 +75,11 @@ static inline bool ia32_enabled(void)
 	return __ia32_enabled;
 }
 
+static inline void ia32_disable(void)
+{
+	__ia32_enabled = false;
+}
+
 #else /* !CONFIG_IA32_EMULATION */
 
 static inline bool ia32_enabled(void)
@@ -82,6 +87,8 @@ static inline bool ia32_enabled(void)
 	return IS_ENABLED(CONFIG_X86_32);
 }
 
+static inline void ia32_disable(void) {}
+
 #endif
 
 #endif /* _ASM_X86_IA32_H */
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 05fd175cec7d5c..13639e57e1f8af 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -569,6 +569,10 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_UD,		exc_invalid_op);
 DECLARE_IDTENTRY_RAW(X86_TRAP_BP,		exc_int3);
 DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF,	exc_page_fault);
 
+#if defined(CONFIG_IA32_EMULATION)
+DECLARE_IDTENTRY_RAW(IA32_SYSCALL_VECTOR,	int80_emulation);
+#endif
+
 #ifdef CONFIG_X86_MCE
 #ifdef CONFIG_X86_64
 DECLARE_IDTENTRY_MCE(X86_TRAP_MC,	exc_machine_check);
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index a2e9317aad4955..5939694dfb28dc 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -113,8 +113,6 @@ struct kprobe_ctlblk {
 };
 
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
-extern int kprobe_exceptions_notify(struct notifier_block *self,
-				    unsigned long val, void *data);
 extern int kprobe_int3_handler(struct pt_regs *regs);
 
 #else
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 4d84122bd6433b..484f4f0131a5cc 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -32,10 +32,6 @@ void entry_SYSCALL_compat(void);
 void entry_SYSCALL_compat_safe_stack(void);
 void entry_SYSRETL_compat_unsafe_stack(void);
 void entry_SYSRETL_compat_end(void);
-void entry_INT80_compat(void);
-#ifdef CONFIG_XEN_PV
-void xen_entry_INT80_compat(void);
-#endif
 #else /* !CONFIG_IA32_EMULATION */
 #define entry_SYSCALL_compat NULL
 #define entry_SYSENTER_compat NULL
diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h
index fd2669b1cb2d95..21f9407be5d357 100644
--- a/arch/x86/include/asm/syscall_wrapper.h
+++ b/arch/x86/include/asm/syscall_wrapper.h
@@ -86,9 +86,6 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 		return sys_ni_syscall();				\
 	}
 
-#define __SYS_NI(abi, name)						\
-	SYSCALL_ALIAS(__##abi##_##name, sys_ni_posix_timers);
-
 #ifdef CONFIG_X86_64
 #define __X64_SYS_STUB0(name)						\
 	__SYS_STUB0(x64, sys_##name)
@@ -100,13 +97,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 #define __X64_COND_SYSCALL(name)					\
 	__COND_SYSCALL(x64, sys_##name)
 
-#define __X64_SYS_NI(name)						\
-	__SYS_NI(x64, sys_##name)
 #else /* CONFIG_X86_64 */
 #define __X64_SYS_STUB0(name)
 #define __X64_SYS_STUBx(x, name, ...)
 #define __X64_COND_SYSCALL(name)
-#define __X64_SYS_NI(name)
 #endif /* CONFIG_X86_64 */
 
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
@@ -120,13 +114,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 #define __IA32_COND_SYSCALL(name)					\
 	__COND_SYSCALL(ia32, sys_##name)
 
-#define __IA32_SYS_NI(name)						\
-	__SYS_NI(ia32, sys_##name)
 #else /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
 #define __IA32_SYS_STUB0(name)
 #define __IA32_SYS_STUBx(x, name, ...)
 #define __IA32_COND_SYSCALL(name)
-#define __IA32_SYS_NI(name)
 #endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
 
 #ifdef CONFIG_IA32_EMULATION
@@ -135,8 +126,7 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
  * additional wrappers (aptly named __ia32_sys_xyzzy) which decode the
  * ia32 regs in the proper order for shared or "common" syscalls. As some
  * syscalls may not be implemented, we need to expand COND_SYSCALL in
- * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this
- * case as well.
+ * kernel/sys_ni.c to cover this case as well.
  */
 #define __IA32_COMPAT_SYS_STUB0(name)					\
 	__SYS_STUB0(ia32, compat_sys_##name)
@@ -148,14 +138,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 #define __IA32_COMPAT_COND_SYSCALL(name)				\
 	__COND_SYSCALL(ia32, compat_sys_##name)
 
-#define __IA32_COMPAT_SYS_NI(name)					\
-	__SYS_NI(ia32, compat_sys_##name)
-
 #else /* CONFIG_IA32_EMULATION */
 #define __IA32_COMPAT_SYS_STUB0(name)
 #define __IA32_COMPAT_SYS_STUBx(x, name, ...)
 #define __IA32_COMPAT_COND_SYSCALL(name)
-#define __IA32_COMPAT_SYS_NI(name)
 #endif /* CONFIG_IA32_EMULATION */
 
 
@@ -175,13 +161,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 #define __X32_COMPAT_COND_SYSCALL(name)					\
 	__COND_SYSCALL(x64, compat_sys_##name)
 
-#define __X32_COMPAT_SYS_NI(name)					\
-	__SYS_NI(x64, compat_sys_##name)
 #else /* CONFIG_X86_X32_ABI */
 #define __X32_COMPAT_SYS_STUB0(name)
 #define __X32_COMPAT_SYS_STUBx(x, name, ...)
 #define __X32_COMPAT_COND_SYSCALL(name)
-#define __X32_COMPAT_SYS_NI(name)
 #endif /* CONFIG_X86_X32_ABI */
 
 
@@ -212,17 +195,12 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 
 /*
  * As some compat syscalls may not be implemented, we need to expand
- * COND_SYSCALL_COMPAT in kernel/sys_ni.c and COMPAT_SYS_NI in
- * kernel/time/posix-stubs.c to cover this case as well.
+ * COND_SYSCALL_COMPAT in kernel/sys_ni.c to cover this case as well.
  */
 #define COND_SYSCALL_COMPAT(name) 					\
 	__IA32_COMPAT_COND_SYSCALL(name)				\
 	__X32_COMPAT_COND_SYSCALL(name)
 
-#define COMPAT_SYS_NI(name)						\
-	__IA32_COMPAT_SYS_NI(name)					\
-	__X32_COMPAT_SYS_NI(name)
-
 #endif /* CONFIG_COMPAT */
 
 #define __SYSCALL_DEFINEx(x, name, ...)					\
@@ -243,8 +221,8 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
  * As the generic SYSCALL_DEFINE0() macro does not decode any parameters for
  * obvious reasons, and passing struct pt_regs *regs to it in %rdi does not
  * hurt, we only need to re-define it here to keep the naming congruent to
- * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() and SYS_NI()
- * macros to work correctly.
+ * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() macro
+ * to work correctly.
  */
 #define SYSCALL_DEFINE0(sname)						\
 	SYSCALL_METADATA(_##sname, 0);					\
@@ -257,10 +235,6 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 	__X64_COND_SYSCALL(name)					\
 	__IA32_COND_SYSCALL(name)
 
-#define SYS_NI(name)							\
-	__X64_SYS_NI(name)						\
-	__IA32_SYS_NI(name)
-
 
 /*
  * For VSYSCALLS, we need to declare these three syscalls with the new
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 7048dfacc04b24..a9088250770f2a 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -100,4 +100,13 @@ static inline void leave_lazy(enum xen_lazy_mode mode)
 
 enum xen_lazy_mode xen_get_lazy_mode(void);
 
+#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI)
+void xen_sanitize_proc_cap_bits(uint32_t *buf);
+#else
+static inline void xen_sanitize_proc_cap_bits(uint32_t *buf)
+{
+	BUG();
+}
+#endif
+
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index d0918a75cb00a0..85a3ce2a3666ad 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -63,6 +63,7 @@ int acpi_fix_pin2_polarity __initdata;
 
 #ifdef CONFIG_X86_LOCAL_APIC
 static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
+static bool has_lapic_cpus __initdata;
 static bool acpi_support_online_capable;
 #endif
 
@@ -233,6 +234,14 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end)
 		return 0;
 
 	/*
+	 * According to https://uefi.org/specs/ACPI/6.5/05_ACPI_Software_Programming_Model.html#processor-local-x2apic-structure
+	 * when MADT provides both valid LAPIC and x2APIC entries, the APIC ID
+	 * in x2APIC must be equal or greater than 0xff.
+	 */
+	if (has_lapic_cpus && apic_id < 0xff)
+		return 0;
+
+	/*
 	 * We need to register disabled CPU as well to permit
 	 * counting disabled CPUs. This allows us to size
 	 * cpus_possible_map more accurately, to permit
@@ -284,6 +293,7 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end)
 			    processor->processor_id, /* ACPI ID */
 			    processor->lapic_flags & ACPI_MADT_ENABLED);
 
+	has_lapic_cpus = true;
 	return 0;
 }
 
@@ -1114,10 +1124,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void)
 
 static int __init acpi_parse_madt_lapic_entries(void)
 {
-	int count;
-	int x2count = 0;
-	int ret;
-	struct acpi_subtable_proc madt_proc[2];
+	int count, x2count = 0;
 
 	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return -ENODEV;
@@ -1126,21 +1133,10 @@ static int __init acpi_parse_madt_lapic_entries(void)
 				      acpi_parse_sapic, MAX_LOCAL_APIC);
 
 	if (!count) {
-		memset(madt_proc, 0, sizeof(madt_proc));
-		madt_proc[0].id = ACPI_MADT_TYPE_LOCAL_APIC;
-		madt_proc[0].handler = acpi_parse_lapic;
-		madt_proc[1].id = ACPI_MADT_TYPE_LOCAL_X2APIC;
-		madt_proc[1].handler = acpi_parse_x2apic;
-		ret = acpi_table_parse_entries_array(ACPI_SIG_MADT,
-				sizeof(struct acpi_table_madt),
-				madt_proc, ARRAY_SIZE(madt_proc), MAX_LOCAL_APIC);
-		if (ret < 0) {
-			pr_err("Error parsing LAPIC/X2APIC entries\n");
-			return ret;
-		}
-
-		count = madt_proc[0].count;
-		x2count = madt_proc[1].count;
+		count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC,
+					acpi_parse_lapic, MAX_LOCAL_APIC);
+		x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC,
+					acpi_parse_x2apic, MAX_LOCAL_APIC);
 	}
 	if (!count && !x2count) {
 		pr_err("No LAPIC entries present\n");
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 73be3931e4f060..aae7456ece0700 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -255,6 +255,16 @@ static void __init_or_module noinline optimize_nops(u8 *instr, size_t len)
 	}
 }
 
+static void __init_or_module noinline optimize_nops_inplace(u8 *instr, size_t len)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	optimize_nops(instr, len);
+	sync_core();
+	local_irq_restore(flags);
+}
+
 /*
  * In this context, "source" is where the instructions are placed in the
  * section .altinstr_replacement, for example during kernel build by the
@@ -438,7 +448,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		 *   patch if feature is *NOT* present.
 		 */
 		if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) {
-			optimize_nops(instr, a->instrlen);
+			optimize_nops_inplace(instr, a->instrlen);
 			continue;
 		}
 
@@ -1685,8 +1695,8 @@ void __init_or_module text_poke_early(void *addr, const void *opcode,
 	} else {
 		local_irq_save(flags);
 		memcpy(addr, opcode, len);
-		local_irq_restore(flags);
 		sync_core();
+		local_irq_restore(flags);
 
 		/*
 		 * Could also do a CLFLUSH here to speed up CPU recovery; but
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a7eab05e5f2977..f322ebd053a91e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1320,6 +1320,9 @@ static void zenbleed_check_cpu(void *unused)
 
 void amd_check_microcode(void)
 {
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+		return;
+
 	on_each_cpu(zenbleed_check_cpu, NULL, 1);
 }
 
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 9373ec01c5ae17..13b45b9c806dae 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -104,8 +104,6 @@ struct cont_desc {
 	size_t		     size;
 };
 
-static u32 ucode_new_rev;
-
 /*
  * Microcode patch container file is prepended to the initrd in cpio
  * format. See Documentation/arch/x86/microcode.rst
@@ -442,12 +440,11 @@ static int __apply_microcode_amd(struct microcode_amd *mc)
  *
  * Returns true if container found (sets @desc), false otherwise.
  */
-static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size)
+static bool early_apply_microcode(u32 cpuid_1_eax, u32 old_rev, void *ucode, size_t size)
 {
 	struct cont_desc desc = { 0 };
 	struct microcode_amd *mc;
 	bool ret = false;
-	u32 rev, dummy;
 
 	desc.cpuid_1_eax = cpuid_1_eax;
 
@@ -457,22 +454,15 @@ static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size)
 	if (!mc)
 		return ret;
 
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
 	/*
 	 * Allow application of the same revision to pick up SMT-specific
 	 * changes even if the revision of the other SMT thread is already
 	 * up-to-date.
 	 */
-	if (rev > mc->hdr.patch_id)
+	if (old_rev > mc->hdr.patch_id)
 		return ret;
 
-	if (!__apply_microcode_amd(mc)) {
-		ucode_new_rev = mc->hdr.patch_id;
-		ret = true;
-	}
-
-	return ret;
+	return !__apply_microcode_amd(mc);
 }
 
 static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
@@ -506,9 +496,12 @@ static void __init find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpi
 	*ret = cp;
 }
 
-void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax)
+void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_eax)
 {
 	struct cpio_data cp = { };
+	u32 dummy;
+
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->old_rev, dummy);
 
 	/* Needed in load_microcode_amd() */
 	ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax;
@@ -517,7 +510,8 @@ void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax)
 	if (!(cp.data && cp.size))
 		return;
 
-	early_apply_microcode(cpuid_1_eax, cp.data, cp.size);
+	if (early_apply_microcode(cpuid_1_eax, ed->old_rev, cp.data, cp.size))
+		native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
 }
 
 static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
@@ -625,10 +619,8 @@ void reload_ucode_amd(unsigned int cpu)
 	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
 
 	if (rev < mc->hdr.patch_id) {
-		if (!__apply_microcode_amd(mc)) {
-			ucode_new_rev = mc->hdr.patch_id;
-			pr_info("reload patch_level=0x%08x\n", ucode_new_rev);
-		}
+		if (!__apply_microcode_amd(mc))
+			pr_info_once("reload revision: 0x%08x\n", mc->hdr.patch_id);
 	}
 }
 
@@ -649,8 +641,6 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 	if (p && (p->patch_id == csig->rev))
 		uci->mc = p->data;
 
-	pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
-
 	return 0;
 }
 
@@ -691,8 +681,6 @@ static enum ucode_state apply_microcode_amd(int cpu)
 	rev = mc_amd->hdr.patch_id;
 	ret = UCODE_UPDATED;
 
-	pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev);
-
 out:
 	uci->cpu_sig.rev = rev;
 	c->microcode	 = rev;
@@ -935,11 +923,6 @@ struct microcode_ops * __init init_amd_microcode(void)
 		pr_warn("AMD CPU family 0x%x not supported\n", c->x86);
 		return NULL;
 	}
-
-	if (ucode_new_rev)
-		pr_info_once("microcode updated early to new patch_level=0x%08x\n",
-			     ucode_new_rev);
-
 	return &microcode_amd_ops;
 }
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 666d25bbc5ad20..232026a239a681 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -41,8 +41,6 @@
 
 #include "internal.h"
 
-#define DRIVER_VERSION	"2.2"
-
 static struct microcode_ops	*microcode_ops;
 bool dis_ucode_ldr = true;
 
@@ -77,6 +75,8 @@ static u32 final_levels[] = {
 	0, /* T-101 terminator */
 };
 
+struct early_load_data early_data;
+
 /*
  * Check the current patch level on this CPU.
  *
@@ -155,9 +155,9 @@ void __init load_ucode_bsp(void)
 		return;
 
 	if (intel)
-		load_ucode_intel_bsp();
+		load_ucode_intel_bsp(&early_data);
 	else
-		load_ucode_amd_bsp(cpuid_1_eax);
+		load_ucode_amd_bsp(&early_data, cpuid_1_eax);
 }
 
 void load_ucode_ap(void)
@@ -828,6 +828,11 @@ static int __init microcode_init(void)
 	if (!microcode_ops)
 		return -ENODEV;
 
+	pr_info_once("Current revision: 0x%08x\n", (early_data.new_rev ?: early_data.old_rev));
+
+	if (early_data.new_rev)
+		pr_info_once("Updated early from: 0x%08x\n", early_data.old_rev);
+
 	microcode_pdev = platform_device_register_simple("microcode", -1, NULL, 0);
 	if (IS_ERR(microcode_pdev))
 		return PTR_ERR(microcode_pdev);
@@ -846,8 +851,6 @@ static int __init microcode_init(void)
 	cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/microcode:online",
 			  mc_cpu_online, mc_cpu_down_prep);
 
-	pr_info("Microcode Update Driver: v%s.", DRIVER_VERSION);
-
 	return 0;
 
  out_pdev:
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 6024feb98d29db..070426b9895fed 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -339,16 +339,9 @@ static enum ucode_state __apply_microcode(struct ucode_cpu_info *uci,
 static enum ucode_state apply_microcode_early(struct ucode_cpu_info *uci)
 {
 	struct microcode_intel *mc = uci->mc;
-	enum ucode_state ret;
-	u32 cur_rev, date;
+	u32 cur_rev;
 
-	ret = __apply_microcode(uci, mc, &cur_rev);
-	if (ret == UCODE_UPDATED) {
-		date = mc->hdr.date;
-		pr_info_once("updated early: 0x%x -> 0x%x, date = %04x-%02x-%02x\n",
-			     cur_rev, mc->hdr.rev, date & 0xffff, date >> 24, (date >> 16) & 0xff);
-	}
-	return ret;
+	return __apply_microcode(uci, mc, &cur_rev);
 }
 
 static __init bool load_builtin_intel_microcode(struct cpio_data *cp)
@@ -413,13 +406,17 @@ static int __init save_builtin_microcode(void)
 early_initcall(save_builtin_microcode);
 
 /* Load microcode on BSP from initrd or builtin blobs */
-void __init load_ucode_intel_bsp(void)
+void __init load_ucode_intel_bsp(struct early_load_data *ed)
 {
 	struct ucode_cpu_info uci;
 
+	ed->old_rev = intel_get_microcode_revision();
+
 	uci.mc = get_microcode_blob(&uci, false);
 	if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED)
 		ucode_patch_va = UCODE_BSP_LOADED;
+
+	ed->new_rev = uci.cpu_sig.rev;
 }
 
 void load_ucode_intel_ap(void)
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index f8047b12329a97..21776c529fa97a 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -37,6 +37,12 @@ struct microcode_ops {
 				use_nmi		: 1;
 };
 
+struct early_load_data {
+	u32 old_rev;
+	u32 new_rev;
+};
+
+extern struct early_load_data early_data;
 extern struct ucode_cpu_info ucode_cpu_info[];
 struct cpio_data find_microcode_in_initrd(const char *path);
 
@@ -92,14 +98,14 @@ extern bool dis_ucode_ldr;
 extern bool force_minrev;
 
 #ifdef CONFIG_CPU_SUP_AMD
-void load_ucode_amd_bsp(unsigned int family);
+void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family);
 void load_ucode_amd_ap(unsigned int family);
 int save_microcode_in_initrd_amd(unsigned int family);
 void reload_ucode_amd(unsigned int cpu);
 struct microcode_ops *init_amd_microcode(void);
 void exit_amd_microcode(void);
 #else /* CONFIG_CPU_SUP_AMD */
-static inline void load_ucode_amd_bsp(unsigned int family) { }
+static inline void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family) { }
 static inline void load_ucode_amd_ap(unsigned int family) { }
 static inline int save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
 static inline void reload_ucode_amd(unsigned int cpu) { }
@@ -108,12 +114,12 @@ static inline void exit_amd_microcode(void) { }
 #endif /* !CONFIG_CPU_SUP_AMD */
 
 #ifdef CONFIG_CPU_SUP_INTEL
-void load_ucode_intel_bsp(void);
+void load_ucode_intel_bsp(struct early_load_data *ed);
 void load_ucode_intel_ap(void);
 void reload_ucode_intel(void);
 struct microcode_ops *init_intel_microcode(void);
 #else /* CONFIG_CPU_SUP_INTEL */
-static inline void load_ucode_intel_bsp(void) { }
+static inline void load_ucode_intel_bsp(struct early_load_data *ed) { }
 static inline void load_ucode_intel_ap(void) { }
 static inline void reload_ucode_intel(void) { }
 static inline struct microcode_ops *init_intel_microcode(void) { return NULL; }
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index e6bba12c759cb7..01fa06dd06b66c 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -262,11 +262,14 @@ static uint32_t  __init ms_hyperv_platform(void)
 static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs)
 {
 	static atomic_t nmi_cpu = ATOMIC_INIT(-1);
+	unsigned int old_cpu, this_cpu;
 
 	if (!unknown_nmi_panic)
 		return NMI_DONE;
 
-	if (atomic_cmpxchg(&nmi_cpu, -1, raw_smp_processor_id()) != -1)
+	old_cpu = -1;
+	this_cpu = raw_smp_processor_id();
+	if (!atomic_try_cmpxchg(&nmi_cpu, &old_cpu, this_cpu))
 		return NMI_HANDLED;
 
 	return NMI_DONE;
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 086a2c3aaaa044..0f8103240fda31 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -255,6 +255,22 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	testl	$X2APIC_ENABLE, %eax
 	jnz	.Lread_apicid_msr
 
+#ifdef CONFIG_X86_X2APIC
+	/*
+	 * If system is in X2APIC mode then MMIO base might not be
+	 * mapped causing the MMIO read below to fault. Faults can't
+	 * be handled at that point.
+	 */
+	cmpl	$0, x2apic_mode(%rip)
+	jz	.Lread_apicid_mmio
+
+	/* Force the AP into X2APIC mode. */
+	orl	$X2APIC_ENABLE, %eax
+	wrmsr
+	jmp	.Lread_apicid_msr
+#endif
+
+.Lread_apicid_mmio:
 	/* Read the APIC ID from the fix-mapped MMIO space. */
 	movq	apic_mmio_base(%rip), %rcx
 	addq	$APIC_ID, %rcx
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 8857abc706e469..660b601f1d6c33 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -121,7 +121,7 @@ static const __initconst struct idt_data def_idts[] = {
 
 static const struct idt_data ia32_idt[] __initconst = {
 #if defined(CONFIG_IA32_EMULATION)
-	SYSG(IA32_SYSCALL_VECTOR,	entry_INT80_compat),
+	SYSG(IA32_SYSCALL_VECTOR,	asm_int80_emulation),
 #elif defined(CONFIG_X86_32)
 	SYSG(IA32_SYSCALL_VECTOR,	entry_INT80_32),
 #endif
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 70472eebe71960..c67285824e8267 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -1234,10 +1234,6 @@ void setup_ghcb(void)
 	if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
 		return;
 
-	/* First make sure the hypervisor talks a supported protocol. */
-	if (!sev_es_negotiate_protocol())
-		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-
 	/*
 	 * Check whether the runtime #VC exception handler is active. It uses
 	 * the per-CPU GHCB page which is set up by sev_es_init_vc_handling().
@@ -1255,6 +1251,13 @@ void setup_ghcb(void)
 	}
 
 	/*
+	 * Make sure the hypervisor talks a supported protocol.
+	 * This gets called only in the BSP boot phase.
+	 */
+	if (!sev_es_negotiate_protocol())
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+
+	/*
 	 * Clear the boot_ghcb. The first exception comes in before the bss
 	 * section is cleared.
 	 */
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index cacf2ede62175d..23d8aaf8d9fd19 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -175,9 +175,6 @@ int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
 	frame = get_sigframe(ksig, regs, sizeof(struct rt_sigframe), &fp);
 	uc_flags = frame_uc_flags(regs);
 
-	if (setup_signal_shadow_stack(ksig))
-		return -EFAULT;
-
 	if (!user_access_begin(frame, sizeof(*frame)))
 		return -EFAULT;
 
@@ -198,6 +195,9 @@ int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
 			return -EFAULT;
 	}
 
+	if (setup_signal_shadow_stack(ksig))
+		return -EFAULT;
+
 	/* Set up registers for signal handler */
 	regs->di = ksig->sig;
 	/* In case the signal handler was declared without prototypes */
diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index ee8c4c3496edd0..eea6ea7f14af98 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -182,6 +182,7 @@ static int kvm_mmu_rmaps_stat_release(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations mmu_rmaps_stat_fops = {
+	.owner		= THIS_MODULE,
 	.open		= kvm_mmu_rmaps_stat_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 4900c078045acc..6ee925d6664846 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2972,6 +2972,25 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
 
 		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux);
 	}
+
+	/*
+	 * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if
+	 * the host/guest supports its use.
+	 *
+	 * guest_can_use() checks a number of requirements on the host/guest to
+	 * ensure that MSR_IA32_XSS is available, but it might report true even
+	 * if X86_FEATURE_XSAVES isn't configured in the guest to ensure host
+	 * MSR_IA32_XSS is always properly restored. For SEV-ES, it is better
+	 * to further check that the guest CPUID actually supports
+	 * X86_FEATURE_XSAVES so that accesses to MSR_IA32_XSS by misbehaved
+	 * guests will still get intercepted and caught in the normal
+	 * kvm_emulate_rdmsr()/kvm_emulated_wrmsr() paths.
+	 */
+	if (guest_can_use(vcpu, X86_FEATURE_XSAVES) &&
+	    guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1);
+	else
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0);
 }
 
 void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7121463123584c..a8bd4e909a1e69 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -103,6 +103,7 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTTOIP,		.always = false },
+	{ .index = MSR_IA32_XSS,			.always = false },
 	{ .index = MSR_EFER,				.always = false },
 	{ .index = MSR_IA32_CR_PAT,			.always = false },
 	{ .index = MSR_AMD64_SEV_ES_GHCB,		.always = true  },
@@ -1855,15 +1856,17 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	bool old_paging = is_paging(vcpu);
 
 #ifdef CONFIG_X86_64
-	if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) {
+	if (vcpu->arch.efer & EFER_LME) {
 		if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
 			vcpu->arch.efer |= EFER_LMA;
-			svm->vmcb->save.efer |= EFER_LMA | EFER_LME;
+			if (!vcpu->arch.guest_state_protected)
+				svm->vmcb->save.efer |= EFER_LMA | EFER_LME;
 		}
 
 		if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) {
 			vcpu->arch.efer &= ~EFER_LMA;
-			svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME);
+			if (!vcpu->arch.guest_state_protected)
+				svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME);
 		}
 	}
 #endif
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index be67ab7fdd104e..c409f934c377fc 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -30,7 +30,7 @@
 #define	IOPM_SIZE PAGE_SIZE * 3
 #define	MSRPM_SIZE PAGE_SIZE * 2
 
-#define MAX_DIRECT_ACCESS_MSRS	46
+#define MAX_DIRECT_ACCESS_MSRS	47
 #define MSRPM_OFFSETS	32
 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2c924075f6f112..1a3aaa7dafae44 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5518,8 +5518,8 @@ static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
 static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 					 struct kvm_xsave *guest_xsave)
 {
-	return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
-					     sizeof(guest_xsave->region));
+	kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
+				      sizeof(guest_xsave->region));
 }
 
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
@@ -13031,7 +13031,10 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.guest_state_protected)
 		return true;
 
-	return vcpu->arch.preempted_in_kernel;
+	if (vcpu != kvm_get_running_vcpu())
+		return vcpu->arch.preempted_in_kernel;
+
+	return static_call(kvm_x86_get_cpl)(vcpu) == 0;
 }
 
 unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index a68f2dda0948c2..70b91de2e053ab 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -32,6 +32,7 @@
 #include <asm/msr.h>
 #include <asm/cmdline.h>
 #include <asm/sev.h>
+#include <asm/ia32.h>
 
 #include "mm_internal.h"
 
@@ -481,6 +482,16 @@ void __init sme_early_init(void)
 	 */
 	if (sev_status & MSR_AMD64_SEV_ES_ENABLED)
 		x86_cpuinit.parallel_bringup = false;
+
+	/*
+	 * The VMM is capable of injecting interrupt 0x80 and triggering the
+	 * compatibility syscall path.
+	 *
+	 * By default, the 32-bit emulation is disabled in order to ensure
+	 * the safety of the VM.
+	 */
+	if (sev_status & MSR_AMD64_SEV_ENABLED)
+		ia32_disable();
 }
 
 void __init mem_encrypt_free_decrypted_mem(void)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 8c10d9abc2394f..e89e415aa74353 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -3025,3 +3025,49 @@ void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp
 #endif
 	WARN(1, "verification of programs using bpf_throw should have failed\n");
 }
+
+void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+			       struct bpf_prog *new, struct bpf_prog *old)
+{
+	u8 *old_addr, *new_addr, *old_bypass_addr;
+	int ret;
+
+	old_bypass_addr = old ? NULL : poke->bypass_addr;
+	old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
+	new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
+
+	/*
+	 * On program loading or teardown, the program's kallsym entry
+	 * might not be in place, so we use __bpf_arch_text_poke to skip
+	 * the kallsyms check.
+	 */
+	if (new) {
+		ret = __bpf_arch_text_poke(poke->tailcall_target,
+					   BPF_MOD_JUMP,
+					   old_addr, new_addr);
+		BUG_ON(ret < 0);
+		if (!old) {
+			ret = __bpf_arch_text_poke(poke->tailcall_bypass,
+						   BPF_MOD_JUMP,
+						   poke->bypass_addr,
+						   NULL);
+			BUG_ON(ret < 0);
+		}
+	} else {
+		ret = __bpf_arch_text_poke(poke->tailcall_bypass,
+					   BPF_MOD_JUMP,
+					   old_bypass_addr,
+					   poke->bypass_addr);
+		BUG_ON(ret < 0);
+		/* let other CPUs finish the execution of program
+		 * so that it will not possible to expose them
+		 * to invalid nop, stack unwind, nop state
+		 */
+		if (!ret)
+			synchronize_rcu();
+		ret = __bpf_arch_text_poke(poke->tailcall_target,
+					   BPF_MOD_JUMP,
+					   old_addr, NULL);
+		BUG_ON(ret < 0);
+	}
+}
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 9b1ec5d8c99c8d..a65fc2ae15b496 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -9,6 +9,7 @@ config XEN
 	select PARAVIRT_CLOCK
 	select X86_HV_CALLBACK_VECTOR
 	depends on X86_64 || (X86_32 && X86_PAE)
+	depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MCORE2 || MATOM || MK8)
 	depends on X86_LOCAL_APIC && X86_TSC
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0337392a312141..3c61bb98c10e28 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -33,9 +33,12 @@ EXPORT_SYMBOL_GPL(hypercall_page);
  * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info
  * but during boot it is switched to point to xen_vcpu_info.
  * The pointer is used in xen_evtchn_do_upcall to acknowledge pending events.
+ * Make sure that xen_vcpu_info doesn't cross a page boundary by making it
+ * cache-line aligned (the struct is guaranteed to have a size of 64 bytes,
+ * which matches the cache line size of 64-bit x86 processors).
  */
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
-DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
+DEFINE_PER_CPU_ALIGNED(struct vcpu_info, xen_vcpu_info);
 
 /* Linux <-> Xen vCPU id mapping */
 DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
@@ -160,6 +163,7 @@ void xen_vcpu_setup(int cpu)
 	int err;
 	struct vcpu_info *vcpup;
 
+	BUILD_BUG_ON(sizeof(*vcpup) > SMP_CACHE_BYTES);
 	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
 
 	/*
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index bbbfdd495ebd3a..aeb33e0a3f7633 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -704,7 +704,7 @@ static struct trap_array_entry trap_array[] = {
 	TRAP_ENTRY(exc_int3,				false ),
 	TRAP_ENTRY(exc_overflow,			false ),
 #ifdef CONFIG_IA32_EMULATION
-	{ entry_INT80_compat,          xen_entry_INT80_compat,          false },
+	TRAP_ENTRY(int80_emulation,			false ),
 #endif
 	TRAP_ENTRY(exc_page_fault,			false ),
 	TRAP_ENTRY(exc_divide_error,			false ),
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 9e5e680087853a..1a9cd18dfbd312 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -156,7 +156,7 @@ xen_pv_trap asm_xenpv_exc_machine_check
 #endif /* CONFIG_X86_MCE */
 xen_pv_trap asm_exc_simd_coprocessor_error
 #ifdef CONFIG_IA32_EMULATION
-xen_pv_trap entry_INT80_compat
+xen_pv_trap asm_int80_emulation
 #endif
 xen_pv_trap asm_exc_xen_unknown_trap
 xen_pv_trap asm_exc_xen_hypervisor_callback
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 408a2aa66c6922..a87ab36889e76c 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -21,7 +21,7 @@ extern void *xen_initial_gdt;
 struct trap_info;
 void xen_copy_trap_info(struct trap_info *traps);
 
-DECLARE_PER_CPU(struct vcpu_info, xen_vcpu_info);
+DECLARE_PER_CPU_ALIGNED(struct vcpu_info, xen_vcpu_info);
 DECLARE_PER_CPU(unsigned long, xen_cr3);
 DECLARE_PER_CPU(unsigned long, xen_current_cr3);
 
diff --git a/block/bdev.c b/block/bdev.c
index e4cfb7adb64581..750aec178b6abf 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -425,6 +425,8 @@ void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 
 void bdev_add(struct block_device *bdev, dev_t dev)
 {
+	if (bdev_stable_writes(bdev))
+		mapping_set_stable_writes(bdev->bd_inode->i_mapping);
 	bdev->bd_dev = dev;
 	bdev->bd_inode->i_rdev = dev;
 	bdev->bd_inode->i_ino = dev;
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4a42ea2972ad85..4b48c2c4409813 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -577,6 +577,7 @@ static void blkg_destroy_all(struct gendisk *disk)
 	struct request_queue *q = disk->queue;
 	struct blkcg_gq *blkg, *n;
 	int count = BLKG_DESTROY_BATCH_SIZE;
+	int i;
 
 restart:
 	spin_lock_irq(&q->queue_lock);
@@ -602,6 +603,18 @@ restart:
 		}
 	}
 
+	/*
+	 * Mark policy deactivated since policy offline has been done, and
+	 * the free is scheduled, so future blkcg_deactivate_policy() can
+	 * be bypassed
+	 */
+	for (i = 0; i < BLKCG_MAX_POLS; i++) {
+		struct blkcg_policy *pol = blkcg_policy[i];
+
+		if (pol)
+			__clear_bit(pol->plid, q->blkcg_pols);
+	}
+
 	q->root_blkg = NULL;
 	spin_unlock_irq(&q->queue_lock);
 }
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 624c03c8fe64e3..fd482439afbc9a 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -249,8 +249,6 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
 {
 	struct blkcg_gq *blkg;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
-
 	if (blkcg == &blkcg_root)
 		return q->root_blkg;
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 9d51e9894ece78..2eca76ccf4ee01 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -501,9 +501,17 @@ static inline void bio_check_ro(struct bio *bio)
 	if (op_is_write(bio_op(bio)) && bdev_read_only(bio->bi_bdev)) {
 		if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
 			return;
+
+		if (bio->bi_bdev->bd_ro_warned)
+			return;
+
+		bio->bi_bdev->bd_ro_warned = true;
+		/*
+		 * Use ioctl to set underlying disk of raid/dm to read-only
+		 * will trigger this.
+		 */
 		pr_warn("Trying to write to read-only block-device %pg\n",
 			bio->bi_bdev);
-		/* Older lvm-tools actually trigger this */
 	}
 }
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e2d11183f62e37..ac18f802c027ea 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1512,14 +1512,26 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q,
 }
 EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
 
+static bool blk_is_flush_data_rq(struct request *rq)
+{
+	return (rq->rq_flags & RQF_FLUSH_SEQ) && !is_flush_rq(rq);
+}
+
 static bool blk_mq_rq_inflight(struct request *rq, void *priv)
 {
 	/*
 	 * If we find a request that isn't idle we know the queue is busy
 	 * as it's checked in the iter.
 	 * Return false to stop the iteration.
+	 *
+	 * In case of queue quiesce, if one flush data request is completed,
+	 * don't count it as inflight given the flush sequence is suspended,
+	 * and the original flush data request is invisible to driver, just
+	 * like other pending requests because of quiesce
 	 */
-	if (blk_mq_request_started(rq)) {
+	if (blk_mq_request_started(rq) && !(blk_queue_quiesced(rq->q) &&
+				blk_is_flush_data_rq(rq) &&
+				blk_mq_request_completed(rq))) {
 		bool *busy = priv;
 
 		*busy = true;
@@ -2858,11 +2870,8 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	};
 	struct request *rq;
 
-	if (unlikely(bio_queue_enter(bio)))
-		return NULL;
-
 	if (blk_mq_attempt_bio_merge(q, bio, nsegs))
-		goto queue_exit;
+		return NULL;
 
 	rq_qos_throttle(q, bio);
 
@@ -2878,35 +2887,23 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	rq_qos_cleanup(q, bio);
 	if (bio->bi_opf & REQ_NOWAIT)
 		bio_wouldblock_error(bio);
-queue_exit:
-	blk_queue_exit(q);
 	return NULL;
 }
 
-static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
-		struct blk_plug *plug, struct bio **bio, unsigned int nsegs)
+/* return true if this @rq can be used for @bio */
+static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug,
+		struct bio *bio)
 {
-	struct request *rq;
-	enum hctx_type type, hctx_type;
+	enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf);
+	enum hctx_type hctx_type = rq->mq_hctx->type;
 
-	if (!plug)
-		return NULL;
-	rq = rq_list_peek(&plug->cached_rq);
-	if (!rq || rq->q != q)
-		return NULL;
-
-	if (blk_mq_attempt_bio_merge(q, *bio, nsegs)) {
-		*bio = NULL;
-		return NULL;
-	}
+	WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq);
 
-	type = blk_mq_get_hctx_type((*bio)->bi_opf);
-	hctx_type = rq->mq_hctx->type;
 	if (type != hctx_type &&
 	    !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT))
-		return NULL;
-	if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf))
-		return NULL;
+		return false;
+	if (op_is_flush(rq->cmd_flags) != op_is_flush(bio->bi_opf))
+		return false;
 
 	/*
 	 * If any qos ->throttle() end up blocking, we will have flushed the
@@ -2914,12 +2911,12 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
 	 * before we throttle.
 	 */
 	plug->cached_rq = rq_list_next(rq);
-	rq_qos_throttle(q, *bio);
+	rq_qos_throttle(rq->q, bio);
 
 	blk_mq_rq_time_init(rq, 0);
-	rq->cmd_flags = (*bio)->bi_opf;
+	rq->cmd_flags = bio->bi_opf;
 	INIT_LIST_HEAD(&rq->queuelist);
-	return rq;
+	return true;
 }
 
 static void bio_set_ioprio(struct bio *bio)
@@ -2949,7 +2946,7 @@ void blk_mq_submit_bio(struct bio *bio)
 	struct blk_plug *plug = blk_mq_plug(bio);
 	const int is_sync = op_is_sync(bio->bi_opf);
 	struct blk_mq_hw_ctx *hctx;
-	struct request *rq;
+	struct request *rq = NULL;
 	unsigned int nr_segs = 1;
 	blk_status_t ret;
 
@@ -2960,20 +2957,36 @@ void blk_mq_submit_bio(struct bio *bio)
 			return;
 	}
 
-	if (!bio_integrity_prep(bio))
-		return;
-
 	bio_set_ioprio(bio);
 
-	rq = blk_mq_get_cached_request(q, plug, &bio, nr_segs);
-	if (!rq) {
-		if (!bio)
+	if (plug) {
+		rq = rq_list_peek(&plug->cached_rq);
+		if (rq && rq->q != q)
+			rq = NULL;
+	}
+	if (rq) {
+		if (!bio_integrity_prep(bio))
 			return;
-		rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
-		if (unlikely(!rq))
+		if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
 			return;
+		if (blk_mq_can_use_cached_rq(rq, plug, bio))
+			goto done;
+		percpu_ref_get(&q->q_usage_counter);
+	} else {
+		if (unlikely(bio_queue_enter(bio)))
+			return;
+		if (!bio_integrity_prep(bio))
+			goto fail;
 	}
 
+	rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
+	if (unlikely(!rq)) {
+fail:
+		blk_queue_exit(q);
+		return;
+	}
+
+done:
 	trace_block_getrq(bio);
 
 	rq_qos_track(q, rq, bio);
diff --git a/block/blk-pm.c b/block/blk-pm.c
index 6b72b2e03fc8a8..42e8420747153b 100644
--- a/block/blk-pm.c
+++ b/block/blk-pm.c
@@ -163,39 +163,16 @@ EXPORT_SYMBOL(blk_pre_runtime_resume);
  * @q: the queue of the device
  *
  * Description:
- *    For historical reasons, this routine merely calls blk_set_runtime_active()
- *    to do the real work of restarting the queue.  It does this regardless of
- *    whether the device's runtime-resume succeeded; even if it failed the
+ *    Restart the queue of a runtime suspended device. It does this regardless
+ *    of whether the device's runtime-resume succeeded; even if it failed the
  *    driver or error handler will need to communicate with the device.
  *
  *    This function should be called near the end of the device's
- *    runtime_resume callback.
+ *    runtime_resume callback to correct queue runtime PM status and re-enable
+ *    peeking requests from the queue.
  */
 void blk_post_runtime_resume(struct request_queue *q)
 {
-	blk_set_runtime_active(q);
-}
-EXPORT_SYMBOL(blk_post_runtime_resume);
-
-/**
- * blk_set_runtime_active - Force runtime status of the queue to be active
- * @q: the queue of the device
- *
- * If the device is left runtime suspended during system suspend the resume
- * hook typically resumes the device and corrects runtime status
- * accordingly. However, that does not affect the queue runtime PM status
- * which is still "suspended". This prevents processing requests from the
- * queue.
- *
- * This function can be used in driver's resume hook to correct queue
- * runtime PM status and re-enable peeking requests from the queue. It
- * should be called before first request is added to the queue.
- *
- * This function is also called by blk_post_runtime_resume() for
- * runtime resumes.  It does everything necessary to restart the queue.
- */
-void blk_set_runtime_active(struct request_queue *q)
-{
 	int old_status;
 
 	if (!q->dev)
@@ -211,4 +188,4 @@ void blk_set_runtime_active(struct request_queue *q)
 	if (old_status != RPM_ACTIVE)
 		blk_clear_pm_only(q);
 }
-EXPORT_SYMBOL(blk_set_runtime_active);
+EXPORT_SYMBOL(blk_post_runtime_resume);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 63e4812623361d..0b2d0476632407 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -615,6 +615,7 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 QUEUE_RW_ENTRY(queue_wb_lat, "wbt_lat_usec");
 #endif
 
+/* Common attributes for bio-based and request-based queues. */
 static struct attribute *queue_attrs[] = {
 	&queue_ra_entry.attr,
 	&queue_max_hw_sectors_entry.attr,
@@ -659,6 +660,7 @@ static struct attribute *queue_attrs[] = {
 	NULL,
 };
 
+/* Request-based queue attributes that are not relevant for bio-based queues. */
 static struct attribute *blk_mq_queue_attrs[] = {
 	&queue_requests_entry.attr,
 	&elv_iosched_entry.attr,
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 13e4377a8b2865..16f5766620a410 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1320,6 +1320,7 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global)
 		   tg_bps_limit(tg, READ), tg_bps_limit(tg, WRITE),
 		   tg_iops_limit(tg, READ), tg_iops_limit(tg, WRITE));
 
+	rcu_read_lock();
 	/*
 	 * Update has_rules[] flags for the updated tg's subtree.  A tg is
 	 * considered to have rules if either the tg itself or any of its
@@ -1347,6 +1348,7 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global)
 		this_tg->latency_target = max(this_tg->latency_target,
 				parent_tg->latency_target);
 	}
+	rcu_read_unlock();
 
 	/*
 	 * We're already holding queue_lock and know @tg is valid.  Let's
diff --git a/crypto/Kconfig b/crypto/Kconfig
index bbf51d55724e3f..70661f58ee41c4 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1297,10 +1297,12 @@ config CRYPTO_JITTERENTROPY
 
 	  See https://www.chronox.de/jent.html
 
+if CRYPTO_JITTERENTROPY
+if CRYPTO_FIPS && EXPERT
+
 choice
 	prompt "CPU Jitter RNG Memory Size"
 	default CRYPTO_JITTERENTROPY_MEMSIZE_2
-	depends on CRYPTO_JITTERENTROPY
 	help
 	  The Jitter RNG measures the execution time of memory accesses.
 	  Multiple consecutive memory accesses are performed. If the memory
@@ -1344,7 +1346,6 @@ config CRYPTO_JITTERENTROPY_OSR
 	int "CPU Jitter RNG Oversampling Rate"
 	range 1 15
 	default 1
-	depends on CRYPTO_JITTERENTROPY
 	help
 	  The Jitter RNG allows the specification of an oversampling rate (OSR).
 	  The Jitter RNG operation requires a fixed amount of timing
@@ -1359,7 +1360,6 @@ config CRYPTO_JITTERENTROPY_OSR
 
 config CRYPTO_JITTERENTROPY_TESTINTERFACE
 	bool "CPU Jitter RNG Test Interface"
-	depends on CRYPTO_JITTERENTROPY
 	help
 	  The test interface allows a privileged process to capture
 	  the raw unconditioned high resolution time stamp noise that
@@ -1377,6 +1377,28 @@ config CRYPTO_JITTERENTROPY_TESTINTERFACE
 
 	  If unsure, select N.
 
+endif	# if CRYPTO_FIPS && EXPERT
+
+if !(CRYPTO_FIPS && EXPERT)
+
+config CRYPTO_JITTERENTROPY_MEMORY_BLOCKS
+	int
+	default 64
+
+config CRYPTO_JITTERENTROPY_MEMORY_BLOCKSIZE
+	int
+	default 32
+
+config CRYPTO_JITTERENTROPY_OSR
+	int
+	default 1
+
+config CRYPTO_JITTERENTROPY_TESTINTERFACE
+	bool
+
+endif	# if !(CRYPTO_FIPS && EXPERT)
+endif	# if CRYPTO_JITTERENTROPY
+
 config CRYPTO_KDF800108_CTR
 	tristate
 	select CRYPTO_HMAC
diff --git a/crypto/ahash.c b/crypto/ahash.c
index deee55f939dc8c..80c3e5354711e1 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -651,6 +651,7 @@ struct crypto_ahash *crypto_clone_ahash(struct crypto_ahash *hash)
 			err = PTR_ERR(shash);
 			goto out_free_nhash;
 		}
+		nhash->using_shash = true;
 		*nctx = shash;
 		return nhash;
 	}
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 9826907eb06e14..7bdad836fc6207 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -135,8 +135,6 @@ source "drivers/uio/Kconfig"
 
 source "drivers/vfio/Kconfig"
 
-source "drivers/vlynq/Kconfig"
-
 source "drivers/virt/Kconfig"
 
 source "drivers/virtio/Kconfig"
diff --git a/drivers/Makefile b/drivers/Makefile
index 722d15be0eb7fd..d828329c268da3 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -151,7 +151,6 @@ obj-$(CONFIG_BCMA)		+= bcma/
 obj-$(CONFIG_VHOST_RING)	+= vhost/
 obj-$(CONFIG_VHOST_IOTLB)	+= vhost/
 obj-$(CONFIG_VHOST)		+= vhost/
-obj-$(CONFIG_VLYNQ)		+= vlynq/
 obj-$(CONFIG_GREYBUS)		+= greybus/
 obj-$(CONFIG_COMEDI)		+= comedi/
 obj-$(CONFIG_STAGING)		+= staging/
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 5c0246b9e52287..d530384f8d6070 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -53,10 +53,12 @@
 
 #define ICB_0_1_IRQ_MASK ((((u64)ICB_1_IRQ_MASK) << 32) | ICB_0_IRQ_MASK)
 
-#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE)) | \
-			   (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \
+#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \
 			   (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, UFI_ERR)))
 
+#define BUTTRESS_ALL_IRQ_MASK (BUTTRESS_IRQ_MASK | \
+			       (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE)))
+
 #define BUTTRESS_IRQ_ENABLE_MASK ((u32)~BUTTRESS_IRQ_MASK)
 #define BUTTRESS_IRQ_DISABLE_MASK ((u32)-1)
 
@@ -74,8 +76,12 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev)
 	vdev->wa.clear_runtime_mem = false;
 	vdev->wa.d3hot_after_power_off = true;
 
-	if (ivpu_device_id(vdev) == PCI_DEVICE_ID_MTL && ivpu_revision(vdev) < 4)
+	REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, BUTTRESS_ALL_IRQ_MASK);
+	if (REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) == BUTTRESS_ALL_IRQ_MASK) {
+		/* Writing 1s does not clear the interrupt status register */
 		vdev->wa.interrupt_clear_with_0 = true;
+		REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, 0x0);
+	}
 
 	IVPU_PRINT_WA(punit_disabled);
 	IVPU_PRINT_WA(clear_runtime_mem);
@@ -502,6 +508,16 @@ static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev)
 	return ret;
 }
 
+static int ivpu_boot_pwr_domain_disable(struct ivpu_device *vdev)
+{
+	ivpu_boot_dpu_active_drive(vdev, false);
+	ivpu_boot_pwr_island_isolation_drive(vdev, true);
+	ivpu_boot_pwr_island_trickle_drive(vdev, false);
+	ivpu_boot_pwr_island_drive(vdev, false);
+
+	return ivpu_boot_wait_for_pwr_island_status(vdev, 0x0);
+}
+
 static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 {
 	u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
@@ -600,25 +616,17 @@ static int ivpu_hw_37xx_info_init(struct ivpu_device *vdev)
 
 static int ivpu_hw_37xx_reset(struct ivpu_device *vdev)
 {
-	int ret;
-	u32 val;
-
-	if (IVPU_WA(punit_disabled))
-		return 0;
+	int ret = 0;
 
-	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
-	if (ret) {
-		ivpu_err(vdev, "Timed out waiting for TRIGGER bit\n");
-		return ret;
+	if (ivpu_boot_pwr_domain_disable(vdev)) {
+		ivpu_err(vdev, "Failed to disable power domain\n");
+		ret = -EIO;
 	}
 
-	val = REGB_RD32(VPU_37XX_BUTTRESS_VPU_IP_RESET);
-	val = REG_SET_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, val);
-	REGB_WR32(VPU_37XX_BUTTRESS_VPU_IP_RESET, val);
-
-	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
-	if (ret)
-		ivpu_err(vdev, "Timed out waiting for RESET completion\n");
+	if (ivpu_pll_disable(vdev)) {
+		ivpu_err(vdev, "Failed to disable PLL\n");
+		ret = -EIO;
+	}
 
 	return ret;
 }
@@ -651,10 +659,6 @@ static int ivpu_hw_37xx_power_up(struct ivpu_device *vdev)
 {
 	int ret;
 
-	ret = ivpu_hw_37xx_reset(vdev);
-	if (ret)
-		ivpu_warn(vdev, "Failed to reset HW: %d\n", ret);
-
 	ret = ivpu_hw_37xx_d0i3_disable(vdev);
 	if (ret)
 		ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
@@ -722,11 +726,11 @@ static int ivpu_hw_37xx_power_down(struct ivpu_device *vdev)
 {
 	int ret = 0;
 
-	if (!ivpu_hw_37xx_is_idle(vdev) && ivpu_hw_37xx_reset(vdev))
-		ivpu_err(vdev, "Failed to reset the VPU\n");
+	if (!ivpu_hw_37xx_is_idle(vdev))
+		ivpu_warn(vdev, "VPU not idle during power down\n");
 
-	if (ivpu_pll_disable(vdev)) {
-		ivpu_err(vdev, "Failed to disable PLL\n");
+	if (ivpu_hw_37xx_reset(vdev)) {
+		ivpu_err(vdev, "Failed to reset VPU\n");
 		ret = -EIO;
 	}
 
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 0ace218783c813..e9b16cbc26f49e 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -250,9 +250,6 @@ int ivpu_rpm_get_if_active(struct ivpu_device *vdev)
 {
 	int ret;
 
-	ivpu_dbg(vdev, RPM, "rpm_get_if_active count %d\n",
-		 atomic_read(&vdev->drm.dev->power.usage_count));
-
 	ret = pm_runtime_get_if_active(vdev->drm.dev, false);
 	drm_WARN_ON(&vdev->drm, ret < 0);
 
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 0b7a01f38b65cc..6cee536c229a63 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -253,8 +253,7 @@ static const struct backlight_ops acpi_backlight_ops = {
 static int video_get_max_state(struct thermal_cooling_device *cooling_dev,
 			       unsigned long *state)
 {
-	struct acpi_device *device = cooling_dev->devdata;
-	struct acpi_video_device *video = acpi_driver_data(device);
+	struct acpi_video_device *video = cooling_dev->devdata;
 
 	*state = video->brightness->count - ACPI_VIDEO_FIRST_LEVEL - 1;
 	return 0;
@@ -263,8 +262,7 @@ static int video_get_max_state(struct thermal_cooling_device *cooling_dev,
 static int video_get_cur_state(struct thermal_cooling_device *cooling_dev,
 			       unsigned long *state)
 {
-	struct acpi_device *device = cooling_dev->devdata;
-	struct acpi_video_device *video = acpi_driver_data(device);
+	struct acpi_video_device *video = cooling_dev->devdata;
 	unsigned long long level;
 	int offset;
 
@@ -283,8 +281,7 @@ static int video_get_cur_state(struct thermal_cooling_device *cooling_dev,
 static int
 video_set_cur_state(struct thermal_cooling_device *cooling_dev, unsigned long state)
 {
-	struct acpi_device *device = cooling_dev->devdata;
-	struct acpi_video_device *video = acpi_driver_data(device);
+	struct acpi_video_device *video = cooling_dev->devdata;
 	int level;
 
 	if (state >= video->brightness->count - ACPI_VIDEO_FIRST_LEVEL)
@@ -1125,7 +1122,6 @@ static int acpi_video_bus_get_one_device(struct acpi_device *device, void *arg)
 
 	strcpy(acpi_device_name(device), ACPI_VIDEO_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_VIDEO_CLASS);
-	device->driver_data = data;
 
 	data->device_id = device_id;
 	data->video = video;
@@ -1747,8 +1743,8 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device)
 	device->backlight->props.brightness =
 			acpi_video_get_brightness(device->backlight);
 
-	device->cooling_dev = thermal_cooling_device_register("LCD",
-				device->dev, &video_cooling_ops);
+	device->cooling_dev = thermal_cooling_device_register("LCD", device,
+							      &video_cooling_ops);
 	if (IS_ERR(device->cooling_dev)) {
 		/*
 		 * Set cooling_dev to NULL so we don't crash trying to free it.
@@ -2031,7 +2027,7 @@ static int acpi_video_bus_add(struct acpi_device *device)
 	 * HP ZBook Fury 16 G10 requires ACPI video's child devices have _PS0
 	 * evaluated to have functional panel brightness control.
 	 */
-	acpi_device_fix_up_power_extended(device);
+	acpi_device_fix_up_power_children(device);
 
 	pr_info("%s [%s] (multi-head: %s  rom: %s  post: %s)\n",
 	       ACPI_VIDEO_DEVICE_NAME, acpi_device_bid(device),
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index f007116a842762..3b4d048c494173 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -397,6 +397,19 @@ void acpi_device_fix_up_power_extended(struct acpi_device *adev)
 }
 EXPORT_SYMBOL_GPL(acpi_device_fix_up_power_extended);
 
+/**
+ * acpi_device_fix_up_power_children - Force a device's children into D0.
+ * @adev: Parent device object whose children's power state is to be fixed up.
+ *
+ * Call acpi_device_fix_up_power() for @adev's children so long as they
+ * are reported as present and enabled.
+ */
+void acpi_device_fix_up_power_children(struct acpi_device *adev)
+{
+	acpi_dev_for_each_child(adev, fix_up_power_if_applicable, NULL);
+}
+EXPORT_SYMBOL_GPL(acpi_device_fix_up_power_children);
+
 int acpi_device_update_power(struct acpi_device *device, int *state_p)
 {
 	int state;
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 3a34a8c425fe4a..55437f5e0c3aee 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -592,7 +592,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 	while (1) {
 
 		if (cx->entry_method == ACPI_CSTATE_HALT)
-			safe_halt();
+			raw_safe_halt();
 		else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) {
 			io_idle(cx->address);
 		} else
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 15a3bdbd0755d4..9bd9f79cd40990 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -448,6 +448,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
 		},
 	},
 	{
+		/* Asus ExpertBook B1402CVA */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "B1402CVA"),
+		},
+	},
+	{
 		/* Asus ExpertBook B1502CBA */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index fa5dd71a80fad9..02bb2cce423f47 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1568,17 +1568,22 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
 	int err;
 	const struct iommu_ops *ops;
 
+	/* Serialise to make dev->iommu stable under our potential fwspec */
+	mutex_lock(&iommu_probe_device_lock);
 	/*
 	 * If we already translated the fwspec there is nothing left to do,
 	 * return the iommu_ops.
 	 */
 	ops = acpi_iommu_fwspec_ops(dev);
-	if (ops)
+	if (ops) {
+		mutex_unlock(&iommu_probe_device_lock);
 		return ops;
+	}
 
 	err = iort_iommu_configure_id(dev, id_in);
 	if (err && err != -EPROBE_DEFER)
 		err = viot_iommu_configure(dev);
+	mutex_unlock(&iommu_probe_device_lock);
 
 	/*
 	 * If we have reason to believe the IOMMU driver missed the initial
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 28c75242fca9c4..62944e35fcee29 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -399,13 +399,13 @@ acpi_evaluate_reference(acpi_handle handle,
 		acpi_handle_debug(list->handles[i], "Found in reference list\n");
 	}
 
-end:
 	if (ACPI_FAILURE(status)) {
 		list->count = 0;
 		kfree(list->handles);
 		list->handles = NULL;
 	}
 
+end:
 	kfree(buffer.pointer);
 
 	return status;
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 6fb4e8dc8c3cf8..09ed67772fae49 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -6180,24 +6180,10 @@ EXPORT_SYMBOL_GPL(ata_pci_remove_one);
 void ata_pci_shutdown_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
-	struct ata_port *ap;
-	unsigned long flags;
 	int i;
 
-	/* Tell EH to disable all devices */
-	for (i = 0; i < host->n_ports; i++) {
-		ap = host->ports[i];
-		spin_lock_irqsave(ap->lock, flags);
-		ap->pflags |= ATA_PFLAG_UNLOADING;
-		ata_port_schedule_eh(ap);
-		spin_unlock_irqrestore(ap->lock, flags);
-	}
-
 	for (i = 0; i < host->n_ports; i++) {
-		ap = host->ports[i];
-
-		/* Wait for EH to complete before freezing the port */
-		ata_port_wait_eh(ap);
+		struct ata_port *ap = host->ports[i];
 
 		ap->pflags |= ATA_PFLAG_FROZEN;
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index c10ff8985203ab..0a0f483124c3a5 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1055,9 +1055,14 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev)
 		 * Ask the sd driver to issue START STOP UNIT on runtime suspend
 		 * and resume and shutdown only. For system level suspend/resume,
 		 * devices power state is handled directly by libata EH.
+		 * Given that disks are always spun up on system resume, also
+		 * make sure that the sd driver forces runtime suspended disks
+		 * to be resumed to correctly reflect the power state of the
+		 * device.
 		 */
-		sdev->manage_runtime_start_stop = true;
-		sdev->manage_shutdown = true;
+		sdev->manage_runtime_start_stop = 1;
+		sdev->manage_shutdown = 1;
+		sdev->force_runtime_start_on_system_start = 1;
 	}
 
 	/*
diff --git a/drivers/ata/pata_falcon.c b/drivers/ata/pata_falcon.c
index 0c2ae430f5aae0..18ceefd176df0f 100644
--- a/drivers/ata/pata_falcon.c
+++ b/drivers/ata/pata_falcon.c
@@ -121,7 +121,7 @@ static struct ata_port_operations pata_falcon_ops = {
 	.set_mode	= pata_falcon_set_mode,
 };
 
-static int __init pata_falcon_init_one(struct platform_device *pdev)
+static int pata_falcon_init_one(struct platform_device *pdev)
 {
 	struct resource *base_mem_res, *ctl_mem_res;
 	struct resource *base_res, *ctl_res, *irq_res;
@@ -216,23 +216,22 @@ static int __init pata_falcon_init_one(struct platform_device *pdev)
 				 IRQF_SHARED, &pata_falcon_sht);
 }
 
-static int __exit pata_falcon_remove_one(struct platform_device *pdev)
+static void pata_falcon_remove_one(struct platform_device *pdev)
 {
 	struct ata_host *host = platform_get_drvdata(pdev);
 
 	ata_host_detach(host);
-
-	return 0;
 }
 
 static struct platform_driver pata_falcon_driver = {
-	.remove = __exit_p(pata_falcon_remove_one),
+	.probe = pata_falcon_init_one,
+	.remove_new = pata_falcon_remove_one,
 	.driver   = {
 		.name	= "atari-falcon-ide",
 	},
 };
 
-module_platform_driver_probe(pata_falcon_driver, pata_falcon_init_one);
+module_platform_driver(pata_falcon_driver);
 
 MODULE_AUTHOR("Bartlomiej Zolnierkiewicz");
 MODULE_DESCRIPTION("low-level driver for Atari Falcon PATA");
diff --git a/drivers/ata/pata_gayle.c b/drivers/ata/pata_gayle.c
index 3bdbe2b65a2b49..94df60ac230782 100644
--- a/drivers/ata/pata_gayle.c
+++ b/drivers/ata/pata_gayle.c
@@ -124,7 +124,7 @@ static struct ata_port_operations pata_gayle_a4000_ops = {
 	.set_mode	= pata_gayle_set_mode,
 };
 
-static int __init pata_gayle_init_one(struct platform_device *pdev)
+static int pata_gayle_init_one(struct platform_device *pdev)
 {
 	struct resource *res;
 	struct gayle_ide_platform_data *pdata;
@@ -193,23 +193,22 @@ static int __init pata_gayle_init_one(struct platform_device *pdev)
 	return 0;
 }
 
-static int __exit pata_gayle_remove_one(struct platform_device *pdev)
+static void pata_gayle_remove_one(struct platform_device *pdev)
 {
 	struct ata_host *host = platform_get_drvdata(pdev);
 
 	ata_host_detach(host);
-
-	return 0;
 }
 
 static struct platform_driver pata_gayle_driver = {
-	.remove = __exit_p(pata_gayle_remove_one),
+	.probe = pata_gayle_init_one,
+	.remove_new = pata_gayle_remove_one,
 	.driver   = {
 		.name	= "amiga-gayle-ide",
 	},
 };
 
-module_platform_driver_probe(pata_gayle_driver, pata_gayle_init_one);
+module_platform_driver(pata_gayle_driver);
 
 MODULE_AUTHOR("Bartlomiej Zolnierkiewicz");
 MODULE_DESCRIPTION("low-level driver for Amiga Gayle PATA");
diff --git a/drivers/ata/pata_isapnp.c b/drivers/ata/pata_isapnp.c
index 25a63d043c8e1f..0f77e042406619 100644
--- a/drivers/ata/pata_isapnp.c
+++ b/drivers/ata/pata_isapnp.c
@@ -82,6 +82,9 @@ static int isapnp_init_one(struct pnp_dev *idev, const struct pnp_device_id *dev
 	if (pnp_port_valid(idev, 1)) {
 		ctl_addr = devm_ioport_map(&idev->dev,
 					   pnp_port_start(idev, 1), 1);
+		if (!ctl_addr)
+			return -ENOMEM;
+
 		ap->ioaddr.altstatus_addr = ctl_addr;
 		ap->ioaddr.ctl_addr = ctl_addr;
 		ap->ops = &isapnp_port_ops;
diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c
index 94fbc3abe60e6a..d3c30a28c410ea 100644
--- a/drivers/atm/solos-pci.c
+++ b/drivers/atm/solos-pci.c
@@ -449,9 +449,9 @@ static ssize_t console_show(struct device *dev, struct device_attribute *attr,
 	struct sk_buff *skb;
 	unsigned int len;
 
-	spin_lock(&card->cli_queue_lock);
+	spin_lock_bh(&card->cli_queue_lock);
 	skb = skb_dequeue(&card->cli_queue[SOLOS_CHAN(atmdev)]);
-	spin_unlock(&card->cli_queue_lock);
+	spin_unlock_bh(&card->cli_queue_lock);
 	if(skb == NULL)
 		return sprintf(buf, "No data.\n");
 
@@ -956,14 +956,14 @@ static void pclose(struct atm_vcc *vcc)
 	struct pkt_hdr *header;
 
 	/* Remove any yet-to-be-transmitted packets from the pending queue */
-	spin_lock(&card->tx_queue_lock);
+	spin_lock_bh(&card->tx_queue_lock);
 	skb_queue_walk_safe(&card->tx_queue[port], skb, tmpskb) {
 		if (SKB_CB(skb)->vcc == vcc) {
 			skb_unlink(skb, &card->tx_queue[port]);
 			solos_pop(vcc, skb);
 		}
 	}
-	spin_unlock(&card->tx_queue_lock);
+	spin_unlock_bh(&card->tx_queue_lock);
 
 	skb = alloc_skb(sizeof(*header), GFP_KERNEL);
 	if (!skb) {
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 9ea22e165acd67..548491de818ef1 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -144,7 +144,7 @@ static DEVICE_ATTR(release, S_IWUSR, NULL, cpu_release_store);
 #endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
 #endif /* CONFIG_HOTPLUG_CPU */
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 #include <linux/kexec.h>
 
 static ssize_t crash_notes_show(struct device *dev,
@@ -189,14 +189,14 @@ static const struct attribute_group crash_note_cpu_attr_group = {
 #endif
 
 static const struct attribute_group *common_cpu_attr_groups[] = {
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	&crash_note_cpu_attr_group,
 #endif
 	NULL
 };
 
 static const struct attribute_group *hotplugable_cpu_attr_groups[] = {
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	&crash_note_cpu_attr_group,
 #endif
 	NULL
diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c
index 91536ee05f144e..7e2d1f0d903a6e 100644
--- a/drivers/base/devcoredump.c
+++ b/drivers/base/devcoredump.c
@@ -362,6 +362,7 @@ void dev_coredumpm(struct device *dev, struct module *owner,
 	devcd->devcd_dev.class = &devcd_class;
 
 	mutex_lock(&devcd->mutex);
+	dev_set_uevent_suppress(&devcd->devcd_dev, true);
 	if (device_add(&devcd->devcd_dev))
 		goto put_device;
 
@@ -376,6 +377,8 @@ void dev_coredumpm(struct device *dev, struct module *owner,
 		              "devcoredump"))
 		dev_warn(dev, "devcoredump create_link failed\n");
 
+	dev_set_uevent_suppress(&devcd->devcd_dev, false);
+	kobject_uevent(&devcd->devcd_dev.kobj, KOBJ_ADD);
 	INIT_DELAYED_WORK(&devcd->del_wk, devcd_del);
 	schedule_delayed_work(&devcd->del_wk, DEVCD_TIMEOUT);
 	mutex_unlock(&devcd->mutex);
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index f3b9a4d0fa3bb2..8a13babd826ce3 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -180,6 +180,9 @@ static inline unsigned long memblk_nr_poison(struct memory_block *mem)
 }
 #endif
 
+/*
+ * Must acquire mem_hotplug_lock in write mode.
+ */
 static int memory_block_online(struct memory_block *mem)
 {
 	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
@@ -204,10 +207,11 @@ static int memory_block_online(struct memory_block *mem)
 	if (mem->altmap)
 		nr_vmemmap_pages = mem->altmap->free;
 
+	mem_hotplug_begin();
 	if (nr_vmemmap_pages) {
 		ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	ret = online_pages(start_pfn + nr_vmemmap_pages,
@@ -215,7 +219,7 @@ static int memory_block_online(struct memory_block *mem)
 	if (ret) {
 		if (nr_vmemmap_pages)
 			mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
-		return ret;
+		goto out;
 	}
 
 	/*
@@ -227,9 +231,14 @@ static int memory_block_online(struct memory_block *mem)
 					  nr_vmemmap_pages);
 
 	mem->zone = zone;
+out:
+	mem_hotplug_done();
 	return ret;
 }
 
+/*
+ * Must acquire mem_hotplug_lock in write mode.
+ */
 static int memory_block_offline(struct memory_block *mem)
 {
 	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
@@ -247,6 +256,7 @@ static int memory_block_offline(struct memory_block *mem)
 	if (mem->altmap)
 		nr_vmemmap_pages = mem->altmap->free;
 
+	mem_hotplug_begin();
 	if (nr_vmemmap_pages)
 		adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
 					  -nr_vmemmap_pages);
@@ -258,13 +268,15 @@ static int memory_block_offline(struct memory_block *mem)
 		if (nr_vmemmap_pages)
 			adjust_present_page_count(pfn_to_page(start_pfn),
 						  mem->group, nr_vmemmap_pages);
-		return ret;
+		goto out;
 	}
 
 	if (nr_vmemmap_pages)
 		mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
 
 	mem->zone = NULL;
+out:
+	mem_hotplug_done();
 	return ret;
 }
 
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index 92592f944a3df2..ac63a73ccdaaa2 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -410,8 +410,7 @@ out:
 			rb_entry(node, struct regmap_range_node, node);
 
 		/* If there's nothing in the cache there's nothing to sync */
-		ret = regcache_read(map, this->selector_reg, &i);
-		if (ret != 0)
+		if (regcache_read(map, this->selector_reg, &i) != 0)
 			continue;
 
 		ret = _regmap_write(map, this->selector_reg, i);
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 800f131222fc8f..b6414e1e645b76 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -67,6 +67,7 @@ struct nbd_sock {
 struct recv_thread_args {
 	struct work_struct work;
 	struct nbd_device *nbd;
+	struct nbd_sock *nsock;
 	int index;
 };
 
@@ -250,7 +251,6 @@ static void nbd_dev_remove(struct nbd_device *nbd)
 	struct gendisk *disk = nbd->disk;
 
 	del_gendisk(disk);
-	put_disk(disk);
 	blk_mq_free_tag_set(&nbd->tag_set);
 
 	/*
@@ -261,7 +261,7 @@ static void nbd_dev_remove(struct nbd_device *nbd)
 	idr_remove(&nbd_index_idr, nbd->index);
 	mutex_unlock(&nbd_index_mutex);
 	destroy_workqueue(nbd->recv_workq);
-	kfree(nbd);
+	put_disk(disk);
 }
 
 static void nbd_dev_remove_work(struct work_struct *work)
@@ -396,6 +396,22 @@ static u32 req_to_nbd_cmd_type(struct request *req)
 	}
 }
 
+static struct nbd_config *nbd_get_config_unlocked(struct nbd_device *nbd)
+{
+	if (refcount_inc_not_zero(&nbd->config_refs)) {
+		/*
+		 * Add smp_mb__after_atomic to ensure that reading nbd->config_refs
+		 * and reading nbd->config is ordered. The pair is the barrier in
+		 * nbd_alloc_and_init_config(), avoid nbd->config_refs is set
+		 * before nbd->config.
+		 */
+		smp_mb__after_atomic();
+		return nbd->config;
+	}
+
+	return NULL;
+}
+
 static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
@@ -410,13 +426,13 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req)
 		return BLK_EH_DONE;
 	}
 
-	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+	config = nbd_get_config_unlocked(nbd);
+	if (!config) {
 		cmd->status = BLK_STS_TIMEOUT;
 		__clear_bit(NBD_CMD_INFLIGHT, &cmd->flags);
 		mutex_unlock(&cmd->lock);
 		goto done;
 	}
-	config = nbd->config;
 
 	if (config->num_connections > 1 ||
 	    (config->num_connections == 1 && nbd->tag_set.timeout)) {
@@ -490,15 +506,9 @@ done:
 	return BLK_EH_DONE;
 }
 
-/*
- *  Send or receive packet. Return a positive value on success and
- *  negtive value on failue, and never return 0.
- */
-static int sock_xmit(struct nbd_device *nbd, int index, int send,
-		     struct iov_iter *iter, int msg_flags, int *sent)
+static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send,
+		       struct iov_iter *iter, int msg_flags, int *sent)
 {
-	struct nbd_config *config = nbd->config;
-	struct socket *sock = config->socks[index]->sock;
 	int result;
 	struct msghdr msg;
 	unsigned int noreclaim_flag;
@@ -542,6 +552,19 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send,
 }
 
 /*
+ *  Send or receive packet. Return a positive value on success and
+ *  negtive value on failure, and never return 0.
+ */
+static int sock_xmit(struct nbd_device *nbd, int index, int send,
+		     struct iov_iter *iter, int msg_flags, int *sent)
+{
+	struct nbd_config *config = nbd->config;
+	struct socket *sock = config->socks[index]->sock;
+
+	return __sock_xmit(nbd, sock, send, iter, msg_flags, sent);
+}
+
+/*
  * Different settings for sk->sk_sndtimeo can result in different return values
  * if there is a signal pending when we enter sendmsg, because reasons?
  */
@@ -697,7 +720,7 @@ out:
 	return 0;
 }
 
-static int nbd_read_reply(struct nbd_device *nbd, int index,
+static int nbd_read_reply(struct nbd_device *nbd, struct socket *sock,
 			  struct nbd_reply *reply)
 {
 	struct kvec iov = {.iov_base = reply, .iov_len = sizeof(*reply)};
@@ -706,7 +729,7 @@ static int nbd_read_reply(struct nbd_device *nbd, int index,
 
 	reply->magic = 0;
 	iov_iter_kvec(&to, ITER_DEST, &iov, 1, sizeof(*reply));
-	result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
+	result = __sock_xmit(nbd, sock, 0, &to, MSG_WAITALL, NULL);
 	if (result < 0) {
 		if (!nbd_disconnected(nbd->config))
 			dev_err(disk_to_dev(nbd->disk),
@@ -830,14 +853,14 @@ static void recv_work(struct work_struct *work)
 	struct nbd_device *nbd = args->nbd;
 	struct nbd_config *config = nbd->config;
 	struct request_queue *q = nbd->disk->queue;
-	struct nbd_sock *nsock;
+	struct nbd_sock *nsock = args->nsock;
 	struct nbd_cmd *cmd;
 	struct request *rq;
 
 	while (1) {
 		struct nbd_reply reply;
 
-		if (nbd_read_reply(nbd, args->index, &reply))
+		if (nbd_read_reply(nbd, nsock->sock, &reply))
 			break;
 
 		/*
@@ -872,7 +895,6 @@ static void recv_work(struct work_struct *work)
 		percpu_ref_put(&q->q_usage_counter);
 	}
 
-	nsock = config->socks[args->index];
 	mutex_lock(&nsock->tx_lock);
 	nbd_mark_nsock_dead(nbd, nsock, 1);
 	mutex_unlock(&nsock->tx_lock);
@@ -978,12 +1000,12 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 	struct nbd_sock *nsock;
 	int ret;
 
-	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+	config = nbd_get_config_unlocked(nbd);
+	if (!config) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Socks array is empty\n");
 		return -EINVAL;
 	}
-	config = nbd->config;
 
 	if (index >= config->num_connections) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
@@ -1216,6 +1238,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
 		INIT_WORK(&args->work, recv_work);
 		args->index = i;
 		args->nbd = nbd;
+		args->nsock = nsock;
 		nsock->cookie++;
 		mutex_unlock(&nsock->tx_lock);
 		sockfd_put(old);
@@ -1398,6 +1421,7 @@ static int nbd_start_device(struct nbd_device *nbd)
 		refcount_inc(&nbd->config_refs);
 		INIT_WORK(&args->work, recv_work);
 		args->nbd = nbd;
+		args->nsock = config->socks[i];
 		args->index = i;
 		queue_work(nbd->recv_workq, &args->work);
 	}
@@ -1531,17 +1555,20 @@ static int nbd_ioctl(struct block_device *bdev, blk_mode_t mode,
 	return error;
 }
 
-static struct nbd_config *nbd_alloc_config(void)
+static int nbd_alloc_and_init_config(struct nbd_device *nbd)
 {
 	struct nbd_config *config;
 
+	if (WARN_ON(nbd->config))
+		return -EINVAL;
+
 	if (!try_module_get(THIS_MODULE))
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	config = kzalloc(sizeof(struct nbd_config), GFP_NOFS);
 	if (!config) {
 		module_put(THIS_MODULE);
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 	}
 
 	atomic_set(&config->recv_threads, 0);
@@ -1549,12 +1576,24 @@ static struct nbd_config *nbd_alloc_config(void)
 	init_waitqueue_head(&config->conn_wait);
 	config->blksize_bits = NBD_DEF_BLKSIZE_BITS;
 	atomic_set(&config->live_connections, 0);
-	return config;
+
+	nbd->config = config;
+	/*
+	 * Order refcount_set(&nbd->config_refs, 1) and nbd->config assignment,
+	 * its pair is the barrier in nbd_get_config_unlocked().
+	 * So nbd_get_config_unlocked() won't see nbd->config as null after
+	 * refcount_inc_not_zero() succeed.
+	 */
+	smp_mb__before_atomic();
+	refcount_set(&nbd->config_refs, 1);
+
+	return 0;
 }
 
 static int nbd_open(struct gendisk *disk, blk_mode_t mode)
 {
 	struct nbd_device *nbd;
+	struct nbd_config *config;
 	int ret = 0;
 
 	mutex_lock(&nbd_index_mutex);
@@ -1567,27 +1606,25 @@ static int nbd_open(struct gendisk *disk, blk_mode_t mode)
 		ret = -ENXIO;
 		goto out;
 	}
-	if (!refcount_inc_not_zero(&nbd->config_refs)) {
-		struct nbd_config *config;
 
+	config = nbd_get_config_unlocked(nbd);
+	if (!config) {
 		mutex_lock(&nbd->config_lock);
 		if (refcount_inc_not_zero(&nbd->config_refs)) {
 			mutex_unlock(&nbd->config_lock);
 			goto out;
 		}
-		config = nbd_alloc_config();
-		if (IS_ERR(config)) {
-			ret = PTR_ERR(config);
+		ret = nbd_alloc_and_init_config(nbd);
+		if (ret) {
 			mutex_unlock(&nbd->config_lock);
 			goto out;
 		}
-		nbd->config = config;
-		refcount_set(&nbd->config_refs, 1);
+
 		refcount_inc(&nbd->refs);
 		mutex_unlock(&nbd->config_lock);
 		if (max_part)
 			set_bit(GD_NEED_PART_SCAN, &disk->state);
-	} else if (nbd_disconnected(nbd->config)) {
+	} else if (nbd_disconnected(config)) {
 		if (max_part)
 			set_bit(GD_NEED_PART_SCAN, &disk->state);
 	}
@@ -1608,6 +1645,13 @@ static void nbd_release(struct gendisk *disk)
 	nbd_put(nbd);
 }
 
+static void nbd_free_disk(struct gendisk *disk)
+{
+	struct nbd_device *nbd = disk->private_data;
+
+	kfree(nbd);
+}
+
 static const struct block_device_operations nbd_fops =
 {
 	.owner =	THIS_MODULE,
@@ -1615,6 +1659,7 @@ static const struct block_device_operations nbd_fops =
 	.release =	nbd_release,
 	.ioctl =	nbd_ioctl,
 	.compat_ioctl =	nbd_ioctl,
+	.free_disk =	nbd_free_disk,
 };
 
 #if IS_ENABLED(CONFIG_DEBUG_FS)
@@ -1983,22 +2028,17 @@ again:
 		pr_err("nbd%d already in use\n", index);
 		return -EBUSY;
 	}
-	if (WARN_ON(nbd->config)) {
-		mutex_unlock(&nbd->config_lock);
-		nbd_put(nbd);
-		return -EINVAL;
-	}
-	config = nbd_alloc_config();
-	if (IS_ERR(config)) {
+
+	ret = nbd_alloc_and_init_config(nbd);
+	if (ret) {
 		mutex_unlock(&nbd->config_lock);
 		nbd_put(nbd);
 		pr_err("couldn't allocate config\n");
-		return PTR_ERR(config);
+		return ret;
 	}
-	nbd->config = config;
-	refcount_set(&nbd->config_refs, 1);
-	set_bit(NBD_RT_BOUND, &config->runtime_flags);
 
+	config = nbd->config;
+	set_bit(NBD_RT_BOUND, &config->runtime_flags);
 	ret = nbd_genl_size_set(info, nbd);
 	if (ret)
 		goto out;
@@ -2201,7 +2241,8 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 	}
 	mutex_unlock(&nbd_index_mutex);
 
-	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+	config = nbd_get_config_unlocked(nbd);
+	if (!config) {
 		dev_err(nbd_to_dev(nbd),
 			"not configured, cannot reconfigure\n");
 		nbd_put(nbd);
@@ -2209,7 +2250,6 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	mutex_lock(&nbd->config_lock);
-	config = nbd->config;
 	if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) ||
 	    !nbd->pid) {
 		dev_err(nbd_to_dev(nbd),
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 22a3cf7f32e233..3021d58ca51c1f 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1464,19 +1464,13 @@ blk_status_t null_process_cmd(struct nullb_cmd *cmd, enum req_op op,
 	return BLK_STS_OK;
 }
 
-static blk_status_t null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
-				    sector_t nr_sectors, enum req_op op)
+static void null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
+			    sector_t nr_sectors, enum req_op op)
 {
 	struct nullb_device *dev = cmd->nq->dev;
 	struct nullb *nullb = dev->nullb;
 	blk_status_t sts;
 
-	if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) {
-		sts = null_handle_throttled(cmd);
-		if (sts != BLK_STS_OK)
-			return sts;
-	}
-
 	if (op == REQ_OP_FLUSH) {
 		cmd->error = errno_to_blk_status(null_handle_flush(nullb));
 		goto out;
@@ -1493,7 +1487,6 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
 
 out:
 	nullb_complete_cmd(cmd);
-	return BLK_STS_OK;
 }
 
 static enum hrtimer_restart nullb_bwtimer_fn(struct hrtimer *timer)
@@ -1724,8 +1717,6 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 	cmd->fake_timeout = should_timeout_request(rq) ||
 		blk_should_fake_timeout(rq->q);
 
-	blk_mq_start_request(rq);
-
 	if (should_requeue_request(rq)) {
 		/*
 		 * Alternate between hitting the core BUSY path, and the
@@ -1738,6 +1729,15 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 		return BLK_STS_OK;
 	}
 
+	if (test_bit(NULLB_DEV_FL_THROTTLED, &nq->dev->flags)) {
+		blk_status_t sts = null_handle_throttled(cmd);
+
+		if (sts != BLK_STS_OK)
+			return sts;
+	}
+
+	blk_mq_start_request(rq);
+
 	if (is_poll) {
 		spin_lock(&nq->poll_lock);
 		list_add_tail(&rq->queuelist, &nq->poll_list);
@@ -1747,7 +1747,8 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (cmd->fake_timeout)
 		return BLK_STS_OK;
 
-	return null_handle_cmd(cmd, sector, nr_sectors, req_op(rq));
+	null_handle_cmd(cmd, sector, nr_sectors, req_op(rq));
+	return BLK_STS_OK;
 }
 
 static void null_queue_rqs(struct request **rqlist)
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index f3892e9ce800ff..572d68d52965f6 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <asm/unaligned.h>
 
+#include <linux/atomic.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -44,6 +45,7 @@ struct vhci_data {
 	bool wakeup;
 	__u16 msft_opcode;
 	bool aosp_capable;
+	atomic_t initialized;
 };
 
 static int vhci_open_dev(struct hci_dev *hdev)
@@ -75,11 +77,10 @@ static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 
 	memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1);
 
-	mutex_lock(&data->open_mutex);
 	skb_queue_tail(&data->readq, skb);
-	mutex_unlock(&data->open_mutex);
 
-	wake_up_interruptible(&data->read_wait);
+	if (atomic_read(&data->initialized))
+		wake_up_interruptible(&data->read_wait);
 	return 0;
 }
 
@@ -464,7 +465,8 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode)
 	skb_put_u8(skb, 0xff);
 	skb_put_u8(skb, opcode);
 	put_unaligned_le16(hdev->id, skb_put(skb, 2));
-	skb_queue_tail(&data->readq, skb);
+	skb_queue_head(&data->readq, skb);
+	atomic_inc(&data->initialized);
 
 	wake_up_interruptible(&data->read_wait);
 	return 0;
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index d57bc066dce6b4..9ed9239b1228f6 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -2158,13 +2158,23 @@ static int sysc_reset(struct sysc *ddata)
 		sysc_val = sysc_read_sysconfig(ddata);
 		sysc_val |= sysc_mask;
 		sysc_write(ddata, sysc_offset, sysc_val);
-		/* Flush posted write */
+
+		/*
+		 * Some devices need a delay before reading registers
+		 * after reset. Presumably a srst_udelay is not needed
+		 * for devices that use a rstctrl register reset.
+		 */
+		if (ddata->cfg.srst_udelay)
+			fsleep(ddata->cfg.srst_udelay);
+
+		/*
+		 * Flush posted write. For devices needing srst_udelay
+		 * this should trigger an interconnect error if the
+		 * srst_udelay value is needed but not configured.
+		 */
 		sysc_val = sysc_read_sysconfig(ddata);
 	}
 
-	if (ddata->cfg.srst_udelay)
-		fsleep(ddata->cfg.srst_udelay);
-
 	if (ddata->post_reset_quirk)
 		ddata->post_reset_quirk(ddata);
 
diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index ad1acd9b7426b1..dbc3950c596090 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -767,6 +767,7 @@ config SM_CAMCC_8450
 
 config SM_CAMCC_8550
 	tristate "SM8550 Camera Clock Controller"
+	depends on ARM64 || COMPILE_TEST
 	select SM_GCC_8550
 	help
 	  Support for the camera clock controller on SM8550 devices.
diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c
index aa53797dbfc145..75071e0cd3216e 100644
--- a/drivers/clk/rockchip/clk-rk3128.c
+++ b/drivers/clk/rockchip/clk-rk3128.c
@@ -138,7 +138,7 @@ PNAME(mux_pll_src_5plls_p)	= { "cpll", "gpll", "gpll_div2", "gpll_div3", "usb480
 PNAME(mux_pll_src_4plls_p)	= { "cpll", "gpll", "gpll_div2", "usb480m" };
 PNAME(mux_pll_src_3plls_p)	= { "cpll", "gpll", "gpll_div2" };
 
-PNAME(mux_aclk_peri_src_p)	= { "gpll_peri", "cpll_peri", "gpll_div2_peri", "gpll_div3_peri" };
+PNAME(mux_clk_peri_src_p)	= { "gpll", "cpll", "gpll_div2", "gpll_div3" };
 PNAME(mux_mmc_src_p)		= { "cpll", "gpll", "gpll_div2", "xin24m" };
 PNAME(mux_clk_cif_out_src_p)		= { "clk_cif_src", "xin24m" };
 PNAME(mux_sclk_vop_src_p)	= { "cpll", "gpll", "gpll_div2", "gpll_div3" };
@@ -275,23 +275,17 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 			RK2928_CLKGATE_CON(0), 11, GFLAGS),
 
 	/* PD_PERI */
-	GATE(0, "gpll_peri", "gpll", CLK_IGNORE_UNUSED,
+	COMPOSITE(0, "clk_peri_src", mux_clk_peri_src_p, 0,
+			RK2928_CLKSEL_CON(10), 14, 2, MFLAGS, 0, 5, DFLAGS,
 			RK2928_CLKGATE_CON(2), 0, GFLAGS),
-	GATE(0, "cpll_peri", "cpll", CLK_IGNORE_UNUSED,
-			RK2928_CLKGATE_CON(2), 0, GFLAGS),
-	GATE(0, "gpll_div2_peri", "gpll_div2", CLK_IGNORE_UNUSED,
-			RK2928_CLKGATE_CON(2), 0, GFLAGS),
-	GATE(0, "gpll_div3_peri", "gpll_div3", CLK_IGNORE_UNUSED,
-			RK2928_CLKGATE_CON(2), 0, GFLAGS),
-	COMPOSITE_NOGATE(0, "aclk_peri_src", mux_aclk_peri_src_p, 0,
-			RK2928_CLKSEL_CON(10), 14, 2, MFLAGS, 0, 5, DFLAGS),
-	COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "aclk_peri_src", 0,
+
+	COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "clk_peri_src", 0,
 			RK2928_CLKSEL_CON(10), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
 			RK2928_CLKGATE_CON(2), 3, GFLAGS),
-	COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "aclk_peri_src", 0,
+	COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "clk_peri_src", 0,
 			RK2928_CLKSEL_CON(10), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
 			RK2928_CLKGATE_CON(2), 2, GFLAGS),
-	GATE(ACLK_PERI, "aclk_peri", "aclk_peri_src", 0,
+	GATE(ACLK_PERI, "aclk_peri", "clk_peri_src", 0,
 			RK2928_CLKGATE_CON(2), 1, GFLAGS),
 
 	GATE(SCLK_TIMER0, "sclk_timer0", "xin24m", 0,
@@ -316,7 +310,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 	GATE(SCLK_MIPI_24M, "clk_mipi_24m", "xin24m", CLK_IGNORE_UNUSED,
 			RK2928_CLKGATE_CON(2), 15, GFLAGS),
 
-	COMPOSITE(SCLK_SDMMC, "sclk_sdmmc0", mux_mmc_src_p, 0,
+	COMPOSITE(SCLK_SDMMC, "sclk_sdmmc", mux_mmc_src_p, 0,
 			RK2928_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 6, DFLAGS,
 			RK2928_CLKGATE_CON(2), 11, GFLAGS),
 
@@ -490,7 +484,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 	GATE(HCLK_I2S_2CH, "hclk_i2s_2ch", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 2, GFLAGS),
 	GATE(0, "hclk_usb_peri", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 13, GFLAGS),
 	GATE(HCLK_HOST2, "hclk_host2", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 3, GFLAGS),
-	GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(3), 13, GFLAGS),
+	GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(5), 13, GFLAGS),
 	GATE(0, "hclk_peri_ahb", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 14, GFLAGS),
 	GATE(HCLK_SPDIF, "hclk_spdif", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 9, GFLAGS),
 	GATE(HCLK_TSP, "hclk_tsp", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 12, GFLAGS),
diff --git a/drivers/clk/rockchip/clk-rk3568.c b/drivers/clk/rockchip/clk-rk3568.c
index 16dabe2b9c47f4..db713e1526cdc3 100644
--- a/drivers/clk/rockchip/clk-rk3568.c
+++ b/drivers/clk/rockchip/clk-rk3568.c
@@ -72,6 +72,7 @@ static struct rockchip_pll_rate_table rk3568_pll_rates[] = {
 	RK3036_PLL_RATE(408000000, 1, 68, 2, 2, 1, 0),
 	RK3036_PLL_RATE(312000000, 1, 78, 6, 1, 1, 0),
 	RK3036_PLL_RATE(297000000, 2, 99, 4, 1, 1, 0),
+	RK3036_PLL_RATE(292500000, 1, 195, 4, 4, 1, 0),
 	RK3036_PLL_RATE(241500000, 2, 161, 4, 2, 1, 0),
 	RK3036_PLL_RATE(216000000, 1, 72, 4, 2, 1, 0),
 	RK3036_PLL_RATE(200000000, 1, 100, 3, 4, 1, 0),
diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c
index 06f5bad3c3e06c..57857c0dfba97e 100644
--- a/drivers/clocksource/timer-riscv.c
+++ b/drivers/clocksource/timer-riscv.c
@@ -25,7 +25,7 @@
 #include <linux/limits.h>
 #include <clocksource/timer-riscv.h>
 #include <asm/smp.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 #include <asm/sbi.h>
 #include <asm/timex.h>
 
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 9a1e194d5cf882..1f6186475715e0 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -307,11 +307,11 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
 
 	WRITE_ONCE(cpudata->highest_perf, highest_perf);
-
+	WRITE_ONCE(cpudata->max_limit_perf, highest_perf);
 	WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1));
-
+	WRITE_ONCE(cpudata->min_limit_perf, AMD_CPPC_LOWEST_PERF(cap1));
 	return 0;
 }
 
@@ -329,11 +329,12 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
 		highest_perf = cppc_perf.highest_perf;
 
 	WRITE_ONCE(cpudata->highest_perf, highest_perf);
-
+	WRITE_ONCE(cpudata->max_limit_perf, highest_perf);
 	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
 		   cppc_perf.lowest_nonlinear_perf);
 	WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf);
+	WRITE_ONCE(cpudata->min_limit_perf, cppc_perf.lowest_perf);
 
 	if (cppc_state == AMD_PSTATE_ACTIVE)
 		return 0;
@@ -432,6 +433,10 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
 	u64 prev = READ_ONCE(cpudata->cppc_req_cached);
 	u64 value = prev;
 
+	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
+			cpudata->max_limit_perf);
+	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
+			cpudata->max_limit_perf);
 	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
 
 	if ((cppc_state == AMD_PSTATE_GUIDED) && (gov_flags & CPUFREQ_GOV_DYNAMIC_SWITCHING)) {
@@ -470,6 +475,22 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy)
 	return 0;
 }
 
+static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
+{
+	u32 max_limit_perf, min_limit_perf;
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
+	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
+
+	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
+	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
+	WRITE_ONCE(cpudata->max_limit_freq, policy->max);
+	WRITE_ONCE(cpudata->min_limit_freq, policy->min);
+
+	return 0;
+}
+
 static int amd_pstate_update_freq(struct cpufreq_policy *policy,
 				  unsigned int target_freq, bool fast_switch)
 {
@@ -480,6 +501,9 @@ static int amd_pstate_update_freq(struct cpufreq_policy *policy,
 	if (!cpudata->max_freq)
 		return -ENODEV;
 
+	if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq)
+		amd_pstate_update_min_max_limit(policy);
+
 	cap_perf = READ_ONCE(cpudata->highest_perf);
 	min_perf = READ_ONCE(cpudata->lowest_perf);
 	max_perf = cap_perf;
@@ -518,7 +542,9 @@ static int amd_pstate_target(struct cpufreq_policy *policy,
 static unsigned int amd_pstate_fast_switch(struct cpufreq_policy *policy,
 				  unsigned int target_freq)
 {
-	return amd_pstate_update_freq(policy, target_freq, true);
+	if (!amd_pstate_update_freq(policy, target_freq, true))
+		return target_freq;
+	return policy->cur;
 }
 
 static void amd_pstate_adjust_perf(unsigned int cpu,
@@ -532,6 +558,10 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 	struct amd_cpudata *cpudata = policy->driver_data;
 	unsigned int target_freq;
 
+	if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq)
+		amd_pstate_update_min_max_limit(policy);
+
+
 	cap_perf = READ_ONCE(cpudata->highest_perf);
 	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
 	max_freq = READ_ONCE(cpudata->max_freq);
@@ -745,6 +775,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 	/* Initial processor data capability frequencies */
 	cpudata->max_freq = max_freq;
 	cpudata->min_freq = min_freq;
+	cpudata->max_limit_freq = max_freq;
+	cpudata->min_limit_freq = min_freq;
 	cpudata->nominal_freq = nominal_freq;
 	cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq;
 
@@ -850,11 +882,16 @@ static ssize_t show_energy_performance_available_preferences(
 {
 	int i = 0;
 	int offset = 0;
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
+		return sysfs_emit_at(buf, offset, "%s\n",
+				energy_perf_strings[EPP_INDEX_PERFORMANCE]);
 
 	while (energy_perf_strings[i] != NULL)
 		offset += sysfs_emit_at(buf, offset, "%s ", energy_perf_strings[i++]);
 
-	sysfs_emit_at(buf, offset, "\n");
+	offset += sysfs_emit_at(buf, offset, "\n");
 
 	return offset;
 }
@@ -1183,16 +1220,25 @@ static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void amd_pstate_epp_init(unsigned int cpu)
+static void amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
 	struct amd_cpudata *cpudata = policy->driver_data;
-	u32 max_perf, min_perf;
+	u32 max_perf, min_perf, min_limit_perf, max_limit_perf;
 	u64 value;
 	s16 epp;
 
 	max_perf = READ_ONCE(cpudata->highest_perf);
 	min_perf = READ_ONCE(cpudata->lowest_perf);
+	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
+	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
+
+	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
+			cpudata->max_limit_perf);
+	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
+			cpudata->max_limit_perf);
+
+	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
+	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
 
 	value = READ_ONCE(cpudata->cppc_req_cached);
 
@@ -1210,9 +1256,6 @@ static void amd_pstate_epp_init(unsigned int cpu)
 	value &= ~AMD_CPPC_DES_PERF(~0L);
 	value |= AMD_CPPC_DES_PERF(0);
 
-	if (cpudata->epp_policy == cpudata->policy)
-		goto skip_epp;
-
 	cpudata->epp_policy = cpudata->policy;
 
 	/* Get BIOS pre-defined epp value */
@@ -1222,7 +1265,7 @@ static void amd_pstate_epp_init(unsigned int cpu)
 		 * This return value can only be negative for shared_memory
 		 * systems where EPP register read/write not supported.
 		 */
-		goto skip_epp;
+		return;
 	}
 
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
@@ -1236,8 +1279,6 @@ static void amd_pstate_epp_init(unsigned int cpu)
 
 	WRITE_ONCE(cpudata->cppc_req_cached, value);
 	amd_pstate_set_epp(cpudata, epp);
-skip_epp:
-	cpufreq_cpu_put(policy);
 }
 
 static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
@@ -1252,7 +1293,7 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
 
 	cpudata->policy = policy->policy;
 
-	amd_pstate_epp_init(policy->cpu);
+	amd_pstate_epp_update_limit(policy);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 494d044b9e7207..33728c242f66ca 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -327,7 +327,7 @@ static int imx6ul_opp_check_speed_grading(struct device *dev)
 			imx6x_disable_freq_in_opp(dev, 696000000);
 
 	if (of_machine_is_compatible("fsl,imx6ull")) {
-		if (val != OCOTP_CFG3_6ULL_SPEED_792MHZ)
+		if (val < OCOTP_CFG3_6ULL_SPEED_792MHZ)
 			imx6x_disable_freq_in_opp(dev, 792000000);
 
 		if (val != OCOTP_CFG3_6ULL_SPEED_900MHZ)
diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c
index 6355a39418c5b2..ea05d9d6749025 100644
--- a/drivers/cpufreq/qcom-cpufreq-nvmem.c
+++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c
@@ -23,8 +23,10 @@
 #include <linux/nvmem-consumer.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_opp.h>
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/soc/qcom/smem.h>
 
@@ -55,6 +57,7 @@ struct qcom_cpufreq_match_data {
 
 struct qcom_cpufreq_drv_cpu {
 	int opp_token;
+	struct device **virt_devs;
 };
 
 struct qcom_cpufreq_drv {
@@ -424,6 +427,30 @@ static const struct qcom_cpufreq_match_data match_data_ipq8074 = {
 	.get_version = qcom_cpufreq_ipq8074_name_version,
 };
 
+static void qcom_cpufreq_suspend_virt_devs(struct qcom_cpufreq_drv *drv, unsigned int cpu)
+{
+	const char * const *name = drv->data->genpd_names;
+	int i;
+
+	if (!drv->cpus[cpu].virt_devs)
+		return;
+
+	for (i = 0; *name; i++, name++)
+		device_set_awake_path(drv->cpus[cpu].virt_devs[i]);
+}
+
+static void qcom_cpufreq_put_virt_devs(struct qcom_cpufreq_drv *drv, unsigned int cpu)
+{
+	const char * const *name = drv->data->genpd_names;
+	int i;
+
+	if (!drv->cpus[cpu].virt_devs)
+		return;
+
+	for (i = 0; *name; i++, name++)
+		pm_runtime_put(drv->cpus[cpu].virt_devs[i]);
+}
+
 static int qcom_cpufreq_probe(struct platform_device *pdev)
 {
 	struct qcom_cpufreq_drv *drv;
@@ -478,6 +505,7 @@ static int qcom_cpufreq_probe(struct platform_device *pdev)
 	of_node_put(np);
 
 	for_each_possible_cpu(cpu) {
+		struct device **virt_devs = NULL;
 		struct dev_pm_opp_config config = {
 			.supported_hw = NULL,
 		};
@@ -498,7 +526,7 @@ static int qcom_cpufreq_probe(struct platform_device *pdev)
 
 		if (drv->data->genpd_names) {
 			config.genpd_names = drv->data->genpd_names;
-			config.virt_devs = NULL;
+			config.virt_devs = &virt_devs;
 		}
 
 		if (config.supported_hw || config.genpd_names) {
@@ -509,6 +537,27 @@ static int qcom_cpufreq_probe(struct platform_device *pdev)
 				goto free_opp;
 			}
 		}
+
+		if (virt_devs) {
+			const char * const *name = config.genpd_names;
+			int i, j;
+
+			for (i = 0; *name; i++, name++) {
+				ret = pm_runtime_resume_and_get(virt_devs[i]);
+				if (ret) {
+					dev_err(cpu_dev, "failed to resume %s: %d\n",
+						*name, ret);
+
+					/* Rollback previous PM runtime calls */
+					name = config.genpd_names;
+					for (j = 0; *name && j < i; j++, name++)
+						pm_runtime_put(virt_devs[j]);
+
+					goto free_opp;
+				}
+			}
+			drv->cpus[cpu].virt_devs = virt_devs;
+		}
 	}
 
 	cpufreq_dt_pdev = platform_device_register_simple("cpufreq-dt", -1,
@@ -522,8 +571,10 @@ static int qcom_cpufreq_probe(struct platform_device *pdev)
 	dev_err(cpu_dev, "Failed to register platform device\n");
 
 free_opp:
-	for_each_possible_cpu(cpu)
+	for_each_possible_cpu(cpu) {
+		qcom_cpufreq_put_virt_devs(drv, cpu);
 		dev_pm_opp_clear_config(drv->cpus[cpu].opp_token);
+	}
 	return ret;
 }
 
@@ -534,15 +585,31 @@ static void qcom_cpufreq_remove(struct platform_device *pdev)
 
 	platform_device_unregister(cpufreq_dt_pdev);
 
-	for_each_possible_cpu(cpu)
+	for_each_possible_cpu(cpu) {
+		qcom_cpufreq_put_virt_devs(drv, cpu);
 		dev_pm_opp_clear_config(drv->cpus[cpu].opp_token);
+	}
 }
 
+static int qcom_cpufreq_suspend(struct device *dev)
+{
+	struct qcom_cpufreq_drv *drv = dev_get_drvdata(dev);
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		qcom_cpufreq_suspend_virt_devs(drv, cpu);
+
+	return 0;
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(qcom_cpufreq_pm_ops, qcom_cpufreq_suspend, NULL);
+
 static struct platform_driver qcom_cpufreq_driver = {
 	.probe = qcom_cpufreq_probe,
 	.remove_new = qcom_cpufreq_remove,
 	.driver = {
 		.name = "qcom-cpufreq-nvmem",
+		.pm = pm_sleep_ptr(&qcom_cpufreq_pm_ops),
 	},
 };
 
diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index 1cc9be85ba4cd1..7d97790b893d70 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -363,10 +363,9 @@ resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled)
 {
 	resource_size_t base = -1;
 
-	down_read(&cxl_dpa_rwsem);
+	lockdep_assert_held(&cxl_dpa_rwsem);
 	if (cxled->dpa_res)
 		base = cxled->dpa_res->start;
-	up_read(&cxl_dpa_rwsem);
 
 	return base;
 }
@@ -839,6 +838,8 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 			cxld->target_type = CXL_DECODER_HOSTONLYMEM;
 		else
 			cxld->target_type = CXL_DECODER_DEVMEM;
+
+		guard(rwsem_write)(&cxl_region_rwsem);
 		if (cxld->id != cxl_num_decoders_committed(port)) {
 			dev_warn(&port->dev,
 				 "decoder%d.%d: Committed out of order\n",
diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index fc5c2b414793bb..2f43d368ba0730 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -227,10 +227,16 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd)
 	if (!port || !is_cxl_endpoint(port))
 		return -EINVAL;
 
-	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	rc = down_read_interruptible(&cxl_region_rwsem);
 	if (rc)
 		return rc;
 
+	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	if (rc) {
+		up_read(&cxl_region_rwsem);
+		return rc;
+	}
+
 	if (cxl_num_decoders_committed(port) == 0) {
 		/* No regions mapped to this memdev */
 		rc = cxl_get_poison_by_memdev(cxlmd);
@@ -239,6 +245,7 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd)
 		rc =  cxl_get_poison_by_endpoint(port);
 	}
 	up_read(&cxl_dpa_rwsem);
+	up_read(&cxl_region_rwsem);
 
 	return rc;
 }
@@ -324,10 +331,16 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	if (!IS_ENABLED(CONFIG_DEBUG_FS))
 		return 0;
 
-	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	rc = down_read_interruptible(&cxl_region_rwsem);
 	if (rc)
 		return rc;
 
+	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	if (rc) {
+		up_read(&cxl_region_rwsem);
+		return rc;
+	}
+
 	rc = cxl_validate_poison_dpa(cxlmd, dpa);
 	if (rc)
 		goto out;
@@ -355,6 +368,7 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_INJECT);
 out:
 	up_read(&cxl_dpa_rwsem);
+	up_read(&cxl_region_rwsem);
 
 	return rc;
 }
@@ -372,10 +386,16 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	if (!IS_ENABLED(CONFIG_DEBUG_FS))
 		return 0;
 
-	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	rc = down_read_interruptible(&cxl_region_rwsem);
 	if (rc)
 		return rc;
 
+	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	if (rc) {
+		up_read(&cxl_region_rwsem);
+		return rc;
+	}
+
 	rc = cxl_validate_poison_dpa(cxlmd, dpa);
 	if (rc)
 		goto out;
@@ -412,6 +432,7 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_CLEAR);
 out:
 	up_read(&cxl_dpa_rwsem);
+	up_read(&cxl_region_rwsem);
 
 	return rc;
 }
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index eff20e83d0a64e..37e1652afbc7ea 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -620,7 +620,7 @@ void read_cdat_data(struct cxl_port *port)
 	struct pci_dev *pdev = NULL;
 	struct cxl_memdev *cxlmd;
 	size_t cdat_length;
-	void *cdat_table;
+	void *cdat_table, *cdat_buf;
 	int rc;
 
 	if (is_cxl_memdev(uport)) {
@@ -651,16 +651,15 @@ void read_cdat_data(struct cxl_port *port)
 		return;
 	}
 
-	cdat_table = devm_kzalloc(dev, cdat_length + sizeof(__le32),
-				  GFP_KERNEL);
-	if (!cdat_table)
+	cdat_buf = devm_kzalloc(dev, cdat_length + sizeof(__le32), GFP_KERNEL);
+	if (!cdat_buf)
 		return;
 
-	rc = cxl_cdat_read_table(dev, cdat_doe, cdat_table, &cdat_length);
+	rc = cxl_cdat_read_table(dev, cdat_doe, cdat_buf, &cdat_length);
 	if (rc)
 		goto err;
 
-	cdat_table = cdat_table + sizeof(__le32);
+	cdat_table = cdat_buf + sizeof(__le32);
 	if (cdat_checksum(cdat_table, cdat_length))
 		goto err;
 
@@ -670,7 +669,7 @@ void read_cdat_data(struct cxl_port *port)
 
 err:
 	/* Don't leave table data allocated on error */
-	devm_kfree(dev, cdat_table);
+	devm_kfree(dev, cdat_buf);
 	dev_err(dev, "Failed to read/validate CDAT.\n");
 }
 EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);
diff --git a/drivers/cxl/core/pmu.c b/drivers/cxl/core/pmu.c
index 7684c843e5a59c..5d8e06b0ba6e88 100644
--- a/drivers/cxl/core/pmu.c
+++ b/drivers/cxl/core/pmu.c
@@ -23,7 +23,7 @@ const struct device_type cxl_pmu_type = {
 
 static void remove_dev(void *dev)
 {
-	device_del(dev);
+	device_unregister(dev);
 }
 
 int devm_cxl_pmu_add(struct device *parent, struct cxl_pmu_regs *regs,
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 38441634e4c683..b7c93bb18f6e75 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -226,9 +226,9 @@ static ssize_t dpa_resource_show(struct device *dev, struct device_attribute *at
 			    char *buf)
 {
 	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
-	u64 base = cxl_dpa_resource_start(cxled);
 
-	return sysfs_emit(buf, "%#llx\n", base);
+	guard(rwsem_read)(&cxl_dpa_rwsem);
+	return sysfs_emit(buf, "%#llx\n", (u64)cxl_dpa_resource_start(cxled));
 }
 static DEVICE_ATTR_RO(dpa_resource);
 
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 56e575c79bb491..3e817a6f94c6a4 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -2467,10 +2467,6 @@ int cxl_get_poison_by_endpoint(struct cxl_port *port)
 	struct cxl_poison_context ctx;
 	int rc = 0;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
-		return rc;
-
 	ctx = (struct cxl_poison_context) {
 		.port = port
 	};
@@ -2480,7 +2476,6 @@ int cxl_get_poison_by_endpoint(struct cxl_port *port)
 		rc = cxl_get_poison_unmapped(to_cxl_memdev(port->uport_dev),
 					     &ctx);
 
-	up_read(&cxl_region_rwsem);
 	return rc;
 }
 
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 38b4110378de05..eb8b733065b24d 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -301,7 +301,7 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence,
 
 		dma_resv_list_entry(fobj, i, obj, &old, &old_usage);
 		if ((old->context == fence->context && old_usage >= usage &&
-		     dma_fence_is_later(fence, old)) ||
+		     dma_fence_is_later_or_same(fence, old)) ||
 		    dma_fence_is_signaled(old)) {
 			dma_resv_list_set(fobj, i, fence, usage);
 			dma_fence_put(old);
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index 6a3abe5b17908d..b53f46245c377f 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -828,6 +828,7 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan)
 	dma_pool_destroy(fsl_chan->tcd_pool);
 	fsl_chan->tcd_pool = NULL;
 	fsl_chan->is_sw = false;
+	fsl_chan->srcid = 0;
 }
 
 void fsl_edma_cleanup_vchan(struct dma_device *dmadev)
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 4635e16d7705e9..238a69bd0d6f5d 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -396,9 +396,8 @@ static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_eng
 		link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS |
 					     DL_FLAG_PM_RUNTIME |
 					     DL_FLAG_RPM_ACTIVE);
-		if (IS_ERR(link)) {
-			dev_err(dev, "Failed to add device_link to %d: %ld\n", i,
-				PTR_ERR(link));
+		if (!link) {
+			dev_err(dev, "Failed to add device_link to %d\n", i);
 			return -EINVAL;
 		}
 
@@ -631,6 +630,8 @@ static int fsl_edma_suspend_late(struct device *dev)
 
 	for (i = 0; i < fsl_edma->n_chans; i++) {
 		fsl_chan = &fsl_edma->chans[i];
+		if (fsl_edma->chan_masked & BIT(i))
+			continue;
 		spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
 		/* Make sure chan is idle or will force disable. */
 		if (unlikely(!fsl_chan->idle)) {
@@ -655,13 +656,16 @@ static int fsl_edma_resume_early(struct device *dev)
 
 	for (i = 0; i < fsl_edma->n_chans; i++) {
 		fsl_chan = &fsl_edma->chans[i];
+		if (fsl_edma->chan_masked & BIT(i))
+			continue;
 		fsl_chan->pm_state = RUNNING;
 		edma_write_tcdreg(fsl_chan, 0, csr);
 		if (fsl_chan->slave_id != 0)
 			fsl_edma_chan_mux(fsl_chan, fsl_chan->slave_id, true);
 	}
 
-	edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr);
+	if (!(fsl_edma->drvdata->flags & FSL_EDMA_DRV_SPLIT_REG))
+		edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr);
 
 	return 0;
 }
diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h
index 7b54a3939ea135..315c004f58e475 100644
--- a/drivers/dma/idxd/registers.h
+++ b/drivers/dma/idxd/registers.h
@@ -440,12 +440,14 @@ union wqcfg {
 /*
  * This macro calculates the offset into the GRPCFG register
  * idxd - struct idxd *
- * n - wq id
- * ofs - the index of the 32b dword for the config register
+ * n - group id
+ * ofs - the index of the 64b qword for the config register
  *
- * The WQCFG register block is divided into groups per each wq. The n index
- * allows us to move to the register group that's for that particular wq.
- * Each register is 32bits. The ofs gives us the number of register to access.
+ * The GRPCFG register block is divided into three sub-registers, which
+ * are GRPWQCFG, GRPENGCFG and GRPFLGCFG. The n index allows us to move
+ * to the register block that contains the three sub-registers.
+ * Each register block is 64bits. And the ofs gives us the offset
+ * within the GRPWQCFG register to access.
  */
 #define GRPWQCFG_OFFSET(idxd_dev, n, ofs) ((idxd_dev)->grpcfg_offset +\
 					   (n) * GRPCFG_SIZE + sizeof(u64) * (ofs))
diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
index c01db23e3333f7..3f922518e3a525 100644
--- a/drivers/dma/idxd/submit.c
+++ b/drivers/dma/idxd/submit.c
@@ -183,13 +183,6 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 	portal = idxd_wq_portal_addr(wq);
 
 	/*
-	 * The wmb() flushes writes to coherent DMA data before
-	 * possibly triggering a DMA read. The wmb() is necessary
-	 * even on UP because the recipient is a device.
-	 */
-	wmb();
-
-	/*
 	 * Pending the descriptor to the lockless list for the irq_entry
 	 * that we designated the descriptor to.
 	 */
@@ -199,6 +192,13 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 		llist_add(&desc->llnode, &ie->pending_llist);
 	}
 
+	/*
+	 * The wmb() flushes writes to coherent DMA data before
+	 * possibly triggering a DMA read. The wmb() is necessary
+	 * even on UP because the recipient is a device.
+	 */
+	wmb();
+
 	if (wq_dedicated(wq)) {
 		iosubmit_cmds512(portal, desc->hw, 1);
 	} else {
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index 72d83cd9ed6bcd..90857d08a1a743 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -1246,8 +1246,8 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy(
 	enum dma_slave_buswidth max_width;
 	struct stm32_dma_desc *desc;
 	size_t xfer_count, offset;
-	u32 num_sgs, best_burst, dma_burst, threshold;
-	int i;
+	u32 num_sgs, best_burst, threshold;
+	int dma_burst, i;
 
 	num_sgs = DIV_ROUND_UP(len, STM32_DMA_ALIGNED_MAX_DATA_ITEMS);
 	desc = kzalloc(struct_size(desc, sg_req, num_sgs), GFP_NOWAIT);
@@ -1266,6 +1266,10 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy(
 		best_burst = stm32_dma_get_best_burst(len, STM32_DMA_MAX_BURST,
 						      threshold, max_width);
 		dma_burst = stm32_dma_get_burst(chan, best_burst);
+		if (dma_burst < 0) {
+			kfree(desc);
+			return NULL;
+		}
 
 		stm32_dma_clear_reg(&desc->sg_req[i].chan_reg);
 		desc->sg_req[i].chan_reg.dma_scr =
diff --git a/drivers/dma/ti/k3-psil-am62.c b/drivers/dma/ti/k3-psil-am62.c
index 2b6fd6e37c6107..1272b1541f61e2 100644
--- a/drivers/dma/ti/k3-psil-am62.c
+++ b/drivers/dma/ti/k3-psil-am62.c
@@ -74,7 +74,9 @@ static struct psil_ep am62_src_ep_map[] = {
 	PSIL_SAUL(0x7505, 21, 35, 8, 36, 0),
 	PSIL_SAUL(0x7506, 22, 43, 8, 43, 0),
 	PSIL_SAUL(0x7507, 23, 43, 8, 44, 0),
-	/* PDMA_MAIN0 - SPI0-3 */
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0x4300),
+	PSIL_PDMA_XY_PKT(0x4301),
 	PSIL_PDMA_XY_PKT(0x4302),
 	PSIL_PDMA_XY_PKT(0x4303),
 	PSIL_PDMA_XY_PKT(0x4304),
@@ -85,8 +87,6 @@ static struct psil_ep am62_src_ep_map[] = {
 	PSIL_PDMA_XY_PKT(0x4309),
 	PSIL_PDMA_XY_PKT(0x430a),
 	PSIL_PDMA_XY_PKT(0x430b),
-	PSIL_PDMA_XY_PKT(0x430c),
-	PSIL_PDMA_XY_PKT(0x430d),
 	/* PDMA_MAIN1 - UART0-6 */
 	PSIL_PDMA_XY_PKT(0x4400),
 	PSIL_PDMA_XY_PKT(0x4401),
@@ -141,7 +141,9 @@ static struct psil_ep am62_dst_ep_map[] = {
 	/* SAUL */
 	PSIL_SAUL(0xf500, 27, 83, 8, 83, 1),
 	PSIL_SAUL(0xf501, 28, 91, 8, 91, 1),
-	/* PDMA_MAIN0 - SPI0-3 */
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0xc300),
+	PSIL_PDMA_XY_PKT(0xc301),
 	PSIL_PDMA_XY_PKT(0xc302),
 	PSIL_PDMA_XY_PKT(0xc303),
 	PSIL_PDMA_XY_PKT(0xc304),
@@ -152,8 +154,6 @@ static struct psil_ep am62_dst_ep_map[] = {
 	PSIL_PDMA_XY_PKT(0xc309),
 	PSIL_PDMA_XY_PKT(0xc30a),
 	PSIL_PDMA_XY_PKT(0xc30b),
-	PSIL_PDMA_XY_PKT(0xc30c),
-	PSIL_PDMA_XY_PKT(0xc30d),
 	/* PDMA_MAIN1 - UART0-6 */
 	PSIL_PDMA_XY_PKT(0xc400),
 	PSIL_PDMA_XY_PKT(0xc401),
diff --git a/drivers/dma/ti/k3-psil-am62a.c b/drivers/dma/ti/k3-psil-am62a.c
index ca9d71f914220a..4cf9123b0e9326 100644
--- a/drivers/dma/ti/k3-psil-am62a.c
+++ b/drivers/dma/ti/k3-psil-am62a.c
@@ -84,7 +84,9 @@ static struct psil_ep am62a_src_ep_map[] = {
 	PSIL_SAUL(0x7505, 21, 35, 8, 36, 0),
 	PSIL_SAUL(0x7506, 22, 43, 8, 43, 0),
 	PSIL_SAUL(0x7507, 23, 43, 8, 44, 0),
-	/* PDMA_MAIN0 - SPI0-3 */
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0x4300),
+	PSIL_PDMA_XY_PKT(0x4301),
 	PSIL_PDMA_XY_PKT(0x4302),
 	PSIL_PDMA_XY_PKT(0x4303),
 	PSIL_PDMA_XY_PKT(0x4304),
@@ -95,8 +97,6 @@ static struct psil_ep am62a_src_ep_map[] = {
 	PSIL_PDMA_XY_PKT(0x4309),
 	PSIL_PDMA_XY_PKT(0x430a),
 	PSIL_PDMA_XY_PKT(0x430b),
-	PSIL_PDMA_XY_PKT(0x430c),
-	PSIL_PDMA_XY_PKT(0x430d),
 	/* PDMA_MAIN1 - UART0-6 */
 	PSIL_PDMA_XY_PKT(0x4400),
 	PSIL_PDMA_XY_PKT(0x4401),
@@ -151,7 +151,9 @@ static struct psil_ep am62a_dst_ep_map[] = {
 	/* SAUL */
 	PSIL_SAUL(0xf500, 27, 83, 8, 83, 1),
 	PSIL_SAUL(0xf501, 28, 91, 8, 91, 1),
-	/* PDMA_MAIN0 - SPI0-3 */
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0xc300),
+	PSIL_PDMA_XY_PKT(0xc301),
 	PSIL_PDMA_XY_PKT(0xc302),
 	PSIL_PDMA_XY_PKT(0xc303),
 	PSIL_PDMA_XY_PKT(0xc304),
@@ -162,8 +164,6 @@ static struct psil_ep am62a_dst_ep_map[] = {
 	PSIL_PDMA_XY_PKT(0xc309),
 	PSIL_PDMA_XY_PKT(0xc30a),
 	PSIL_PDMA_XY_PKT(0xc30b),
-	PSIL_PDMA_XY_PKT(0xc30c),
-	PSIL_PDMA_XY_PKT(0xc30d),
 	/* PDMA_MAIN1 - UART0-6 */
 	PSIL_PDMA_XY_PKT(0xc400),
 	PSIL_PDMA_XY_PKT(0xc401),
diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index a6dc3997bf5c50..ce7cf736f02084 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -925,7 +925,6 @@ dpll_pin_parent_pin_set(struct dpll_pin *pin, struct nlattr *parent_nest,
 			struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[DPLL_A_PIN_MAX + 1];
-	enum dpll_pin_state state;
 	u32 ppin_idx;
 	int ret;
 
@@ -936,10 +935,14 @@ dpll_pin_parent_pin_set(struct dpll_pin *pin, struct nlattr *parent_nest,
 		return -EINVAL;
 	}
 	ppin_idx = nla_get_u32(tb[DPLL_A_PIN_PARENT_ID]);
-	state = nla_get_u32(tb[DPLL_A_PIN_STATE]);
-	ret = dpll_pin_on_pin_state_set(pin, ppin_idx, state, extack);
-	if (ret)
-		return ret;
+
+	if (tb[DPLL_A_PIN_STATE]) {
+		enum dpll_pin_state state = nla_get_u32(tb[DPLL_A_PIN_STATE]);
+
+		ret = dpll_pin_on_pin_state_set(pin, ppin_idx, state, extack);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
 }
@@ -1093,9 +1096,10 @@ int dpll_nl_pin_id_get_doit(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 	hdr = genlmsg_put_reply(msg, info, &dpll_nl_family, 0,
 				DPLL_CMD_PIN_ID_GET);
-	if (!hdr)
+	if (!hdr) {
+		nlmsg_free(msg);
 		return -EMSGSIZE;
-
+	}
 	pin = dpll_pin_find_from_nlattr(info);
 	if (!IS_ERR(pin)) {
 		ret = dpll_msg_add_pin_handle(msg, pin);
@@ -1123,8 +1127,10 @@ int dpll_nl_pin_get_doit(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 	hdr = genlmsg_put_reply(msg, info, &dpll_nl_family, 0,
 				DPLL_CMD_PIN_GET);
-	if (!hdr)
+	if (!hdr) {
+		nlmsg_free(msg);
 		return -EMSGSIZE;
+	}
 	ret = dpll_cmd_pin_get_one(msg, pin, info->extack);
 	if (ret) {
 		nlmsg_free(msg);
@@ -1256,8 +1262,10 @@ int dpll_nl_device_id_get_doit(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 	hdr = genlmsg_put_reply(msg, info, &dpll_nl_family, 0,
 				DPLL_CMD_DEVICE_ID_GET);
-	if (!hdr)
+	if (!hdr) {
+		nlmsg_free(msg);
 		return -EMSGSIZE;
+	}
 
 	dpll = dpll_device_find_from_nlattr(info);
 	if (!IS_ERR(dpll)) {
@@ -1284,8 +1292,10 @@ int dpll_nl_device_get_doit(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 	hdr = genlmsg_put_reply(msg, info, &dpll_nl_family, 0,
 				DPLL_CMD_DEVICE_GET);
-	if (!hdr)
+	if (!hdr) {
+		nlmsg_free(msg);
 		return -EMSGSIZE;
+	}
 
 	ret = dpll_device_get_one(dpll, msg, info->extack);
 	if (ret) {
diff --git a/drivers/edac/versal_edac.c b/drivers/edac/versal_edac.c
index 87e730dfefa08d..8625de20fc7175 100644
--- a/drivers/edac/versal_edac.c
+++ b/drivers/edac/versal_edac.c
@@ -966,10 +966,10 @@ static int mc_probe(struct platform_device *pdev)
 	edac_mc_id = emif_get_id(pdev->dev.of_node);
 
 	regval = readl(ddrmc_baseaddr + XDDR_REG_CONFIG0_OFFSET);
-	num_chans = FIELD_PREP(XDDR_REG_CONFIG0_NUM_CHANS_MASK, regval);
+	num_chans = FIELD_GET(XDDR_REG_CONFIG0_NUM_CHANS_MASK, regval);
 	num_chans++;
 
-	num_csrows = FIELD_PREP(XDDR_REG_CONFIG0_NUM_RANKS_MASK, regval);
+	num_csrows = FIELD_GET(XDDR_REG_CONFIG0_NUM_RANKS_MASK, regval);
 	num_csrows *= 2;
 	if (!num_csrows)
 		num_csrows = 1;
diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index aa597cda0d8874..2828e9573e90be 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -717,14 +717,11 @@ static void create_units(struct fw_device *device)
 					fw_unit_attributes,
 					&unit->attribute_group);
 
-		if (device_register(&unit->device) < 0)
-			goto skip_unit;
-
 		fw_device_get(device);
-		continue;
-
-	skip_unit:
-		kfree(unit);
+		if (device_register(&unit->device) < 0) {
+			put_device(&unit->device);
+			continue;
+		}
 	}
 }
 
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index 7edf2c95282fa2..e779d866022b9f 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -1519,9 +1519,9 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev)
 	sdev->use_10_for_rw = 1;
 
 	if (sbp2_param_exclusive_login) {
-		sdev->manage_system_start_stop = true;
-		sdev->manage_runtime_start_stop = true;
-		sdev->manage_shutdown = true;
+		sdev->manage_system_start_stop = 1;
+		sdev->manage_runtime_start_stop = 1;
+		sdev->manage_shutdown = 1;
 	}
 
 	if (sdev->type == TYPE_ROM)
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 74d00b0c83fea7..4a98a859d44d34 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -131,7 +131,7 @@ config RASPBERRYPI_FIRMWARE
 
 config FW_CFG_SYSFS
 	tristate "QEMU fw_cfg device support in sysfs"
-	depends on SYSFS && (ARM || ARM64 || PARISC || PPC_PMAC || SPARC || X86)
+	depends on SYSFS && (ARM || ARM64 || PARISC || PPC_PMAC || RISCV || SPARC || X86)
 	depends on HAS_IOPORT_MAP
 	default n
 	help
diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 07b72c67924704..6146b2927d5c56 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -99,6 +99,7 @@ struct ffa_drv_info {
 	void *tx_buffer;
 	bool mem_ops_native;
 	bool bitmap_created;
+	bool notif_enabled;
 	unsigned int sched_recv_irq;
 	unsigned int cpuhp_state;
 	struct ffa_pcpu_irq __percpu *irq_pcpu;
@@ -782,7 +783,7 @@ static void ffa_notification_info_get(void)
 			if (ids_processed >= max_ids - 1)
 				break;
 
-			part_id = packed_id_list[++ids_processed];
+			part_id = packed_id_list[ids_processed++];
 
 			if (!ids_count[list]) { /* Global Notification */
 				__do_sched_recv_cb(part_id, 0, false);
@@ -794,7 +795,7 @@ static void ffa_notification_info_get(void)
 				if (ids_processed >= max_ids - 1)
 					break;
 
-				vcpu_id = packed_id_list[++ids_processed];
+				vcpu_id = packed_id_list[ids_processed++];
 
 				__do_sched_recv_cb(part_id, vcpu_id, true);
 			}
@@ -889,6 +890,8 @@ static int ffa_memory_lend(struct ffa_mem_ops_args *args)
 
 #define FFA_SECURE_PARTITION_ID_FLAG	BIT(15)
 
+#define ffa_notifications_disabled()	(!drv_info->notif_enabled)
+
 enum notify_type {
 	NON_SECURE_VM,
 	SECURE_PARTITION,
@@ -908,6 +911,9 @@ static int ffa_sched_recv_cb_update(u16 part_id, ffa_sched_recv_cb callback,
 	struct ffa_dev_part_info *partition;
 	bool cb_valid;
 
+	if (ffa_notifications_disabled())
+		return -EOPNOTSUPP;
+
 	partition = xa_load(&drv_info->partition_info, part_id);
 	write_lock(&partition->rw_lock);
 
@@ -1001,6 +1007,9 @@ static int ffa_notify_relinquish(struct ffa_device *dev, int notify_id)
 	int rc;
 	enum notify_type type = ffa_notify_type_get(dev->vm_id);
 
+	if (ffa_notifications_disabled())
+		return -EOPNOTSUPP;
+
 	if (notify_id >= FFA_MAX_NOTIFICATIONS)
 		return -EINVAL;
 
@@ -1027,6 +1036,9 @@ static int ffa_notify_request(struct ffa_device *dev, bool is_per_vcpu,
 	u32 flags = 0;
 	enum notify_type type = ffa_notify_type_get(dev->vm_id);
 
+	if (ffa_notifications_disabled())
+		return -EOPNOTSUPP;
+
 	if (notify_id >= FFA_MAX_NOTIFICATIONS)
 		return -EINVAL;
 
@@ -1057,6 +1069,9 @@ static int ffa_notify_send(struct ffa_device *dev, int notify_id,
 {
 	u32 flags = 0;
 
+	if (ffa_notifications_disabled())
+		return -EOPNOTSUPP;
+
 	if (is_per_vcpu)
 		flags |= (PER_VCPU_NOTIFICATION_FLAG | vcpu << 16);
 
@@ -1233,7 +1248,7 @@ static void ffa_partitions_cleanup(void)
 	if (!count)
 		return;
 
-	info = kcalloc(count, sizeof(**info), GFP_KERNEL);
+	info = kcalloc(count, sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return;
 
@@ -1311,8 +1326,10 @@ static int ffa_sched_recv_irq_map(void)
 
 static void ffa_sched_recv_irq_unmap(void)
 {
-	if (drv_info->sched_recv_irq)
+	if (drv_info->sched_recv_irq) {
 		irq_dispose_mapping(drv_info->sched_recv_irq);
+		drv_info->sched_recv_irq = 0;
+	}
 }
 
 static int ffa_cpuhp_pcpu_irq_enable(unsigned int cpu)
@@ -1329,17 +1346,23 @@ static int ffa_cpuhp_pcpu_irq_disable(unsigned int cpu)
 
 static void ffa_uninit_pcpu_irq(void)
 {
-	if (drv_info->cpuhp_state)
+	if (drv_info->cpuhp_state) {
 		cpuhp_remove_state(drv_info->cpuhp_state);
+		drv_info->cpuhp_state = 0;
+	}
 
-	if (drv_info->notif_pcpu_wq)
+	if (drv_info->notif_pcpu_wq) {
 		destroy_workqueue(drv_info->notif_pcpu_wq);
+		drv_info->notif_pcpu_wq = NULL;
+	}
 
 	if (drv_info->sched_recv_irq)
 		free_percpu_irq(drv_info->sched_recv_irq, drv_info->irq_pcpu);
 
-	if (drv_info->irq_pcpu)
+	if (drv_info->irq_pcpu) {
 		free_percpu(drv_info->irq_pcpu);
+		drv_info->irq_pcpu = NULL;
+	}
 }
 
 static int ffa_init_pcpu_irq(unsigned int irq)
@@ -1388,22 +1411,23 @@ static void ffa_notifications_cleanup(void)
 		ffa_notification_bitmap_destroy();
 		drv_info->bitmap_created = false;
 	}
+	drv_info->notif_enabled = false;
 }
 
-static int ffa_notifications_setup(void)
+static void ffa_notifications_setup(void)
 {
 	int ret, irq;
 
 	ret = ffa_features(FFA_NOTIFICATION_BITMAP_CREATE, 0, NULL, NULL);
 	if (ret) {
-		pr_err("Notifications not supported, continuing with it ..\n");
-		return 0;
+		pr_info("Notifications not supported, continuing with it ..\n");
+		return;
 	}
 
 	ret = ffa_notification_bitmap_create();
 	if (ret) {
-		pr_err("notification_bitmap_create error %d\n", ret);
-		return ret;
+		pr_info("Notification bitmap create error %d\n", ret);
+		return;
 	}
 	drv_info->bitmap_created = true;
 
@@ -1422,14 +1446,11 @@ static int ffa_notifications_setup(void)
 	hash_init(drv_info->notifier_hash);
 	mutex_init(&drv_info->notify_lock);
 
-	/* Register internal scheduling callback */
-	ret = ffa_sched_recv_cb_update(drv_info->vm_id, ffa_self_notif_handle,
-				       drv_info, true);
-	if (!ret)
-		return ret;
+	drv_info->notif_enabled = true;
+	return;
 cleanup:
+	pr_info("Notification setup failed %d, not enabled\n", ret);
 	ffa_notifications_cleanup();
-	return ret;
 }
 
 static int __init ffa_init(void)
@@ -1483,17 +1504,18 @@ static int __init ffa_init(void)
 	mutex_init(&drv_info->rx_lock);
 	mutex_init(&drv_info->tx_lock);
 
-	ffa_setup_partitions();
-
 	ffa_set_up_mem_ops_native_flag();
 
-	ret = ffa_notifications_setup();
+	ffa_notifications_setup();
+
+	ffa_setup_partitions();
+
+	ret = ffa_sched_recv_cb_update(drv_info->vm_id, ffa_self_notif_handle,
+				       drv_info, true);
 	if (ret)
-		goto partitions_cleanup;
+		pr_info("Failed to register driver sched callback %d\n", ret);
 
 	return 0;
-partitions_cleanup:
-	ffa_partitions_cleanup();
 free_pages:
 	if (drv_info->tx_buffer)
 		free_pages_exact(drv_info->tx_buffer, RXTX_BUFFER_SIZE);
diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index c2435be0ae1be8..e11555de99ab86 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -152,7 +152,7 @@ struct perf_dom_info {
 	u32 opp_count;
 	u32 sustained_freq_khz;
 	u32 sustained_perf_level;
-	u32 mult_factor;
+	unsigned long mult_factor;
 	struct scmi_perf_domain_info info;
 	struct scmi_opp opp[MAX_OPPS];
 	struct scmi_fc_info *fc_info;
@@ -268,13 +268,14 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph,
 		dom_info->sustained_perf_level =
 					le32_to_cpu(attr->sustained_perf_level);
 		if (!dom_info->sustained_freq_khz ||
-		    !dom_info->sustained_perf_level)
+		    !dom_info->sustained_perf_level ||
+		    dom_info->level_indexing_mode)
 			/* CPUFreq converts to kHz, hence default 1000 */
 			dom_info->mult_factor =	1000;
 		else
 			dom_info->mult_factor =
-					(dom_info->sustained_freq_khz * 1000) /
-					dom_info->sustained_perf_level;
+					(dom_info->sustained_freq_khz * 1000UL)
+					/ dom_info->sustained_perf_level;
 		strscpy(dom_info->info.name, attr->name,
 			SCMI_SHORT_NAME_MAX_SIZE);
 	}
@@ -798,7 +799,7 @@ static int scmi_dvfs_device_opps_add(const struct scmi_protocol_handle *ph,
 		if (!dom->level_indexing_mode)
 			freq = dom->opp[idx].perf * dom->mult_factor;
 		else
-			freq = dom->opp[idx].indicative_freq * 1000;
+			freq = dom->opp[idx].indicative_freq * dom->mult_factor;
 
 		data.level = dom->opp[idx].perf;
 		data.freq = freq;
@@ -845,7 +846,8 @@ static int scmi_dvfs_freq_set(const struct scmi_protocol_handle *ph, u32 domain,
 	} else {
 		struct scmi_opp *opp;
 
-		opp = LOOKUP_BY_FREQ(dom->opps_by_freq, freq / 1000);
+		opp = LOOKUP_BY_FREQ(dom->opps_by_freq,
+				     freq / dom->mult_factor);
 		if (!opp)
 			return -EIO;
 
@@ -879,7 +881,7 @@ static int scmi_dvfs_freq_get(const struct scmi_protocol_handle *ph, u32 domain,
 		if (!opp)
 			return -EIO;
 
-		*freq = opp->indicative_freq * 1000;
+		*freq = opp->indicative_freq * dom->mult_factor;
 	}
 
 	return ret;
@@ -902,7 +904,7 @@ static int scmi_dvfs_est_power_get(const struct scmi_protocol_handle *ph,
 		if (!dom->level_indexing_mode)
 			opp_freq = opp->perf * dom->mult_factor;
 		else
-			opp_freq = opp->indicative_freq * 1000;
+			opp_freq = opp->indicative_freq * dom->mult_factor;
 
 		if (opp_freq < *freq)
 			continue;
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index ef4c12f0877ba4..06964a3c130f6a 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -28,7 +28,7 @@ cflags-$(CONFIG_ARM)		+= -DEFI_HAVE_STRLEN -DEFI_HAVE_STRNLEN \
 				   -DEFI_HAVE_MEMCHR -DEFI_HAVE_STRRCHR \
 				   -DEFI_HAVE_STRCMP -fno-builtin -fpic \
 				   $(call cc-option,-mno-single-pic-base)
-cflags-$(CONFIG_RISCV)		+= -fpic
+cflags-$(CONFIG_RISCV)		+= -fpic -DNO_ALTERNATIVE
 cflags-$(CONFIG_LOONGARCH)	+= -fpie
 
 cflags-$(CONFIG_EFI_PARAMS_FROM_FDT)	+= -I$(srctree)/scripts/dtc/libfdt
diff --git a/drivers/firmware/efi/libstub/loongarch-stub.c b/drivers/firmware/efi/libstub/loongarch-stub.c
index 72c71ae201f0da..d6ec5d4b8dbe08 100644
--- a/drivers/firmware/efi/libstub/loongarch-stub.c
+++ b/drivers/firmware/efi/libstub/loongarch-stub.c
@@ -35,9 +35,9 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 	return status;
 }
 
-unsigned long kernel_entry_address(void)
+unsigned long kernel_entry_address(unsigned long kernel_addr)
 {
 	unsigned long base = (unsigned long)&kernel_offset - kernel_offset;
 
-	return (unsigned long)&kernel_entry - base + VMLINUX_LOAD_ADDRESS;
+	return (unsigned long)&kernel_entry - base + kernel_addr;
 }
diff --git a/drivers/firmware/efi/libstub/loongarch.c b/drivers/firmware/efi/libstub/loongarch.c
index 807cba2693fc17..0e0aa6cda73f7c 100644
--- a/drivers/firmware/efi/libstub/loongarch.c
+++ b/drivers/firmware/efi/libstub/loongarch.c
@@ -37,9 +37,9 @@ static efi_status_t exit_boot_func(struct efi_boot_memmap *map, void *priv)
 	return EFI_SUCCESS;
 }
 
-unsigned long __weak kernel_entry_address(void)
+unsigned long __weak kernel_entry_address(unsigned long kernel_addr)
 {
-	return *(unsigned long *)(PHYSADDR(VMLINUX_LOAD_ADDRESS) + 8);
+	return *(unsigned long *)(kernel_addr + 8) - VMLINUX_LOAD_ADDRESS + kernel_addr;
 }
 
 efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image,
@@ -73,7 +73,7 @@ efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image,
 	csr_write64(CSR_DMW0_INIT, LOONGARCH_CSR_DMWIN0);
 	csr_write64(CSR_DMW1_INIT, LOONGARCH_CSR_DMWIN1);
 
-	real_kernel_entry = (void *)kernel_entry_address();
+	real_kernel_entry = (void *)kernel_entry_address(kernel_addr);
 
 	real_kernel_entry(true, (unsigned long)cmdline_ptr,
 			  (unsigned long)efi_system_table);
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 1bfdae34df3934..da9b7b8d0716df 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -307,17 +307,20 @@ static void setup_unaccepted_memory(void)
 		efi_err("Memory acceptance protocol failed\n");
 }
 
+static efi_char16_t *efistub_fw_vendor(void)
+{
+	unsigned long vendor = efi_table_attr(efi_system_table, fw_vendor);
+
+	return (efi_char16_t *)vendor;
+}
+
 static const efi_char16_t apple[] = L"Apple";
 
 static void setup_quirks(struct boot_params *boot_params)
 {
-	efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long)
-		efi_table_attr(efi_system_table, fw_vendor);
-
-	if (!memcmp(fw_vendor, apple, sizeof(apple))) {
-		if (IS_ENABLED(CONFIG_APPLE_PROPERTIES))
-			retrieve_apple_device_properties(boot_params);
-	}
+	if (IS_ENABLED(CONFIG_APPLE_PROPERTIES) &&
+	    !memcmp(efistub_fw_vendor(), apple, sizeof(apple)))
+		retrieve_apple_device_properties(boot_params);
 }
 
 /*
@@ -765,11 +768,25 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry)
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && !efi_nokaslr) {
 		u64 range = KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR - kernel_total_size;
+		static const efi_char16_t ami[] = L"American Megatrends";
 
 		efi_get_seed(seed, sizeof(seed));
 
 		virt_addr += (range * seed[1]) >> 32;
 		virt_addr &= ~(CONFIG_PHYSICAL_ALIGN - 1);
+
+		/*
+		 * Older Dell systems with AMI UEFI firmware v2.0 may hang
+		 * while decompressing the kernel if physical address
+		 * randomization is enabled.
+		 *
+		 * https://bugzilla.kernel.org/show_bug.cgi?id=218173
+		 */
+		if (efi_system_table->hdr.revision <= EFI_2_00_SYSTEM_TABLE_REVISION &&
+		    !memcmp(efistub_fw_vendor(), ami, sizeof(ami))) {
+			efi_debug("AMI firmware v2.0 or older detected - disabling physical KASLR\n");
+			seed[0] = 0;
+		}
 	}
 
 	status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr,
diff --git a/drivers/firmware/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c
index 3f2f7bf6e33526..5b439d04079c84 100644
--- a/drivers/firmware/efi/unaccepted_memory.c
+++ b/drivers/firmware/efi/unaccepted_memory.c
@@ -101,7 +101,7 @@ retry:
 	 * overlap on physical address level.
 	 */
 	list_for_each_entry(entry, &accepting_list, list) {
-		if (entry->end < range.start)
+		if (entry->end <= range.start)
 			continue;
 		if (entry->start >= range.end)
 			continue;
diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index a69399a6b7c005..1448f61173b357 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -211,7 +211,7 @@ static void fw_cfg_io_cleanup(void)
 
 /* arch-specific ctrl & data register offsets are not available in ACPI, DT */
 #if !(defined(FW_CFG_CTRL_OFF) && defined(FW_CFG_DATA_OFF))
-# if (defined(CONFIG_ARM) || defined(CONFIG_ARM64))
+# if (defined(CONFIG_ARM) || defined(CONFIG_ARM64) || defined(CONFIG_RISCV))
 #  define FW_CFG_CTRL_OFF 0x08
 #  define FW_CFG_DATA_OFF 0x00
 #  define FW_CFG_DMA_OFF 0x10
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index 4a4f61bf6c5824..8c59332429c260 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -282,13 +282,15 @@ static void dwapb_irq_enable(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct dwapb_gpio *gpio = to_dwapb_gpio(gc);
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 	unsigned long flags;
 	u32 val;
 
 	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
-	val = dwapb_read(gpio, GPIO_INTEN);
-	val |= BIT(irqd_to_hwirq(d));
+	val = dwapb_read(gpio, GPIO_INTEN) | BIT(hwirq);
 	dwapb_write(gpio, GPIO_INTEN, val);
+	val = dwapb_read(gpio, GPIO_INTMASK) & ~BIT(hwirq);
+	dwapb_write(gpio, GPIO_INTMASK, val);
 	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
 
@@ -296,12 +298,14 @@ static void dwapb_irq_disable(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct dwapb_gpio *gpio = to_dwapb_gpio(gc);
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 	unsigned long flags;
 	u32 val;
 
 	raw_spin_lock_irqsave(&gc->bgpio_lock, flags);
-	val = dwapb_read(gpio, GPIO_INTEN);
-	val &= ~BIT(irqd_to_hwirq(d));
+	val = dwapb_read(gpio, GPIO_INTMASK) | BIT(hwirq);
+	dwapb_write(gpio, GPIO_INTMASK, val);
+	val = dwapb_read(gpio, GPIO_INTEN) & ~BIT(hwirq);
 	dwapb_write(gpio, GPIO_INTEN, val);
 	raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags);
 }
diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c
index 02ffda6c1e5124..f713d1ef7746e4 100644
--- a/drivers/gpio/gpiolib-cdev.c
+++ b/drivers/gpio/gpiolib-cdev.c
@@ -2481,10 +2481,7 @@ static int lineinfo_unwatch(struct gpio_chardev_data *cdev, void __user *ip)
 	return 0;
 }
 
-/*
- * gpio_ioctl() - ioctl handler for the GPIO chardev
- */
-static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+static long gpio_ioctl_unlocked(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct gpio_chardev_data *cdev = file->private_data;
 	struct gpio_device *gdev = cdev->gdev;
@@ -2521,6 +2518,17 @@ static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	}
 }
 
+/*
+ * gpio_ioctl() - ioctl handler for the GPIO chardev
+ */
+static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct gpio_chardev_data *cdev = file->private_data;
+
+	return call_ioctl_locked(file, cmd, arg, cdev->gdev,
+				 gpio_ioctl_unlocked);
+}
+
 #ifdef CONFIG_COMPAT
 static long gpio_ioctl_compat(struct file *file, unsigned int cmd,
 			      unsigned long arg)
diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c
index 6f309a3b2d9ade..12d853845bb803 100644
--- a/drivers/gpio/gpiolib-sysfs.c
+++ b/drivers/gpio/gpiolib-sysfs.c
@@ -474,14 +474,17 @@ static ssize_t export_store(const struct class *class,
 		goto done;
 
 	status = gpiod_set_transitory(desc, false);
-	if (!status) {
-		status = gpiod_export(desc, true);
-		if (status < 0)
-			gpiod_free(desc);
-		else
-			set_bit(FLAG_SYSFS, &desc->flags);
+	if (status) {
+		gpiod_free(desc);
+		goto done;
 	}
 
+	status = gpiod_export(desc, true);
+	if (status < 0)
+		gpiod_free(desc);
+	else
+		set_bit(FLAG_SYSFS, &desc->flags);
+
 done:
 	if (status)
 		pr_debug("%s: status %d\n", __func__, status);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 8b4ca2576a3d69..9d92ca1576771b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -248,6 +248,7 @@ extern int amdgpu_umsch_mm;
 extern int amdgpu_seamless;
 
 extern int amdgpu_user_partt_mode;
+extern int amdgpu_agp;
 
 #define AMDGPU_VM_MAX_NUM_CTX			4096
 #define AMDGPU_SG_THRESHOLD			(256*1024*1024)
@@ -1159,11 +1160,18 @@ uint32_t amdgpu_device_rreg(struct amdgpu_device *adev,
 			    uint32_t reg, uint32_t acc_flags);
 u32 amdgpu_device_indirect_rreg_ext(struct amdgpu_device *adev,
 				    u64 reg_addr);
+uint32_t amdgpu_device_xcc_rreg(struct amdgpu_device *adev,
+				uint32_t reg, uint32_t acc_flags,
+				uint32_t xcc_id);
 void amdgpu_device_wreg(struct amdgpu_device *adev,
 			uint32_t reg, uint32_t v,
 			uint32_t acc_flags);
 void amdgpu_device_indirect_wreg_ext(struct amdgpu_device *adev,
 				     u64 reg_addr, u32 reg_data);
+void amdgpu_device_xcc_wreg(struct amdgpu_device *adev,
+			    uint32_t reg, uint32_t v,
+			    uint32_t acc_flags,
+			    uint32_t xcc_id);
 void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev,
 			     uint32_t reg, uint32_t v, uint32_t xcc_id);
 void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value);
@@ -1204,8 +1212,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 #define RREG32_NO_KIQ(reg) amdgpu_device_rreg(adev, (reg), AMDGPU_REGS_NO_KIQ)
 #define WREG32_NO_KIQ(reg, v) amdgpu_device_wreg(adev, (reg), (v), AMDGPU_REGS_NO_KIQ)
 
-#define RREG32_KIQ(reg) amdgpu_kiq_rreg(adev, (reg))
-#define WREG32_KIQ(reg, v) amdgpu_kiq_wreg(adev, (reg), (v))
+#define RREG32_KIQ(reg) amdgpu_kiq_rreg(adev, (reg), 0)
+#define WREG32_KIQ(reg, v) amdgpu_kiq_wreg(adev, (reg), (v), 0)
 
 #define RREG8(reg) amdgpu_mm_rreg8(adev, (reg))
 #define WREG8(reg, v) amdgpu_mm_wreg8(adev, (reg), (v))
@@ -1215,6 +1223,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 #define WREG32(reg, v) amdgpu_device_wreg(adev, (reg), (v), 0)
 #define REG_SET(FIELD, v) (((v) << FIELD##_SHIFT) & FIELD##_MASK)
 #define REG_GET(FIELD, v) (((v) << FIELD##_SHIFT) & FIELD##_MASK)
+#define RREG32_XCC(reg, inst) amdgpu_device_xcc_rreg(adev, (reg), 0, inst)
+#define WREG32_XCC(reg, v, inst) amdgpu_device_xcc_wreg(adev, (reg), (v), 0, inst)
 #define RREG32_PCIE(reg) adev->pcie_rreg(adev, (reg))
 #define WREG32_PCIE(reg, v) adev->pcie_wreg(adev, (reg), (v))
 #define RREG32_PCIE_PORT(reg) adev->pciep_rreg(adev, (reg))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 4da82fc64fef45..2deebece810e78 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -1494,6 +1494,9 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev)
 	if (adev->asic_type < CHIP_RAVEN)
 		return false;
 
+	if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
+		return false;
+
 	/*
 	 * If ACPI_FADT_LOW_POWER_S0 is not set in the FADT, it is generally
 	 * risky to do any special firmware-related preparations for entering
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index b8412202a1b0e1..75dc58470393ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -547,7 +547,7 @@ int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct amdgpu_device *dst,
 	struct amdgpu_device *adev = dst, *peer_adev;
 	int num_links;
 
-	if (adev->asic_type != CHIP_ALDEBARAN)
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(9, 4, 2))
 		return 0;
 
 	if (src)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c
index 490c8f5ddb602a..f6598b9e4faa35 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c
@@ -300,14 +300,13 @@ static int kgd_gfx_v9_4_3_hqd_load(struct amdgpu_device *adev, void *mqd,
 	hqd_end = SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_AQL_DISPATCH_ID_HI);
 
 	for (reg = hqd_base; reg <= hqd_end; reg++)
-		WREG32_RLC(reg, mqd_hqd[reg - hqd_base]);
+		WREG32_XCC(reg, mqd_hqd[reg - hqd_base], inst);
 
 
 	/* Activate doorbell logic before triggering WPTR poll. */
 	data = REG_SET_FIELD(m->cp_hqd_pq_doorbell_control,
 			     CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 1);
-	WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_PQ_DOORBELL_CONTROL),
-				data);
+	WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_PQ_DOORBELL_CONTROL, data);
 
 	if (wptr) {
 		/* Don't read wptr with get_user because the user
@@ -336,27 +335,24 @@ static int kgd_gfx_v9_4_3_hqd_load(struct amdgpu_device *adev, void *mqd,
 		guessed_wptr += m->cp_hqd_pq_wptr_lo & ~(queue_size - 1);
 		guessed_wptr += (uint64_t)m->cp_hqd_pq_wptr_hi << 32;
 
-		WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_LO),
-		       lower_32_bits(guessed_wptr));
-		WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_HI),
-		       upper_32_bits(guessed_wptr));
-		WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_POLL_ADDR),
-		       lower_32_bits((uintptr_t)wptr));
-		WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst),
-			regCP_HQD_PQ_WPTR_POLL_ADDR_HI),
+		WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_LO,
+			lower_32_bits(guessed_wptr));
+		WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_HI,
+			upper_32_bits(guessed_wptr));
+		WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_POLL_ADDR,
+			lower_32_bits((uintptr_t)wptr));
+		WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_PQ_WPTR_POLL_ADDR_HI,
 			upper_32_bits((uintptr_t)wptr));
-		WREG32(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_PQ_WPTR_POLL_CNTL1),
-		       (uint32_t)kgd_gfx_v9_get_queue_mask(adev, pipe_id,
-			       queue_id));
+		WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_PQ_WPTR_POLL_CNTL1,
+			(uint32_t)kgd_gfx_v9_get_queue_mask(adev, pipe_id, queue_id));
 	}
 
 	/* Start the EOP fetcher */
-	WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_EOP_RPTR),
-	       REG_SET_FIELD(m->cp_hqd_eop_rptr,
-			     CP_HQD_EOP_RPTR, INIT_FETCHER, 1));
+	WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_EOP_RPTR,
+	       REG_SET_FIELD(m->cp_hqd_eop_rptr, CP_HQD_EOP_RPTR, INIT_FETCHER, 1));
 
 	data = REG_SET_FIELD(m->cp_hqd_active, CP_HQD_ACTIVE, ACTIVE, 1);
-	WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), regCP_HQD_ACTIVE), data);
+	WREG32_SOC15_RLC(GC, GET_INST(GC, inst), regCP_HQD_ACTIVE, data);
 
 	kgd_gfx_v9_release_queue(adev, inst);
 
@@ -494,15 +490,15 @@ static uint32_t kgd_gfx_v9_4_3_set_address_watch(
 			VALID,
 			1);
 
-	WREG32_RLC((SOC15_REG_OFFSET(GC, GET_INST(GC, inst),
+	WREG32_XCC((SOC15_REG_OFFSET(GC, GET_INST(GC, inst),
 			regTCP_WATCH0_ADDR_H) +
 			(watch_id * TCP_WATCH_STRIDE)),
-			watch_address_high);
+			watch_address_high, inst);
 
-	WREG32_RLC((SOC15_REG_OFFSET(GC, GET_INST(GC, inst),
+	WREG32_XCC((SOC15_REG_OFFSET(GC, GET_INST(GC, inst),
 			regTCP_WATCH0_ADDR_L) +
 			(watch_id * TCP_WATCH_STRIDE)),
-			watch_address_low);
+			watch_address_low, inst);
 
 	return watch_address_cntl;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 51011e8ee90dcf..00fbc0f44c929b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -91,8 +91,8 @@ void kgd_gfx_v9_program_sh_mem_settings(struct amdgpu_device *adev, uint32_t vmi
 {
 	kgd_gfx_v9_lock_srbm(adev, 0, 0, 0, vmid, inst);
 
-	WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmSH_MEM_CONFIG), sh_mem_config);
-	WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmSH_MEM_BASES), sh_mem_bases);
+	WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmSH_MEM_CONFIG, sh_mem_config);
+	WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmSH_MEM_BASES, sh_mem_bases);
 	/* APE1 no longer exists on GFX9 */
 
 	kgd_gfx_v9_unlock_srbm(adev, inst);
@@ -239,14 +239,13 @@ int kgd_gfx_v9_hqd_load(struct amdgpu_device *adev, void *mqd,
 
 	for (reg = hqd_base;
 	     reg <= SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_HI); reg++)
-		WREG32_RLC(reg, mqd_hqd[reg - hqd_base]);
+		WREG32_XCC(reg, mqd_hqd[reg - hqd_base], inst);
 
 
 	/* Activate doorbell logic before triggering WPTR poll. */
 	data = REG_SET_FIELD(m->cp_hqd_pq_doorbell_control,
 			     CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 1);
-	WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_PQ_DOORBELL_CONTROL),
-					data);
+	WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_PQ_DOORBELL_CONTROL, data);
 
 	if (wptr) {
 		/* Don't read wptr with get_user because the user
@@ -275,25 +274,24 @@ int kgd_gfx_v9_hqd_load(struct amdgpu_device *adev, void *mqd,
 		guessed_wptr += m->cp_hqd_pq_wptr_lo & ~(queue_size - 1);
 		guessed_wptr += (uint64_t)m->cp_hqd_pq_wptr_hi << 32;
 
-		WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_LO),
-		       lower_32_bits(guessed_wptr));
-		WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_HI),
-		       upper_32_bits(guessed_wptr));
-		WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_POLL_ADDR),
-		       lower_32_bits((uintptr_t)wptr));
-		WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_POLL_ADDR_HI),
-		       upper_32_bits((uintptr_t)wptr));
-		WREG32_SOC15(GC, GET_INST(GC, inst), mmCP_PQ_WPTR_POLL_CNTL1,
-		       (uint32_t)kgd_gfx_v9_get_queue_mask(adev, pipe_id, queue_id));
+		WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_LO,
+			lower_32_bits(guessed_wptr));
+		WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_HI,
+			upper_32_bits(guessed_wptr));
+		WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_POLL_ADDR,
+			lower_32_bits((uintptr_t)wptr));
+		WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_POLL_ADDR_HI,
+			upper_32_bits((uintptr_t)wptr));
+		WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_PQ_WPTR_POLL_CNTL1,
+			(uint32_t)kgd_gfx_v9_get_queue_mask(adev, pipe_id, queue_id));
 	}
 
 	/* Start the EOP fetcher */
-	WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_EOP_RPTR),
-	       REG_SET_FIELD(m->cp_hqd_eop_rptr,
-			     CP_HQD_EOP_RPTR, INIT_FETCHER, 1));
+	WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_EOP_RPTR,
+	       REG_SET_FIELD(m->cp_hqd_eop_rptr, CP_HQD_EOP_RPTR, INIT_FETCHER, 1));
 
 	data = REG_SET_FIELD(m->cp_hqd_active, CP_HQD_ACTIVE, ACTIVE, 1);
-	WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_ACTIVE), data);
+	WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_ACTIVE, data);
 
 	kgd_gfx_v9_release_queue(adev, inst);
 
@@ -556,7 +554,7 @@ int kgd_gfx_v9_hqd_destroy(struct amdgpu_device *adev, void *mqd,
 		break;
 	}
 
-	WREG32_RLC(SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_DEQUEUE_REQUEST), type);
+	WREG32_SOC15_RLC(GC, GET_INST(GC, inst), mmCP_HQD_DEQUEUE_REQUEST, type);
 
 	end_jiffies = (utimeout * HZ / 1000) + jiffies;
 	while (true) {
@@ -908,8 +906,8 @@ void kgd_gfx_v9_get_iq_wait_times(struct amdgpu_device *adev,
 					uint32_t inst)
 
 {
-	*wait_times = RREG32(SOC15_REG_OFFSET(GC, GET_INST(GC, inst),
-			mmCP_IQ_WAIT_TIME2));
+	*wait_times = RREG32_SOC15_RLC(GC, GET_INST(GC, inst),
+			mmCP_IQ_WAIT_TIME2);
 }
 
 void kgd_gfx_v9_set_vm_context_page_table_base(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 781e5c5ce04d22..702f6610d02435 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -172,6 +172,7 @@ int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
 	}
 
 	rcu_read_unlock();
+	*result = NULL;
 	return -ENOENT;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 86f88512eb7e19..e50be65000303a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -207,7 +207,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p,
 	}
 
 	for (i = 0; i < p->nchunks; i++) {
-		struct drm_amdgpu_cs_chunk __user **chunk_ptr = NULL;
+		struct drm_amdgpu_cs_chunk __user *chunk_ptr = NULL;
 		struct drm_amdgpu_cs_chunk user_chunk;
 		uint32_t __user *cdata;
 
@@ -1415,7 +1415,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		if (r == -ENOMEM)
 			DRM_ERROR("Not enough memory for command submission!\n");
 		else if (r != -ERESTARTSYS && r != -EAGAIN)
-			DRM_ERROR("Failed to process the buffer list %d!\n", r);
+			DRM_DEBUG("Failed to process the buffer list %d!\n", r);
 		goto error_fini;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index a53f436fa9f1ae..0e61ebdb3f3e59 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -638,6 +638,9 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	if (!adev->didt_rreg)
+		return -EOPNOTSUPP;
+
 	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
@@ -694,6 +697,9 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	if (!adev->didt_wreg)
+		return -EOPNOTSUPP;
+
 	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index fd8cd8e2d3f245..8dee52ce26d0cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -73,6 +73,7 @@
 #include "amdgpu_pmu.h"
 #include "amdgpu_fru_eeprom.h"
 #include "amdgpu_reset.h"
+#include "amdgpu_virt.h"
 
 #include <linux/suspend.h>
 #include <drm/task_barrier.h>
@@ -472,7 +473,7 @@ uint32_t amdgpu_device_rreg(struct amdgpu_device *adev,
 		if (!(acc_flags & AMDGPU_REGS_NO_KIQ) &&
 		    amdgpu_sriov_runtime(adev) &&
 		    down_read_trylock(&adev->reset_domain->sem)) {
-			ret = amdgpu_kiq_rreg(adev, reg);
+			ret = amdgpu_kiq_rreg(adev, reg, 0);
 			up_read(&adev->reset_domain->sem);
 		} else {
 			ret = readl(((void __iomem *)adev->rmmio) + (reg * 4));
@@ -509,6 +510,49 @@ uint8_t amdgpu_mm_rreg8(struct amdgpu_device *adev, uint32_t offset)
 	BUG();
 }
 
+
+/**
+ * amdgpu_device_xcc_rreg - read a memory mapped IO or indirect register with specific XCC
+ *
+ * @adev: amdgpu_device pointer
+ * @reg: dword aligned register offset
+ * @acc_flags: access flags which require special behavior
+ * @xcc_id: xcc accelerated compute core id
+ *
+ * Returns the 32 bit value from the offset specified.
+ */
+uint32_t amdgpu_device_xcc_rreg(struct amdgpu_device *adev,
+				uint32_t reg, uint32_t acc_flags,
+				uint32_t xcc_id)
+{
+	uint32_t ret, rlcg_flag;
+
+	if (amdgpu_device_skip_hw_access(adev))
+		return 0;
+
+	if ((reg * 4) < adev->rmmio_size) {
+		if (amdgpu_sriov_vf(adev) &&
+		    !amdgpu_sriov_runtime(adev) &&
+		    adev->gfx.rlc.rlcg_reg_access_supported &&
+		    amdgpu_virt_get_rlcg_reg_access_flag(adev, acc_flags,
+							 GC_HWIP, false,
+							 &rlcg_flag)) {
+			ret = amdgpu_virt_rlcg_reg_rw(adev, reg, 0, rlcg_flag, xcc_id);
+		} else if (!(acc_flags & AMDGPU_REGS_NO_KIQ) &&
+		    amdgpu_sriov_runtime(adev) &&
+		    down_read_trylock(&adev->reset_domain->sem)) {
+			ret = amdgpu_kiq_rreg(adev, reg, xcc_id);
+			up_read(&adev->reset_domain->sem);
+		} else {
+			ret = readl(((void __iomem *)adev->rmmio) + (reg * 4));
+		}
+	} else {
+		ret = adev->pcie_rreg(adev, reg * 4);
+	}
+
+	return ret;
+}
+
 /*
  * MMIO register write with bytes helper functions
  * @offset:bytes offset from MMIO start
@@ -556,7 +600,7 @@ void amdgpu_device_wreg(struct amdgpu_device *adev,
 		if (!(acc_flags & AMDGPU_REGS_NO_KIQ) &&
 		    amdgpu_sriov_runtime(adev) &&
 		    down_read_trylock(&adev->reset_domain->sem)) {
-			amdgpu_kiq_wreg(adev, reg, v);
+			amdgpu_kiq_wreg(adev, reg, v, 0);
 			up_read(&adev->reset_domain->sem);
 		} else {
 			writel(v, ((void __iomem *)adev->rmmio) + (reg * 4));
@@ -598,6 +642,47 @@ void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev,
 }
 
 /**
+ * amdgpu_device_xcc_wreg - write to a memory mapped IO or indirect register with specific XCC
+ *
+ * @adev: amdgpu_device pointer
+ * @reg: dword aligned register offset
+ * @v: 32 bit value to write to the register
+ * @acc_flags: access flags which require special behavior
+ * @xcc_id: xcc accelerated compute core id
+ *
+ * Writes the value specified to the offset specified.
+ */
+void amdgpu_device_xcc_wreg(struct amdgpu_device *adev,
+			uint32_t reg, uint32_t v,
+			uint32_t acc_flags, uint32_t xcc_id)
+{
+	uint32_t rlcg_flag;
+
+	if (amdgpu_device_skip_hw_access(adev))
+		return;
+
+	if ((reg * 4) < adev->rmmio_size) {
+		if (amdgpu_sriov_vf(adev) &&
+		    !amdgpu_sriov_runtime(adev) &&
+		    adev->gfx.rlc.rlcg_reg_access_supported &&
+		    amdgpu_virt_get_rlcg_reg_access_flag(adev, acc_flags,
+							 GC_HWIP, true,
+							 &rlcg_flag)) {
+			amdgpu_virt_rlcg_reg_rw(adev, reg, v, rlcg_flag, xcc_id);
+		} else if (!(acc_flags & AMDGPU_REGS_NO_KIQ) &&
+		    amdgpu_sriov_runtime(adev) &&
+		    down_read_trylock(&adev->reset_domain->sem)) {
+			amdgpu_kiq_wreg(adev, reg, v, xcc_id);
+			up_read(&adev->reset_domain->sem);
+		} else {
+			writel(v, ((void __iomem *)adev->rmmio) + (reg * 4));
+		}
+	} else {
+		adev->pcie_wreg(adev, reg * 4, v);
+	}
+}
+
+/**
  * amdgpu_device_indirect_rreg - read an indirect register
  *
  * @adev: amdgpu_device pointer
@@ -2499,6 +2584,18 @@ static int amdgpu_device_init_schedulers(struct amdgpu_device *adev)
 				  ring->name);
 			return r;
 		}
+		r = amdgpu_uvd_entity_init(adev, ring);
+		if (r) {
+			DRM_ERROR("Failed to create UVD scheduling entity on ring %s.\n",
+				  ring->name);
+			return r;
+		}
+		r = amdgpu_vce_entity_init(adev, ring);
+		if (r) {
+			DRM_ERROR("Failed to create VCE scheduling entity on ring %s.\n",
+				  ring->name);
+			return r;
+		}
 	}
 
 	amdgpu_xcp_update_partition_sched_list(adev);
@@ -3694,10 +3791,6 @@ static void amdgpu_device_set_mcbp(struct amdgpu_device *adev)
 		adev->gfx.mcbp = true;
 	else if (amdgpu_mcbp == 0)
 		adev->gfx.mcbp = false;
-	else if ((amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(9, 0, 0)) &&
-		 (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(10, 0, 0)) &&
-		 adev->gfx.num_gfx_rings)
-		adev->gfx.mcbp = true;
 
 	if (amdgpu_sriov_vf(adev))
 		adev->gfx.mcbp = true;
@@ -4423,8 +4516,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 
 	amdgpu_ras_suspend(adev);
 
-	amdgpu_ttm_set_buffer_funcs_status(adev, false);
-
 	amdgpu_device_ip_suspend_phase1(adev);
 
 	if (!adev->in_s0ix)
@@ -4434,6 +4525,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	if (r)
 		return r;
 
+	amdgpu_ttm_set_buffer_funcs_status(adev, false);
+
 	amdgpu_fence_driver_hw_fini(adev);
 
 	amdgpu_device_ip_suspend_phase2(adev);
@@ -4441,6 +4534,10 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_release_full_gpu(adev, false);
 
+	r = amdgpu_dpm_notify_rlc_state(adev, false);
+	if (r)
+		return r;
+
 	return 0;
 }
 
@@ -4486,19 +4583,18 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	}
 	amdgpu_fence_driver_hw_init(adev);
 
-	r = amdgpu_device_ip_late_init(adev);
-	if (r)
-		goto exit;
-
-	queue_delayed_work(system_wq, &adev->delayed_init_work,
-			   msecs_to_jiffies(AMDGPU_RESUME_MS));
-
 	if (!adev->in_s0ix) {
 		r = amdgpu_amdkfd_resume(adev, adev->in_runpm);
 		if (r)
 			goto exit;
 	}
 
+	r = amdgpu_device_ip_late_init(adev);
+	if (r)
+		goto exit;
+
+	queue_delayed_work(system_wq, &adev->delayed_init_work,
+			   msecs_to_jiffies(AMDGPU_RESUME_MS));
 exit:
 	if (amdgpu_sriov_vf(adev)) {
 		amdgpu_virt_init_data_exchange(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 0cacd0b9f8bead..b8fbe97efe1d3c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -340,14 +340,11 @@ int amdgpu_display_crtc_set_config(struct drm_mode_set *set,
 		adev->have_disp_power_ref = true;
 		return ret;
 	}
-	/* if we have no active crtcs, then drop the power ref
-	 * we got before
+	/* if we have no active crtcs, then go to
+	 * drop the power ref we got before
 	 */
-	if (!active && adev->have_disp_power_ref) {
-		pm_runtime_put_autosuspend(dev->dev);
+	if (!active && adev->have_disp_power_ref)
 		adev->have_disp_power_ref = false;
-	}
-
 out:
 	/* drop the power reference we got coming in here */
 	pm_runtime_put_autosuspend(dev->dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 3095a3a864af71..8b33b130ea36e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -207,6 +207,7 @@ int amdgpu_user_partt_mode = AMDGPU_AUTO_COMPUTE_PARTITION_MODE;
 int amdgpu_umsch_mm;
 int amdgpu_seamless = -1; /* auto */
 uint amdgpu_debug_mask;
+int amdgpu_agp = -1; /* auto */
 
 static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
 
@@ -961,6 +962,15 @@ module_param_named(seamless, amdgpu_seamless, int, 0444);
 MODULE_PARM_DESC(debug_mask, "debug options for amdgpu, disabled by default");
 module_param_named(debug_mask, amdgpu_debug_mask, uint, 0444);
 
+/**
+ * DOC: agp (int)
+ * Enable the AGP aperture.  This provides an aperture in the GPU's internal
+ * address space for direct access to system memory.  Note that these accesses
+ * are non-snooped, so they are only used for access to uncached memory.
+ */
+MODULE_PARM_DESC(agp, "AGP (-1 = auto (default), 0 = disable, 1 = enable)");
+module_param_named(agp, amdgpu_agp, int, 0444);
+
 /* These devices are not supported by amdgpu.
  * They are supported by the mach64, r128, radeon drivers
  */
@@ -2253,6 +2263,8 @@ retry_init:
 		pm_runtime_mark_last_busy(ddev->dev);
 		pm_runtime_put_autosuspend(ddev->dev);
 
+		pci_wake_from_d3(pdev, TRUE);
+
 		/*
 		 * For runpm implemented via BACO, PMFW will handle the
 		 * timing for BACO in and out:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index a2a29dcb24227b..b9674c57c4365f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -931,12 +931,12 @@ void amdgpu_gfx_ras_error_func(struct amdgpu_device *adev,
 		func(adev, ras_error_status, i);
 }
 
-uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
+uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg, uint32_t xcc_id)
 {
 	signed long r, cnt = 0;
 	unsigned long flags;
 	uint32_t seq, reg_val_offs = 0, value = 0;
-	struct amdgpu_kiq *kiq = &adev->gfx.kiq[0];
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq[xcc_id];
 	struct amdgpu_ring *ring = &kiq->ring;
 
 	if (amdgpu_device_skip_hw_access(adev))
@@ -999,12 +999,12 @@ failed_kiq_read:
 	return ~0;
 }
 
-void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
+void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, uint32_t xcc_id)
 {
 	signed long r, cnt = 0;
 	unsigned long flags;
 	uint32_t seq;
-	struct amdgpu_kiq *kiq = &adev->gfx.kiq[0];
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq[xcc_id];
 	struct amdgpu_ring *ring = &kiq->ring;
 
 	BUG_ON(!ring->funcs->emit_wreg);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 7088c5015675be..f23bafec71c5ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -521,8 +521,8 @@ int amdgpu_gfx_process_ras_data_cb(struct amdgpu_device *adev,
 int amdgpu_gfx_cp_ecc_error_irq(struct amdgpu_device *adev,
 				  struct amdgpu_irq_src *source,
 				  struct amdgpu_iv_entry *entry);
-uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg);
-void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v);
+uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg, uint32_t xcc_id);
+void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, uint32_t xcc_id);
 int amdgpu_gfx_get_num_kcq(struct amdgpu_device *adev);
 void amdgpu_gfx_cp_init_microcode(struct amdgpu_device *adev, uint32_t ucode_id);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 2dce338b0f1e74..d2f273d77e5955 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -181,6 +181,9 @@ uint64_t amdgpu_gmc_agp_addr(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 
+	if (!bo->ttm)
+		return AMDGPU_BO_INVALID_OFFSET;
+
 	if (bo->ttm->num_pages != 1 || bo->ttm->caching == ttm_cached)
 		return AMDGPU_BO_INVALID_OFFSET;
 
@@ -826,7 +829,10 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev)
 				gc_ver == IP_VERSION(9, 4, 3) ||
 				gc_ver >= IP_VERSION(10, 3, 0));
 
-	gmc->noretry = (amdgpu_noretry == -1) ? noretry_default : amdgpu_noretry;
+	if (!amdgpu_sriov_xnack_support(adev))
+		gmc->noretry = 1;
+	else
+		gmc->noretry = (amdgpu_noretry == -1) ? noretry_default : amdgpu_noretry;
 }
 
 void amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
index 5a828c175e3a0a..cf33eb219e2574 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
@@ -143,6 +143,46 @@ int amdgpu_mca_mpio_ras_sw_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+void amdgpu_mca_bank_set_init(struct mca_bank_set *mca_set)
+{
+	if (!mca_set)
+		return;
+
+	memset(mca_set, 0, sizeof(*mca_set));
+	INIT_LIST_HEAD(&mca_set->list);
+}
+
+int amdgpu_mca_bank_set_add_entry(struct mca_bank_set *mca_set, struct mca_bank_entry *entry)
+{
+	struct mca_bank_node *node;
+
+	if (!entry)
+		return -EINVAL;
+
+	node = kvzalloc(sizeof(*node), GFP_KERNEL);
+	if (!node)
+		return -ENOMEM;
+
+	memcpy(&node->entry, entry, sizeof(*entry));
+
+	INIT_LIST_HEAD(&node->node);
+	list_add_tail(&node->node, &mca_set->list);
+
+	mca_set->nr_entries++;
+
+	return 0;
+}
+
+void amdgpu_mca_bank_set_release(struct mca_bank_set *mca_set)
+{
+	struct mca_bank_node *node, *tmp;
+
+	list_for_each_entry_safe(node, tmp, &mca_set->list, node) {
+		list_del(&node->node);
+		kvfree(node);
+	}
+}
+
 void amdgpu_mca_smu_init_funcs(struct amdgpu_device *adev, const struct amdgpu_mca_smu_funcs *mca_funcs)
 {
 	struct amdgpu_mca *mca = &adev->mca;
@@ -160,6 +200,65 @@ int amdgpu_mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable)
 	return -EOPNOTSUPP;
 }
 
+static void amdgpu_mca_smu_mca_bank_dump(struct amdgpu_device *adev, int idx, struct mca_bank_entry *entry)
+{
+	dev_info(adev->dev, "[Hardware error] Accelerator Check Architecture events logged\n");
+	dev_info(adev->dev, "[Hardware error] aca entry[%02d].STATUS=0x%016llx\n",
+		 idx, entry->regs[MCA_REG_IDX_STATUS]);
+	dev_info(adev->dev, "[Hardware error] aca entry[%02d].ADDR=0x%016llx\n",
+		 idx, entry->regs[MCA_REG_IDX_ADDR]);
+	dev_info(adev->dev, "[Hardware error] aca entry[%02d].MISC0=0x%016llx\n",
+		 idx, entry->regs[MCA_REG_IDX_MISC0]);
+	dev_info(adev->dev, "[Hardware error] aca entry[%02d].IPID=0x%016llx\n",
+		 idx, entry->regs[MCA_REG_IDX_IPID]);
+	dev_info(adev->dev, "[Hardware error] aca entry[%02d].SYND=0x%016llx\n",
+		 idx, entry->regs[MCA_REG_IDX_SYND]);
+}
+
+int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type, struct ras_err_data *err_data)
+{
+	struct amdgpu_smuio_mcm_config_info mcm_info;
+	struct mca_bank_set mca_set;
+	struct mca_bank_node *node;
+	struct mca_bank_entry *entry;
+	uint32_t count;
+	int ret, i = 0;
+
+	amdgpu_mca_bank_set_init(&mca_set);
+
+	ret = amdgpu_mca_smu_get_mca_set(adev, blk, type, &mca_set);
+	if (ret)
+		goto out_mca_release;
+
+	list_for_each_entry(node, &mca_set.list, node) {
+		entry = &node->entry;
+
+		amdgpu_mca_smu_mca_bank_dump(adev, i++, entry);
+
+		count = 0;
+		ret = amdgpu_mca_smu_parse_mca_error_count(adev, blk, type, entry, &count);
+		if (ret)
+			goto out_mca_release;
+
+		if (!count)
+			continue;
+
+		mcm_info.socket_id = entry->info.socket_id;
+		mcm_info.die_id = entry->info.aid;
+
+		if (type == AMDGPU_MCA_ERROR_TYPE_UE)
+			amdgpu_ras_error_statistic_ue_count(err_data, &mcm_info, (uint64_t)count);
+		else
+			amdgpu_ras_error_statistic_ce_count(err_data, &mcm_info, (uint64_t)count);
+	}
+
+out_mca_release:
+	amdgpu_mca_bank_set_release(&mca_set);
+
+	return ret;
+}
+
+
 int amdgpu_mca_smu_get_valid_mca_count(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, uint32_t *count)
 {
 	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
@@ -173,17 +272,77 @@ int amdgpu_mca_smu_get_valid_mca_count(struct amdgpu_device *adev, enum amdgpu_m
 	return -EOPNOTSUPP;
 }
 
-int amdgpu_mca_smu_get_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
-				   enum amdgpu_mca_error_type type, uint32_t *count)
+int amdgpu_mca_smu_get_mca_set_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
+					    enum amdgpu_mca_error_type type, uint32_t *total)
 {
 	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
-	if (!count)
+	struct mca_bank_set mca_set;
+	struct mca_bank_node *node;
+	struct mca_bank_entry *entry;
+	uint32_t count;
+	int ret;
+
+	if (!total)
 		return -EINVAL;
 
-	if (mca_funcs && mca_funcs->mca_get_error_count)
-		return mca_funcs->mca_get_error_count(adev, blk, type, count);
+	if (!mca_funcs)
+		return -EOPNOTSUPP;
 
-	return -EOPNOTSUPP;
+	if (!mca_funcs->mca_get_ras_mca_set || !mca_funcs->mca_get_valid_mca_count)
+		return -EOPNOTSUPP;
+
+	amdgpu_mca_bank_set_init(&mca_set);
+
+	ret = mca_funcs->mca_get_ras_mca_set(adev, blk, type, &mca_set);
+	if (ret)
+		goto err_mca_set_release;
+
+	*total = 0;
+	list_for_each_entry(node, &mca_set.list, node) {
+		entry = &node->entry;
+
+		count = 0;
+		ret = mca_funcs->mca_parse_mca_error_count(adev, blk, type, entry, &count);
+		if (ret)
+			goto err_mca_set_release;
+
+		*total += count;
+	}
+
+err_mca_set_release:
+	amdgpu_mca_bank_set_release(&mca_set);
+
+	return ret;
+}
+
+int amdgpu_mca_smu_parse_mca_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
+					 enum amdgpu_mca_error_type type, struct mca_bank_entry *entry, uint32_t *count)
+{
+	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
+	if (!count || !entry)
+		return -EINVAL;
+
+	if (!mca_funcs || !mca_funcs->mca_parse_mca_error_count)
+		return -EOPNOTSUPP;
+
+
+	return mca_funcs->mca_parse_mca_error_count(adev, blk, type, entry, count);
+}
+
+int amdgpu_mca_smu_get_mca_set(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
+			       enum amdgpu_mca_error_type type, struct mca_bank_set *mca_set)
+{
+	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
+
+	if (!mca_set)
+		return -EINVAL;
+
+	if (!mca_funcs || !mca_funcs->mca_get_ras_mca_set)
+		return -EOPNOTSUPP;
+
+	WARN_ON(!list_empty(&mca_set->list));
+
+	return mca_funcs->mca_get_ras_mca_set(adev, blk, type, mca_set);
 }
 
 int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_error_type type,
@@ -230,14 +389,21 @@ static int amdgpu_mca_smu_debug_mode_set(void *data, u64 val)
 static void mca_dump_entry(struct seq_file *m, struct mca_bank_entry *entry)
 {
 	int i, idx = entry->idx;
+	int reg_idx_array[] = {
+		MCA_REG_IDX_STATUS,
+		MCA_REG_IDX_ADDR,
+		MCA_REG_IDX_MISC0,
+		MCA_REG_IDX_IPID,
+		MCA_REG_IDX_SYND,
+	};
 
 	seq_printf(m, "mca entry[%d].type: %s\n", idx, entry->type == AMDGPU_MCA_ERROR_TYPE_UE ? "UE" : "CE");
 	seq_printf(m, "mca entry[%d].ip: %d\n", idx, entry->ip);
 	seq_printf(m, "mca entry[%d].info: socketid:%d aid:%d hwid:0x%03x mcatype:0x%04x\n",
 		   idx, entry->info.socket_id, entry->info.aid, entry->info.hwid, entry->info.mcatype);
 
-	for (i = 0; i < ARRAY_SIZE(entry->regs); i++)
-		seq_printf(m, "mca entry[%d].regs[%d]: 0x%016llx\n", idx, i, entry->regs[i]);
+	for (i = 0; i < ARRAY_SIZE(reg_idx_array); i++)
+		seq_printf(m, "mca entry[%d].regs[%d]: 0x%016llx\n", idx, reg_idx_array[i], entry->regs[reg_idx_array[i]]);
 }
 
 static int mca_dump_show(struct seq_file *m, enum amdgpu_mca_error_type type)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
index 28ad463cf5c945..e51e8918e6671a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
@@ -25,6 +25,29 @@
 
 #define MCA_MAX_REGS_COUNT	(16)
 
+#define MCA_REG_FIELD(x, h, l)			(((x) & GENMASK_ULL(h, l)) >> l)
+#define MCA_REG__STATUS__VAL(x)			MCA_REG_FIELD(x, 63, 63)
+#define MCA_REG__STATUS__OVERFLOW(x)		MCA_REG_FIELD(x, 62, 62)
+#define MCA_REG__STATUS__UC(x)			MCA_REG_FIELD(x, 61, 61)
+#define MCA_REG__STATUS__EN(x)			MCA_REG_FIELD(x, 60, 60)
+#define MCA_REG__STATUS__MISCV(x)		MCA_REG_FIELD(x, 59, 59)
+#define MCA_REG__STATUS__ADDRV(x)		MCA_REG_FIELD(x, 58, 58)
+#define MCA_REG__STATUS__PCC(x)			MCA_REG_FIELD(x, 57, 57)
+#define MCA_REG__STATUS__ERRCOREIDVAL(x)	MCA_REG_FIELD(x, 56, 56)
+#define MCA_REG__STATUS__TCC(x)			MCA_REG_FIELD(x, 55, 55)
+#define MCA_REG__STATUS__SYNDV(x)		MCA_REG_FIELD(x, 53, 53)
+#define MCA_REG__STATUS__CECC(x)		MCA_REG_FIELD(x, 46, 46)
+#define MCA_REG__STATUS__UECC(x)		MCA_REG_FIELD(x, 45, 45)
+#define MCA_REG__STATUS__DEFERRED(x)		MCA_REG_FIELD(x, 44, 44)
+#define MCA_REG__STATUS__POISON(x)		MCA_REG_FIELD(x, 43, 43)
+#define MCA_REG__STATUS__SCRUB(x)		MCA_REG_FIELD(x, 40, 40)
+#define MCA_REG__STATUS__ERRCOREID(x)		MCA_REG_FIELD(x, 37, 32)
+#define MCA_REG__STATUS__ADDRLSB(x)		MCA_REG_FIELD(x, 29, 24)
+#define MCA_REG__STATUS__ERRORCODEEXT(x)	MCA_REG_FIELD(x, 21, 16)
+#define MCA_REG__STATUS__ERRORCODE(x)		MCA_REG_FIELD(x, 15, 0)
+
+#define MCA_REG__SYND__ERRORINFORMATION(x)	MCA_REG_FIELD(x, 17, 0)
+
 enum amdgpu_mca_ip {
 	AMDGPU_MCA_IP_UNKNOW = -1,
 	AMDGPU_MCA_IP_PSP = 0,
@@ -33,6 +56,7 @@ enum amdgpu_mca_ip {
 	AMDGPU_MCA_IP_SMU,
 	AMDGPU_MCA_IP_MP5,
 	AMDGPU_MCA_IP_UMC,
+	AMDGPU_MCA_IP_PCS_XGMI,
 	AMDGPU_MCA_IP_COUNT,
 };
 
@@ -57,6 +81,15 @@ struct amdgpu_mca {
 	const struct amdgpu_mca_smu_funcs *mca_funcs;
 };
 
+enum mca_reg_idx {
+	MCA_REG_IDX_STATUS		= 1,
+	MCA_REG_IDX_ADDR		= 2,
+	MCA_REG_IDX_MISC0		= 3,
+	MCA_REG_IDX_IPID		= 5,
+	MCA_REG_IDX_SYND		= 6,
+	MCA_REG_IDX_COUNT		= 16,
+};
+
 struct mca_bank_info {
 	int socket_id;
 	int aid;
@@ -72,18 +105,28 @@ struct mca_bank_entry {
 	uint64_t regs[MCA_MAX_REGS_COUNT];
 };
 
+struct mca_bank_node {
+	struct mca_bank_entry entry;
+	struct list_head node;
+};
+
+struct mca_bank_set {
+	int nr_entries;
+	struct list_head list;
+};
+
 struct amdgpu_mca_smu_funcs {
 	int max_ue_count;
 	int max_ce_count;
 	int (*mca_set_debug_mode)(struct amdgpu_device *adev, bool enable);
-	int (*mca_get_error_count)(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
-				   enum amdgpu_mca_error_type type, uint32_t *count);
+	int (*mca_get_ras_mca_set)(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type,
+				   struct mca_bank_set *mca_set);
+	int (*mca_parse_mca_error_count)(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type,
+					 struct mca_bank_entry *entry, uint32_t *count);
 	int (*mca_get_valid_mca_count)(struct amdgpu_device *adev, enum amdgpu_mca_error_type type,
 				       uint32_t *count);
 	int (*mca_get_mca_entry)(struct amdgpu_device *adev, enum amdgpu_mca_error_type type,
 				 int idx, struct mca_bank_entry *entry);
-	int (*mca_get_ras_mca_idx_array)(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
-					 enum amdgpu_mca_error_type type, int *idx_array, int *idx_array_size);
 };
 
 void amdgpu_mca_query_correctable_error_count(struct amdgpu_device *adev,
@@ -107,11 +150,22 @@ int amdgpu_mca_mpio_ras_sw_init(struct amdgpu_device *adev);
 void amdgpu_mca_smu_init_funcs(struct amdgpu_device *adev, const struct amdgpu_mca_smu_funcs *mca_funcs);
 int amdgpu_mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable);
 int amdgpu_mca_smu_get_valid_mca_count(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, uint32_t *count);
+int amdgpu_mca_smu_get_mca_set_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
+					   enum amdgpu_mca_error_type type, uint32_t *total);
 int amdgpu_mca_smu_get_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
 				   enum amdgpu_mca_error_type type, uint32_t *count);
+int amdgpu_mca_smu_parse_mca_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
+					 enum amdgpu_mca_error_type type, struct mca_bank_entry *entry, uint32_t *count);
+int amdgpu_mca_smu_get_mca_set(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
+			       enum amdgpu_mca_error_type type, struct mca_bank_set *mca_set);
 int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_error_type type,
 				 int idx, struct mca_bank_entry *entry);
 
 void amdgpu_mca_smu_debugfs_init(struct amdgpu_device *adev, struct dentry *root);
 
+void amdgpu_mca_bank_set_init(struct mca_bank_set *mca_set);
+int amdgpu_mca_bank_set_add_entry(struct mca_bank_set *mca_set, struct mca_bank_entry *entry);
+void amdgpu_mca_bank_set_release(struct mca_bank_set *mca_set);
+int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type, struct ras_err_data *err_data);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 0dcb6c36b02c0b..5ad03f2afdb45a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1062,9 +1062,6 @@ static const char * const amdgpu_vram_names[] = {
  */
 int amdgpu_bo_init(struct amdgpu_device *adev)
 {
-	/* set the default AGP aperture state */
-	amdgpu_gmc_set_agp_default(adev, &adev->gmc);
-
 	/* On A+A platform, VRAM can be mapped as WB */
 	if (!adev->gmc.xgmi.connected_to_cpu && !adev->gmc.is_app_apu) {
 		/* reserve PAT memory space to WC for VRAM */
@@ -1346,6 +1343,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
 
 	abo = ttm_to_amdgpu_bo(bo);
 
+	WARN_ON(abo->vm_bo);
+
 	if (abo->kfd_bo)
 		amdgpu_amdkfd_release_notify(abo);
 
@@ -1530,10 +1529,14 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo)
 u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	uint64_t offset;
+	uint64_t offset = AMDGPU_BO_INVALID_OFFSET;
+
+	if (bo->tbo.resource->mem_type == TTM_PL_TT)
+		offset = amdgpu_gmc_agp_addr(&bo->tbo);
 
-	offset = (bo->tbo.resource->start << PAGE_SHIFT) +
-		 amdgpu_ttm_domain_start(adev, bo->tbo.resource->mem_type);
+	if (offset == AMDGPU_BO_INVALID_OFFSET)
+		offset = (bo->tbo.resource->start << PAGE_SHIFT) +
+			amdgpu_ttm_domain_start(adev, bo->tbo.resource->mem_type);
 
 	return amdgpu_gmc_sign_extend(offset);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 32b701cc0376d3..a21045d018f2b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -1473,6 +1473,11 @@ int psp_xgmi_get_topology_info(struct psp_context *psp,
 				topology->nodes[i].num_links = (requires_reflection && topology->nodes[i].num_links) ?
 								topology->nodes[i].num_links : node_num_links;
 			}
+			/* popluate the connected port num info if supported and available */
+			if (ta_port_num_support && topology->nodes[i].num_links) {
+				memcpy(topology->nodes[i].port_num, link_extend_info_output->nodes[i].port_num,
+				       sizeof(struct xgmi_connected_port_num) * TA_XGMI__MAX_PORT_NUM);
+			}
 
 			/* reflect the topology information for bi-directionality */
 			if (requires_reflection && topology->nodes[i].num_hops)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index 5d36ad3f48c74a..c4d9cbde55b9bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -150,6 +150,7 @@ struct psp_xgmi_node_info {
 	uint8_t					is_sharing_enabled;
 	enum ta_xgmi_assigned_sdma_engine	sdma_engine;
 	uint8_t					num_links;
+	struct xgmi_connected_port_num		port_num[TA_XGMI__MAX_PORT_NUM];
 };
 
 struct psp_xgmi_topology_info {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index b7fe5951b166eb..63fb4cd85e53b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -28,6 +28,7 @@
 #include <linux/reboot.h>
 #include <linux/syscalls.h>
 #include <linux/pm_runtime.h>
+#include <linux/list_sort.h>
 
 #include "amdgpu.h"
 #include "amdgpu_ras.h"
@@ -1165,13 +1166,53 @@ static void amdgpu_rasmgr_error_data_statistic_update(struct ras_manager *obj, s
 	}
 }
 
-/* query/inject/cure begin */
-int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
-				  struct ras_query_if *info)
+static int amdgpu_ras_query_error_status_helper(struct amdgpu_device *adev,
+						struct ras_query_if *info,
+						struct ras_err_data *err_data,
+						unsigned int error_query_mode)
 {
+	enum amdgpu_ras_block blk = info ? info->head.block : AMDGPU_RAS_BLOCK_COUNT;
 	struct amdgpu_ras_block_object *block_obj = NULL;
+
+	if (error_query_mode == AMDGPU_RAS_INVALID_ERROR_QUERY)
+		return -EINVAL;
+
+	if (error_query_mode == AMDGPU_RAS_DIRECT_ERROR_QUERY) {
+		if (info->head.block == AMDGPU_RAS_BLOCK__UMC) {
+			amdgpu_ras_get_ecc_info(adev, err_data);
+		} else {
+			block_obj = amdgpu_ras_get_ras_block(adev, info->head.block, 0);
+			if (!block_obj || !block_obj->hw_ops) {
+				dev_dbg_once(adev->dev, "%s doesn't config RAS function\n",
+					     get_ras_block_str(&info->head));
+				return -EINVAL;
+			}
+
+			if (block_obj->hw_ops->query_ras_error_count)
+				block_obj->hw_ops->query_ras_error_count(adev, err_data);
+
+			if ((info->head.block == AMDGPU_RAS_BLOCK__SDMA) ||
+			    (info->head.block == AMDGPU_RAS_BLOCK__GFX) ||
+			    (info->head.block == AMDGPU_RAS_BLOCK__MMHUB)) {
+				if (block_obj->hw_ops->query_ras_error_status)
+					block_obj->hw_ops->query_ras_error_status(adev);
+			}
+		}
+	} else {
+		/* FIXME: add code to check return value later */
+		amdgpu_mca_smu_log_ras_error(adev, blk, AMDGPU_MCA_ERROR_TYPE_UE, err_data);
+		amdgpu_mca_smu_log_ras_error(adev, blk, AMDGPU_MCA_ERROR_TYPE_CE, err_data);
+	}
+
+	return 0;
+}
+
+/* query/inject/cure begin */
+int amdgpu_ras_query_error_status(struct amdgpu_device *adev, struct ras_query_if *info)
+{
 	struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head);
 	struct ras_err_data err_data;
+	unsigned int error_query_mode;
 	int ret;
 
 	if (!obj)
@@ -1181,27 +1222,14 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
 	if (ret)
 		return ret;
 
-	if (info->head.block == AMDGPU_RAS_BLOCK__UMC) {
-		amdgpu_ras_get_ecc_info(adev, &err_data);
-	} else {
-		block_obj = amdgpu_ras_get_ras_block(adev, info->head.block, 0);
-		if (!block_obj || !block_obj->hw_ops)   {
-			dev_dbg_once(adev->dev, "%s doesn't config RAS function\n",
-				     get_ras_block_str(&info->head));
-			ret = -EINVAL;
-			goto out_fini_err_data;
-		}
-
-		if (block_obj->hw_ops->query_ras_error_count)
-			block_obj->hw_ops->query_ras_error_count(adev, &err_data);
+	if (!amdgpu_ras_get_error_query_mode(adev, &error_query_mode))
+		return -EINVAL;
 
-		if ((info->head.block == AMDGPU_RAS_BLOCK__SDMA) ||
-		    (info->head.block == AMDGPU_RAS_BLOCK__GFX) ||
-		    (info->head.block == AMDGPU_RAS_BLOCK__MMHUB)) {
-				if (block_obj->hw_ops->query_ras_error_status)
-					block_obj->hw_ops->query_ras_error_status(adev);
-			}
-	}
+	ret = amdgpu_ras_query_error_status_helper(adev, info,
+						   &err_data,
+						   error_query_mode);
+	if (ret)
+		goto out_fini_err_data;
 
 	amdgpu_rasmgr_error_data_statistic_update(obj, &err_data);
 
@@ -1537,7 +1565,8 @@ static void amdgpu_ras_sysfs_remove_bad_page_node(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 
-	sysfs_remove_file_from_group(&adev->dev->kobj,
+	if (adev->dev->kobj.sd)
+		sysfs_remove_file_from_group(&adev->dev->kobj,
 				&con->badpages_attr.attr,
 				RAS_FS_NAME);
 }
@@ -1556,7 +1585,8 @@ static int amdgpu_ras_sysfs_remove_dev_attr_node(struct amdgpu_device *adev)
 		.attrs = attrs,
 	};
 
-	sysfs_remove_group(&adev->dev->kobj, &group);
+	if (adev->dev->kobj.sd)
+		sysfs_remove_group(&adev->dev->kobj, &group);
 
 	return 0;
 }
@@ -1603,7 +1633,8 @@ int amdgpu_ras_sysfs_remove(struct amdgpu_device *adev,
 	if (!obj || !obj->attr_inuse)
 		return -EINVAL;
 
-	sysfs_remove_file_from_group(&adev->dev->kobj,
+	if (adev->dev->kobj.sd)
+		sysfs_remove_file_from_group(&adev->dev->kobj,
 				&obj->sysfs_attr.attr,
 				RAS_FS_NAME);
 	obj->attr_inuse = 0;
@@ -3397,6 +3428,26 @@ bool amdgpu_ras_get_mca_debug_mode(struct amdgpu_device *adev)
 		return true;
 }
 
+bool amdgpu_ras_get_error_query_mode(struct amdgpu_device *adev,
+				     unsigned int *error_query_mode)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
+
+	if (!con) {
+		*error_query_mode = AMDGPU_RAS_INVALID_ERROR_QUERY;
+		return false;
+	}
+
+	if (mca_funcs && mca_funcs->mca_set_debug_mode)
+		*error_query_mode =
+			(con->is_mca_debug_mode) ? AMDGPU_RAS_DIRECT_ERROR_QUERY : AMDGPU_RAS_FIRMWARE_ERROR_QUERY;
+	else
+		*error_query_mode = AMDGPU_RAS_DIRECT_ERROR_QUERY;
+
+	return true;
+}
+
 /* Register each ip ras block into amdgpu ras */
 int amdgpu_ras_register_ras_block(struct amdgpu_device *adev,
 		struct amdgpu_ras_block_object *ras_block_obj)
@@ -3615,6 +3666,21 @@ static struct ras_err_node *amdgpu_ras_error_node_new(void)
 	return err_node;
 }
 
+static int ras_err_info_cmp(void *priv, const struct list_head *a, const struct list_head *b)
+{
+	struct ras_err_node *nodea = container_of(a, struct ras_err_node, node);
+	struct ras_err_node *nodeb = container_of(b, struct ras_err_node, node);
+	struct amdgpu_smuio_mcm_config_info *infoa = &nodea->err_info.mcm_info;
+	struct amdgpu_smuio_mcm_config_info *infob = &nodeb->err_info.mcm_info;
+
+	if (unlikely(infoa->socket_id != infob->socket_id))
+		return infoa->socket_id - infob->socket_id;
+	else
+		return infoa->die_id - infob->die_id;
+
+	return 0;
+}
+
 static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_data,
 						      struct amdgpu_smuio_mcm_config_info *mcm_info)
 {
@@ -3632,6 +3698,7 @@ static struct ras_err_info *amdgpu_ras_error_get_info(struct ras_err_data *err_d
 
 	err_data->err_list_count++;
 	list_add_tail(&err_node->node, &err_data->err_node_list);
+	list_sort(NULL, &err_data->err_node_list, ras_err_info_cmp);
 
 	return &err_node->err_info;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 665414c22ca95f..19161916ac46b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -320,6 +320,12 @@ enum amdgpu_ras_ret {
 	AMDGPU_RAS_PT,
 };
 
+enum amdgpu_ras_error_query_mode {
+	AMDGPU_RAS_INVALID_ERROR_QUERY		= 0,
+	AMDGPU_RAS_DIRECT_ERROR_QUERY		= 1,
+	AMDGPU_RAS_FIRMWARE_ERROR_QUERY		= 2,
+};
+
 /* ras error status reisger fields */
 #define ERR_STATUS_LO__ERR_STATUS_VALID_FLAG__SHIFT	0x0
 #define ERR_STATUS_LO__ERR_STATUS_VALID_FLAG_MASK	0x00000001L
@@ -769,6 +775,8 @@ int amdgpu_ras_set_context(struct amdgpu_device *adev, struct amdgpu_ras *ras_co
 
 void amdgpu_ras_set_mca_debug_mode(struct amdgpu_device *adev, bool enable);
 bool amdgpu_ras_get_mca_debug_mode(struct amdgpu_device *adev);
+bool amdgpu_ras_get_error_query_mode(struct amdgpu_device *adev,
+				     unsigned int *mode);
 
 int amdgpu_ras_register_ras_block(struct amdgpu_device *adev,
 				struct amdgpu_ras_block_object *ras_block_obj);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 65aa218380be1b..2fde93b00cab37 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -214,6 +214,12 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 			control->i2c_address = EEPROM_I2C_MADDR_0;
 		return true;
 	case IP_VERSION(13, 0, 0):
+		if (strnstr(atom_ctx->vbios_pn, "D707",
+			    sizeof(atom_ctx->vbios_pn)))
+			control->i2c_address = EEPROM_I2C_MADDR_0;
+		else
+			control->i2c_address = EEPROM_I2C_MADDR_4;
+		return true;
 	case IP_VERSION(13, 0, 6):
 	case IP_VERSION(13, 0, 10):
 		control->i2c_address = EEPROM_I2C_MADDR_4;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 05991c5c8ddbf3..ab4a762aed5bde 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -959,10 +959,8 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 		return 0;
 
 	addr = amdgpu_gmc_agp_addr(bo);
-	if (addr != AMDGPU_BO_INVALID_OFFSET) {
-		bo->resource->start = addr >> PAGE_SHIFT;
+	if (addr != AMDGPU_BO_INVALID_OFFSET)
 		return 0;
-	}
 
 	/* allocate GART space */
 	placement.num_placement = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 815b7c34ed33c0..07d930339b0781 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -398,21 +398,22 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
  * amdgpu_uvd_entity_init - init entity
  *
  * @adev: amdgpu_device pointer
+ * @ring: amdgpu_ring pointer to check
  *
+ * Initialize the entity used for handle management in the kernel driver.
  */
-int amdgpu_uvd_entity_init(struct amdgpu_device *adev)
+int amdgpu_uvd_entity_init(struct amdgpu_device *adev, struct amdgpu_ring *ring)
 {
-	struct amdgpu_ring *ring;
-	struct drm_gpu_scheduler *sched;
-	int r;
+	if (ring == &adev->uvd.inst[0].ring) {
+		struct drm_gpu_scheduler *sched = &ring->sched;
+		int r;
 
-	ring = &adev->uvd.inst[0].ring;
-	sched = &ring->sched;
-	r = drm_sched_entity_init(&adev->uvd.entity, DRM_SCHED_PRIORITY_NORMAL,
-				  &sched, 1, NULL);
-	if (r) {
-		DRM_ERROR("Failed setting up UVD kernel entity.\n");
-		return r;
+		r = drm_sched_entity_init(&adev->uvd.entity, DRM_SCHED_PRIORITY_NORMAL,
+					  &sched, 1, NULL);
+		if (r) {
+			DRM_ERROR("Failed setting up UVD kernel entity.\n");
+			return r;
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
index a9f342537c6834..9dfad2f48ef40c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
@@ -73,7 +73,7 @@ struct amdgpu_uvd {
 
 int amdgpu_uvd_sw_init(struct amdgpu_device *adev);
 int amdgpu_uvd_sw_fini(struct amdgpu_device *adev);
-int amdgpu_uvd_entity_init(struct amdgpu_device *adev);
+int amdgpu_uvd_entity_init(struct amdgpu_device *adev, struct amdgpu_ring *ring);
 int amdgpu_uvd_prepare_suspend(struct amdgpu_device *adev);
 int amdgpu_uvd_suspend(struct amdgpu_device *adev);
 int amdgpu_uvd_resume(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 1904edf6840716..59acf424a078f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -230,21 +230,22 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev)
  * amdgpu_vce_entity_init - init entity
  *
  * @adev: amdgpu_device pointer
+ * @ring: amdgpu_ring pointer to check
  *
+ * Initialize the entity used for handle management in the kernel driver.
  */
-int amdgpu_vce_entity_init(struct amdgpu_device *adev)
+int amdgpu_vce_entity_init(struct amdgpu_device *adev, struct amdgpu_ring *ring)
 {
-	struct amdgpu_ring *ring;
-	struct drm_gpu_scheduler *sched;
-	int r;
-
-	ring = &adev->vce.ring[0];
-	sched = &ring->sched;
-	r = drm_sched_entity_init(&adev->vce.entity, DRM_SCHED_PRIORITY_NORMAL,
-				  &sched, 1, NULL);
-	if (r != 0) {
-		DRM_ERROR("Failed setting up VCE run queue.\n");
-		return r;
+	if (ring == &adev->vce.ring[0]) {
+		struct drm_gpu_scheduler *sched = &ring->sched;
+		int r;
+
+		r = drm_sched_entity_init(&adev->vce.entity, DRM_SCHED_PRIORITY_NORMAL,
+					  &sched, 1, NULL);
+		if (r != 0) {
+			DRM_ERROR("Failed setting up VCE run queue.\n");
+			return r;
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
index ea680fc9a6c356..6e53f872d084ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
@@ -55,7 +55,7 @@ struct amdgpu_vce {
 
 int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size);
 int amdgpu_vce_sw_fini(struct amdgpu_device *adev);
-int amdgpu_vce_entity_init(struct amdgpu_device *adev);
+int amdgpu_vce_entity_init(struct amdgpu_device *adev, struct amdgpu_ring *ring);
 int amdgpu_vce_suspend(struct amdgpu_device *adev);
 int amdgpu_vce_resume(struct amdgpu_device *adev);
 void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index a0aa624f5a923c..3a632c3b1a2cdc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -73,9 +73,10 @@ void amdgpu_virt_init_setting(struct amdgpu_device *adev)
 
 void amdgpu_virt_kiq_reg_write_reg_wait(struct amdgpu_device *adev,
 					uint32_t reg0, uint32_t reg1,
-					uint32_t ref, uint32_t mask)
+					uint32_t ref, uint32_t mask,
+					uint32_t xcc_inst)
 {
-	struct amdgpu_kiq *kiq = &adev->gfx.kiq[0];
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq[xcc_inst];
 	struct amdgpu_ring *ring = &kiq->ring;
 	signed long r, cnt = 0;
 	unsigned long flags;
@@ -942,7 +943,7 @@ void amdgpu_virt_update_sriov_video_codec(struct amdgpu_device *adev,
 	}
 }
 
-static bool amdgpu_virt_get_rlcg_reg_access_flag(struct amdgpu_device *adev,
+bool amdgpu_virt_get_rlcg_reg_access_flag(struct amdgpu_device *adev,
 						 u32 acc_flags, u32 hwip,
 						 bool write, u32 *rlcg_flag)
 {
@@ -975,7 +976,7 @@ static bool amdgpu_virt_get_rlcg_reg_access_flag(struct amdgpu_device *adev,
 	return ret;
 }
 
-static u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 flag, u32 xcc_id)
+u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 flag, u32 xcc_id)
 {
 	struct amdgpu_rlcg_reg_access_ctrl *reg_access_ctrl;
 	uint32_t timeout = 50000;
@@ -1093,3 +1094,13 @@ u32 amdgpu_sriov_rreg(struct amdgpu_device *adev,
 	else
 		return RREG32(offset);
 }
+
+bool amdgpu_sriov_xnack_support(struct amdgpu_device *adev)
+{
+	bool xnack_mode = true;
+
+	if (amdgpu_sriov_vf(adev) && adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2))
+		xnack_mode = false;
+
+	return xnack_mode;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index 858ef21ae51596..d4207e44141f18 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -334,7 +334,8 @@ bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev);
 void amdgpu_virt_init_setting(struct amdgpu_device *adev);
 void amdgpu_virt_kiq_reg_write_reg_wait(struct amdgpu_device *adev,
 					uint32_t reg0, uint32_t rreg1,
-					uint32_t ref, uint32_t mask);
+					uint32_t ref, uint32_t mask,
+					uint32_t xcc_inst);
 int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init);
 int amdgpu_virt_release_full_gpu(struct amdgpu_device *adev, bool init);
 int amdgpu_virt_reset_gpu(struct amdgpu_device *adev);
@@ -365,4 +366,9 @@ u32 amdgpu_sriov_rreg(struct amdgpu_device *adev,
 bool amdgpu_virt_fw_load_skip_check(struct amdgpu_device *adev,
 			uint32_t ucode_id);
 void amdgpu_virt_post_reset(struct amdgpu_device *adev);
+bool amdgpu_sriov_xnack_support(struct amdgpu_device *adev);
+bool amdgpu_virt_get_rlcg_reg_access_flag(struct amdgpu_device *adev,
+					  u32 acc_flags, u32 hwip,
+					  bool write, u32 *rlcg_flag);
+u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 flag, u32 xcc_id);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 904252456d2582..5baefb548a2909 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -285,6 +285,7 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm)
 	list_for_each_entry_safe(vm_bo, tmp, &vm->idle, vm_status) {
 		struct amdgpu_bo *bo = vm_bo->bo;
 
+		vm_bo->moved = true;
 		if (!bo || bo->tbo.type != ttm_bo_type_kernel)
 			list_move(&vm_bo->vm_status, &vm_bo->vm->moved);
 		else if (bo->parent)
@@ -1098,8 +1099,8 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 				bo = gem_to_amdgpu_bo(gobj);
 		}
 		mem = bo->tbo.resource;
-		if (mem->mem_type == TTM_PL_TT ||
-		    mem->mem_type == AMDGPU_PL_PREEMPT)
+		if (mem && (mem->mem_type == TTM_PL_TT ||
+			    mem->mem_type == AMDGPU_PL_PREEMPT))
 			pages_addr = bo->tbo.ttm->dma_address;
 	}
 
@@ -2139,7 +2140,8 @@ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout)
  * Returns:
  * 0 for success, error for failure.
  */
-int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id)
+int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+		   int32_t xcp_id)
 {
 	struct amdgpu_bo *root_bo;
 	struct amdgpu_bo_vm *root;
@@ -2158,6 +2160,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp
 	INIT_LIST_HEAD(&vm->done);
 	INIT_LIST_HEAD(&vm->pt_freed);
 	INIT_WORK(&vm->pt_free_work, amdgpu_vm_pt_free_work);
+	INIT_KFIFO(vm->faults);
 
 	r = amdgpu_vm_init_entities(adev, vm);
 	if (r)
@@ -2192,34 +2195,33 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp
 				false, &root, xcp_id);
 	if (r)
 		goto error_free_delayed;
-	root_bo = &root->bo;
+
+	root_bo = amdgpu_bo_ref(&root->bo);
 	r = amdgpu_bo_reserve(root_bo, true);
-	if (r)
-		goto error_free_root;
+	if (r) {
+		amdgpu_bo_unref(&root->shadow);
+		amdgpu_bo_unref(&root_bo);
+		goto error_free_delayed;
+	}
 
+	amdgpu_vm_bo_base_init(&vm->root, vm, root_bo);
 	r = dma_resv_reserve_fences(root_bo->tbo.base.resv, 1);
 	if (r)
-		goto error_unreserve;
-
-	amdgpu_vm_bo_base_init(&vm->root, vm, root_bo);
+		goto error_free_root;
 
 	r = amdgpu_vm_pt_clear(adev, vm, root, false);
 	if (r)
-		goto error_unreserve;
+		goto error_free_root;
 
 	amdgpu_bo_unreserve(vm->root.bo);
-
-	INIT_KFIFO(vm->faults);
+	amdgpu_bo_unref(&root_bo);
 
 	return 0;
 
-error_unreserve:
-	amdgpu_bo_unreserve(vm->root.bo);
-
 error_free_root:
-	amdgpu_bo_unref(&root->shadow);
+	amdgpu_vm_pt_free_root(adev, vm);
+	amdgpu_bo_unreserve(vm->root.bo);
 	amdgpu_bo_unref(&root_bo);
-	vm->root.bo = NULL;
 
 error_free_delayed:
 	dma_fence_put(vm->last_tlb_flush);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
index a2287bb252235e..a160265ddc07c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
@@ -642,13 +642,14 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry)
 
 	if (!entry->bo)
 		return;
+
+	entry->bo->vm_bo = NULL;
 	shadow = amdgpu_bo_shadowed(entry->bo);
 	if (shadow) {
 		ttm_bo_set_bulk_move(&shadow->tbo, NULL);
 		amdgpu_bo_unref(&shadow);
 	}
 	ttm_bo_set_bulk_move(&entry->bo->tbo, NULL);
-	entry->bo->vm_bo = NULL;
 
 	spin_lock(&entry->vm->status_lock);
 	list_del(&entry->vm_status);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 9d5d742ee9d366..bd20cb3b981984 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -103,6 +103,53 @@ static const int walf_pcs_err_noncorrectable_mask_reg_aldebaran[] = {
 	smnPCS_GOPX1_PCS_ERROR_NONCORRECTABLE_MASK + 0x100000
 };
 
+static const int xgmi3x16_pcs_err_status_reg_v6_4[] = {
+	smnPCS_XGMI3X16_PCS_ERROR_STATUS,
+	smnPCS_XGMI3X16_PCS_ERROR_STATUS + 0x100000
+};
+
+static const int xgmi3x16_pcs_err_noncorrectable_mask_reg_v6_4[] = {
+	smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK,
+	smnPCS_XGMI3X16_PCS_ERROR_NONCORRECTABLE_MASK + 0x100000
+};
+
+static const u64 xgmi_v6_4_0_mca_base_array[] = {
+	0x11a09200,
+	0x11b09200,
+};
+
+static const char *xgmi_v6_4_0_ras_error_code_ext[32] = {
+	[0x00] = "XGMI PCS DataLossErr",
+	[0x01] = "XGMI PCS TrainingErr",
+	[0x02] = "XGMI PCS FlowCtrlAckErr",
+	[0x03] = "XGMI PCS RxFifoUnderflowErr",
+	[0x04] = "XGMI PCS RxFifoOverflowErr",
+	[0x05] = "XGMI PCS CRCErr",
+	[0x06] = "XGMI PCS BERExceededErr",
+	[0x07] = "XGMI PCS TxMetaDataErr",
+	[0x08] = "XGMI PCS ReplayBufParityErr",
+	[0x09] = "XGMI PCS DataParityErr",
+	[0x0a] = "XGMI PCS ReplayFifoOverflowErr",
+	[0x0b] = "XGMI PCS ReplayFifoUnderflowErr",
+	[0x0c] = "XGMI PCS ElasticFifoOverflowErr",
+	[0x0d] = "XGMI PCS DeskewErr",
+	[0x0e] = "XGMI PCS FlowCtrlCRCErr",
+	[0x0f] = "XGMI PCS DataStartupLimitErr",
+	[0x10] = "XGMI PCS FCInitTimeoutErr",
+	[0x11] = "XGMI PCS RecoveryTimeoutErr",
+	[0x12] = "XGMI PCS ReadySerialTimeoutErr",
+	[0x13] = "XGMI PCS ReadySerialAttemptErr",
+	[0x14] = "XGMI PCS RecoveryAttemptErr",
+	[0x15] = "XGMI PCS RecoveryRelockAttemptErr",
+	[0x16] = "XGMI PCS ReplayAttemptErr",
+	[0x17] = "XGMI PCS SyncHdrErr",
+	[0x18] = "XGMI PCS TxReplayTimeoutErr",
+	[0x19] = "XGMI PCS RxReplayTimeoutErr",
+	[0x1a] = "XGMI PCS LinkSubTxTimeoutErr",
+	[0x1b] = "XGMI PCS LinkSubRxTimeoutErr",
+	[0x1c] = "XGMI PCS RxCMDPktErr",
+};
+
 static const struct amdgpu_pcs_ras_field xgmi_pcs_ras_fields[] = {
 	{"XGMI PCS DataLossErr",
 	 SOC15_REG_FIELD(XGMI0_PCS_GOPX16_PCS_ERROR_STATUS, DataLossErr)},
@@ -926,7 +973,7 @@ static void pcs_clear_status(struct amdgpu_device *adev, uint32_t pcs_status_reg
 	WREG32_PCIE(pcs_status_reg, 0);
 }
 
-static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev)
+static void amdgpu_xgmi_legacy_reset_ras_error_count(struct amdgpu_device *adev)
 {
 	uint32_t i;
 
@@ -952,6 +999,49 @@ static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev)
 	default:
 		break;
 	}
+
+	switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) {
+	case IP_VERSION(6, 4, 0):
+		for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_v6_4); i++)
+			pcs_clear_status(adev,
+					xgmi3x16_pcs_err_status_reg_v6_4[i]);
+		break;
+	default:
+		break;
+	}
+}
+
+static void __xgmi_v6_4_0_reset_error_count(struct amdgpu_device *adev, int xgmi_inst, u64 mca_base)
+{
+	WREG64_MCA(xgmi_inst, mca_base, MCA_REG_IDX_STATUS, 0ULL);
+}
+
+static void xgmi_v6_4_0_reset_error_count(struct amdgpu_device *adev, int xgmi_inst)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(xgmi_v6_4_0_mca_base_array); i++)
+		__xgmi_v6_4_0_reset_error_count(adev, xgmi_inst, xgmi_v6_4_0_mca_base_array[i]);
+}
+
+static void xgmi_v6_4_0_reset_ras_error_count(struct amdgpu_device *adev)
+{
+	int i;
+
+	for_each_inst(i, adev->aid_mask)
+		xgmi_v6_4_0_reset_error_count(adev, i);
+}
+
+static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev)
+{
+	switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) {
+	case IP_VERSION(6, 4, 0):
+		xgmi_v6_4_0_reset_ras_error_count(adev);
+		break;
+	default:
+		amdgpu_xgmi_legacy_reset_ras_error_count(adev);
+		break;
+	}
 }
 
 static int amdgpu_xgmi_query_pcs_error_status(struct amdgpu_device *adev,
@@ -969,7 +1059,9 @@ static int amdgpu_xgmi_query_pcs_error_status(struct amdgpu_device *adev,
 
 	if (is_xgmi_pcs) {
 		if (amdgpu_ip_version(adev, XGMI_HWIP, 0) ==
-		    IP_VERSION(6, 1, 0)) {
+		    IP_VERSION(6, 1, 0) ||
+		    amdgpu_ip_version(adev, XGMI_HWIP, 0) ==
+		    IP_VERSION(6, 4, 0)) {
 			pcs_ras_fields = &xgmi3x16_pcs_ras_fields[0];
 			field_array_size = ARRAY_SIZE(xgmi3x16_pcs_ras_fields);
 		} else {
@@ -1003,11 +1095,11 @@ static int amdgpu_xgmi_query_pcs_error_status(struct amdgpu_device *adev,
 	return 0;
 }
 
-static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
-					     void *ras_error_status)
+static void amdgpu_xgmi_legacy_query_ras_error_count(struct amdgpu_device *adev,
+						     void *ras_error_status)
 {
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
-	int i;
+	int i, supported = 1;
 	uint32_t data, mask_data = 0;
 	uint32_t ue_cnt = 0, ce_cnt = 0;
 
@@ -1071,7 +1163,25 @@ static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
 		}
 		break;
 	default:
-		dev_warn(adev->dev, "XGMI RAS error query not supported");
+		supported = 0;
+		break;
+	}
+
+	switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) {
+	case IP_VERSION(6, 4, 0):
+		/* check xgmi3x16 pcs error */
+		for (i = 0; i < ARRAY_SIZE(xgmi3x16_pcs_err_status_reg_v6_4); i++) {
+			data = RREG32_PCIE(xgmi3x16_pcs_err_status_reg_v6_4[i]);
+			mask_data =
+				RREG32_PCIE(xgmi3x16_pcs_err_noncorrectable_mask_reg_v6_4[i]);
+			if (data)
+				amdgpu_xgmi_query_pcs_error_status(adev, data,
+						mask_data, &ue_cnt, &ce_cnt, true, true);
+		}
+		break;
+	default:
+		if (!supported)
+			dev_warn(adev->dev, "XGMI RAS error query not supported");
 		break;
 	}
 
@@ -1081,32 +1191,116 @@ static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
 	err_data->ce_count += ce_cnt;
 }
 
+static enum amdgpu_mca_error_type xgmi_v6_4_0_pcs_mca_get_error_type(struct amdgpu_device *adev, u64 status)
+{
+	const char *error_str;
+	int ext_error_code;
+
+	ext_error_code = MCA_REG__STATUS__ERRORCODEEXT(status);
+
+	error_str = ext_error_code < ARRAY_SIZE(xgmi_v6_4_0_ras_error_code_ext) ?
+		xgmi_v6_4_0_ras_error_code_ext[ext_error_code] : NULL;
+	if (error_str)
+		dev_info(adev->dev, "%s detected\n", error_str);
+
+	switch (ext_error_code) {
+	case 0:
+		return AMDGPU_MCA_ERROR_TYPE_UE;
+	case 6:
+		return AMDGPU_MCA_ERROR_TYPE_CE;
+	default:
+		return -EINVAL;
+	}
+
+	return -EINVAL;
+}
+
+static void __xgmi_v6_4_0_query_error_count(struct amdgpu_device *adev, struct amdgpu_smuio_mcm_config_info *mcm_info,
+					    u64 mca_base, struct ras_err_data *err_data)
+{
+	int xgmi_inst = mcm_info->die_id;
+	u64 status = 0;
+
+	status = RREG64_MCA(xgmi_inst, mca_base, MCA_REG_IDX_STATUS);
+	if (!MCA_REG__STATUS__VAL(status))
+		return;
+
+	switch (xgmi_v6_4_0_pcs_mca_get_error_type(adev, status)) {
+	case AMDGPU_MCA_ERROR_TYPE_UE:
+		amdgpu_ras_error_statistic_ue_count(err_data, mcm_info, 1ULL);
+		break;
+	case AMDGPU_MCA_ERROR_TYPE_CE:
+		amdgpu_ras_error_statistic_ce_count(err_data, mcm_info, 1ULL);
+		break;
+	default:
+		break;
+	}
+
+	WREG64_MCA(xgmi_inst, mca_base, MCA_REG_IDX_STATUS, 0ULL);
+}
+
+static void xgmi_v6_4_0_query_error_count(struct amdgpu_device *adev, int xgmi_inst, struct ras_err_data *err_data)
+{
+	struct amdgpu_smuio_mcm_config_info mcm_info = {
+		.socket_id = adev->smuio.funcs->get_socket_id(adev),
+		.die_id = xgmi_inst,
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(xgmi_v6_4_0_mca_base_array); i++)
+		__xgmi_v6_4_0_query_error_count(adev, &mcm_info, xgmi_v6_4_0_mca_base_array[i], err_data);
+}
+
+static void xgmi_v6_4_0_query_ras_error_count(struct amdgpu_device *adev, void *ras_error_status)
+{
+	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+	int i;
+
+	for_each_inst(i, adev->aid_mask)
+		xgmi_v6_4_0_query_error_count(adev, i, err_data);
+}
+
+static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
+					      void *ras_error_status)
+{
+	switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) {
+	case IP_VERSION(6, 4, 0):
+		xgmi_v6_4_0_query_ras_error_count(adev, ras_error_status);
+		break;
+	default:
+		amdgpu_xgmi_legacy_query_ras_error_count(adev, ras_error_status);
+		break;
+	}
+}
+
 /* Trigger XGMI/WAFL error */
 static int amdgpu_ras_error_inject_xgmi(struct amdgpu_device *adev,
 			void *inject_if, uint32_t instance_mask)
 {
-	int ret = 0;
+	int ret1, ret2;
 	struct ta_ras_trigger_error_input *block_info =
 				(struct ta_ras_trigger_error_input *)inject_if;
 
 	if (amdgpu_dpm_set_df_cstate(adev, DF_CSTATE_DISALLOW))
 		dev_warn(adev->dev, "Failed to disallow df cstate");
 
-	if (amdgpu_dpm_set_xgmi_plpd_mode(adev, XGMI_PLPD_DISALLOW))
+	ret1 = amdgpu_dpm_set_xgmi_plpd_mode(adev, XGMI_PLPD_DISALLOW);
+	if (ret1 && ret1 != -EOPNOTSUPP)
 		dev_warn(adev->dev, "Failed to disallow XGMI power down");
 
-	ret = psp_ras_trigger_error(&adev->psp, block_info, instance_mask);
+	ret2 = psp_ras_trigger_error(&adev->psp, block_info, instance_mask);
 
 	if (amdgpu_ras_intr_triggered())
-		return ret;
+		return ret2;
 
-	if (amdgpu_dpm_set_xgmi_plpd_mode(adev, XGMI_PLPD_DEFAULT))
+	ret1 = amdgpu_dpm_set_xgmi_plpd_mode(adev, XGMI_PLPD_DEFAULT);
+	if (ret1 && ret1 != -EOPNOTSUPP)
 		dev_warn(adev->dev, "Failed to allow XGMI power down");
 
 	if (amdgpu_dpm_set_df_cstate(adev, DF_CSTATE_ALLOW))
 		dev_warn(adev->dev, "Failed to allow df cstate");
 
-	return ret;
+	return ret2;
 }
 
 struct amdgpu_ras_block_hw_ops  xgmi_ras_hw_ops = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 0c6133cc5e5780..8ed4a6fb147a2a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -89,6 +89,10 @@ MODULE_FIRMWARE("amdgpu/gc_11_5_0_me.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_mec.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_rlc.bin");
 
+static const struct soc15_reg_golden golden_settings_gc_11_0[] = {
+	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL, 0x20000000, 0x20000000)
+};
+
 static const struct soc15_reg_golden golden_settings_gc_11_0_1[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regCGTT_GS_NGG_CLK_CTRL, 0x9fff8fff, 0x00000010),
@@ -304,6 +308,10 @@ static void gfx_v11_0_init_golden_registers(struct amdgpu_device *adev)
 	default:
 		break;
 	}
+	soc15_program_register_sequence(adev,
+					golden_settings_gc_11_0,
+					(const u32)ARRAY_SIZE(golden_settings_gc_11_0));
+
 }
 
 static void gfx_v11_0_write_data_to_reg(struct amdgpu_ring *ring, int eng_sel,
@@ -419,7 +427,7 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 		cpu_ptr = &adev->wb.wb[index];
 
-		r = amdgpu_ib_get(adev, NULL, 16, AMDGPU_IB_POOL_DIRECT, &ib);
+		r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib);
 		if (r) {
 			DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
 			goto err1;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 885ebd703260f0..1943beb135c4c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -883,8 +883,8 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	gpu_addr = adev->wb.gpu_addr + (index * 4);
 	adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
-	r = amdgpu_ib_get(adev, NULL, 16,
-					AMDGPU_IB_POOL_DIRECT, &ib);
+
+	r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib);
 	if (r)
 		goto err1;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index e3ff6e46f3f738..69c50091074601 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1039,8 +1039,8 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	gpu_addr = adev->wb.gpu_addr + (index * 4);
 	adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
-	r = amdgpu_ib_get(adev, NULL, 16,
-					AMDGPU_IB_POOL_DIRECT, &ib);
+
+	r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib);
 	if (r)
 		goto err1;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 41bbabd9ad4db5..4a09cc0d8ce07f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -297,8 +297,8 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	gpu_addr = adev->wb.gpu_addr + (index * 4);
 	adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
-	r = amdgpu_ib_get(adev, NULL, 16,
-			  AMDGPU_IB_POOL_DIRECT, &ib);
+
+	r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib);
 	if (r)
 		goto err1;
 
@@ -1102,6 +1102,7 @@ static void gfx_v9_4_3_init_rlcg_reg_access_ctrl(struct amdgpu_device *adev)
 		reg_access_ctrl->grbm_idx = SOC15_REG_OFFSET(GC, GET_INST(GC, xcc_id), regGRBM_GFX_INDEX);
 		reg_access_ctrl->spare_int = SOC15_REG_OFFSET(GC, GET_INST(GC, xcc_id), regRLC_SPARE_INT);
 	}
+	adev->gfx.rlc.rlcg_reg_access_supported = true;
 }
 
 static int gfx_v9_4_3_rlc_init(struct amdgpu_device *adev)
@@ -2738,16 +2739,16 @@ static void gfx_v9_4_3_xcc_set_compute_eop_interrupt_state(
 
 	switch (state) {
 	case AMDGPU_IRQ_STATE_DISABLE:
-		mec_int_cntl = RREG32(mec_int_cntl_reg);
+		mec_int_cntl = RREG32_XCC(mec_int_cntl_reg, xcc_id);
 		mec_int_cntl = REG_SET_FIELD(mec_int_cntl, CP_ME1_PIPE0_INT_CNTL,
 					     TIME_STAMP_INT_ENABLE, 0);
-		WREG32(mec_int_cntl_reg, mec_int_cntl);
+		WREG32_XCC(mec_int_cntl_reg, mec_int_cntl, xcc_id);
 		break;
 	case AMDGPU_IRQ_STATE_ENABLE:
-		mec_int_cntl = RREG32(mec_int_cntl_reg);
+		mec_int_cntl = RREG32_XCC(mec_int_cntl_reg, xcc_id);
 		mec_int_cntl = REG_SET_FIELD(mec_int_cntl, CP_ME1_PIPE0_INT_CNTL,
 					     TIME_STAMP_INT_ENABLE, 1);
-		WREG32(mec_int_cntl_reg, mec_int_cntl);
+		WREG32_XCC(mec_int_cntl_reg, mec_int_cntl, xcc_id);
 		break;
 	default:
 		break;
@@ -3799,6 +3800,27 @@ static void gfx_v9_4_3_inst_query_ras_err_count(struct amdgpu_device *adev,
 		}
 	}
 
+	/* handle extra register entries of UE */
+	for (; i < ARRAY_SIZE(gfx_v9_4_3_ue_reg_list); i++) {
+		for (j = 0; j < gfx_v9_4_3_ue_reg_list[i].se_num; j++) {
+			for (k = 0; k < gfx_v9_4_3_ue_reg_list[i].reg_entry.reg_inst; k++) {
+				/* no need to select if instance number is 1 */
+				if (gfx_v9_4_3_ue_reg_list[i].se_num > 1 ||
+					gfx_v9_4_3_ue_reg_list[i].reg_entry.reg_inst > 1)
+					gfx_v9_4_3_xcc_select_se_sh(adev, j, 0, k, xcc_id);
+
+				amdgpu_ras_inst_query_ras_error_count(adev,
+					&(gfx_v9_4_3_ue_reg_list[i].reg_entry),
+					1,
+					gfx_v9_4_3_ras_mem_list_array[gfx_v9_4_3_ue_reg_list[i].mem_id_type].mem_id_ent,
+					gfx_v9_4_3_ras_mem_list_array[gfx_v9_4_3_ue_reg_list[i].mem_id_type].size,
+					GET_INST(GC, xcc_id),
+					AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE,
+					&ue_count);
+			}
+		}
+	}
+
 	gfx_v9_4_3_xcc_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff,
 			xcc_id);
 	mutex_unlock(&adev->grbm_idx_mutex);
@@ -3838,6 +3860,23 @@ static void gfx_v9_4_3_inst_reset_ras_err_count(struct amdgpu_device *adev,
 		}
 	}
 
+	/* handle extra register entries of UE */
+	for (; i < ARRAY_SIZE(gfx_v9_4_3_ue_reg_list); i++) {
+		for (j = 0; j < gfx_v9_4_3_ue_reg_list[i].se_num; j++) {
+			for (k = 0; k < gfx_v9_4_3_ue_reg_list[i].reg_entry.reg_inst; k++) {
+				/* no need to select if instance number is 1 */
+				if (gfx_v9_4_3_ue_reg_list[i].se_num > 1 ||
+					gfx_v9_4_3_ue_reg_list[i].reg_entry.reg_inst > 1)
+					gfx_v9_4_3_xcc_select_se_sh(adev, j, 0, k, xcc_id);
+
+				amdgpu_ras_inst_reset_ras_error_count(adev,
+					&(gfx_v9_4_3_ue_reg_list[i].reg_entry),
+					1,
+					GET_INST(GC, xcc_id));
+			}
+		}
+	}
+
 	gfx_v9_4_3_xcc_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff,
 			xcc_id);
 	mutex_unlock(&adev->grbm_idx_mutex);
@@ -4300,7 +4339,7 @@ const struct amdgpu_ip_block_version gfx_v9_4_3_ip_block = {
 	.type = AMD_IP_BLOCK_TYPE_GFX,
 	.major = 9,
 	.minor = 4,
-	.rev = 0,
+	.rev = 3,
 	.funcs = &gfx_v9_4_3_ip_funcs,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index d8a4fddab9c1d0..a5a05c16c10d7b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -268,7 +268,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	if (adev->gfx.kiq[0].ring.sched.ready && !adev->enable_mes &&
 	    (amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev))) {
 		amdgpu_virt_kiq_reg_write_reg_wait(adev, req, ack, inv_req,
-				1 << vmid);
+				1 << vmid, GET_INST(GC, 0));
 		return;
 	}
 
@@ -672,9 +672,10 @@ static void gmc_v10_0_vram_gtt_location(struct amdgpu_device *adev,
 	/* add the xgmi offset of the physical node */
 	base += adev->gmc.xgmi.physical_node_id * adev->gmc.xgmi.node_segment_size;
 
+	amdgpu_gmc_set_agp_default(adev, mc);
 	amdgpu_gmc_vram_location(adev, &adev->gmc, base);
 	amdgpu_gmc_gart_location(adev, mc, AMDGPU_GART_PLACEMENT_BEST_FIT);
-	if (!amdgpu_sriov_vf(adev))
+	if (!amdgpu_sriov_vf(adev) && (amdgpu_agp == 1))
 		amdgpu_gmc_agp_location(adev, mc);
 
 	/* base offset of vram pages */
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index 4713a62ad586f9..23d7b548d13f44 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -229,7 +229,7 @@ static void gmc_v11_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	if ((adev->gfx.kiq[0].ring.sched.ready || adev->mes.ring.sched.ready) &&
 	    (amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev))) {
 		amdgpu_virt_kiq_reg_write_reg_wait(adev, req, ack, inv_req,
-				1 << vmid);
+				1 << vmid, GET_INST(GC, 0));
 		return;
 	}
 
@@ -637,10 +637,12 @@ static void gmc_v11_0_vram_gtt_location(struct amdgpu_device *adev,
 
 	base = adev->mmhub.funcs->get_fb_location(adev);
 
+	amdgpu_gmc_set_agp_default(adev, mc);
 	amdgpu_gmc_vram_location(adev, &adev->gmc, base);
 	amdgpu_gmc_gart_location(adev, mc, AMDGPU_GART_PLACEMENT_HIGH);
-	if (!amdgpu_sriov_vf(adev) ||
-	    (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(11, 5, 0)))
+	if (!amdgpu_sriov_vf(adev) &&
+	    (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(11, 5, 0)) &&
+	    (amdgpu_agp == 1))
 		amdgpu_gmc_agp_location(adev, mc);
 
 	/* base offset of vram pages */
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 7f66954fd3027c..42e103d7077d52 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -211,6 +211,7 @@ static void gmc_v6_0_vram_gtt_location(struct amdgpu_device *adev,
 
 	base <<= 24;
 
+	amdgpu_gmc_set_agp_default(adev, mc);
 	amdgpu_gmc_vram_location(adev, mc, base);
 	amdgpu_gmc_gart_location(adev, mc, AMDGPU_GART_PLACEMENT_BEST_FIT);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 61ca1a82b651aa..efc16e580f1e27 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -239,6 +239,7 @@ static void gmc_v7_0_vram_gtt_location(struct amdgpu_device *adev,
 
 	base <<= 24;
 
+	amdgpu_gmc_set_agp_default(adev, mc);
 	amdgpu_gmc_vram_location(adev, mc, base);
 	amdgpu_gmc_gart_location(adev, mc, AMDGPU_GART_PLACEMENT_BEST_FIT);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index fa59749c2aefa6..ff4ae73d27ecd2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -413,6 +413,7 @@ static void gmc_v8_0_vram_gtt_location(struct amdgpu_device *adev,
 		base = RREG32(mmMC_VM_FB_LOCATION) & 0xFFFF;
 	base <<= 24;
 
+	amdgpu_gmc_set_agp_default(adev, mc);
 	amdgpu_gmc_vram_location(adev, mc, base);
 	amdgpu_gmc_gart_location(adev, mc, AMDGPU_GART_PLACEMENT_BEST_FIT);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index b66c5f7e1c5657..2ac5820e9c9241 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -817,7 +817,7 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 					uint32_t vmhub, uint32_t flush_type)
 {
 	bool use_semaphore = gmc_v9_0_use_invalidate_semaphore(adev, vmhub);
-	u32 j, inv_req, tmp, sem, req, ack;
+	u32 j, inv_req, tmp, sem, req, ack, inst;
 	const unsigned int eng = 17;
 	struct amdgpu_vmhub *hub;
 
@@ -832,13 +832,17 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	/* This is necessary for a HW workaround under SRIOV as well
 	 * as GFXOFF under bare metal
 	 */
-	if (adev->gfx.kiq[0].ring.sched.ready &&
+	if (vmhub >= AMDGPU_MMHUB0(0))
+		inst = GET_INST(GC, 0);
+	else
+		inst = vmhub;
+	if (adev->gfx.kiq[inst].ring.sched.ready &&
 	    (amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev))) {
 		uint32_t req = hub->vm_inv_eng0_req + hub->eng_distance * eng;
 		uint32_t ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng;
 
 		amdgpu_virt_kiq_reg_write_reg_wait(adev, req, ack, inv_req,
-						   1 << vmid);
+						   1 << vmid, inst);
 		return;
 	}
 
@@ -856,9 +860,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 		for (j = 0; j < adev->usec_timeout; j++) {
 			/* a read return value of 1 means semaphore acquire */
 			if (vmhub >= AMDGPU_MMHUB0(0))
-				tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, sem);
+				tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, sem, inst);
 			else
-				tmp = RREG32_SOC15_IP_NO_KIQ(GC, sem);
+				tmp = RREG32_SOC15_IP_NO_KIQ(GC, sem, inst);
 			if (tmp & 0x1)
 				break;
 			udelay(1);
@@ -869,9 +873,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	}
 
 	if (vmhub >= AMDGPU_MMHUB0(0))
-		WREG32_SOC15_IP_NO_KIQ(MMHUB, req, inv_req);
+		WREG32_SOC15_IP_NO_KIQ(MMHUB, req, inv_req, inst);
 	else
-		WREG32_SOC15_IP_NO_KIQ(GC, req, inv_req);
+		WREG32_SOC15_IP_NO_KIQ(GC, req, inv_req, inst);
 
 	/*
 	 * Issue a dummy read to wait for the ACK register to
@@ -884,9 +888,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 
 	for (j = 0; j < adev->usec_timeout; j++) {
 		if (vmhub >= AMDGPU_MMHUB0(0))
-			tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, ack);
+			tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, ack, inst);
 		else
-			tmp = RREG32_SOC15_IP_NO_KIQ(GC, ack);
+			tmp = RREG32_SOC15_IP_NO_KIQ(GC, ack, inst);
 		if (tmp & (1 << vmid))
 			break;
 		udelay(1);
@@ -899,9 +903,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 		 * write with 0 means semaphore release
 		 */
 		if (vmhub >= AMDGPU_MMHUB0(0))
-			WREG32_SOC15_IP_NO_KIQ(MMHUB, sem, 0);
+			WREG32_SOC15_IP_NO_KIQ(MMHUB, sem, 0, inst);
 		else
-			WREG32_SOC15_IP_NO_KIQ(GC, sem, 0);
+			WREG32_SOC15_IP_NO_KIQ(GC, sem, 0, inst);
 	}
 
 	spin_unlock(&adev->gmc.invalidate_lock);
@@ -1176,7 +1180,10 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 		if (uncached) {
 			mtype = MTYPE_UC;
 		} else if (ext_coherent) {
-			mtype = is_local ? MTYPE_CC : MTYPE_UC;
+			if (adev->rev_id)
+				mtype = is_local ? MTYPE_CC : MTYPE_UC;
+			else
+				mtype = MTYPE_UC;
 		} else if (adev->flags & AMD_IS_APU) {
 			mtype = is_local ? mtype_local : MTYPE_NC;
 		} else {
@@ -1297,7 +1304,7 @@ static void gmc_v9_0_override_vm_pte_flags(struct amdgpu_device *adev,
 
 			*flags = (*flags & ~AMDGPU_PTE_MTYPE_VG10_MASK) |
 				 AMDGPU_PTE_MTYPE_VG10(mtype_local);
-		} else {
+		} else if (adev->rev_id) {
 			/* MTYPE_UC case */
 			*flags = (*flags & ~AMDGPU_PTE_MTYPE_VG10_MASK) |
 				 AMDGPU_PTE_MTYPE_VG10(MTYPE_CC);
@@ -1614,6 +1621,8 @@ static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev,
 {
 	u64 base = adev->mmhub.funcs->get_fb_location(adev);
 
+	amdgpu_gmc_set_agp_default(adev, mc);
+
 	/* add the xgmi offset of the physical node */
 	base += adev->gmc.xgmi.physical_node_id * adev->gmc.xgmi.node_segment_size;
 	if (adev->gmc.xgmi.connected_to_cpu) {
@@ -1621,7 +1630,7 @@ static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev,
 	} else {
 		amdgpu_gmc_vram_location(adev, mc, base);
 		amdgpu_gmc_gart_location(adev, mc, AMDGPU_GART_PLACEMENT_BEST_FIT);
-		if (!amdgpu_sriov_vf(adev))
+		if (!amdgpu_sriov_vf(adev) && (amdgpu_agp == 1))
 			amdgpu_gmc_agp_location(adev, mc);
 	}
 	/* base offset of vram pages */
@@ -2161,8 +2170,6 @@ static int gmc_v9_0_sw_fini(void *handle)
 
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3))
 		amdgpu_gmc_sysfs_fini(adev);
-	adev->gmc.num_mem_partitions = 0;
-	kfree(adev->gmc.mem_partitions);
 
 	amdgpu_gmc_ras_fini(adev);
 	amdgpu_gem_force_release(adev);
@@ -2176,6 +2183,9 @@ static int gmc_v9_0_sw_fini(void *handle)
 	amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0);
 	amdgpu_bo_fini(adev);
 
+	adev->gmc.num_mem_partitions = 0;
+	kfree(adev->gmc.mem_partitions);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
index 3f3a6445c006f2..4db6bb73ead427 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c
@@ -129,6 +129,11 @@ static void hdp_v4_0_get_clockgating_state(struct amdgpu_device *adev,
 {
 	int data;
 
+	if (amdgpu_ip_version(adev, HDP_HWIP, 0) == IP_VERSION(4, 4, 2)) {
+		/* Default enabled */
+		*flags |= AMD_CG_SUPPORT_HDP_MGCG;
+		return;
+	}
 	/* AMD_CG_SUPPORT_HDP_LS */
 	data = RREG32(SOC15_REG_OFFSET(HDP, 0, mmHDP_MEM_POWER_LS));
 	if (data & HDP_MEM_POWER_LS__LS_ENABLE_MASK)
@@ -145,6 +150,10 @@ static void hdp_v4_0_init_registers(struct amdgpu_device *adev)
 		break;
 	}
 
+	/* Do not program registers if VF */
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	WREG32_FIELD15(HDP, 0, HDP_MISC_CNTL, FLUSH_INVALIDATE_CACHE, 1);
 
 	if (amdgpu_ip_version(adev, HDP_HWIP, 0) == IP_VERSION(4, 4, 0))
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
index 9a8ec4d7e3334c..82b6b62c170ba4 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
@@ -654,9 +654,11 @@ static void jpeg_v4_0_3_dec_ring_set_wptr(struct amdgpu_ring *ring)
  */
 static void jpeg_v4_0_3_dec_ring_insert_start(struct amdgpu_ring *ring)
 {
-	amdgpu_ring_write(ring, PACKETJ(regUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x62a04); /* PCTL0_MMHUB_DEEPSLEEP_IB */
+	if (!amdgpu_sriov_vf(ring->adev)) {
+		amdgpu_ring_write(ring, PACKETJ(regUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
+			0, 0, PACKETJ_TYPE0));
+		amdgpu_ring_write(ring, 0x62a04); /* PCTL0_MMHUB_DEEPSLEEP_IB */
+	}
 
 	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
 		0, 0, PACKETJ_TYPE0));
@@ -672,9 +674,11 @@ static void jpeg_v4_0_3_dec_ring_insert_start(struct amdgpu_ring *ring)
  */
 static void jpeg_v4_0_3_dec_ring_insert_end(struct amdgpu_ring *ring)
 {
-	amdgpu_ring_write(ring, PACKETJ(regUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x62a04);
+	if (!amdgpu_sriov_vf(ring->adev)) {
+		amdgpu_ring_write(ring, PACKETJ(regUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
+			0, 0, PACKETJ_TYPE0));
+		amdgpu_ring_write(ring, 0x62a04);
+	}
 
 	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
 		0, 0, PACKETJ_TYPE0));
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index 9df011323d4b97..6ede85b28cc8c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -155,13 +155,6 @@ static int jpeg_v4_0_5_hw_init(void *handle)
 	struct amdgpu_ring *ring = adev->jpeg.inst->ring_dec;
 	int r;
 
-	adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
-				(adev->doorbell_index.vcn.vcn_ring0_1 << 1), 0);
-
-	WREG32_SOC15(VCN, 0, regVCN_JPEG_DB_CTRL,
-		ring->doorbell_index << VCN_JPEG_DB_CTRL__OFFSET__SHIFT |
-		VCN_JPEG_DB_CTRL__EN_MASK);
-
 	r = amdgpu_ring_test_helper(ring);
 	if (r)
 		return r;
@@ -336,6 +329,14 @@ static int jpeg_v4_0_5_start(struct amdgpu_device *adev)
 	if (adev->pm.dpm_enabled)
 		amdgpu_dpm_enable_jpeg(adev, true);
 
+	/* doorbell programming is done for every playback */
+	adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
+				(adev->doorbell_index.vcn.vcn_ring0_1 << 1), 0);
+
+	WREG32_SOC15(VCN, 0, regVCN_JPEG_DB_CTRL,
+		ring->doorbell_index << VCN_JPEG_DB_CTRL__OFFSET__SHIFT |
+		VCN_JPEG_DB_CTRL__EN_MASK);
+
 	/* disable power gating */
 	r = jpeg_v4_0_5_disable_static_power_gating(adev);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
index ea142611be1c06..9b0146732e13ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
@@ -130,6 +130,9 @@ static void mmhub_v1_8_init_system_aperture_regs(struct amdgpu_device *adev)
 	uint64_t value;
 	int i;
 
+	if (amdgpu_sriov_vf(adev))
+		return;
+
 	inst_mask = adev->aid_mask;
 	for_each_inst(i, inst_mask) {
 		/* Program the AGP BAR */
@@ -139,9 +142,6 @@ static void mmhub_v1_8_init_system_aperture_regs(struct amdgpu_device *adev)
 		WREG32_SOC15(MMHUB, i, regMC_VM_AGP_TOP,
 			     adev->gmc.agp_end >> 24);
 
-		if (amdgpu_sriov_vf(adev))
-			return;
-
 		/* Program the system aperture low logical page number. */
 		WREG32_SOC15(MMHUB, i, regMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 			min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
index 676ab1d20d2f62..1f52b4b1db030c 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
@@ -259,17 +259,17 @@ const struct nbio_hdp_flush_reg nbio_v7_11_hdp_flush_reg = {
 
 static void nbio_v7_11_init_registers(struct amdgpu_device *adev)
 {
-/*	uint32_t def, data;
+	uint32_t def, data;
+
+	def = data = RREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3);
+	data = REG_SET_FIELD(data, BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3,
+				CI_SWUS_MAX_READ_REQUEST_SIZE_MODE, 1);
+	data = REG_SET_FIELD(data, BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3,
+				CI_SWUS_MAX_READ_REQUEST_SIZE_PRIV, 1);
 
-		def = data = RREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3);
-		data = REG_SET_FIELD(data, BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3,
-			CI_SWUS_MAX_READ_REQUEST_SIZE_MODE, 1);
-		data = REG_SET_FIELD(data, BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3,
-			CI_SWUS_MAX_READ_REQUEST_SIZE_PRIV, 1);
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3, data);
 
-		if (def != data)
-			WREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3, data);
-*/
 }
 
 static void nbio_v7_11_update_medium_grain_clock_gating(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index 23f26f8caad4cf..25a3da83e0fb97 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -611,11 +611,6 @@ static void nbio_v7_9_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 
 		dev_info(adev->dev, "RAS controller interrupt triggered "
 					"by NBIF error\n");
-
-		/* ras_controller_int is dedicated for nbif ras error,
-		 * not the global interrupt for sync flood
-		 */
-		amdgpu_ras_reset_gpu(adev);
 	}
 
 	amdgpu_ras_error_data_fini(&err_data);
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index 3cf4684d0d3f3c..df1844d0800f2e 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -60,7 +60,7 @@ MODULE_FIRMWARE("amdgpu/psp_14_0_0_ta.bin");
 #define GFX_CMD_USB_PD_USE_LFB 0x480
 
 /* Retry times for vmbx ready wait */
-#define PSP_VMBX_POLLING_LIMIT 20000
+#define PSP_VMBX_POLLING_LIMIT 3000
 
 /* VBIOS gfl defines */
 #define MBOX_READY_MASK 0x80000000
@@ -161,14 +161,18 @@ static int psp_v13_0_wait_for_vmbx_ready(struct psp_context *psp)
 static int psp_v13_0_wait_for_bootloader(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
-	int retry_loop, ret;
+	int retry_loop, retry_cnt, ret;
 
+	retry_cnt =
+		(amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 6)) ?
+			PSP_VMBX_POLLING_LIMIT :
+			10;
 	/* Wait for bootloader to signify that it is ready having bit 31 of
 	 * C2PMSG_35 set to 1. All other bits are expected to be cleared.
 	 * If there is an error in processing command, bits[7:0] will be set.
 	 * This is applicable for PSP v13.0.6 and newer.
 	 */
-	for (retry_loop = 0; retry_loop < PSP_VMBX_POLLING_LIMIT; retry_loop++) {
+	for (retry_loop = 0; retry_loop < retry_cnt; retry_loop++) {
 		ret = psp_wait_for(
 			psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35),
 			0x80000000, 0xffffffff, false);
@@ -821,7 +825,7 @@ static int psp_v13_0_query_boot_status(struct psp_context *psp)
 	if (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6))
 		return 0;
 
-	if (RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_59) < 0x00a10007)
+	if (RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_59) < 0x00a10109)
 		return 0;
 
 	for_each_inst(i, inst_mask) {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 45377a1752503b..8d5d86675a7fea 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -813,12 +813,12 @@ static int sdma_v2_4_early_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int r;
 
+	adev->sdma.num_instances = SDMA_MAX_INSTANCE;
+
 	r = sdma_v2_4_init_microcode(adev);
 	if (r)
 		return r;
 
-	adev->sdma.num_instances = SDMA_MAX_INSTANCE;
-
 	sdma_v2_4_set_ring_funcs(adev);
 	sdma_v2_4_set_buffer_funcs(adev);
 	sdma_v2_4_set_vm_pte_funcs(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index c46bc6aa4f48f8..0f24af6f28102b 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -427,6 +427,7 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev,
 				      uint32_t inst_mask)
 {
 	struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES];
+	u32 doorbell_offset, doorbell;
 	u32 rb_cntl, ib_cntl;
 	int i, unset = 0;
 
@@ -444,6 +445,18 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev,
 		ib_cntl = RREG32_SDMA(i, regSDMA_GFX_IB_CNTL);
 		ib_cntl = REG_SET_FIELD(ib_cntl, SDMA_GFX_IB_CNTL, IB_ENABLE, 0);
 		WREG32_SDMA(i, regSDMA_GFX_IB_CNTL, ib_cntl);
+
+		if (sdma[i]->use_doorbell) {
+			doorbell = RREG32_SDMA(i, regSDMA_GFX_DOORBELL);
+			doorbell_offset = RREG32_SDMA(i, regSDMA_GFX_DOORBELL_OFFSET);
+
+			doorbell = REG_SET_FIELD(doorbell, SDMA_GFX_DOORBELL, ENABLE, 0);
+			doorbell_offset = REG_SET_FIELD(doorbell_offset,
+					SDMA_GFX_DOORBELL_OFFSET,
+					OFFSET, 0);
+			WREG32_SDMA(i, regSDMA_GFX_DOORBELL, doorbell);
+			WREG32_SDMA(i, regSDMA_GFX_DOORBELL_OFFSET, doorbell_offset);
+		}
 	}
 }
 
@@ -631,12 +644,6 @@ static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i)
 	rb_cntl = sdma_v4_4_2_rb_cntl(ring, rb_cntl);
 	WREG32_SDMA(i, regSDMA_GFX_RB_CNTL, rb_cntl);
 
-	/* Initialize the ring buffer's read and write pointers */
-	WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, 0);
-	WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, 0);
-	WREG32_SDMA(i, regSDMA_GFX_RB_WPTR, 0);
-	WREG32_SDMA(i, regSDMA_GFX_RB_WPTR_HI, 0);
-
 	/* set the wb address whether it's enabled or not */
 	WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_ADDR_HI,
 	       upper_32_bits(adev->wb.gpu_addr + wb_offset) & 0xFFFFFFFF);
@@ -654,6 +661,12 @@ static void sdma_v4_4_2_gfx_resume(struct amdgpu_device *adev, unsigned int i)
 	/* before programing wptr to a less value, need set minor_ptr_update first */
 	WREG32_SDMA(i, regSDMA_GFX_MINOR_PTR_UPDATE, 1);
 
+	/* Initialize the ring buffer's read and write pointers */
+	WREG32_SDMA(i, regSDMA_GFX_RB_RPTR, 0);
+	WREG32_SDMA(i, regSDMA_GFX_RB_RPTR_HI, 0);
+	WREG32_SDMA(i, regSDMA_GFX_RB_WPTR, 0);
+	WREG32_SDMA(i, regSDMA_GFX_RB_WPTR_HI, 0);
+
 	doorbell = RREG32_SDMA(i, regSDMA_GFX_DOORBELL);
 	doorbell_offset = RREG32_SDMA(i, regSDMA_GFX_DOORBELL_OFFSET);
 
@@ -2048,7 +2061,7 @@ const struct amdgpu_ip_block_version sdma_v4_4_2_ip_block = {
 	.type = AMD_IP_BLOCK_TYPE_SDMA,
 	.major = 4,
 	.minor = 4,
-	.rev = 0,
+	.rev = 2,
 	.funcs = &sdma_v4_4_2_ip_funcs,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 83c240f741b519..0058f3f7cf6e43 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -1643,6 +1643,32 @@ static void sdma_v5_2_get_clockgating_state(void *handle, u64 *flags)
 		*flags |= AMD_CG_SUPPORT_SDMA_LS;
 }
 
+static void sdma_v5_2_ring_begin_use(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	/* SDMA 5.2.3 (RMB) FW doesn't seem to properly
+	 * disallow GFXOFF in some cases leading to
+	 * hangs in SDMA.  Disallow GFXOFF while SDMA is active.
+	 * We can probably just limit this to 5.2.3,
+	 * but it shouldn't hurt for other parts since
+	 * this GFXOFF will be disallowed anyway when SDMA is
+	 * active, this just makes it explicit.
+	 */
+	amdgpu_gfx_off_ctrl(adev, false);
+}
+
+static void sdma_v5_2_ring_end_use(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	/* SDMA 5.2.3 (RMB) FW doesn't seem to properly
+	 * disallow GFXOFF in some cases leading to
+	 * hangs in SDMA.  Allow GFXOFF when SDMA is complete.
+	 */
+	amdgpu_gfx_off_ctrl(adev, true);
+}
+
 const struct amd_ip_funcs sdma_v5_2_ip_funcs = {
 	.name = "sdma_v5_2",
 	.early_init = sdma_v5_2_early_init,
@@ -1690,6 +1716,8 @@ static const struct amdgpu_ring_funcs sdma_v5_2_ring_funcs = {
 	.test_ib = sdma_v5_2_ring_test_ib,
 	.insert_nop = sdma_v5_2_ring_insert_nop,
 	.pad_ib = sdma_v5_2_ring_pad_ib,
+	.begin_use = sdma_v5_2_ring_begin_use,
+	.end_use = sdma_v5_2_ring_end_use,
 	.emit_wreg = sdma_v5_2_ring_emit_wreg,
 	.emit_reg_wait = sdma_v5_2_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = sdma_v5_2_ring_emit_reg_write_reg_wait,
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index d4b8d62f42943f..51342809af0347 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1161,6 +1161,11 @@ static int soc15_common_early_init(void *handle)
 			AMD_PG_SUPPORT_VCN_DPG |
 			AMD_PG_SUPPORT_JPEG;
 		adev->external_rev_id = adev->rev_id + 0x46;
+		/* GC 9.4.3 uses MMIO register region hole at a different offset */
+		if (!amdgpu_sriov_vf(adev)) {
+			adev->rmmio_remap.reg_offset = 0x1A000;
+			adev->rmmio_remap.bus_addr = adev->rmmio_base + 0x1A000;
+		}
 		break;
 	default:
 		/* FIXME: not supported yet */
@@ -1418,11 +1423,14 @@ static void soc15_common_get_clockgating_state(void *handle, u64 *flags)
 	if (amdgpu_sriov_vf(adev))
 		*flags = 0;
 
-	adev->nbio.funcs->get_clockgating_state(adev, flags);
+	if (adev->nbio.funcs && adev->nbio.funcs->get_clockgating_state)
+		adev->nbio.funcs->get_clockgating_state(adev, flags);
 
-	adev->hdp.funcs->get_clock_gating_state(adev, flags);
+	if (adev->hdp.funcs && adev->hdp.funcs->get_clock_gating_state)
+		adev->hdp.funcs->get_clock_gating_state(adev, flags);
 
-	if (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 2)) {
+	if ((amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 2)) &&
+	    (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6))) {
 		/* AMD_CG_SUPPORT_DRM_MGCG */
 		data = RREG32(SOC15_REG_OFFSET(MP0, 0, mmMP0_MISC_CGTT_CTRL0));
 		if (!(data & 0x01000000))
@@ -1435,9 +1443,11 @@ static void soc15_common_get_clockgating_state(void *handle, u64 *flags)
 	}
 
 	/* AMD_CG_SUPPORT_ROM_MGCG */
-	adev->smuio.funcs->get_clock_gating_state(adev, flags);
+	if (adev->smuio.funcs && adev->smuio.funcs->get_clock_gating_state)
+		adev->smuio.funcs->get_clock_gating_state(adev, flags);
 
-	adev->df.funcs->get_clockgating_state(adev, flags);
+	if (adev->df.funcs && adev->df.funcs->get_clockgating_state)
+		adev->df.funcs->get_clockgating_state(adev, flags);
 }
 
 static int soc15_common_set_powergating_state(void *handle,
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
index da683afa0222f1..242b24f73c1744 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
@@ -69,7 +69,7 @@
 
 #define RREG32_SOC15_IP(ip, reg) __RREG32_SOC15_RLC__(reg, 0, ip##_HWIP, 0)
 
-#define RREG32_SOC15_IP_NO_KIQ(ip, reg) __RREG32_SOC15_RLC__(reg, AMDGPU_REGS_NO_KIQ, ip##_HWIP, 0)
+#define RREG32_SOC15_IP_NO_KIQ(ip, reg, inst) __RREG32_SOC15_RLC__(reg, AMDGPU_REGS_NO_KIQ, ip##_HWIP, inst)
 
 #define RREG32_SOC15_NO_KIQ(ip, inst, reg) \
 	__RREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, \
@@ -86,8 +86,8 @@
 #define WREG32_SOC15_IP(ip, reg, value) \
 	 __WREG32_SOC15_RLC__(reg, value, 0, ip##_HWIP, 0)
 
-#define WREG32_SOC15_IP_NO_KIQ(ip, reg, value) \
-	 __WREG32_SOC15_RLC__(reg, value, AMDGPU_REGS_NO_KIQ, ip##_HWIP, 0)
+#define WREG32_SOC15_IP_NO_KIQ(ip, reg, value, inst) \
+	 __WREG32_SOC15_RLC__(reg, value, AMDGPU_REGS_NO_KIQ, ip##_HWIP, inst)
 
 #define WREG32_SOC15_NO_KIQ(ip, inst, reg, value) \
 	__WREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, \
@@ -140,7 +140,7 @@
 
 /* for GC only */
 #define RREG32_RLC(reg) \
-	__RREG32_SOC15_RLC__(reg, AMDGPU_REGS_RLC, GC_HWIP)
+	__RREG32_SOC15_RLC__(reg, AMDGPU_REGS_RLC, GC_HWIP, 0)
 
 #define WREG32_RLC_NO_KIQ(reg, value, hwip) \
 	__WREG32_SOC15_RLC__(reg, value, AMDGPU_REGS_NO_KIQ | AMDGPU_REGS_RLC, hwip, 0)
@@ -204,4 +204,10 @@
 			+ adev->asic_funcs->encode_ext_smn_addressing(ext), \
 			value) \
 
+#define RREG64_MCA(ext, mca_base, idx) \
+	RREG64_PCIE_EXT(adev->asic_funcs->encode_ext_smn_addressing(ext) + mca_base + (idx * 8))
+
+#define WREG64_MCA(ext, mca_base, idx, val) \
+	WREG64_PCIE_EXT(adev->asic_funcs->encode_ext_smn_addressing(ext) + mca_base + (idx * 8), val)
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index d5083c54933015..48c6efcdeac974 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -381,6 +381,7 @@ soc21_asic_reset_method(struct amdgpu_device *adev)
 		return AMD_RESET_METHOD_MODE1;
 	case IP_VERSION(13, 0, 4):
 	case IP_VERSION(13, 0, 11):
+	case IP_VERSION(14, 0, 0):
 		return AMD_RESET_METHOD_MODE2;
 	default:
 		if (amdgpu_dpm_is_baco_supported(adev))
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
index 770b4b4e313838..e9c2ff74f0bc1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
@@ -88,7 +88,7 @@ static void umc_v12_0_reset_error_count(struct amdgpu_device *adev)
 		umc_v12_0_reset_error_count_per_channel, NULL);
 }
 
-static bool umc_v12_0_is_uncorrectable_error(uint64_t mc_umc_status)
+bool umc_v12_0_is_uncorrectable_error(uint64_t mc_umc_status)
 {
 	return ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
 		(REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 ||
@@ -96,7 +96,7 @@ static bool umc_v12_0_is_uncorrectable_error(uint64_t mc_umc_status)
 		REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, TCC) == 1));
 }
 
-static bool umc_v12_0_is_correctable_error(uint64_t mc_umc_status)
+bool umc_v12_0_is_correctable_error(uint64_t mc_umc_status)
 {
 	return (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
 		(REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1 ||
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.h b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.h
index 4885b9fff27217..b34b1e358f8b82 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.h
@@ -117,6 +117,9 @@
 		(pa) |= (UMC_V12_0_CHANNEL_HASH_CH6(channel_idx, pa) << UMC_V12_0_PA_CH6_BIT); \
 	} while (0)
 
+bool umc_v12_0_is_uncorrectable_error(uint64_t mc_umc_status);
+bool umc_v12_0_is_correctable_error(uint64_t mc_umc_status);
+
 extern const uint32_t
 	umc_v12_0_channel_idx_tbl[]
 			[UMC_V12_0_UMC_INSTANCE_NUM]
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c
index 58a8f78c003c7a..a6006f231c6559 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c
@@ -577,8 +577,6 @@ static int uvd_v3_1_sw_init(void *handle)
 	ptr += ucode_len;
 	memcpy(&adev->uvd.keyselect, ptr, 4);
 
-	r = amdgpu_uvd_entity_init(adev);
-
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index d3b1e31f545032..1aa09ad7bbe3e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -127,8 +127,6 @@ static int uvd_v4_2_sw_init(void *handle)
 	if (r)
 		return r;
 
-	r = amdgpu_uvd_entity_init(adev);
-
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index 5a8116437abf6f..f8b229b7543584 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -125,8 +125,6 @@ static int uvd_v5_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	r = amdgpu_uvd_entity_init(adev);
-
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 74c09230aeb32b..a9a6880f44e330 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -432,8 +432,6 @@ static int uvd_v6_0_sw_init(void *handle)
 		}
 	}
 
-	r = amdgpu_uvd_entity_init(adev);
-
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 1c42cf10cc2937..6068b784dc6938 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -480,10 +480,6 @@ static int uvd_v7_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	r = amdgpu_uvd_entity_init(adev);
-	if (r)
-		return r;
-
 	r = amdgpu_virt_alloc_mm_table(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index 67eb01fef789b9..a08e7abca423bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -441,8 +441,6 @@ static int vce_v2_0_sw_init(void *handle)
 			return r;
 	}
 
-	r = amdgpu_vce_entity_init(adev);
-
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 18f6e62af33984..f4760748d34998 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -450,8 +450,6 @@ static int vce_v3_0_sw_init(void *handle)
 			return r;
 	}
 
-	r = amdgpu_vce_entity_init(adev);
-
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
index e0b70cd3b697c5..06d787385ad460 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
@@ -486,11 +486,6 @@ static int vce_v4_0_sw_init(void *handle)
 			return r;
 	}
 
-
-	r = amdgpu_vce_entity_init(adev);
-	if (r)
-		return r;
-
 	r = amdgpu_virt_alloc_mm_table(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 9cc32f577e38ac..4c8e278a0d0cc4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1128,7 +1128,7 @@ static inline struct kfd_node *kfd_node_by_irq_ids(struct amdgpu_device *adev,
 	struct kfd_dev *dev = adev->kfd.dev;
 	uint32_t i;
 
-	if (adev->ip_versions[GC_HWIP][0] != IP_VERSION(9, 4, 3))
+	if (KFD_GC_VERSION(dev) != IP_VERSION(9, 4, 3))
 		return dev->nodes[0];
 
 	for (i = 0; i < dev->num_nodes; i++)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index fbf053001af978..7a33e06f5c9009 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1416,8 +1416,13 @@ bool kfd_process_xnack_mode(struct kfd_process *p, bool supported)
 		 * per-process XNACK mode selection. But let the dev->noretry
 		 * setting still influence the default XNACK mode.
 		 */
-		if (supported && KFD_SUPPORT_XNACK_PER_PROCESS(dev))
+		if (supported && KFD_SUPPORT_XNACK_PER_PROCESS(dev)) {
+			if (!amdgpu_sriov_xnack_support(dev->kfd->adev)) {
+				pr_debug("SRIOV platform xnack not supported\n");
+				return false;
+			}
 			continue;
+		}
 
 		/* GFXv10 and later GPUs do not support shader preemption
 		 * during page faults. This can lead to poor QoS for queue
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 77649392e23310..77f493262e0584 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -169,16 +169,43 @@ int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p)
 	return 0;
 }
 
+static void pqm_clean_queue_resource(struct process_queue_manager *pqm,
+				     struct process_queue_node *pqn)
+{
+	struct kfd_node *dev;
+	struct kfd_process_device *pdd;
+
+	dev = pqn->q->device;
+
+	pdd = kfd_get_process_device_data(dev, pqm->process);
+	if (!pdd) {
+		pr_err("Process device data doesn't exist\n");
+		return;
+	}
+
+	if (pqn->q->gws) {
+		if (KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) &&
+		    !dev->kfd->shared_resources.enable_mes)
+			amdgpu_amdkfd_remove_gws_from_process(
+				pqm->process->kgd_process_info, pqn->q->gws);
+		pdd->qpd.num_gws = 0;
+	}
+
+	if (dev->kfd->shared_resources.enable_mes) {
+		amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->gang_ctx_bo);
+		if (pqn->q->wptr_bo)
+			amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->wptr_bo);
+	}
+}
+
 void pqm_uninit(struct process_queue_manager *pqm)
 {
 	struct process_queue_node *pqn, *next;
 
 	list_for_each_entry_safe(pqn, next, &pqm->queues, process_queue_list) {
-		if (pqn->q && pqn->q->gws &&
-		    KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) &&
-		    !pqn->q->device->kfd->shared_resources.enable_mes)
-			amdgpu_amdkfd_remove_gws_from_process(pqm->process->kgd_process_info,
-				pqn->q->gws);
+		if (pqn->q)
+			pqm_clean_queue_resource(pqm, pqn);
+
 		kfd_procfs_del_queue(pqn->q);
 		uninit_queue(pqn->q);
 		list_del(&pqn->process_queue_list);
@@ -461,22 +488,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 				goto err_destroy_queue;
 		}
 
-		if (pqn->q->gws) {
-			if (KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) &&
-			    !dev->kfd->shared_resources.enable_mes)
-				amdgpu_amdkfd_remove_gws_from_process(
-						pqm->process->kgd_process_info,
-						pqn->q->gws);
-			pdd->qpd.num_gws = 0;
-		}
-
-		if (dev->kfd->shared_resources.enable_mes) {
-			amdgpu_amdkfd_free_gtt_mem(dev->adev,
-						   pqn->q->gang_ctx_bo);
-			if (pqn->q->wptr_bo)
-				amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->wptr_bo);
-
-		}
+		pqm_clean_queue_resource(pqm, pqn);
 		uninit_queue(pqn->q);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index e67d06a4280954..a15bfb5223e8fe 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1255,9 +1255,11 @@ svm_range_get_pte_flags(struct kfd_node *node,
 		}
 		break;
 	case IP_VERSION(9, 4, 3):
-		mtype_local = amdgpu_mtype_local == 1 ? AMDGPU_VM_MTYPE_NC :
-			      (amdgpu_mtype_local == 2 || ext_coherent ?
-					AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_RW);
+		if (ext_coherent)
+			mtype_local = node->adev->rev_id ? AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_UC;
+		else
+			mtype_local = amdgpu_mtype_local == 1 ? AMDGPU_VM_MTYPE_NC :
+				amdgpu_mtype_local == 2 ? AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_RW;
 		snoop = true;
 		if (uncached) {
 			mapping_flags |= AMDGPU_VM_MTYPE_UC;
@@ -1651,18 +1653,24 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
 			if (test_bit(gpuidx, prange->bitmap_access))
 				bitmap_set(ctx->bitmap, gpuidx, 1);
 		}
+
+		/*
+		 * If prange is already mapped or with always mapped flag,
+		 * update mapping on GPUs with ACCESS attribute
+		 */
+		if (bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) {
+			if (prange->mapped_to_gpu ||
+			    prange->flags & KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED)
+				bitmap_copy(ctx->bitmap, prange->bitmap_access, MAX_GPU_INSTANCE);
+		}
 	} else {
 		bitmap_or(ctx->bitmap, prange->bitmap_access,
 			  prange->bitmap_aip, MAX_GPU_INSTANCE);
 	}
 
 	if (bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) {
-		bitmap_copy(ctx->bitmap, prange->bitmap_access, MAX_GPU_INSTANCE);
-		if (!prange->mapped_to_gpu ||
-		    bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) {
-			r = 0;
-			goto free_ctx;
-		}
+		r = 0;
+		goto free_ctx;
 	}
 
 	if (prange->actual_loc && !prange->ttm_res) {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 6f99f6754c119e..c8c00c2a5224a7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2079,7 +2079,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev)
 	struct dmub_srv_create_params create_params;
 	struct dmub_srv_region_params region_params;
 	struct dmub_srv_region_info region_info;
-	struct dmub_srv_fb_params fb_params;
+	struct dmub_srv_memory_params memory_params;
 	struct dmub_srv_fb_info *fb_info;
 	struct dmub_srv *dmub_srv;
 	const struct dmcub_firmware_header_v1_0 *hdr;
@@ -2182,6 +2182,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev)
 		adev->dm.dmub_fw->data +
 		le32_to_cpu(hdr->header.ucode_array_offset_bytes) +
 		PSP_HEADER_BYTES;
+	region_params.is_mailbox_in_inbox = false;
 
 	status = dmub_srv_calc_region_info(dmub_srv, &region_params,
 					   &region_info);
@@ -2205,10 +2206,10 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev)
 		return r;
 
 	/* Rebase the regions on the framebuffer address. */
-	memset(&fb_params, 0, sizeof(fb_params));
-	fb_params.cpu_addr = adev->dm.dmub_bo_cpu_addr;
-	fb_params.gpu_addr = adev->dm.dmub_bo_gpu_addr;
-	fb_params.region_info = &region_info;
+	memset(&memory_params, 0, sizeof(memory_params));
+	memory_params.cpu_fb_addr = adev->dm.dmub_bo_cpu_addr;
+	memory_params.gpu_fb_addr = adev->dm.dmub_bo_gpu_addr;
+	memory_params.region_info = &region_info;
 
 	adev->dm.dmub_fb_info =
 		kzalloc(sizeof(*adev->dm.dmub_fb_info), GFP_KERNEL);
@@ -2220,7 +2221,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev)
 		return -ENOMEM;
 	}
 
-	status = dmub_srv_calc_fb_info(dmub_srv, &fb_params, fb_info);
+	status = dmub_srv_calc_mem_info(dmub_srv, &memory_params, fb_info);
 	if (status != DMUB_STATUS_OK) {
 		DRM_ERROR("Error calculating DMUB FB info: %d\n", status);
 		return -EINVAL;
@@ -5181,6 +5182,9 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
 	if (plane->type == DRM_PLANE_TYPE_CURSOR)
 		return;
 
+	if (new_plane_state->rotation != DRM_MODE_ROTATE_0)
+		goto ffu;
+
 	num_clips = drm_plane_get_damage_clips_count(new_plane_state);
 	clips = drm_plane_get_damage_clips(new_plane_state);
 
@@ -6266,7 +6270,7 @@ int amdgpu_dm_connector_atomic_set_property(struct drm_connector *connector,
 		dm_new_state->underscan_enable = val;
 		ret = 0;
 	} else if (property == adev->mode_info.abm_level_property) {
-		dm_new_state->abm_level = val;
+		dm_new_state->abm_level = val ?: ABM_LEVEL_IMMEDIATE_DISABLE;
 		ret = 0;
 	}
 
@@ -6311,7 +6315,8 @@ int amdgpu_dm_connector_atomic_get_property(struct drm_connector *connector,
 		*val = dm_state->underscan_enable;
 		ret = 0;
 	} else if (property == adev->mode_info.abm_level_property) {
-		*val = dm_state->abm_level;
+		*val = (dm_state->abm_level != ABM_LEVEL_IMMEDIATE_DISABLE) ?
+			dm_state->abm_level : 0;
 		ret = 0;
 	}
 
@@ -6384,7 +6389,8 @@ void amdgpu_dm_connector_funcs_reset(struct drm_connector *connector)
 		state->pbn = 0;
 
 		if (connector->connector_type == DRM_MODE_CONNECTOR_eDP)
-			state->abm_level = amdgpu_dm_abm_level;
+			state->abm_level = amdgpu_dm_abm_level ?:
+				ABM_LEVEL_IMMEDIATE_DISABLE;
 
 		__drm_atomic_helper_connector_reset(connector, &state->base);
 	}
@@ -7481,6 +7487,9 @@ static int amdgpu_dm_i2c_xfer(struct i2c_adapter *i2c_adap,
 	int i;
 	int result = -EIO;
 
+	if (!ddc_service->ddc_pin || !ddc_service->ddc_pin->hw_info.hw_supported)
+		return result;
+
 	cmd.payloads = kcalloc(num, sizeof(struct i2c_payload), GFP_KERNEL);
 
 	if (!cmd.payloads)
@@ -9603,14 +9612,14 @@ static bool should_reset_plane(struct drm_atomic_state *state,
 	struct drm_plane *other;
 	struct drm_plane_state *old_other_state, *new_other_state;
 	struct drm_crtc_state *new_crtc_state;
+	struct amdgpu_device *adev = drm_to_adev(plane->dev);
 	int i;
 
 	/*
-	 * TODO: Remove this hack once the checks below are sufficient
-	 * enough to determine when we need to reset all the planes on
-	 * the stream.
+	 * TODO: Remove this hack for all asics once it proves that the
+	 * fast updates works fine on DCN3.2+.
 	 */
-	if (state->allow_modeset)
+	if (adev->ip_versions[DCE_HWIP][0] < IP_VERSION(3, 2, 0) && state->allow_modeset)
 		return true;
 
 	/* Exit early if we know that we're adding or removing the plane. */
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 9cd83b78010278..aac98f93545a22 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -63,6 +63,12 @@ static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps)
 		DRM_DEBUG_DRIVER("Disabling FAMS on monitor with panel id %X\n", panel_id);
 		edid_caps->panel_patch.disable_fams = true;
 		break;
+	/* Workaround for some monitors that do not clear DPCD 0x317 if FreeSync is unsupported */
+	case drm_edid_encode_panel_id('A', 'U', 'O', 0xA7AB):
+	case drm_edid_encode_panel_id('A', 'U', 'O', 0xE69B):
+		DRM_DEBUG_DRIVER("Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id);
+		edid_caps->panel_patch.remove_sink_ext_caps = true;
+		break;
 	default:
 		return;
 	}
@@ -536,11 +542,8 @@ bool dm_helpers_dp_read_dpcd(
 
 	struct amdgpu_dm_connector *aconnector = link->priv;
 
-	if (!aconnector) {
-		drm_dbg_dp(aconnector->base.dev,
-			   "Failed to find connector for link!\n");
+	if (!aconnector)
 		return false;
-	}
 
 	return drm_dp_dpcd_read(&aconnector->dm_dp_aux.aux, address, data,
 				size) == size;
@@ -1216,6 +1219,9 @@ bool dm_helpers_dp_handle_test_pattern_request(
 
 	}
 
+	pipe_ctx->stream->test_pattern.type = test_pattern;
+	pipe_ctx->stream->test_pattern.color_space = test_pattern_color_space;
+
 	dc_link_dp_set_test_pattern(
 		(struct dc_link *) link,
 		test_pattern,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index d3b13d362edacc..11da0eebee6c4b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -1604,31 +1604,31 @@ enum dc_status dm_dp_mst_is_port_support_mode(
 	unsigned int upper_link_bw_in_kbps = 0, down_link_bw_in_kbps = 0;
 	unsigned int max_compressed_bw_in_kbps = 0;
 	struct dc_dsc_bw_range bw_range = {0};
-	struct drm_dp_mst_topology_mgr *mst_mgr;
+	uint16_t full_pbn = aconnector->mst_output_port->full_pbn;
 
 	/*
-	 * check if the mode could be supported if DSC pass-through is supported
-	 * AND check if there enough bandwidth available to support the mode
-	 * with DSC enabled.
+	 * Consider the case with the depth of the mst topology tree is equal or less than 2
+	 * A. When dsc bitstream can be transmitted along the entire path
+	 *    1. dsc is possible between source and branch/leaf device (common dsc params is possible), AND
+	 *    2. dsc passthrough supported at MST branch, or
+	 *    3. dsc decoding supported at leaf MST device
+	 *    Use maximum dsc compression as bw constraint
+	 * B. When dsc bitstream cannot be transmitted along the entire path
+	 *    Use native bw as bw constraint
 	 */
 	if (is_dsc_common_config_possible(stream, &bw_range) &&
-	    aconnector->mst_output_port->passthrough_aux) {
-		mst_mgr = aconnector->mst_output_port->mgr;
-		mutex_lock(&mst_mgr->lock);
-
+	   (aconnector->mst_output_port->passthrough_aux ||
+	    aconnector->dsc_aux == &aconnector->mst_output_port->aux)) {
 		cur_link_settings = stream->link->verified_link_cap;
 
 		upper_link_bw_in_kbps = dc_link_bandwidth_kbps(aconnector->dc_link,
-							       &cur_link_settings
-							       );
-		down_link_bw_in_kbps = kbps_from_pbn(aconnector->mst_output_port->full_pbn);
+							       &cur_link_settings);
+		down_link_bw_in_kbps = kbps_from_pbn(full_pbn);
 
 		/* pick the bottleneck */
 		end_to_end_bw_in_kbps = min(upper_link_bw_in_kbps,
 					    down_link_bw_in_kbps);
 
-		mutex_unlock(&mst_mgr->lock);
-
 		/*
 		 * use the maximum dsc compression bandwidth as the required
 		 * bandwidth for the mode
@@ -1643,8 +1643,7 @@ enum dc_status dm_dp_mst_is_port_support_mode(
 		/* check if mode could be supported within full_pbn */
 		bpp = convert_dc_color_depth_into_bpc(stream->timing.display_color_depth) * 3;
 		pbn = drm_dp_calc_pbn_mode(stream->timing.pix_clk_100hz / 10, bpp, false);
-
-		if (pbn > aconnector->mst_output_port->full_pbn)
+		if (pbn > full_pbn)
 			return DC_FAIL_BANDWIDTH_VALIDATE;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h
index 0f580ea37576dc..133af994a08c17 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h
@@ -37,7 +37,7 @@
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_encoder.h>
 #include <drm/drm_atomic.h>
-#include "dcn10/dcn10_optc.h"
+#include "dc/inc/hw/optc.h"
 
 #include "dc/inc/core_types.h"
 
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 7cdb1a8a0ba06b..2d1f5efa9091a4 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -1014,13 +1014,20 @@ static enum bp_result get_ss_info_v4_5(
 		DC_LOG_BIOS("AS_SIGNAL_TYPE_HDMI ss_percentage: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	case AS_SIGNAL_TYPE_DISPLAY_PORT:
-		ss_info->spread_spectrum_percentage =
+		if (bp->base.integrated_info) {
+			DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", bp->base.integrated_info->gpuclk_ss_percentage);
+			ss_info->spread_spectrum_percentage =
+					bp->base.integrated_info->gpuclk_ss_percentage;
+			ss_info->type.CENTER_MODE =
+					bp->base.integrated_info->gpuclk_ss_type;
+		} else {
+			ss_info->spread_spectrum_percentage =
 				disp_cntl_tbl->dp_ss_percentage;
-		ss_info->spread_spectrum_range =
+			ss_info->spread_spectrum_range =
 				disp_cntl_tbl->dp_ss_rate_10hz * 10;
-		if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
-			ss_info->type.CENTER_MODE = true;
-
+			if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
+				ss_info->type.CENTER_MODE = true;
+		}
 		DC_LOG_BIOS("AS_SIGNAL_TYPE_DISPLAY_PORT ss_percentage: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	case AS_SIGNAL_TYPE_GPU_PLL:
@@ -2814,6 +2821,8 @@ static enum bp_result get_integrated_info_v2_2(
 	info->ma_channel_number = info_v2_2->umachannelnumber;
 	info->dp_ss_control =
 		le16_to_cpu(info_v2_2->reserved1);
+	info->gpuclk_ss_percentage = info_v2_2->gpuclk_ss_percentage;
+	info->gpuclk_ss_type = info_v2_2->gpuclk_ss_type;
 
 	for (i = 0; i < NUMBER_OF_UCHAR_FOR_GUID; ++i) {
 		info->ext_disp_conn_info.gu_id[i] =
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
index b2c4f97afc8b4c..8776055bbeaaea 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
@@ -334,7 +334,7 @@ static struct wm_table lpddr5_wm_table = {
 		{
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 11.65333,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
@@ -342,7 +342,7 @@ static struct wm_table lpddr5_wm_table = {
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 11.65333,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
@@ -350,7 +350,7 @@ static struct wm_table lpddr5_wm_table = {
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 11.65333,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
@@ -358,7 +358,7 @@ static struct wm_table lpddr5_wm_table = {
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 11.65333,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index f80917f6153b36..d5fde7d23fbf8e 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -111,17 +111,21 @@ static int dcn35_get_active_display_cnt_wa(
 	return display_count;
 }
 
-static void dcn35_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable)
+static void dcn35_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context,
+		bool safe_to_lower, bool disable)
 {
 	struct dc *dc = clk_mgr_base->ctx->dc;
 	int i;
 
 	for (i = 0; i < dc->res_pool->pipe_count; ++i) {
-		struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe = safe_to_lower
+			? &context->res_ctx.pipe_ctx[i]
+			: &dc->current_state->res_ctx.pipe_ctx[i];
 
 		if (pipe->top_pipe || pipe->prev_odm_pipe)
 			continue;
-		if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) {
+		if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal) ||
+				     !pipe->stream->link_enc)) {
 			struct stream_encoder *stream_enc = pipe->stream_res.stream_enc;
 
 			if (disable) {
@@ -228,6 +232,10 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base,
 	if (dc->work_arounds.skip_clock_update)
 		return;
 
+	/* DTBCLK is fixed, so set a default if unspecified. */
+	if (new_clocks->dtbclk_en && !new_clocks->ref_dtbclk_khz)
+		new_clocks->ref_dtbclk_khz = 600000;
+
 	/*
 	 * if it is safe to lower, but we are already in the lower state, we don't have to do anything
 	 * also if safe to lower is false, we just go in the higher state
@@ -261,8 +269,10 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base,
 
 		if (!clk_mgr_base->clks.dtbclk_en && new_clocks->dtbclk_en) {
 			dcn35_smu_set_dtbclk(clk_mgr, true);
-			dcn35_update_clocks_update_dtb_dto(clk_mgr, context, clk_mgr_base->clks.ref_dtbclk_khz);
 			clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en;
+
+			dcn35_update_clocks_update_dtb_dto(clk_mgr, context, new_clocks->ref_dtbclk_khz);
+			clk_mgr_base->clks.ref_dtbclk_khz = new_clocks->ref_dtbclk_khz;
 		}
 
 		/* check that we're not already in D0 */
@@ -301,26 +311,21 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base,
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
-		dcn35_disable_otg_wa(clk_mgr_base, context, true);
+		dcn35_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true);
 
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
 		dcn35_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
-		dcn35_disable_otg_wa(clk_mgr_base, context, false);
+		dcn35_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false);
 
 		update_dispclk = true;
 	}
 
-	if (!new_clocks->dtbclk_en) {
-		new_clocks->ref_dtbclk_khz = 600000;
-	}
-
 	/* clock limits are received with MHz precision, divide by 1000 to prevent setting clocks at every call */
 	if (!dc->debug.disable_dtb_ref_clk_switch &&
-			should_set_clock(safe_to_lower, new_clocks->ref_dtbclk_khz / 1000, clk_mgr_base->clks.ref_dtbclk_khz / 1000)) {
-		/* DCCG requires KHz precision for DTBCLK */
-		dcn35_smu_set_dtbclk(clk_mgr, true);
-
-		dcn35_update_clocks_update_dtb_dto(clk_mgr, context, clk_mgr_base->clks.ref_dtbclk_khz);
+	    should_set_clock(safe_to_lower, new_clocks->ref_dtbclk_khz / 1000,
+			     clk_mgr_base->clks.ref_dtbclk_khz / 1000)) {
+		dcn35_update_clocks_update_dtb_dto(clk_mgr, context, new_clocks->ref_dtbclk_khz);
+		clk_mgr_base->clks.ref_dtbclk_khz = new_clocks->ref_dtbclk_khz;
 	}
 
 	if (dpp_clock_lowered) {
@@ -439,32 +444,32 @@ static struct wm_table ddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 	}
@@ -476,32 +481,32 @@ static struct wm_table lpddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 	}
@@ -511,11 +516,6 @@ static DpmClocks_t_dcn35 dummy_clocks;
 
 static struct dcn35_watermarks dummy_wms = { 0 };
 
-static struct dcn35_ss_info_table ss_info_table = {
-	.ss_divider = 1000,
-	.ss_percentage = {0, 0, 375, 375, 375}
-};
-
 static void dcn35_build_watermark_ranges(struct clk_bw_params *bw_params, struct dcn35_watermarks *table)
 {
 	int i, num_valid_sets;
@@ -649,27 +649,47 @@ static unsigned int convert_wck_ratio(uint8_t wck_ratio)
 	return 1;
 }
 
+static inline uint32_t calc_dram_speed_mts(const MemPstateTable_t *entry)
+{
+	return entry->UClk * convert_wck_ratio(entry->WckRatio) * 2;
+}
+
 static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk_mgr,
 						    struct integrated_info *bios_info,
 						    DpmClocks_t_dcn35 *clock_table)
 {
 	struct clk_bw_params *bw_params = clk_mgr->base.bw_params;
 	struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1];
-	uint32_t max_pstate = 0,  max_uclk = 0, max_fclk = 0;
-	uint32_t min_pstate = 0, max_dispclk = 0, max_dppclk = 0;
+	uint32_t max_fclk = 0, min_pstate = 0, max_dispclk = 0, max_dppclk = 0;
+	uint32_t max_pstate = 0, max_dram_speed_mts = 0, min_dram_speed_mts = 0;
 	int i;
 
+	/* Determine min/max p-state values. */
 	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
-		if (is_valid_clock_value(clock_table->MemPstateTable[i].UClk) &&
-		    clock_table->MemPstateTable[i].UClk > max_uclk) {
-			max_uclk = clock_table->MemPstateTable[i].UClk;
+		uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
+
+		if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts > max_dram_speed_mts) {
+			max_dram_speed_mts = dram_speed_mts;
 			max_pstate = i;
 		}
 	}
 
-	/* We expect the table to contain at least one valid Uclk entry. */
-	ASSERT(is_valid_clock_value(max_uclk));
+	min_dram_speed_mts = max_dram_speed_mts;
+	min_pstate = max_pstate;
+
+	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
+		uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
+
+		if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts < min_dram_speed_mts) {
+			min_dram_speed_mts = dram_speed_mts;
+			min_pstate = i;
+		}
+	}
 
+	/* We expect the table to contain at least one valid P-state entry. */
+	ASSERT(clock_table->NumMemPstatesEnabled &&
+	       is_valid_clock_value(max_dram_speed_mts) &&
+	       is_valid_clock_value(min_dram_speed_mts));
 
 	/* dispclk and dppclk can be max at any voltage, same number of levels for both */
 	if (clock_table->NumDispClkLevelsEnabled <= NUM_DISPCLK_DPM_LEVELS &&
@@ -679,47 +699,46 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 		max_dppclk = find_max_clk_value(clock_table->DppClocks,
 			clock_table->NumDispClkLevelsEnabled);
 	} else {
+		/* Invalid number of entries in the table from PMFW. */
 		ASSERT(0);
 	}
-	if (clock_table->NumFclkLevelsEnabled <= NUM_FCLK_DPM_LEVELS)
-		max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq,
-			clock_table->NumFclkLevelsEnabled);
 
-	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
-		uint32_t min_uclk = clock_table->MemPstateTable[0].UClk;
-		int j;
+	/* Base the clock table on dcfclk, need at least one entry regardless of pmfw table */
+	ASSERT(clock_table->NumDcfClkLevelsEnabled > 0);
 
-		for (j = 1; j < clock_table->NumMemPstatesEnabled; j++) {
-			if (is_valid_clock_value(clock_table->MemPstateTable[j].UClk) &&
-			    clock_table->MemPstateTable[j].UClk < min_uclk &&
-			    clock_table->MemPstateTable[j].Voltage <= clock_table->SocVoltage[i]) {
-				min_uclk = clock_table->MemPstateTable[j].UClk;
-				min_pstate = j;
-			}
-		}
+	max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, clock_table->NumFclkLevelsEnabled);
+
+	for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) {
+		int j;
 
+		/* First search defaults for the clocks we don't read using closest lower or equal default dcfclk */
 		for (j = bw_params->clk_table.num_entries - 1; j > 0; j--)
 			if (bw_params->clk_table.entries[j].dcfclk_mhz <= clock_table->DcfClocks[i])
-			break;
+				break;
 
 		bw_params->clk_table.entries[i].phyclk_mhz = bw_params->clk_table.entries[j].phyclk_mhz;
 		bw_params->clk_table.entries[i].phyclk_d18_mhz = bw_params->clk_table.entries[j].phyclk_d18_mhz;
 		bw_params->clk_table.entries[i].dtbclk_mhz = bw_params->clk_table.entries[j].dtbclk_mhz;
-		bw_params->clk_table.entries[i].fclk_mhz = max_fclk;
+
+		/* Now update clocks we do read */
 		bw_params->clk_table.entries[i].memclk_mhz = clock_table->MemPstateTable[min_pstate].MemClk;
 		bw_params->clk_table.entries[i].voltage = clock_table->MemPstateTable[min_pstate].Voltage;
 		bw_params->clk_table.entries[i].dcfclk_mhz = clock_table->DcfClocks[i];
 		bw_params->clk_table.entries[i].socclk_mhz = clock_table->SocClocks[i];
 		bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk;
 		bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk;
-		bw_params->clk_table.entries[i].wck_ratio = convert_wck_ratio(
-			clock_table->MemPstateTable[min_pstate].WckRatio);
-		}
+		bw_params->clk_table.entries[i].wck_ratio =
+			convert_wck_ratio(clock_table->MemPstateTable[min_pstate].WckRatio);
+
+		/* Dcfclk and Fclk are tied, but at a different ratio */
+		bw_params->clk_table.entries[i].fclk_mhz = min(max_fclk, 2 * clock_table->DcfClocks[i]);
+	}
 
 	/* Make sure to include at least one entry at highest pstate */
 	if (max_pstate != min_pstate || i == 0) {
 		if (i > MAX_NUM_DPM_LVL - 1)
 			i = MAX_NUM_DPM_LVL - 1;
+
 		bw_params->clk_table.entries[i].fclk_mhz = max_fclk;
 		bw_params->clk_table.entries[i].memclk_mhz = clock_table->MemPstateTable[max_pstate].MemClk;
 		bw_params->clk_table.entries[i].voltage = clock_table->MemPstateTable[max_pstate].Voltage;
@@ -735,6 +754,7 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	}
 	bw_params->clk_table.num_entries = i--;
 
+	/* Make sure all highest clocks are included*/
 	bw_params->clk_table.entries[i].socclk_mhz =
 		find_max_clk_value(clock_table->SocClocks, NUM_SOCCLK_DPM_LEVELS);
 	bw_params->clk_table.entries[i].dispclk_mhz =
@@ -753,6 +773,11 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	bw_params->clk_table.num_entries_per_clk.num_fclk_levels = clock_table->NumFclkLevelsEnabled;
 	bw_params->clk_table.num_entries_per_clk.num_memclk_levels = clock_table->NumMemPstatesEnabled;
 	bw_params->clk_table.num_entries_per_clk.num_socclk_levels = clock_table->NumSocClkLevelsEnabled;
+
+	/*
+	 * Set any 0 clocks to max default setting. Not an issue for
+	 * power since we aren't doing switching in such case anyway
+	 */
 	for (i = 0; i < bw_params->clk_table.num_entries; i++) {
 		if (!bw_params->clk_table.entries[i].fclk_mhz) {
 			bw_params->clk_table.entries[i].fclk_mhz = def_max.fclk_mhz;
@@ -814,23 +839,24 @@ static void dcn35_set_idle_state(struct clk_mgr *clk_mgr_base, bool allow_idle)
 	struct dc *dc = clk_mgr_base->ctx->dc;
 	uint32_t val = dcn35_smu_read_ips_scratch(clk_mgr);
 
-	if (dc->config.disable_ips == 0) {
-		val |= DMUB_IPS1_ALLOW_MASK;
-		val |= DMUB_IPS2_ALLOW_MASK;
-	} else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS1) {
+	if (dc->config.disable_ips == DMUB_IPS_ENABLE ||
+		dc->config.disable_ips == DMUB_IPS_DISABLE_DYNAMIC) {
 		val = val & ~DMUB_IPS1_ALLOW_MASK;
 		val = val & ~DMUB_IPS2_ALLOW_MASK;
-	} else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS2) {
-		val |= DMUB_IPS1_ALLOW_MASK;
-		val = val & ~DMUB_IPS2_ALLOW_MASK;
-	} else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS2_Z10) {
+	} else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS1) {
 		val |= DMUB_IPS1_ALLOW_MASK;
 		val |= DMUB_IPS2_ALLOW_MASK;
+	} else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS2) {
+		val = val & ~DMUB_IPS1_ALLOW_MASK;
+		val |= DMUB_IPS2_ALLOW_MASK;
+	} else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS2_Z10) {
+		val = val & ~DMUB_IPS1_ALLOW_MASK;
+		val = val & ~DMUB_IPS2_ALLOW_MASK;
 	}
 
 	if (!allow_idle) {
-		val = val & ~DMUB_IPS1_ALLOW_MASK;
-		val = val & ~DMUB_IPS2_ALLOW_MASK;
+		val |= DMUB_IPS1_ALLOW_MASK;
+		val |= DMUB_IPS2_ALLOW_MASK;
 	}
 
 	dcn35_smu_write_ips_scratch(clk_mgr, val);
@@ -960,21 +986,6 @@ struct clk_mgr_funcs dcn35_fpga_funcs = {
 	.get_dtb_ref_clk_frequency = dcn31_get_dtb_ref_freq_khz,
 };
 
-static void dcn35_read_ss_info_from_lut(struct clk_mgr_internal *clk_mgr)
-{
-	uint32_t clock_source;
-	struct dc_context *ctx = clk_mgr->base.ctx;
-
-	REG_GET(CLK1_CLK2_BYPASS_CNTL, CLK2_BYPASS_SEL, &clock_source);
-
-	clk_mgr->dprefclk_ss_percentage = ss_info_table.ss_percentage[clock_source];
-
-	if (clk_mgr->dprefclk_ss_percentage != 0) {
-		clk_mgr->ss_on_dprefclk = true;
-		clk_mgr->dprefclk_ss_divider = ss_info_table.ss_divider;
-	}
-}
-
 void dcn35_clk_mgr_construct(
 		struct dc_context *ctx,
 		struct clk_mgr_dcn35 *clk_mgr,
@@ -1038,17 +1049,11 @@ void dcn35_clk_mgr_construct(
 	dcn35_dump_clk_registers(&clk_mgr->base.base.boot_snapshot, &clk_mgr->base.base, &log_info);
 
 	clk_mgr->base.base.dprefclk_khz = dcn35_smu_get_dprefclk(&clk_mgr->base);
-	clk_mgr->base.base.clks.ref_dtbclk_khz = dcn35_smu_get_dtbclk(&clk_mgr->base);
-
-	if (!clk_mgr->base.base.clks.ref_dtbclk_khz)
-		dcn35_smu_set_dtbclk(&clk_mgr->base, true);
+	clk_mgr->base.base.clks.ref_dtbclk_khz = 600000;
 
-	clk_mgr->base.base.clks.dtbclk_en = true;
 	dce_clock_read_ss_info(&clk_mgr->base);
 	/*when clk src is from FCH, it could have ss, same clock src as DPREF clk*/
 
-	dcn35_read_ss_info_from_lut(&clk_mgr->base);
-
 	clk_mgr->base.base.bw_params = &dcn35_bw_params;
 
 	if (clk_mgr->base.base.ctx->dc->debug.pstate_enabled) {
@@ -1114,7 +1119,7 @@ void dcn35_clk_mgr_construct(
 		dm_helpers_free_gpu_mem(clk_mgr->base.base.ctx, DC_MEM_ALLOC_TYPE_FRAME_BUFFER,
 				smu_dpm_clks.dpm_clks);
 
-	if (ctx->dc->config.disable_ips == 0) {
+	if (ctx->dc->config.disable_ips != DMUB_IPS_DISABLE_ALL) {
 		bool ips_support = false;
 
 		/*avoid call pmfw at init*/
@@ -1124,10 +1129,9 @@ void dcn35_clk_mgr_construct(
 			ctx->dc->debug.disable_dpp_power_gate = false;
 			ctx->dc->debug.disable_hubp_power_gate = false;
 			ctx->dc->debug.disable_dsc_power_gate = false;
-			ctx->dc->debug.disable_hpo_power_gate = false;
 		} else {
 			/*let's reset the config control flag*/
-			ctx->dc->config.disable_ips = 1; /*pmfw not support it, disable it all*/
+			ctx->dc->config.disable_ips = DMUB_IPS_DISABLE_ALL; /*pmfw not support it, disable it all*/
 		}
 	}
 }
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 4360a696f10a3e..5c118520664595 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -2582,6 +2582,9 @@ static enum surface_update_type det_surface_update(const struct dc *dc,
 	if (u->gamut_remap_matrix)
 		update_flags->bits.gamut_remap_change = 1;
 
+	if (u->blend_tf)
+		update_flags->bits.gamma_change = 1;
+
 	if (u->gamma) {
 		enum surface_pixel_format format = SURFACE_PIXEL_FORMAT_GRPH_BEGIN;
 
@@ -3175,7 +3178,7 @@ static bool update_planes_and_stream_state(struct dc *dc,
 			struct pipe_ctx *otg_master = resource_get_otg_master_for_stream(&context->res_ctx,
 					context->streams[i]);
 
-			if (otg_master->stream->test_pattern.type != DP_TEST_PATTERN_VIDEO_MODE)
+			if (otg_master && otg_master->stream->test_pattern.type != DP_TEST_PATTERN_VIDEO_MODE)
 				resource_build_test_pattern_params(&context->res_ctx, otg_master);
 		}
 	}
@@ -4113,8 +4116,17 @@ static bool commit_minimal_transition_state_for_windowed_mpo_odm(struct dc *dc,
 	bool success = false;
 	struct dc_state *minimal_transition_context;
 	struct pipe_split_policy_backup policy;
+	struct mall_temp_config mall_temp_config;
 
 	/* commit based on new context */
+	/* Since all phantom pipes are removed in full validation,
+	 * we have to save and restore the subvp/mall config when
+	 * we do a minimal transition since the flags marking the
+	 * pipe as subvp/phantom will be cleared (dc copy constructor
+	 * creates a shallow copy).
+	 */
+	if (dc->res_pool->funcs->save_mall_state)
+		dc->res_pool->funcs->save_mall_state(dc, context, &mall_temp_config);
 	minimal_transition_context = create_minimal_transition_state(dc,
 			context, &policy);
 	if (minimal_transition_context) {
@@ -4123,9 +4135,20 @@ static bool commit_minimal_transition_state_for_windowed_mpo_odm(struct dc *dc,
 			dc->hwss.is_pipe_topology_transition_seamless(
 					dc, minimal_transition_context, context)) {
 			DC_LOG_DC("%s base = new state\n", __func__);
+
 			success = dc_commit_state_no_check(dc, minimal_transition_context) == DC_OK;
 		}
 		release_minimal_transition_state(dc, minimal_transition_context, &policy);
+		if (dc->res_pool->funcs->restore_mall_state)
+			dc->res_pool->funcs->restore_mall_state(dc, context, &mall_temp_config);
+		/* If we do a minimal transition with plane removal and the context
+		 * has subvp we also have to retain back the phantom stream / planes
+		 * since the refcount is decremented as part of the min transition
+		 * (we commit a state with no subvp, so the phantom streams / planes
+		 * had to be removed).
+		 */
+		if (dc->res_pool->funcs->retain_phantom_pipes)
+			dc->res_pool->funcs->retain_phantom_pipes(dc, context);
 	}
 
 	if (!success) {
@@ -4884,7 +4907,7 @@ void dc_allow_idle_optimizations(struct dc *dc, bool allow)
 	if (dc->debug.disable_idle_power_optimizations)
 		return;
 
-	if (dc->caps.ips_support && dc->config.disable_ips)
+	if (dc->caps.ips_support && (dc->config.disable_ips == DMUB_IPS_DISABLE_ALL))
 		return;
 
 	if (dc->clk_mgr != NULL && dc->clk_mgr->funcs->is_smu_present)
@@ -4905,14 +4928,14 @@ bool dc_dmub_is_ips_idle_state(struct dc *dc)
 	if (dc->debug.disable_idle_power_optimizations)
 		return false;
 
-	if (!dc->caps.ips_support || dc->config.disable_ips)
+	if (!dc->caps.ips_support || (dc->config.disable_ips == DMUB_IPS_DISABLE_ALL))
 		return false;
 
 	if (dc->hwss.get_idle_state)
 		idle_state = dc->hwss.get_idle_state(dc);
 
-	if ((idle_state & DMUB_IPS1_ALLOW_MASK) ||
-		(idle_state & DMUB_IPS2_ALLOW_MASK))
+	if (!(idle_state & DMUB_IPS1_ALLOW_MASK) ||
+		!(idle_state & DMUB_IPS2_ALLOW_MASK))
 		return true;
 
 	return false;
@@ -5072,18 +5095,28 @@ void dc_mclk_switch_using_fw_based_vblank_stretch_shut_down(struct dc *dc)
  */
 bool dc_is_dmub_outbox_supported(struct dc *dc)
 {
-	/* DCN31 B0 USB4 DPIA needs dmub notifications for interrupts */
-	if (dc->ctx->asic_id.chip_family == FAMILY_YELLOW_CARP &&
-	    dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0 &&
-	    !dc->debug.dpia_debug.bits.disable_dpia)
-		return true;
+	switch (dc->ctx->asic_id.chip_family) {
 
-	if (dc->ctx->asic_id.chip_family == AMDGPU_FAMILY_GC_11_0_1 &&
-	    !dc->debug.dpia_debug.bits.disable_dpia)
-		return true;
+	case FAMILY_YELLOW_CARP:
+		/* DCN31 B0 USB4 DPIA needs dmub notifications for interrupts */
+		if (dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0 &&
+		    !dc->debug.dpia_debug.bits.disable_dpia)
+			return true;
+	break;
+
+	case AMDGPU_FAMILY_GC_11_0_1:
+	case AMDGPU_FAMILY_GC_11_5_0:
+		if (!dc->debug.dpia_debug.bits.disable_dpia)
+			return true;
+	break;
+
+	default:
+		break;
+	}
 
 	/* dmub aux needs dmub notifications to be enabled */
 	return dc->debug.enable_dmub_aux_for_legacy_ddc;
+
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 1d48278cba96c5..a1f1d100399275 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -5190,6 +5190,9 @@ bool dc_resource_acquire_secondary_pipe_for_mpc_odm_legacy(
 	sec_next = sec_pipe->next_odm_pipe;
 	sec_prev = sec_pipe->prev_odm_pipe;
 
+	if (pri_pipe == NULL)
+		return false;
+
 	*sec_pipe = *pri_pipe;
 
 	sec_pipe->top_pipe = sec_top;
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 6e54ca055fcb70..2cafd644baff83 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -49,7 +49,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.256"
+#define DC_VER "3.2.259"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -874,6 +874,7 @@ struct dc_debug_options {
 	unsigned int seamless_boot_odm_combine;
 	unsigned int force_odm_combine_4to1; //bit vector based on otg inst
 	int minimum_z8_residency_time;
+	int minimum_z10_residency_time;
 	bool disable_z9_mpc;
 	unsigned int force_fclk_khz;
 	bool enable_tri_buf;
@@ -1608,7 +1609,6 @@ struct dc_link {
 	enum edp_revision edp_revision;
 	union dpcd_sink_ext_caps dpcd_sink_ext_caps;
 
-	struct backlight_settings backlight_settings;
 	struct psr_settings psr_settings;
 
 	struct replay_settings replay_settings;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index ba142bef626bf5..0e07699c1e8352 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -120,6 +120,80 @@ void dc_dmub_srv_send_inbox0_cmd(struct dc_dmub_srv *dc_dmub_srv,
 	}
 }
 
+bool dc_dmub_srv_cmd_list_queue_execute(struct dc_dmub_srv *dc_dmub_srv,
+		unsigned int count,
+		union dmub_rb_cmd *cmd_list)
+{
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	struct dmub_srv *dmub;
+	enum dmub_status status;
+	int i;
+
+	if (!dc_dmub_srv || !dc_dmub_srv->dmub)
+		return false;
+
+	dmub = dc_dmub_srv->dmub;
+
+	for (i = 0 ; i < count; i++) {
+		// Queue command
+		status = dmub_srv_cmd_queue(dmub, &cmd_list[i]);
+
+		if (status == DMUB_STATUS_QUEUE_FULL) {
+			/* Execute and wait for queue to become empty again. */
+			dmub_srv_cmd_execute(dmub);
+			dmub_srv_wait_for_idle(dmub, 100000);
+
+			/* Requeue the command. */
+			status = dmub_srv_cmd_queue(dmub, &cmd_list[i]);
+		}
+
+		if (status != DMUB_STATUS_OK) {
+			DC_ERROR("Error queueing DMUB command: status=%d\n", status);
+			dc_dmub_srv_log_diagnostic_data(dc_dmub_srv);
+			return false;
+		}
+	}
+
+	status = dmub_srv_cmd_execute(dmub);
+	if (status != DMUB_STATUS_OK) {
+		DC_ERROR("Error starting DMUB execution: status=%d\n", status);
+		dc_dmub_srv_log_diagnostic_data(dc_dmub_srv);
+		return false;
+	}
+
+	return true;
+}
+
+bool dc_dmub_srv_wait_for_idle(struct dc_dmub_srv *dc_dmub_srv,
+		enum dm_dmub_wait_type wait_type,
+		union dmub_rb_cmd *cmd_list)
+{
+	struct dmub_srv *dmub;
+	enum dmub_status status;
+
+	if (!dc_dmub_srv || !dc_dmub_srv->dmub)
+		return false;
+
+	dmub = dc_dmub_srv->dmub;
+
+	// Wait for DMUB to process command
+	if (wait_type != DM_DMUB_WAIT_TYPE_NO_WAIT) {
+		status = dmub_srv_wait_for_idle(dmub, 100000);
+
+		if (status != DMUB_STATUS_OK) {
+			DC_LOG_DEBUG("No reply for DMUB command: status=%d\n", status);
+			dc_dmub_srv_log_diagnostic_data(dc_dmub_srv);
+			return false;
+		}
+
+		// Copy data back from ring buffer into command
+		if (wait_type == DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY)
+			dmub_rb_get_return_data(&dmub->inbox1_rb, cmd_list);
+	}
+
+	return true;
+}
+
 bool dc_dmub_srv_cmd_run(struct dc_dmub_srv *dc_dmub_srv, union dmub_rb_cmd *cmd, enum dm_dmub_wait_type wait_type)
 {
 	return dc_dmub_srv_cmd_run_list(dc_dmub_srv, 1, cmd, wait_type);
@@ -1128,11 +1202,11 @@ void dc_dmub_srv_exit_low_power_state(const struct dc *dc)
 		allow_state = dc->hwss.get_idle_state(dc);
 		dc->hwss.set_idle_state(dc, false);
 
-		if (allow_state & DMUB_IPS2_ALLOW_MASK) {
+		if (!(allow_state & DMUB_IPS2_ALLOW_MASK)) {
 			// Wait for evaluation time
 			udelay(dc->debug.ips2_eval_delay_us);
 			commit_state = dc->hwss.get_idle_state(dc);
-			if (commit_state & DMUB_IPS2_COMMIT_MASK) {
+			if (!(commit_state & DMUB_IPS2_COMMIT_MASK)) {
 				// Tell PMFW to exit low power state
 				dc->clk_mgr->funcs->exit_low_power_state(dc->clk_mgr);
 
@@ -1142,7 +1216,7 @@ void dc_dmub_srv_exit_low_power_state(const struct dc *dc)
 
 				for (i = 0; i < max_num_polls; ++i) {
 					commit_state = dc->hwss.get_idle_state(dc);
-					if (!(commit_state & DMUB_IPS2_COMMIT_MASK))
+					if (commit_state & DMUB_IPS2_COMMIT_MASK)
 						break;
 
 					udelay(1);
@@ -1161,10 +1235,10 @@ void dc_dmub_srv_exit_low_power_state(const struct dc *dc)
 		}
 
 		dc_dmub_srv_notify_idle(dc, false);
-		if (allow_state & DMUB_IPS1_ALLOW_MASK) {
+		if (!(allow_state & DMUB_IPS1_ALLOW_MASK)) {
 			for (i = 0; i < max_num_polls; ++i) {
 				commit_state = dc->hwss.get_idle_state(dc);
-				if (!(commit_state & DMUB_IPS1_COMMIT_MASK))
+				if (commit_state & DMUB_IPS1_COMMIT_MASK)
 					break;
 
 				udelay(1);
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
index 31150b21439484..d4a60f53faab12 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
@@ -56,6 +56,14 @@ void dc_dmub_srv_wait_idle(struct dc_dmub_srv *dc_dmub_srv);
 
 bool dc_dmub_srv_optimized_init_done(struct dc_dmub_srv *dc_dmub_srv);
 
+bool dc_dmub_srv_cmd_list_queue_execute(struct dc_dmub_srv *dc_dmub_srv,
+		unsigned int count,
+		union dmub_rb_cmd *cmd_list);
+
+bool dc_dmub_srv_wait_for_idle(struct dc_dmub_srv *dc_dmub_srv,
+		enum dm_dmub_wait_type wait_type,
+		union dmub_rb_cmd *cmd_list);
+
 bool dc_dmub_srv_cmd_run(struct dc_dmub_srv *dc_dmub_srv, union dmub_rb_cmd *cmd, enum dm_dmub_wait_type wait_type);
 
 bool dc_dmub_srv_cmd_run_list(struct dc_dmub_srv *dc_dmub_srv, unsigned int count, union dmub_rb_cmd *cmd_list, enum dm_dmub_wait_type wait_type);
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index 35ae245ef722b9..eeeeeef4d71734 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -142,7 +142,8 @@ enum dp_test_link_rate {
 	DP_TEST_LINK_RATE_HBR3		= 0x1E,
 	DP_TEST_LINK_RATE_UHBR10	= 0x01,
 	DP_TEST_LINK_RATE_UHBR20	= 0x02,
-	DP_TEST_LINK_RATE_UHBR13_5	= 0x03,
+	DP_TEST_LINK_RATE_UHBR13_5_LEGACY	= 0x03, /* For backward compatibility*/
+	DP_TEST_LINK_RATE_UHBR13_5	= 0x04,
 };
 
 struct dc_link_settings {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index 9649934ea186d6..e2a3aa8812df49 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -465,6 +465,7 @@ struct dc_cursor_mi_param {
 	struct fixed31_32 v_scale_ratio;
 	enum dc_rotation_angle rotation;
 	bool mirror;
+	struct dc_stream_state *stream;
 };
 
 /* IPP related types */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 40dc51853d62a9..35d146217aef0f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -177,6 +177,7 @@ struct dc_panel_patch {
 	unsigned int disable_fams;
 	unsigned int skip_avmute;
 	unsigned int mst_start_top_delay;
+	unsigned int remove_sink_ext_caps;
 };
 
 struct dc_edid_caps {
@@ -990,10 +991,6 @@ struct link_mst_stream_allocation_table {
 	struct link_mst_stream_allocation stream_allocations[MAX_CONTROLLER_NUM];
 };
 
-struct backlight_settings {
-	uint32_t backlight_millinits;
-};
-
 /* PSR feature flags */
 struct psr_settings {
 	bool psr_feature_enabled;		// PSR is supported by sink
@@ -1037,7 +1034,9 @@ struct replay_config {
 	bool replay_smu_opt_supported;                  // SMU optimization is supported
 	unsigned int replay_enable_option;              // Replay enablement option
 	uint32_t debug_flags;                           // Replay debug flags
-	bool replay_timing_sync_supported;             // Replay desync is supported
+	bool replay_timing_sync_supported; // Replay desync is supported
+	bool force_disable_desync_error_check;             // Replay desync is supported
+	bool received_desync_error_hpd; //Replay Received Desync Error HPD.
 	union replay_error_status replay_error_status; // Replay error status
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
index c50aa30614be2c..051e4c2b4cf271 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
@@ -128,21 +128,6 @@
 	SRI(DC_ABM1_ACE_THRES_12, ABM, id), \
 	NBIO_SR(BIOS_SCRATCH_2)
 
-#define ABM_DCN32_REG_LIST(id)\
-	SRI(DC_ABM1_HG_SAMPLE_RATE, ABM, id), \
-	SRI(DC_ABM1_LS_SAMPLE_RATE, ABM, id), \
-	SRI(BL1_PWM_BL_UPDATE_SAMPLE_RATE, ABM, id), \
-	SRI(DC_ABM1_HG_MISC_CTRL, ABM, id), \
-	SRI(DC_ABM1_IPCSC_COEFF_SEL, ABM, id), \
-	SRI(BL1_PWM_CURRENT_ABM_LEVEL, ABM, id), \
-	SRI(BL1_PWM_TARGET_ABM_LEVEL, ABM, id), \
-	SRI(BL1_PWM_USER_LEVEL, ABM, id), \
-	SRI(DC_ABM1_LS_MIN_MAX_PIXEL_VALUE_THRES, ABM, id), \
-	SRI(DC_ABM1_HGLS_REG_READ_PROGRESS, ABM, id), \
-	SRI(DC_ABM1_ACE_OFFSET_SLOPE_0, ABM, id), \
-	SRI(DC_ABM1_ACE_THRES_12, ABM, id), \
-	NBIO_SR(BIOS_SCRATCH_2)
-
 #define ABM_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
index aaf6c981fd9e13..ab81594a7fadcc 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
@@ -26,7 +26,7 @@
 #ifndef __DC_TIMING_GENERATOR_DCN10_H__
 #define __DC_TIMING_GENERATOR_DCN10_H__
 
-#include "timing_generator.h"
+#include "optc.h"
 
 #define DCN10TG_FROM_TG(tg)\
 	container_of(tg, struct optc, base)
@@ -594,190 +594,6 @@ struct dcn_optc_mask {
 	TG_REG_FIELD_LIST_DCN3_5(uint32_t)
 };
 
-struct optc {
-	struct timing_generator base;
-
-	const struct dcn_optc_registers *tg_regs;
-	const struct dcn_optc_shift *tg_shift;
-	const struct dcn_optc_mask *tg_mask;
-
-	int opp_count;
-
-	uint32_t max_h_total;
-	uint32_t max_v_total;
-
-	uint32_t min_h_blank;
-
-	uint32_t min_h_sync_width;
-	uint32_t min_v_sync_width;
-	uint32_t min_v_blank;
-	uint32_t min_v_blank_interlace;
-
-	int vstartup_start;
-	int vupdate_offset;
-	int vupdate_width;
-	int vready_offset;
-	struct dc_crtc_timing orginal_patched_timing;
-	enum signal_type signal;
-};
-
 void dcn10_timing_generator_init(struct optc *optc);
 
-struct dcn_otg_state {
-	uint32_t v_blank_start;
-	uint32_t v_blank_end;
-	uint32_t v_sync_a_pol;
-	uint32_t v_total;
-	uint32_t v_total_max;
-	uint32_t v_total_min;
-	uint32_t v_total_min_sel;
-	uint32_t v_total_max_sel;
-	uint32_t v_sync_a_start;
-	uint32_t v_sync_a_end;
-	uint32_t h_blank_start;
-	uint32_t h_blank_end;
-	uint32_t h_sync_a_start;
-	uint32_t h_sync_a_end;
-	uint32_t h_sync_a_pol;
-	uint32_t h_total;
-	uint32_t underflow_occurred_status;
-	uint32_t otg_enabled;
-	uint32_t blank_enabled;
-	uint32_t vertical_interrupt1_en;
-	uint32_t vertical_interrupt1_line;
-	uint32_t vertical_interrupt2_en;
-	uint32_t vertical_interrupt2_line;
-};
-
-void optc1_read_otg_state(struct optc *optc1,
-		struct dcn_otg_state *s);
-
-bool optc1_get_hw_timing(struct timing_generator *tg,
-		struct dc_crtc_timing *hw_crtc_timing);
-
-bool optc1_validate_timing(
-	struct timing_generator *optc,
-	const struct dc_crtc_timing *timing);
-
-void optc1_program_timing(
-	struct timing_generator *optc,
-	const struct dc_crtc_timing *dc_crtc_timing,
-	int vready_offset,
-	int vstartup_start,
-	int vupdate_offset,
-	int vupdate_width,
-	const enum signal_type signal,
-	bool use_vbios);
-
-void optc1_setup_vertical_interrupt0(
-		struct timing_generator *optc,
-		uint32_t start_line,
-		uint32_t end_line);
-void optc1_setup_vertical_interrupt1(
-		struct timing_generator *optc,
-		uint32_t start_line);
-void optc1_setup_vertical_interrupt2(
-		struct timing_generator *optc,
-		uint32_t start_line);
-
-void optc1_program_global_sync(
-		struct timing_generator *optc,
-		int vready_offset,
-		int vstartup_start,
-		int vupdate_offset,
-		int vupdate_width);
-
-bool optc1_disable_crtc(struct timing_generator *optc);
-
-bool optc1_is_counter_moving(struct timing_generator *optc);
-
-void optc1_get_position(struct timing_generator *optc,
-		struct crtc_position *position);
-
-uint32_t optc1_get_vblank_counter(struct timing_generator *optc);
-
-void optc1_get_crtc_scanoutpos(
-	struct timing_generator *optc,
-	uint32_t *v_blank_start,
-	uint32_t *v_blank_end,
-	uint32_t *h_position,
-	uint32_t *v_position);
-
-void optc1_set_early_control(
-	struct timing_generator *optc,
-	uint32_t early_cntl);
-
-void optc1_wait_for_state(struct timing_generator *optc,
-		enum crtc_state state);
-
-void optc1_set_blank(struct timing_generator *optc,
-		bool enable_blanking);
-
-bool optc1_is_blanked(struct timing_generator *optc);
-
-void optc1_program_blank_color(
-		struct timing_generator *optc,
-		const struct tg_color *black_color);
-
-bool optc1_did_triggered_reset_occur(
-	struct timing_generator *optc);
-
-void optc1_enable_reset_trigger(struct timing_generator *optc, int source_tg_inst);
-
-void optc1_disable_reset_trigger(struct timing_generator *optc);
-
-void optc1_lock(struct timing_generator *optc);
-
-void optc1_unlock(struct timing_generator *optc);
-
-void optc1_enable_optc_clock(struct timing_generator *optc, bool enable);
-
-void optc1_set_drr(
-	struct timing_generator *optc,
-	const struct drr_params *params);
-
-void optc1_set_vtotal_min_max(struct timing_generator *optc, int vtotal_min, int vtotal_max);
-
-void optc1_set_static_screen_control(
-	struct timing_generator *optc,
-	uint32_t event_triggers,
-	uint32_t num_frames);
-
-void optc1_program_stereo(struct timing_generator *optc,
-	const struct dc_crtc_timing *timing, struct crtc_stereo_flags *flags);
-
-bool optc1_is_stereo_left_eye(struct timing_generator *optc);
-
-void optc1_clear_optc_underflow(struct timing_generator *optc);
-
-void optc1_tg_init(struct timing_generator *optc);
-
-bool optc1_is_tg_enabled(struct timing_generator *optc);
-
-bool optc1_is_optc_underflow_occurred(struct timing_generator *optc);
-
-void optc1_set_blank_data_double_buffer(struct timing_generator *optc, bool enable);
-
-void optc1_set_timing_double_buffer(struct timing_generator *optc, bool enable);
-
-bool optc1_get_otg_active_size(struct timing_generator *optc,
-		uint32_t *otg_active_width,
-		uint32_t *otg_active_height);
-
-void optc1_enable_crtc_reset(
-		struct timing_generator *optc,
-		int source_tg_inst,
-		struct crtc_trigger_info *crtc_tp);
-
-bool optc1_configure_crc(struct timing_generator *optc,
-			  const struct crc_params *params);
-
-bool optc1_get_crc(struct timing_generator *optc,
-		    uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb);
-
-bool optc1_is_two_pixels_per_containter(const struct dc_crtc_timing *timing);
-
-void optc1_set_vtg_params(struct timing_generator *optc,
-		const struct dc_crtc_timing *dc_crtc_timing, bool program_fp2);
-
 #endif /* __DC_TIMING_GENERATOR_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
index 5eebe7f03ddc72..c9ae2d8f0096fa 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
@@ -137,7 +137,15 @@ void dsc2_get_enc_caps(struct dsc_enc_caps *dsc_enc_caps, int pixel_clock_100Hz)
 		dsc_enc_caps->max_total_throughput_mps = DCN20_MAX_DISPLAY_CLOCK_Mhz * 2;
 	}
 
-	// TODO DSC: This is actually image width limitation, not a slice width. This should be added to the criteria to use ODM.
+	/* For pixel clock bigger than a single-pipe limit needing four engines ODM 4:1, which then quardruples our
+	 * throughput and number of slices
+	 */
+	if (pixel_clock_100Hz > DCN20_MAX_PIXEL_CLOCK_Mhz*10000*2) {
+		dsc_enc_caps->slice_caps.bits.NUM_SLICES_12 = 1;
+		dsc_enc_caps->slice_caps.bits.NUM_SLICES_16 = 1;
+		dsc_enc_caps->max_total_throughput_mps = DCN20_MAX_DISPLAY_CLOCK_Mhz * 4;
+	}
+
 	dsc_enc_caps->max_slice_width = 5184; /* (including 64 overlap pixels for eDP MSO mode) */
 	dsc_enc_caps->bpp_increment_div = 16; /* 1/16th of a bit */
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
index 139cf31d2e456f..89c3bf0fe0c991 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
@@ -1077,8 +1077,16 @@ void hubp2_cursor_set_position(
 	if (src_y_offset < 0)
 		src_y_offset = 0;
 	/* Save necessary cursor info x, y position. w, h is saved in attribute func. */
-	hubp->cur_rect.x = src_x_offset + param->viewport.x;
-	hubp->cur_rect.y = src_y_offset + param->viewport.y;
+	if (param->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 &&
+	    param->rotation != ROTATION_ANGLE_0) {
+		hubp->cur_rect.x = 0;
+		hubp->cur_rect.y = 0;
+		hubp->cur_rect.w = param->stream->timing.h_addressable;
+		hubp->cur_rect.h = param->stream->timing.v_addressable;
+	} else {
+		hubp->cur_rect.x = src_x_offset + param->viewport.x;
+		hubp->cur_rect.y = src_y_offset + param->viewport.y;
+	}
 }
 
 void hubp2_clk_cntl(struct hubp *hubp, bool enable)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
index 677361d74a4ecf..c97391edb5ff7a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
@@ -871,7 +871,7 @@ static const struct dc_plane_cap plane_cap = {
 static const struct dc_debug_options debug_defaults_drv = {
 	.disable_z10 = false,
 	.enable_z9_disable_interface = true,
-	.minimum_z8_residency_time = 2000,
+	.minimum_z8_residency_time = 2100,
 	.psr_skip_crtc_disable = true,
 	.replay_skip_crtc_disabled = true,
 	.disable_dmcu = true,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c
index addedcfd1238be..479f3683c0b70e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c
@@ -325,6 +325,43 @@ static void dccg35_set_dpstreamclk(
 	}
 }
 
+static void dccg35_set_physymclk_root_clock_gating(
+		struct dccg *dccg,
+		int phy_inst,
+		bool enable)
+{
+	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
+
+	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
+		return;
+
+	switch (phy_inst) {
+	case 0:
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
+				PHYASYMCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
+		break;
+	case 1:
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
+				PHYBSYMCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
+		break;
+	case 2:
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
+				PHYCSYMCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
+		break;
+	case 3:
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
+				PHYDSYMCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
+		break;
+	case 4:
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
+				PHYESYMCLK_ROOT_GATE_DISABLE, enable ? 1 : 0);
+		break;
+	default:
+		BREAK_TO_DEBUGGER();
+		return;
+	}
+}
+
 static void dccg35_set_physymclk(
 		struct dccg *dccg,
 		int phy_inst,
@@ -340,16 +377,10 @@ static void dccg35_set_physymclk(
 			REG_UPDATE_2(PHYASYMCLK_CLOCK_CNTL,
 					PHYASYMCLK_EN, 1,
 					PHYASYMCLK_SRC_SEL, clk_src);
-			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
-				REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
-					PHYASYMCLK_ROOT_GATE_DISABLE, 1);
 		} else {
 			REG_UPDATE_2(PHYASYMCLK_CLOCK_CNTL,
 					PHYASYMCLK_EN, 0,
 					PHYASYMCLK_SRC_SEL, 0);
-			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
-				REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
-					PHYASYMCLK_ROOT_GATE_DISABLE, 0);
 		}
 		break;
 	case 1:
@@ -357,16 +388,10 @@ static void dccg35_set_physymclk(
 			REG_UPDATE_2(PHYBSYMCLK_CLOCK_CNTL,
 					PHYBSYMCLK_EN, 1,
 					PHYBSYMCLK_SRC_SEL, clk_src);
-			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
-				REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
-					PHYBSYMCLK_ROOT_GATE_DISABLE, 1);
 		} else {
 			REG_UPDATE_2(PHYBSYMCLK_CLOCK_CNTL,
 					PHYBSYMCLK_EN, 0,
 					PHYBSYMCLK_SRC_SEL, 0);
-			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
-				REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
-					PHYBSYMCLK_ROOT_GATE_DISABLE, 0);
 		}
 		break;
 	case 2:
@@ -374,16 +399,10 @@ static void dccg35_set_physymclk(
 			REG_UPDATE_2(PHYCSYMCLK_CLOCK_CNTL,
 					PHYCSYMCLK_EN, 1,
 					PHYCSYMCLK_SRC_SEL, clk_src);
-			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
-				REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
-					PHYCSYMCLK_ROOT_GATE_DISABLE, 1);
 		} else {
 			REG_UPDATE_2(PHYCSYMCLK_CLOCK_CNTL,
 					PHYCSYMCLK_EN, 0,
 					PHYCSYMCLK_SRC_SEL, 0);
-			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
-				REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
-					PHYCSYMCLK_ROOT_GATE_DISABLE, 0);
 		}
 		break;
 	case 3:
@@ -391,16 +410,10 @@ static void dccg35_set_physymclk(
 			REG_UPDATE_2(PHYDSYMCLK_CLOCK_CNTL,
 					PHYDSYMCLK_EN, 1,
 					PHYDSYMCLK_SRC_SEL, clk_src);
-			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
-				REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
-					PHYDSYMCLK_ROOT_GATE_DISABLE, 1);
 		} else {
 			REG_UPDATE_2(PHYDSYMCLK_CLOCK_CNTL,
 					PHYDSYMCLK_EN, 0,
 					PHYDSYMCLK_SRC_SEL, 0);
-			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
-				REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
-					PHYDSYMCLK_ROOT_GATE_DISABLE, 0);
 		}
 		break;
 	case 4:
@@ -408,16 +421,10 @@ static void dccg35_set_physymclk(
 			REG_UPDATE_2(PHYESYMCLK_CLOCK_CNTL,
 					PHYESYMCLK_EN, 1,
 					PHYESYMCLK_SRC_SEL, clk_src);
-			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
-				REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
-					PHYESYMCLK_ROOT_GATE_DISABLE, 1);
 		} else {
 			REG_UPDATE_2(PHYESYMCLK_CLOCK_CNTL,
 					PHYESYMCLK_EN, 0,
 					PHYESYMCLK_SRC_SEL, 0);
-			if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
-				REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
-					PHYESYMCLK_ROOT_GATE_DISABLE, 0);
 		}
 		break;
 	default:
@@ -490,8 +497,8 @@ void dccg35_init(struct dccg *dccg)
 
 	if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
 		for (otg_inst = 0; otg_inst < 5; otg_inst++)
-			dccg35_set_physymclk(dccg, otg_inst,
-					     PHYSYMCLK_FORCE_SRC_SYMCLK, false);
+			dccg35_set_physymclk_root_clock_gating(dccg, otg_inst,
+					false);
 /*
 	dccg35_enable_global_fgcg_rep(
 		dccg, dccg->ctx->dc->debug.enable_fine_grain_clock_gating.bits
@@ -754,7 +761,9 @@ static const struct dccg_funcs dccg35_funcs = {
 	.disable_symclk32_se = dccg31_disable_symclk32_se,
 	.enable_symclk32_le = dccg31_enable_symclk32_le,
 	.disable_symclk32_le = dccg31_disable_symclk32_le,
+	.set_symclk32_le_root_clock_gating = dccg31_set_symclk32_le_root_clock_gating,
 	.set_physymclk = dccg35_set_physymclk,
+	.set_physymclk_root_clock_gating = dccg35_set_physymclk_root_clock_gating,
 	.set_dtbclk_dto = dccg35_set_dtbclk_dto,
 	.set_audio_dtbclk_dto = dccg31_set_audio_dtbclk_dto,
 	.set_fifo_errdet_ovr_en = dccg2_set_fifo_errdet_ovr_en,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_stream_encoder.c
index 001f9eb6692075..62a8f0b5600620 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_stream_encoder.c
@@ -261,12 +261,6 @@ static void enc35_stream_encoder_enable(
 			/* invalid mode ! */
 			ASSERT_CRITICAL(false);
 		}
-
-		REG_UPDATE(DIG_FE_CLK_CNTL, DIG_FE_CLK_EN, 1);
-		REG_UPDATE(DIG_FE_EN_CNTL, DIG_FE_ENABLE, 1);
-	} else {
-		REG_UPDATE(DIG_FE_EN_CNTL, DIG_FE_ENABLE, 0);
-		REG_UPDATE(DIG_FE_CLK_CNTL, DIG_FE_CLK_EN, 0);
 	}
 }
 
@@ -436,6 +430,8 @@ static void enc35_disable_fifo(struct stream_encoder *enc)
 	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
 
 	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 0);
+	REG_UPDATE(DIG_FE_EN_CNTL, DIG_FE_ENABLE, 0);
+	REG_UPDATE(DIG_FE_CLK_CNTL, DIG_FE_CLK_EN, 0);
 }
 
 static void enc35_enable_fifo(struct stream_encoder *enc)
@@ -443,6 +439,8 @@ static void enc35_enable_fifo(struct stream_encoder *enc)
 	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
 
 	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7);
+	REG_UPDATE(DIG_FE_CLK_CNTL, DIG_FE_CLK_EN, 1);
+	REG_UPDATE(DIG_FE_EN_CNTL, DIG_FE_ENABLE, 1);
 
 	enc35_reset_fifo(enc, true);
 	enc35_reset_fifo(enc, false);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.c
index 0f60c40e1fc50a..d19db8e9b8a54f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.c
@@ -261,6 +261,7 @@ void pg_cntl35_hpo_pg_control(struct pg_cntl *pg_cntl, bool power_on)
 	uint32_t power_gate = power_on ? 0 : 1;
 	uint32_t pwr_status = power_on ? 0 : 2;
 	uint32_t org_ip_request_cntl;
+	uint32_t power_forceon;
 	bool block_enabled;
 
 	if (pg_cntl->ctx->dc->debug.ignore_pg ||
@@ -277,6 +278,10 @@ void pg_cntl35_hpo_pg_control(struct pg_cntl *pg_cntl, bool power_on)
 			return;
 	}
 
+	REG_GET(DOMAIN25_PG_CONFIG, DOMAIN_POWER_FORCEON, &power_forceon);
+	if (power_forceon)
+		return;
+
 	REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl);
 	if (org_ip_request_cntl == 0)
 		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1);
@@ -304,6 +309,7 @@ void pg_cntl35_io_clk_pg_control(struct pg_cntl *pg_cntl, bool power_on)
 	uint32_t power_gate = power_on ? 0 : 1;
 	uint32_t pwr_status = power_on ? 0 : 2;
 	uint32_t org_ip_request_cntl;
+	uint32_t power_forceon;
 	bool block_enabled;
 
 	if (pg_cntl->ctx->dc->debug.ignore_pg ||
@@ -319,6 +325,10 @@ void pg_cntl35_io_clk_pg_control(struct pg_cntl *pg_cntl, bool power_on)
 			return;
 	}
 
+	REG_GET(DOMAIN22_PG_CONFIG, DOMAIN_POWER_FORCEON, &power_forceon);
+	if (power_forceon)
+		return;
+
 	REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl);
 	if (org_ip_request_cntl == 0)
 		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1);
@@ -332,6 +342,13 @@ void pg_cntl35_io_clk_pg_control(struct pg_cntl *pg_cntl, bool power_on)
 	pg_cntl->pg_res_enable[PG_DCIO] = power_on;
 }
 
+void pg_cntl35_set_force_poweron_domain22(struct pg_cntl *pg_cntl, bool power_on)
+{
+	struct dcn_pg_cntl *pg_cntl_dcn = TO_DCN_PG_CNTL(pg_cntl);
+
+	REG_UPDATE(DOMAIN22_PG_CONFIG, DOMAIN_POWER_FORCEON, power_on ? 1 : 0);
+}
+
 static bool pg_cntl35_plane_otg_status(struct pg_cntl *pg_cntl)
 {
 	struct dcn_pg_cntl *pg_cntl_dcn = TO_DCN_PG_CNTL(pg_cntl);
@@ -501,7 +518,8 @@ static const struct pg_cntl_funcs pg_cntl35_funcs = {
 	.mpcc_pg_control = pg_cntl35_mpcc_pg_control,
 	.opp_pg_control = pg_cntl35_opp_pg_control,
 	.optc_pg_control = pg_cntl35_optc_pg_control,
-	.dwb_pg_control = pg_cntl35_dwb_pg_control
+	.dwb_pg_control = pg_cntl35_dwb_pg_control,
+	.set_force_poweron_domain22 = pg_cntl35_set_force_poweron_domain22
 };
 
 struct pg_cntl *pg_cntl35_create(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.h b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.h
index 3de240884d22fa..069dae08e2224b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.h
@@ -183,6 +183,7 @@ void pg_cntl35_optc_pg_control(struct pg_cntl *pg_cntl,
 	unsigned int optc_inst, bool power_on);
 void pg_cntl35_dwb_pg_control(struct pg_cntl *pg_cntl, bool power_on);
 void pg_cntl35_init_pg_status(struct pg_cntl *pg_cntl);
+void pg_cntl35_set_force_poweron_domain22(struct pg_cntl *pg_cntl, bool power_on);
 
 struct pg_cntl *pg_cntl35_create(
 	struct dc_context *ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_resource.c
index 3c7c810bab1ff7..70ef1e7ff84113 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_resource.c
@@ -610,7 +610,23 @@ static struct dce_hwseq_registers hwseq_reg;
 	HWS_SF(, DMU_CLK_CNTL, LONO_FGCG_REP_DIS, mask_sh),\
 	HWS_SF(, DMU_CLK_CNTL, LONO_DISPCLK_GATE_DISABLE, mask_sh),\
 	HWS_SF(, DMU_CLK_CNTL, LONO_SOCCLK_GATE_DISABLE, mask_sh),\
-	HWS_SF(, DMU_CLK_CNTL, LONO_DMCUBCLK_GATE_DISABLE, mask_sh)
+	HWS_SF(, DMU_CLK_CNTL, LONO_DMCUBCLK_GATE_DISABLE, mask_sh),\
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, SYMCLKA_FE_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, SYMCLKB_FE_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, SYMCLKC_FE_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, SYMCLKD_FE_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, SYMCLKE_FE_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, HDMICHARCLK0_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, SYMCLKA_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, SYMCLKB_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, SYMCLKC_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, SYMCLKD_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, SYMCLKE_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, PHYASYMCLK_ROOT_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, PHYBSYMCLK_ROOT_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, PHYCSYMCLK_ROOT_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, PHYDSYMCLK_ROOT_GATE_DISABLE, mask_sh), \
+	HWS_SF(, DCCG_GATE_DISABLE_CNTL2, PHYESYMCLK_ROOT_GATE_DISABLE, mask_sh)
 
 static const struct dce_hwseq_shift hwseq_shift = {
 		HWSEQ_DCN35_MASK_SH_LIST(__SHIFT)
@@ -708,7 +724,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 			.i2c = true,
 			.dmcu = false, // This is previously known to cause hang on S3 cycles if enabled
 			.dscl = true,
-			.cm = true,
+			.cm = false,
 			.mpc = true,
 			.optc = true,
 			.vpg = true,
@@ -719,14 +735,14 @@ static const struct dc_debug_options debug_defaults_drv = {
 		.bits = {
 			.dpp = true,
 			.dsc = true,/*dscclk and dsc pg*/
-			.hdmistream = false,
-			.hdmichar = false,
-			.dpstream = false,
-			.symclk32_se = false,
-			.symclk32_le = false,
-			.symclk_fe = false,
-			.physymclk = false,
-			.dpiasymclk = false,
+			.hdmistream = true,
+			.hdmichar = true,
+			.dpstream = true,
+			.symclk32_se = true,
+			.symclk32_le = true,
+			.symclk_fe = true,
+			.physymclk = true,
+			.dpiasymclk = true,
 		}
 	},
 	.seamless_boot_odm_combine = DML_FAIL_SOURCE_PIXEL_FORMAT,
@@ -741,7 +757,6 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_boot_optimizations = false,
 	.disable_unbounded_requesting = false,
 	.disable_mem_low_power = false,
-	.enable_hpo_pg_support = false,
 	//must match enable_single_display_2to1_odm_policy to support dynamic ODM transitions
 	.enable_double_buffered_dsc_pg_support = true,
 	.enable_dp_dig_pixel_rate_div_policy = 1,
@@ -1697,6 +1712,13 @@ static bool dcn35_validate_bandwidth(struct dc *dc,
 
 	out = dml2_validate(dc, context, fast_validate);
 
+	if (fast_validate)
+		return out;
+
+	DC_FP_START();
+	dcn35_decide_zstate_support(dc, context);
+	DC_FP_END();
+
 	return out;
 }
 
@@ -1842,7 +1864,7 @@ static bool dcn35_resource_construct(
 
 	/* Use pipe context based otg sync logic */
 	dc->config.use_pipe_ctx_sync_logic = true;
-	dc->config.use_default_clock_table = false;
+
 	/* read VBIOS LTTPR caps */
 	{
 		if (ctx->dc_bios->funcs->get_lttpr_caps) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index ea7d60f9a9b45a..6042a5a6a44f8c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -61,8 +61,12 @@ endif
 endif
 
 ifneq ($(CONFIG_FRAME_WARN),0)
+ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y)
+frame_warn_flag := -Wframe-larger-than=3072
+else
 frame_warn_flag := -Wframe-larger-than=2048
 endif
+endif
 
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dc_features.h b/drivers/gpu/drm/amd/display/dc/dml/dc_features.h
index 2cbdd75429ffd6..6e669a2c5b2d44 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dc_features.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dc_features.h
@@ -36,7 +36,7 @@
  * Define the maximum amount of states supported by the ASIC. Every ASIC has a
  * specific number of states; this macro defines the maximum number of states.
  */
-#define DC__VOLTAGE_STATES 20
+#define DC__VOLTAGE_STATES 40
 #define DC__NUM_DPP__4 1
 #define DC__NUM_DPP__0_PRESENT 1
 #define DC__NUM_DPP__1_PRESENT 1
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index 7fc8b18096ba87..ec77b2b41ba367 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -950,10 +950,8 @@ static enum dcn_zstate_support_state  decide_zstate_support(struct dc *dc, struc
 {
 	int plane_count;
 	int i;
-	unsigned int min_dst_y_next_start_us;
 
 	plane_count = 0;
-	min_dst_y_next_start_us = 0;
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		if (context->res_ctx.pipe_ctx[i].plane_state)
 			plane_count++;
@@ -975,26 +973,15 @@ static enum dcn_zstate_support_state  decide_zstate_support(struct dc *dc, struc
 	else if (context->stream_count == 1 &&  context->streams[0]->signal == SIGNAL_TYPE_EDP) {
 		struct dc_link *link = context->streams[0]->sink->link;
 		struct dc_stream_status *stream_status = &context->stream_status[0];
-		struct dc_stream_state *current_stream = context->streams[0];
 		int minmum_z8_residency = dc->debug.minimum_z8_residency_time > 0 ? dc->debug.minimum_z8_residency_time : 1000;
 		bool allow_z8 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z8_residency;
 		bool is_pwrseq0 = link->link_index == 0;
-		bool isFreesyncVideo;
-
-		isFreesyncVideo = current_stream->adjust.v_total_min == current_stream->adjust.v_total_max;
-		isFreesyncVideo = isFreesyncVideo && current_stream->timing.v_total < current_stream->adjust.v_total_min;
-		for (i = 0; i < dc->res_pool->pipe_count; i++) {
-			if (context->res_ctx.pipe_ctx[i].stream == current_stream && isFreesyncVideo) {
-				min_dst_y_next_start_us = context->res_ctx.pipe_ctx[i].dlg_regs.min_dst_y_next_start_us;
-				break;
-			}
-		}
 
 		/* Don't support multi-plane configurations */
 		if (stream_status->plane_count > 1)
 			return DCN_ZSTATE_SUPPORT_DISALLOW;
 
-		if (is_pwrseq0 && (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || min_dst_y_next_start_us > 5000))
+		if (is_pwrseq0 && context->bw_ctx.dml.vba.StutterPeriod > 5000.0)
 			return DCN_ZSTATE_SUPPORT_ALLOW;
 		else if (is_pwrseq0 && link->psr_settings.psr_version == DC_PSR_VERSION_1 && !link->panel_config.psr.disable_psr)
 			return allow_z8 ? DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY : DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
index ad741a723c0e8a..3686f1e7de3abf 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c
@@ -5128,7 +5128,7 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			ViewportExceedsSurface = true;
 
 		if (v->SourcePixelFormat[k] != dm_444_64 && v->SourcePixelFormat[k] != dm_444_32 && v->SourcePixelFormat[k] != dm_444_16
-				&& v->SourcePixelFormat[k] != dm_444_16 && v->SourcePixelFormat[k] != dm_444_8 && v->SourcePixelFormat[k] != dm_rgbe) {
+				&& v->SourcePixelFormat[k] != dm_444_8 && v->SourcePixelFormat[k] != dm_rgbe) {
 			if (v->ViewportWidthChroma[k] > v->SurfaceWidthC[k] || v->ViewportHeightChroma[k] > v->SurfaceHeightC[k]) {
 				ViewportExceedsSurface = true;
 			}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index 9ec4172d1c2d81..b46cde52506699 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -1192,13 +1192,16 @@ static bool update_pipe_slice_table_with_split_flags(
 	 */
 	struct pipe_ctx *pipe;
 	bool odm;
-	int i;
+	int dc_pipe_idx, dml_pipe_idx = 0;
 	bool updated = false;
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		pipe = &context->res_ctx.pipe_ctx[i];
+	for (dc_pipe_idx = 0;
+			dc_pipe_idx < dc->res_pool->pipe_count; dc_pipe_idx++) {
+		pipe = &context->res_ctx.pipe_ctx[dc_pipe_idx];
+		if (resource_is_pipe_type(pipe, FREE_PIPE))
+			continue;
 
-		if (merge[i]) {
+		if (merge[dc_pipe_idx]) {
 			if (resource_is_pipe_type(pipe, OPP_HEAD))
 				/* merging OPP head means reducing ODM slice
 				 * count by 1
@@ -1213,17 +1216,18 @@ static bool update_pipe_slice_table_with_split_flags(
 			updated = true;
 		}
 
-		if (split[i]) {
-			odm = vba->ODMCombineEnabled[vba->pipe_plane[i]] !=
+		if (split[dc_pipe_idx]) {
+			odm = vba->ODMCombineEnabled[vba->pipe_plane[dml_pipe_idx]] !=
 					dm_odm_combine_mode_disabled;
 			if (odm && resource_is_pipe_type(pipe, OPP_HEAD))
 				update_slice_table_for_stream(
-						table, pipe->stream, split[i] - 1);
+						table, pipe->stream, split[dc_pipe_idx] - 1);
 			else if (!odm && resource_is_pipe_type(pipe, DPP_PIPE))
 				update_slice_table_for_plane(table, pipe,
-						pipe->plane_state, split[i] - 1);
+						pipe->plane_state, split[dc_pipe_idx] - 1);
 			updated = true;
 		}
+		dml_pipe_idx++;
 	}
 	return updated;
 }
@@ -2231,6 +2235,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 	int i, pipe_idx, vlevel_temp = 0;
 	double dcfclk = dcn3_2_soc.clock_limits[0].dcfclk_mhz;
 	double dcfclk_from_validation = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb];
+	double dram_speed_from_validation = context->bw_ctx.dml.vba.DRAMSpeed;
 	double dcfclk_from_fw_based_mclk_switching = dcfclk_from_validation;
 	bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] !=
 			dm_dram_clock_change_unsupported;
@@ -2418,7 +2423,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 	}
 
 	if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].valid) {
-		min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed;
+		min_dram_speed_mts = dram_speed_from_validation;
 		min_dram_speed_mts_margin = 160;
 
 		context->bw_ctx.dml.soc.dram_clock_change_latency_us =
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index a5fe523668e94a..f154a3eb1d1a0a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -124,7 +124,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 			.phyclk_mhz = 600.0,
 			.phyclk_d18_mhz = 667.0,
 			.dscclk_mhz = 186.0,
-			.dtbclk_mhz = 625.0,
+			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 1,
@@ -133,7 +133,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
 			.dscclk_mhz = 209.0,
-			.dtbclk_mhz = 625.0,
+			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 2,
@@ -142,7 +142,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
 			.dscclk_mhz = 209.0,
-			.dtbclk_mhz = 625.0,
+			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 3,
@@ -151,7 +151,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
 			.dscclk_mhz = 371.0,
-			.dtbclk_mhz = 625.0,
+			.dtbclk_mhz = 600.0,
 		},
 		{
 			.state = 4,
@@ -160,14 +160,14 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
 			.dscclk_mhz = 417.0,
-			.dtbclk_mhz = 625.0,
+			.dtbclk_mhz = 600.0,
 		},
 	},
 	.num_states = 5,
-	.sr_exit_time_us = 9.0,
-	.sr_enter_plus_exit_time_us = 11.0,
-	.sr_exit_z8_time_us = 50.0, /*changed from 442.0*/
-	.sr_enter_plus_exit_z8_time_us = 50.0,/*changed from 560.0*/
+	.sr_exit_time_us = 14.0,
+	.sr_enter_plus_exit_time_us = 16.0,
+	.sr_exit_z8_time_us = 525.0,
+	.sr_enter_plus_exit_z8_time_us = 715.0,
 	.fclk_change_latency_us = 20.0,
 	.usr_retraining_latency_us = 2,
 	.writeback_latency_us = 12.0,
@@ -329,6 +329,52 @@ void dcn35_update_bw_bounding_box_fpu(struct dc *dc,
 	/*temp till dml2 fully work without dml1*/
 	dml_init_instance(&dc->dml, &dcn3_5_soc, &dcn3_5_ip,
 				DML_PROJECT_DCN31);
+
+	/*copy to dml2, before dml2_create*/
+	if (clk_table->num_entries > 2) {
+
+		for (i = 0; i < clk_table->num_entries; i++) {
+			dc->dml2_options.bbox_overrides.clks_table.num_states =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dcfclk_mhz =
+				clock_limits[i].dcfclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].fclk_mhz =
+				clock_limits[i].fabricclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dispclk_mhz =
+				clock_limits[i].dispclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dppclk_mhz =
+				clock_limits[i].dppclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].socclk_mhz =
+				clock_limits[i].socclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].memclk_mhz =
+				clk_table->entries[i].memclk_mhz * clk_table->entries[i].wck_ratio;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz =
+				clock_limits[i].dtbclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_fclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dispclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dppclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_socclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_memclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dtbclk_levels =
+				clk_table->num_entries;
+		}
+	}
+
+	/* Update latency values */
+	dc->dml2_options.bbox_overrides.dram_clock_change_latency_us = dcn3_5_soc.dram_clock_change_latency_us;
+
+	dc->dml2_options.bbox_overrides.sr_exit_latency_us = dcn3_5_soc.sr_exit_time_us;
+	dc->dml2_options.bbox_overrides.sr_enter_plus_exit_latency_us = dcn3_5_soc.sr_enter_plus_exit_time_us;
+
+	dc->dml2_options.bbox_overrides.sr_exit_z8_time_us = dcn3_5_soc.sr_exit_z8_time_us;
+	dc->dml2_options.bbox_overrides.sr_enter_plus_exit_z8_time_us = dcn3_5_soc.sr_enter_plus_exit_z8_time_us;
 }
 
 static bool is_dual_plane(enum surface_pixel_format format)
@@ -507,3 +553,37 @@ int dcn35_populate_dml_pipes_from_context_fpu(struct dc *dc,
 
 	return pipe_cnt;
 }
+
+void dcn35_decide_zstate_support(struct dc *dc, struct dc_state *context)
+{
+	enum dcn_zstate_support_state support = DCN_ZSTATE_SUPPORT_DISALLOW;
+	unsigned int i, plane_count = 0;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (context->res_ctx.pipe_ctx[i].plane_state)
+			plane_count++;
+	}
+
+	if (plane_count == 0) {
+		support = DCN_ZSTATE_SUPPORT_ALLOW;
+	} else if (plane_count == 1 && context->stream_count == 1 && context->streams[0]->signal == SIGNAL_TYPE_EDP) {
+		struct dc_link *link = context->streams[0]->sink->link;
+		bool is_pwrseq0 = link && link->link_index == 0;
+		bool is_psr1 = link && link->psr_settings.psr_version == DC_PSR_VERSION_1 && !link->panel_config.psr.disable_psr;
+		int minmum_z8_residency =
+			dc->debug.minimum_z8_residency_time > 0 ? dc->debug.minimum_z8_residency_time : 1000;
+		bool allow_z8 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z8_residency;
+		int minmum_z10_residency =
+			dc->debug.minimum_z10_residency_time > 0 ? dc->debug.minimum_z10_residency_time : 5000;
+		bool allow_z10 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z10_residency;
+
+		if (is_pwrseq0 && allow_z10)
+			support = DCN_ZSTATE_SUPPORT_ALLOW;
+		else if (is_pwrseq0 && is_psr1)
+			support = allow_z8 ? DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY : DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY;
+		else if (allow_z8)
+			support = DCN_ZSTATE_SUPPORT_ALLOW_Z8_ONLY;
+	}
+
+	context->bw_ctx.bw.dcn.clk.zstate_support = support;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.h
index e8d5a170893e3b..067480fc369132 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.h
@@ -39,4 +39,6 @@ int dcn35_populate_dml_pipes_from_context_fpu(struct dc *dc,
 					      display_e2e_pipe_params_st *pipes,
 					      bool fast_validate);
 
+void dcn35_decide_zstate_support(struct dc *dc, struct dc_state *context);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
index 510be909cd752e..b95bf27f2fe2fe 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
@@ -5420,7 +5420,7 @@ static void CalculateOutputLink(
 					*OutBpp = TruncToValidBPP((1 - Downspreading / 100) * 13500, OutputLinkDPLanes, HTotal, HActive, PixelClockBackEnd, ForcedOutputLinkBPP, LinkDSCEnable, Output,
 												OutputFormat, DSCInputBitPerComponent, NumberOfDSCSlices, (dml_uint_t)AudioSampleRate, AudioSampleLayout, ODMModeNoDSC, ODMModeDSC, RequiredSlots);
 
-					if (OutBpp == 0 && PHYCLKD32PerState < 20000 / 32 && DSCEnable == dml_dsc_enable_if_necessary && ForcedOutputLinkBPP == 0) {
+					if (*OutBpp == 0 && PHYCLKD32PerState < 20000 / 32 && DSCEnable == dml_dsc_enable_if_necessary && ForcedOutputLinkBPP == 0) {
 						*RequiresDSC = true;
 						LinkDSCEnable = true;
 						*OutBpp = TruncToValidBPP((1 - Downspreading / 100) * 13500, OutputLinkDPLanes, HTotal, HActive, PixelClockBackEnd, ForcedOutputLinkBPP, LinkDSCEnable, Output,
@@ -9447,12 +9447,12 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 
 		// Output
 		CalculateWatermarks_params->Watermark = &s->dummy_watermark; // Watermarks *Watermark
-		CalculateWatermarks_params->DRAMClockChangeSupport = &mode_lib->ms.support.DRAMClockChangeSupport[j];
+		CalculateWatermarks_params->DRAMClockChangeSupport = &mode_lib->ms.support.DRAMClockChangeSupport[0];
 		CalculateWatermarks_params->MaxActiveDRAMClockChangeLatencySupported = &s->dummy_single_array[0][0]; // dml_float_t *MaxActiveDRAMClockChangeLatencySupported[]
 		CalculateWatermarks_params->SubViewportLinesNeededInMALL = &mode_lib->ms.SubViewportLinesNeededInMALL[j]; // dml_uint_t SubViewportLinesNeededInMALL[]
-		CalculateWatermarks_params->FCLKChangeSupport = &mode_lib->ms.support.FCLKChangeSupport[j];
+		CalculateWatermarks_params->FCLKChangeSupport = &mode_lib->ms.support.FCLKChangeSupport[0];
 		CalculateWatermarks_params->MaxActiveFCLKChangeLatencySupported = &s->dummy_single[0]; // dml_float_t *MaxActiveFCLKChangeLatencySupported
-		CalculateWatermarks_params->USRRetrainingSupport = &mode_lib->ms.support.USRRetrainingSupport[j];
+		CalculateWatermarks_params->USRRetrainingSupport = &mode_lib->ms.support.USRRetrainingSupport[0];
 
 		CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 			&mode_lib->scratch,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c
index d2046e770c507f..1a2b24cc6b61d5 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c
@@ -55,10 +55,11 @@ struct dc_pipe_mapping_scratch {
 	struct dc_plane_pipe_pool pipe_pool;
 };
 
-static bool get_plane_id(const struct dc_state *state, const struct dc_plane_state *plane,
-	unsigned int stream_id, unsigned int *plane_id)
+static bool get_plane_id(struct dml2_context *dml2, const struct dc_state *state, const struct dc_plane_state *plane,
+	unsigned int stream_id, unsigned int plane_index, unsigned int *plane_id)
 {
 	int i, j;
+	bool is_plane_duplicate = dml2->v20.scratch.plane_duplicate_exists;
 
 	if (!plane_id)
 		return false;
@@ -66,7 +67,8 @@ static bool get_plane_id(const struct dc_state *state, const struct dc_plane_sta
 	for (i = 0; i < state->stream_count; i++) {
 		if (state->streams[i]->stream_id == stream_id) {
 			for (j = 0; j < state->stream_status[i].plane_count; j++) {
-				if (state->stream_status[i].plane_states[j] == plane) {
+				if (state->stream_status[i].plane_states[j] == plane &&
+					(!is_plane_duplicate || (is_plane_duplicate && (j == plane_index)))) {
 					*plane_id = (i << 16) | j;
 					return true;
 				}
@@ -123,8 +125,9 @@ static struct pipe_ctx *find_master_pipe_of_plane(struct dml2_context *ctx,
 	unsigned int plane_id_assigned_to_pipe;
 
 	for (i = 0; i < ctx->config.dcn_pipe_count; i++) {
-		if (state->res_ctx.pipe_ctx[i].plane_state && get_plane_id(state, state->res_ctx.pipe_ctx[i].plane_state,
-			state->res_ctx.pipe_ctx[i].stream->stream_id, &plane_id_assigned_to_pipe)) {
+		if (state->res_ctx.pipe_ctx[i].plane_state && get_plane_id(ctx, state, state->res_ctx.pipe_ctx[i].plane_state,
+			state->res_ctx.pipe_ctx[i].stream->stream_id,
+			ctx->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_plane_index[state->res_ctx.pipe_ctx[i].pipe_idx], &plane_id_assigned_to_pipe)) {
 			if (plane_id_assigned_to_pipe == plane_id)
 				return &state->res_ctx.pipe_ctx[i];
 		}
@@ -141,8 +144,9 @@ static unsigned int find_pipes_assigned_to_plane(struct dml2_context *ctx,
 	unsigned int plane_id_assigned_to_pipe;
 
 	for (i = 0; i < ctx->config.dcn_pipe_count; i++) {
-		if (state->res_ctx.pipe_ctx[i].plane_state && get_plane_id(state, state->res_ctx.pipe_ctx[i].plane_state,
-			state->res_ctx.pipe_ctx[i].stream->stream_id, &plane_id_assigned_to_pipe)) {
+		if (state->res_ctx.pipe_ctx[i].plane_state && get_plane_id(ctx, state, state->res_ctx.pipe_ctx[i].plane_state,
+			state->res_ctx.pipe_ctx[i].stream->stream_id,
+			ctx->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_plane_index[state->res_ctx.pipe_ctx[i].pipe_idx], &plane_id_assigned_to_pipe)) {
 			if (plane_id_assigned_to_pipe == plane_id)
 				pipes[num_found++] = i;
 		}
@@ -609,6 +613,7 @@ static struct pipe_ctx *assign_pipes_to_plane(struct dml2_context *ctx, struct d
 		const struct dc_plane_state *plane,
 		int odm_factor,
 		int mpc_factor,
+		int plane_index,
 		struct dc_plane_pipe_pool *pipe_pool,
 		const struct dc_state *existing_state)
 {
@@ -620,7 +625,7 @@ static struct pipe_ctx *assign_pipes_to_plane(struct dml2_context *ctx, struct d
 	unsigned int next_pipe_to_assign;
 	int odm_slice, mpc_slice;
 
-	if (!get_plane_id(state, plane, stream->stream_id, &plane_id)) {
+	if (!get_plane_id(ctx, state, plane, stream->stream_id, plane_index, &plane_id)) {
 		ASSERT(false);
 		return master_pipe;
 	}
@@ -667,12 +672,16 @@ static void free_pipe(struct pipe_ctx *pipe)
 }
 
 static void free_unused_pipes_for_plane(struct dml2_context *ctx, struct dc_state *state,
-	const struct dc_plane_state *plane, const struct dc_plane_pipe_pool *pool, unsigned int stream_id)
+	const struct dc_plane_state *plane, const struct dc_plane_pipe_pool *pool, unsigned int stream_id, int plane_index)
 {
 	int i;
+	bool is_plane_duplicate = ctx->v20.scratch.plane_duplicate_exists;
+
 	for (i = 0; i < ctx->config.dcn_pipe_count; i++) {
 		if (state->res_ctx.pipe_ctx[i].plane_state == plane &&
 			state->res_ctx.pipe_ctx[i].stream->stream_id == stream_id &&
+			(!is_plane_duplicate || (is_plane_duplicate &&
+			ctx->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_plane_index[state->res_ctx.pipe_ctx[i].pipe_idx] == plane_index)) &&
 			!is_pipe_used(pool, state->res_ctx.pipe_ctx[i].pipe_idx)) {
 			free_pipe(&state->res_ctx.pipe_ctx[i]);
 		}
@@ -717,19 +726,20 @@ static void map_pipes_for_stream(struct dml2_context *ctx, struct dc_state *stat
 }
 
 static void map_pipes_for_plane(struct dml2_context *ctx, struct dc_state *state, const struct dc_stream_state *stream, const struct dc_plane_state *plane,
-		struct dc_pipe_mapping_scratch *scratch, const struct dc_state *existing_state)
+		int plane_index, struct dc_pipe_mapping_scratch *scratch, const struct dc_state *existing_state)
 {
 	int odm_slice_index;
 	unsigned int plane_id;
 	struct pipe_ctx *master_pipe = NULL;
 	int i;
 
-	if (!get_plane_id(state, plane, stream->stream_id, &plane_id)) {
+	if (!get_plane_id(ctx, state, plane, stream->stream_id, plane_index, &plane_id)) {
 		ASSERT(false);
 		return;
 	}
 
-	master_pipe = assign_pipes_to_plane(ctx, state, stream, plane, scratch->odm_info.odm_factor, scratch->mpc_info.mpc_factor, &scratch->pipe_pool, existing_state);
+	master_pipe = assign_pipes_to_plane(ctx, state, stream, plane, scratch->odm_info.odm_factor,
+			scratch->mpc_info.mpc_factor, plane_index, &scratch->pipe_pool, existing_state);
 	sort_pipes_for_splitting(&scratch->pipe_pool);
 
 	for (odm_slice_index = 0; odm_slice_index < scratch->odm_info.odm_factor; odm_slice_index++) {
@@ -755,7 +765,7 @@ static void map_pipes_for_plane(struct dml2_context *ctx, struct dc_state *state
 		}
 	}
 
-	free_unused_pipes_for_plane(ctx, state, plane, &scratch->pipe_pool, stream->stream_id);
+	free_unused_pipes_for_plane(ctx, state, plane, &scratch->pipe_pool, stream->stream_id, plane_index);
 }
 
 static unsigned int get_mpc_factor(struct dml2_context *ctx,
@@ -768,7 +778,7 @@ static unsigned int get_mpc_factor(struct dml2_context *ctx,
 	unsigned int plane_id;
 	unsigned int cfg_idx;
 
-	get_plane_id(state, status->plane_states[plane_idx], stream_id, &plane_id);
+	get_plane_id(ctx, state, status->plane_states[plane_idx], stream_id, plane_idx, &plane_id);
 	cfg_idx = find_disp_cfg_idx_by_plane_id(mapping, plane_id);
 	if (ctx->architecture == dml2_architecture_20)
 		return (unsigned int)disp_cfg->hw.DPPPerSurface[cfg_idx];
@@ -911,26 +921,14 @@ bool dml2_map_dc_pipes(struct dml2_context *ctx, struct dc_state *state, const s
 	unsigned int stream_id;
 
 	const unsigned int *ODMMode, *DPPPerSurface;
-	unsigned int odm_mode_array[__DML2_WRAPPER_MAX_STREAMS_PLANES__] = {0}, dpp_per_surface_array[__DML2_WRAPPER_MAX_STREAMS_PLANES__] = {0};
 	struct dc_pipe_mapping_scratch scratch;
 
 	if (ctx->config.map_dc_pipes_with_callbacks)
 		return map_dc_pipes_with_callbacks(
 				ctx, state, disp_cfg, mapping, existing_state);
 
-	if (ctx->architecture == dml2_architecture_21) {
-		/*
-		 * Extract ODM and DPP outputs from DML2.1 and map them in an array as required for pipe mapping in dml2_map_dc_pipes.
-		 * As data cannot be directly extracted in const pointers, assign these arrays to const pointers before proceeding to
-		 * maximize the reuse of existing code. Const pointers are required because dml2.0 dml_display_cfg_st is const.
-		 *
-		 */
-		ODMMode = (const unsigned int *)odm_mode_array;
-		DPPPerSurface = (const unsigned int *)dpp_per_surface_array;
-	} else {
-		ODMMode = (unsigned int *)disp_cfg->hw.ODMMode;
-		DPPPerSurface = disp_cfg->hw.DPPPerSurface;
-	}
+	ODMMode = (unsigned int *)disp_cfg->hw.ODMMode;
+	DPPPerSurface = disp_cfg->hw.DPPPerSurface;
 
 	for (stream_index = 0; stream_index < state->stream_count; stream_index++) {
 		memset(&scratch, 0, sizeof(struct dc_pipe_mapping_scratch));
@@ -958,8 +956,8 @@ bool dml2_map_dc_pipes(struct dml2_context *ctx, struct dc_state *state, const s
 
 		for (plane_index = 0; plane_index < state->stream_status[stream_index].plane_count; plane_index++) {
 			// Planes are ordered top to bottom.
-			if (get_plane_id(state, state->stream_status[stream_index].plane_states[plane_index],
-				stream_id, &plane_id)) {
+			if (get_plane_id(ctx, state, state->stream_status[stream_index].plane_states[plane_index],
+				stream_id, plane_index, &plane_id)) {
 				plane_disp_cfg_index = find_disp_cfg_idx_by_plane_id(mapping, plane_id);
 
 				// Setup mpc_info for this plane
@@ -983,7 +981,8 @@ bool dml2_map_dc_pipes(struct dml2_context *ctx, struct dc_state *state, const s
 				// Clear the pool assignment scratch (which is per plane)
 				memset(&scratch.pipe_pool, 0, sizeof(struct dc_plane_pipe_pool));
 
-				map_pipes_for_plane(ctx, state, state->streams[stream_index], state->stream_status[stream_index].plane_states[plane_index], &scratch, existing_state);
+				map_pipes_for_plane(ctx, state, state->streams[stream_index],
+					state->stream_status[stream_index].plane_states[plane_index], plane_index, &scratch, existing_state);
 			} else {
 				// Plane ID cannot be generated, therefore no DML mapping can be performed.
 				ASSERT(false);
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_internal_types.h b/drivers/gpu/drm/amd/display/dc/dml2/dml2_internal_types.h
index ed5b767d46e030..1cf8a884c0fbef 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_internal_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_internal_types.h
@@ -75,6 +75,8 @@ struct dml2_dml_to_dc_pipe_mapping {
 	bool dml_pipe_idx_to_stream_id_valid[__DML2_WRAPPER_MAX_STREAMS_PLANES__];
 	unsigned int dml_pipe_idx_to_plane_id[__DML2_WRAPPER_MAX_STREAMS_PLANES__];
 	bool dml_pipe_idx_to_plane_id_valid[__DML2_WRAPPER_MAX_STREAMS_PLANES__];
+	unsigned int dml_pipe_idx_to_plane_index[__DML2_WRAPPER_MAX_STREAMS_PLANES__];
+	bool dml_pipe_idx_to_plane_index_valid[__DML2_WRAPPER_MAX_STREAMS_PLANES__];
 };
 
 struct dml2_wrapper_scratch {
@@ -96,6 +98,7 @@ struct dml2_wrapper_scratch {
 
 	struct dml2_dml_to_dc_pipe_mapping dml_to_dc_pipe_mapping;
 	bool enable_flexible_pipe_mapping;
+	bool plane_duplicate_exists;
 };
 
 struct dml2_helper_det_policy_scratch {
@@ -104,7 +107,6 @@ struct dml2_helper_det_policy_scratch {
 
 enum dml2_architecture {
 	dml2_architecture_20,
-	dml2_architecture_21
 };
 
 struct dml2_context {
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 89836f175a138e..db06a5b749b408 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -231,6 +231,7 @@ void dml2_init_socbb_params(struct dml2_context *dml2, const struct dc *in_dc, s
 		out->num_chans = 4;
 		out->round_trip_ping_latency_dcfclk_cycles = 106;
 		out->smn_latency_us = 2;
+		out->dispclk_dppclk_vco_speed_mhz = 3600;
 		break;
 
 	case dml_project_dcn351:
@@ -340,25 +341,42 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 		break;
 	}
 
-	/* Override from passed values, mainly for debugging purposes, if available */
-	if (dml2->config.bbox_overrides.sr_exit_latency_us) {
-		p->in_states->state_array[0].sr_exit_time_us = dml2->config.bbox_overrides.sr_exit_latency_us;
-	}
+	/* Override from passed values, if available */
+	for (i = 0; i < p->in_states->num_states; i++) {
+		if (dml2->config.bbox_overrides.sr_exit_latency_us) {
+			p->in_states->state_array[i].sr_exit_time_us =
+				dml2->config.bbox_overrides.sr_exit_latency_us;
+		}
 
-	if (dml2->config.bbox_overrides.sr_enter_plus_exit_latency_us) {
-		p->in_states->state_array[0].sr_enter_plus_exit_time_us = dml2->config.bbox_overrides.sr_enter_plus_exit_latency_us;
-	}
+		if (dml2->config.bbox_overrides.sr_enter_plus_exit_latency_us) {
+			p->in_states->state_array[i].sr_enter_plus_exit_time_us =
+				dml2->config.bbox_overrides.sr_enter_plus_exit_latency_us;
+		}
 
-	if (dml2->config.bbox_overrides.urgent_latency_us) {
-		p->in_states->state_array[0].urgent_latency_pixel_data_only_us = dml2->config.bbox_overrides.urgent_latency_us;
-	}
+		if (dml2->config.bbox_overrides.sr_exit_z8_time_us) {
+			p->in_states->state_array[i].sr_exit_z8_time_us =
+				dml2->config.bbox_overrides.sr_exit_z8_time_us;
+		}
 
-	if (dml2->config.bbox_overrides.dram_clock_change_latency_us) {
-		p->in_states->state_array[0].dram_clock_change_latency_us = dml2->config.bbox_overrides.dram_clock_change_latency_us;
-	}
+		if (dml2->config.bbox_overrides.sr_enter_plus_exit_z8_time_us) {
+			p->in_states->state_array[i].sr_enter_plus_exit_z8_time_us =
+				dml2->config.bbox_overrides.sr_enter_plus_exit_z8_time_us;
+		}
 
-	if (dml2->config.bbox_overrides.fclk_change_latency_us) {
-		p->in_states->state_array[0].fclk_change_latency_us = dml2->config.bbox_overrides.fclk_change_latency_us;
+		if (dml2->config.bbox_overrides.urgent_latency_us) {
+			p->in_states->state_array[i].urgent_latency_pixel_data_only_us =
+				dml2->config.bbox_overrides.urgent_latency_us;
+		}
+
+		if (dml2->config.bbox_overrides.dram_clock_change_latency_us) {
+			p->in_states->state_array[i].dram_clock_change_latency_us =
+				dml2->config.bbox_overrides.dram_clock_change_latency_us;
+		}
+
+		if (dml2->config.bbox_overrides.fclk_change_latency_us) {
+			p->in_states->state_array[i].fclk_change_latency_us =
+				dml2->config.bbox_overrides.fclk_change_latency_us;
+		}
 	}
 
 	/* DCFCLK stas values are project specific */
@@ -405,8 +423,9 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 		}
 
 		for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dtbclk_levels; i++) {
-			p->in_states->state_array[i].dtbclk_mhz =
-				dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz;
+			if (dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz > 0)
+				p->in_states->state_array[i].dtbclk_mhz =
+					dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz;
 		}
 
 		for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dispclk_levels; i++) {
@@ -497,8 +516,8 @@ void dml2_translate_socbb_params(const struct dc *in, struct soc_bounding_box_st
 	out->do_urgent_latency_adjustment = in_soc_params->do_urgent_latency_adjustment;
 	out->dram_channel_width_bytes = (dml_uint_t)in_soc_params->dram_channel_width_bytes;
 	out->fabric_datapath_to_dcn_data_return_bytes = (dml_uint_t)in_soc_params->fabric_datapath_to_dcn_data_return_bytes;
-	out->gpuvm_min_page_size_kbytes = in_soc_params->gpuvm_min_page_size_bytes * 1024;
-	out->hostvm_min_page_size_kbytes = in_soc_params->hostvm_min_page_size_bytes * 1024;
+	out->gpuvm_min_page_size_kbytes = in_soc_params->gpuvm_min_page_size_bytes / 1024;
+	out->hostvm_min_page_size_kbytes = in_soc_params->hostvm_min_page_size_bytes / 1024;
 	out->mall_allocated_for_dcn_mbytes = (dml_uint_t)in_soc_params->mall_allocated_for_dcn_mbytes;
 	out->max_avg_dram_bw_use_normal_percent = in_soc_params->max_avg_dram_bw_use_normal_percent;
 	out->max_avg_fabric_bw_use_normal_percent = in_soc_params->max_avg_fabric_bw_use_normal_percent;
@@ -930,10 +949,11 @@ static unsigned int map_stream_to_dml_display_cfg(const struct dml2_context *dml
 	return location;
 }
 
-static bool get_plane_id(const struct dc_state *context, const struct dc_plane_state *plane,
-		unsigned int stream_id, unsigned int *plane_id)
+static bool get_plane_id(struct dml2_context *dml2, const struct dc_state *context, const struct dc_plane_state *plane,
+		unsigned int stream_id, unsigned int plane_index, unsigned int *plane_id)
 {
 	int i, j;
+	bool is_plane_duplicate = dml2->v20.scratch.plane_duplicate_exists;
 
 	if (!plane_id)
 		return false;
@@ -941,7 +961,8 @@ static bool get_plane_id(const struct dc_state *context, const struct dc_plane_s
 	for (i = 0; i < context->stream_count; i++) {
 		if (context->streams[i]->stream_id == stream_id) {
 			for (j = 0; j < context->stream_status[i].plane_count; j++) {
-				if (context->stream_status[i].plane_states[j] == plane) {
+				if (context->stream_status[i].plane_states[j] == plane &&
+					(!is_plane_duplicate || (is_plane_duplicate && (j == plane_index)))) {
 					*plane_id = (i << 16) | j;
 					return true;
 				}
@@ -953,13 +974,13 @@ static bool get_plane_id(const struct dc_state *context, const struct dc_plane_s
 }
 
 static unsigned int map_plane_to_dml_display_cfg(const struct dml2_context *dml2, const struct dc_plane_state *plane,
-		const struct dc_state *context, const struct dml_display_cfg_st *dml_dispcfg, unsigned int stream_id)
+		const struct dc_state *context, const struct dml_display_cfg_st *dml_dispcfg, unsigned int stream_id, int plane_index)
 {
 	unsigned int plane_id;
 	int i = 0;
 	int location = -1;
 
-	if (!get_plane_id(context, plane, stream_id, &plane_id)) {
+	if (!get_plane_id(context->bw_ctx.dml2, context, plane, stream_id, plane_index, &plane_id)) {
 		ASSERT(false);
 		return -1;
 	}
@@ -990,7 +1011,41 @@ static void apply_legacy_svp_drr_settings(struct dml2_context *dml2, const struc
 	}
 }
 
-void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, const struct dc_state *context, struct dml_display_cfg_st *dml_dispcfg)
+static void dml2_populate_pipe_to_plane_index_mapping(struct dml2_context *dml2, struct dc_state *state)
+{
+	unsigned int i;
+	unsigned int pipe_index = 0;
+	unsigned int plane_index = 0;
+	struct dml2_dml_to_dc_pipe_mapping *dml_to_dc_pipe_mapping = &dml2->v20.scratch.dml_to_dc_pipe_mapping;
+
+	for (i = 0; i < __DML2_WRAPPER_MAX_STREAMS_PLANES__; i++) {
+		dml_to_dc_pipe_mapping->dml_pipe_idx_to_plane_index_valid[i] = false;
+		dml_to_dc_pipe_mapping->dml_pipe_idx_to_plane_index[i] = 0;
+	}
+
+	for (i = 0; i < __DML2_WRAPPER_MAX_STREAMS_PLANES__; i++) {
+		struct pipe_ctx *pipe = &state->res_ctx.pipe_ctx[i];
+
+		if (!pipe || !pipe->stream || !pipe->plane_state)
+			continue;
+
+		while (pipe) {
+			pipe_index = pipe->pipe_idx;
+
+			if (pipe->stream && dml_to_dc_pipe_mapping->dml_pipe_idx_to_plane_index_valid[pipe_index] == false) {
+				dml_to_dc_pipe_mapping->dml_pipe_idx_to_plane_index[pipe_index] = plane_index;
+				plane_index++;
+				dml_to_dc_pipe_mapping->dml_pipe_idx_to_plane_index_valid[pipe_index] = true;
+			}
+
+			pipe = pipe->bottom_pipe;
+		}
+
+		plane_index = 0;
+	}
+}
+
+void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, struct dc_state *context, struct dml_display_cfg_st *dml_dispcfg)
 {
 	int i = 0, j = 0;
 	int disp_cfg_stream_location, disp_cfg_plane_location;
@@ -1003,9 +1058,14 @@ void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, const struct d
 	}
 
 	//Generally these are set by referencing our latest BB/IP params in dcn32_resource.c file
-	dml_dispcfg->plane.GPUVMEnable = true;
-	dml_dispcfg->plane.GPUVMMaxPageTableLevels = 4;
-	dml_dispcfg->plane.HostVMEnable = false;
+	dml_dispcfg->plane.GPUVMEnable = dml2->v20.dml_core_ctx.ip.gpuvm_enable;
+	dml_dispcfg->plane.GPUVMMaxPageTableLevels = dml2->v20.dml_core_ctx.ip.gpuvm_max_page_table_levels;
+	dml_dispcfg->plane.HostVMEnable = dml2->v20.dml_core_ctx.ip.hostvm_enable;
+	dml_dispcfg->plane.HostVMMaxPageTableLevels = dml2->v20.dml_core_ctx.ip.hostvm_max_page_table_levels;
+	if (dml2->v20.dml_core_ctx.ip.hostvm_enable)
+		dml2->v20.dml_core_ctx.policy.AllowForPStateChangeOrStutterInVBlankFinal = dml_prefetch_support_uclk_fclk_and_stutter;
+
+	dml2_populate_pipe_to_plane_index_mapping(dml2, context);
 
 	for (i = 0; i < context->stream_count; i++) {
 		disp_cfg_stream_location = map_stream_to_dml_display_cfg(dml2, context->streams[i], dml_dispcfg);
@@ -1043,7 +1103,7 @@ void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, const struct d
 		} else {
 			for (j = 0; j < context->stream_status[i].plane_count; j++) {
 				disp_cfg_plane_location = map_plane_to_dml_display_cfg(dml2,
-					context->stream_status[i].plane_states[j], context, dml_dispcfg, context->streams[i]->stream_id);
+					context->stream_status[i].plane_states[j], context, dml_dispcfg, context->streams[i]->stream_id, j);
 
 				if (disp_cfg_plane_location < 0)
 					disp_cfg_plane_location = dml_dispcfg->num_surfaces++;
@@ -1067,7 +1127,7 @@ void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, const struct d
 
 				dml_dispcfg->plane.BlendingAndTiming[disp_cfg_plane_location] = disp_cfg_stream_location;
 
-				if (get_plane_id(context, context->stream_status[i].plane_states[j], context->streams[i]->stream_id,
+				if (get_plane_id(dml2, context, context->stream_status[i].plane_states[j], context->streams[i]->stream_id, j,
 					&dml2->v20.scratch.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[disp_cfg_plane_location]))
 					dml2->v20.scratch.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id_valid[disp_cfg_plane_location] = true;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.h b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.h
index dac6d27b14cde6..d764773938f4ef 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.h
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.h
@@ -34,7 +34,7 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 void dml2_translate_ip_params(const struct dc *in_dc, struct ip_params_st *out);
 void dml2_translate_socbb_params(const struct dc *in_dc, struct soc_bounding_box_st *out);
 void dml2_translate_soc_states(const struct dc *in_dc, struct soc_states_st *out, int num_states);
-void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, const struct dc_state *context, struct dml_display_cfg_st *dml_dispcfg);
+void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, struct dc_state *context, struct dml_display_cfg_st *dml_dispcfg);
 void dml2_update_pipe_ctx_dchub_regs(struct _vcs_dpi_dml_display_rq_regs_st *rq_regs, struct _vcs_dpi_dml_display_dlg_regs_st *disp_dlg_regs, struct _vcs_dpi_dml_display_ttu_regs_st *disp_ttu_regs, struct pipe_ctx *out);
 bool is_dp2p0_output_encoder(const struct pipe_ctx *pipe);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_utils.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_utils.c
index 69fd96f4f3b037..2498b8341199ba 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_utils.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_utils.c
@@ -209,10 +209,11 @@ static int find_dml_pipe_idx_by_plane_id(struct dml2_context *ctx, unsigned int
 	return -1;
 }
 
-static bool get_plane_id(const struct dc_state *state, const struct dc_plane_state *plane,
-	unsigned int stream_id, unsigned int *plane_id)
+static bool get_plane_id(struct dml2_context *dml2, const struct dc_state *state, const struct dc_plane_state *plane,
+	unsigned int stream_id, unsigned int plane_index, unsigned int *plane_id)
 {
 	int i, j;
+	bool is_plane_duplicate = dml2->v20.scratch.plane_duplicate_exists;
 
 	if (!plane_id)
 		return false;
@@ -220,7 +221,8 @@ static bool get_plane_id(const struct dc_state *state, const struct dc_plane_sta
 	for (i = 0; i < state->stream_count; i++) {
 		if (state->streams[i]->stream_id == stream_id) {
 			for (j = 0; j < state->stream_status[i].plane_count; j++) {
-				if (state->stream_status[i].plane_states[j] == plane) {
+				if (state->stream_status[i].plane_states[j] == plane &&
+					(!is_plane_duplicate || (is_plane_duplicate && (j == plane_index)))) {
 					*plane_id = (i << 16) | j;
 					return true;
 				}
@@ -304,8 +306,9 @@ void dml2_calculate_rq_and_dlg_params(const struct dc *dc, struct dc_state *cont
 		 * there is a need to know which DML pipe index maps to which DC pipe. The code below
 		 * finds a dml_pipe_index from the plane id if a plane is valid. If a plane is not valid then
 		 * it finds a dml_pipe_index from the stream id. */
-		if (get_plane_id(context, context->res_ctx.pipe_ctx[dc_pipe_ctx_index].plane_state,
-			context->res_ctx.pipe_ctx[dc_pipe_ctx_index].stream->stream_id, &plane_id)) {
+		if (get_plane_id(in_ctx, context, context->res_ctx.pipe_ctx[dc_pipe_ctx_index].plane_state,
+			context->res_ctx.pipe_ctx[dc_pipe_ctx_index].stream->stream_id,
+			in_ctx->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_plane_index[context->res_ctx.pipe_ctx[dc_pipe_ctx_index].pipe_idx], &plane_id)) {
 			dml_pipe_idx = find_dml_pipe_idx_by_plane_id(in_ctx, plane_id);
 		} else {
 			dml_pipe_idx = dml2_helper_find_dml_pipe_idx_by_stream_id(in_ctx, context->res_ctx.pipe_ctx[dc_pipe_ctx_index].stream->stream_id);
@@ -445,8 +448,9 @@ bool dml2_verify_det_buffer_configuration(struct dml2_context *in_ctx, struct dc
 	for (i = 0; i < MAX_PIPES; i++) {
 		if (!display_state->res_ctx.pipe_ctx[i].stream)
 			continue;
-		if (get_plane_id(display_state, display_state->res_ctx.pipe_ctx[i].plane_state,
-			display_state->res_ctx.pipe_ctx[i].stream->stream_id, &plane_id))
+		if (get_plane_id(in_ctx, display_state, display_state->res_ctx.pipe_ctx[i].plane_state,
+			display_state->res_ctx.pipe_ctx[i].stream->stream_id,
+			in_ctx->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_plane_index[display_state->res_ctx.pipe_ctx[i].pipe_idx], &plane_id))
 			dml_pipe_idx = find_dml_pipe_idx_by_plane_id(in_ctx, plane_id);
 		else
 			dml_pipe_idx = dml2_helper_find_dml_pipe_idx_by_stream_id(in_ctx, display_state->res_ctx.pipe_ctx[i].stream->stream_id);
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
index 0a06bf3b135aa6..8f231418870f2a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
@@ -639,7 +639,7 @@ static bool dml2_validate_and_build_resource(const struct dc *in_dc, struct dc_s
 	return result;
 }
 
-static bool dml2_validate_only(const struct dc_state *context)
+static bool dml2_validate_only(struct dc_state *context)
 {
 	struct dml2_context *dml2 = context->bw_ctx.dml2;
 	unsigned int result = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
index 317f90776d972e..fe15baa4bf0948 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
@@ -139,6 +139,8 @@ struct dml2_soc_bbox_overrides {
 	double urgent_latency_us;
 	double sr_exit_latency_us;
 	double sr_enter_plus_exit_latency_us;
+	double sr_exit_z8_time_us;
+	double sr_enter_plus_exit_z8_time_us;
 	double dram_clock_change_latency_us;
 	double fclk_change_latency_us;
 	unsigned int dram_num_chan;
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
index 3966845c769453..e8b5f17beb9636 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
@@ -512,6 +512,11 @@ static bool intersect_dsc_caps(
 		dsc_sink_caps->slice_caps1.bits.NUM_SLICES_4 && dsc_enc_caps->slice_caps.bits.NUM_SLICES_4;
 	dsc_common_caps->slice_caps.bits.NUM_SLICES_8 =
 		dsc_sink_caps->slice_caps1.bits.NUM_SLICES_8 && dsc_enc_caps->slice_caps.bits.NUM_SLICES_8;
+	dsc_common_caps->slice_caps.bits.NUM_SLICES_12 =
+		dsc_sink_caps->slice_caps1.bits.NUM_SLICES_12 && dsc_enc_caps->slice_caps.bits.NUM_SLICES_12;
+	dsc_common_caps->slice_caps.bits.NUM_SLICES_16 =
+		dsc_sink_caps->slice_caps2.bits.NUM_SLICES_16 && dsc_enc_caps->slice_caps.bits.NUM_SLICES_16;
+
 	if (!dsc_common_caps->slice_caps.raw)
 		return false;
 
@@ -703,6 +708,12 @@ static int get_available_dsc_slices(union dsc_enc_slice_caps slice_caps, int *av
 	if (slice_caps.bits.NUM_SLICES_8)
 		available_slices[idx++] = 8;
 
+	if (slice_caps.bits.NUM_SLICES_12)
+		available_slices[idx++] = 12;
+
+	if (slice_caps.bits.NUM_SLICES_16)
+		available_slices[idx++] = 16;
+
 	return idx;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dce/dce_hwseq.h
index 2fefdf40612da8..44b4df6469d1aa 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce/dce_hwseq.h
@@ -1183,7 +1183,23 @@ struct dce_hwseq_registers {
 	type LONO_FGCG_REP_DIS;\
 	type LONO_DISPCLK_GATE_DISABLE;\
 	type LONO_SOCCLK_GATE_DISABLE;\
-	type LONO_DMCUBCLK_GATE_DISABLE;
+	type LONO_DMCUBCLK_GATE_DISABLE;\
+	type SYMCLKA_FE_GATE_DISABLE;\
+	type SYMCLKB_FE_GATE_DISABLE;\
+	type SYMCLKC_FE_GATE_DISABLE;\
+	type SYMCLKD_FE_GATE_DISABLE;\
+	type SYMCLKE_FE_GATE_DISABLE;\
+	type HDMICHARCLK0_GATE_DISABLE;\
+	type SYMCLKA_GATE_DISABLE;\
+	type SYMCLKB_GATE_DISABLE;\
+	type SYMCLKC_GATE_DISABLE;\
+	type SYMCLKD_GATE_DISABLE;\
+	type SYMCLKE_GATE_DISABLE;\
+	type PHYASYMCLK_ROOT_GATE_DISABLE;\
+	type PHYBSYMCLK_ROOT_GATE_DISABLE;\
+	type PHYCSYMCLK_ROOT_GATE_DISABLE;\
+	type PHYDSYMCLK_ROOT_GATE_DISABLE;\
+	type PHYESYMCLK_ROOT_GATE_DISABLE;
 
 struct dce_hwseq_shift {
 	HWSEQ_REG_FIELD_LIST(uint8_t)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
index 2b8b8366538e96..cdb903116eb7ca 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
@@ -3417,7 +3417,8 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz,
 		.v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert,
 		.rotation = pipe_ctx->plane_state->rotation,
-		.mirror = pipe_ctx->plane_state->horizontal_mirror
+		.mirror = pipe_ctx->plane_state->horizontal_mirror,
+		.stream = pipe_ctx->stream,
 	};
 	bool pipe_split_on = false;
 	bool odm_combine_on = (pipe_ctx->next_odm_pipe != NULL) ||
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
index 1b9f21fd4f1732..c1a9b746c43fef 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
@@ -487,8 +487,7 @@ bool dcn32_set_mcm_luts(
 		if (plane_state->blend_tf->type == TF_TYPE_HWPWL)
 			lut_params = &plane_state->blend_tf->pwl;
 		else if (plane_state->blend_tf->type == TF_TYPE_DISTRIBUTED_POINTS) {
-			cm_helper_translate_curve_to_hw_format(plane_state->ctx,
-					plane_state->blend_tf,
+			cm3_helper_translate_curve_to_hw_format(plane_state->blend_tf,
 					&dpp_base->regamma_params, false);
 			lut_params = &dpp_base->regamma_params;
 		}
@@ -503,8 +502,7 @@ bool dcn32_set_mcm_luts(
 		else if (plane_state->in_shaper_func->type == TF_TYPE_DISTRIBUTED_POINTS) {
 			// TODO: dpp_base replace
 			ASSERT(false);
-			cm_helper_translate_curve_to_hw_format(plane_state->ctx,
-					plane_state->in_shaper_func,
+			cm3_helper_translate_curve_to_hw_format(plane_state->in_shaper_func,
 					&dpp_base->shaper_params, true);
 			lut_params = &dpp_base->shaper_params;
 		}
@@ -615,12 +613,6 @@ void dcn32_update_force_pstate(struct dc *dc, struct dc_state *context)
 		    pipe->stream->fpo_in_use)) {
 			if (hubp && hubp->funcs->hubp_update_force_pstate_disallow)
 				hubp->funcs->hubp_update_force_pstate_disallow(hubp, false);
-		}
-
-		/* Today only FPO uses cursor P-State force. Only clear cursor P-State force
-		 * if it's not FPO.
-		 */
-		if (!pipe->stream || !pipe->stream->fpo_in_use) {
 			if (hubp && hubp->funcs->hubp_update_force_cursor_pstate_disallow)
 				hubp->funcs->hubp_update_force_cursor_pstate_disallow(hubp, false);
 		}
@@ -632,17 +624,10 @@ void dcn32_update_force_pstate(struct dc *dc, struct dc_state *context)
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 		struct hubp *hubp = pipe->plane_res.hubp;
 
-		if (pipe->stream && pipe->plane_state && pipe->stream->mall_stream_config.type == SUBVP_MAIN) {
+		if (pipe->stream && (pipe->stream->mall_stream_config.type == SUBVP_MAIN ||
+				pipe->stream->fpo_in_use)) {
 			if (hubp && hubp->funcs->hubp_update_force_pstate_disallow)
 				hubp->funcs->hubp_update_force_pstate_disallow(hubp, true);
-		}
-
-		if (pipe->stream && pipe->stream->fpo_in_use) {
-			if (hubp && hubp->funcs->hubp_update_force_pstate_disallow)
-				hubp->funcs->hubp_update_force_pstate_disallow(hubp, true);
-			/* For now only force cursor p-state disallow for FPO
-			 * Needs to be added for subvp once FW side gets updated
-			 */
 			if (hubp && hubp->funcs->hubp_update_force_cursor_pstate_disallow)
 				hubp->funcs->hubp_update_force_cursor_pstate_disallow(hubp, true);
 		}
@@ -975,6 +960,12 @@ void dcn32_init_hw(struct dc *dc)
 		dc->caps.dmub_caps.subvp_psr = dc->ctx->dmub_srv->dmub->feature_caps.subvp_psr_support;
 		dc->caps.dmub_caps.gecc_enable = dc->ctx->dmub_srv->dmub->feature_caps.gecc_enable;
 		dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch;
+
+		if (dc->ctx->dmub_srv->dmub->fw_version <
+		    DMUB_FW_VERSION(7, 0, 35)) {
+			dc->debug.force_disable_subvp = true;
+			dc->debug.disable_fpo_optimizations = true;
+		}
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index 34737d60b965b8..5a8258287438e9 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -138,16 +138,25 @@ void dcn35_init_hw(struct dc *dc)
 	if (dc->clk_mgr && dc->clk_mgr->funcs->init_clocks)
 		dc->clk_mgr->funcs->init_clocks(dc->clk_mgr);
 
-	REG_WRITE(DCCG_GATE_DISABLE_CNTL, 0);
-	REG_WRITE(DCCG_GATE_DISABLE_CNTL2, 0x3F000000);
-	REG_WRITE(DCCG_GATE_DISABLE_CNTL5, 0x1f7c3fcf);
-
 	//dcn35_set_dmu_fgcg(hws, dc->debug.enable_fine_grain_clock_gating.bits.dmu);
 
 	if (!dcb->funcs->is_accelerated_mode(dcb)) {
 		/*this calls into dmubfw to do the init*/
 		hws->funcs.bios_golden_init(dc);
 	}
+
+	REG_WRITE(DCCG_GATE_DISABLE_CNTL, 0);
+	REG_WRITE(DCCG_GATE_DISABLE_CNTL2,  0);
+
+	/* Disable gating for PHYASYMCLK. This will be enabled in dccg if needed */
+	REG_UPDATE_5(DCCG_GATE_DISABLE_CNTL2, PHYASYMCLK_ROOT_GATE_DISABLE, 1,
+			PHYBSYMCLK_ROOT_GATE_DISABLE, 1,
+			PHYCSYMCLK_ROOT_GATE_DISABLE, 1,
+			PHYDSYMCLK_ROOT_GATE_DISABLE, 1,
+			PHYESYMCLK_ROOT_GATE_DISABLE, 1);
+
+	REG_WRITE(DCCG_GATE_DISABLE_CNTL5, 0x1f7c3fcf);
+
 	// Initialize the dccg
 	if (res_pool->dccg->funcs->dccg_init)
 		res_pool->dccg->funcs->dccg_init(res_pool->dccg);
@@ -274,7 +283,19 @@ void dcn35_init_hw(struct dc *dc)
 	if (!dc->debug.disable_clock_gate) {
 		/* enable all DCN clock gating */
 		REG_WRITE(DCCG_GATE_DISABLE_CNTL, 0);
-		REG_WRITE(DCCG_GATE_DISABLE_CNTL2, 0);
+
+		REG_UPDATE_5(DCCG_GATE_DISABLE_CNTL2, SYMCLKA_FE_GATE_DISABLE, 0,
+				SYMCLKB_FE_GATE_DISABLE, 0,
+				SYMCLKC_FE_GATE_DISABLE, 0,
+				SYMCLKD_FE_GATE_DISABLE, 0,
+				SYMCLKE_FE_GATE_DISABLE, 0);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL2, HDMICHARCLK0_GATE_DISABLE, 0);
+		REG_UPDATE_5(DCCG_GATE_DISABLE_CNTL2, SYMCLKA_GATE_DISABLE, 0,
+				SYMCLKB_GATE_DISABLE, 0,
+				SYMCLKC_GATE_DISABLE, 0,
+				SYMCLKD_GATE_DISABLE, 0,
+				SYMCLKE_GATE_DISABLE, 0);
+
 		REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0);
 	}
 
@@ -311,6 +332,9 @@ void dcn35_init_hw(struct dc *dc)
 	if (dc->res_pool->pg_cntl) {
 		if (dc->res_pool->pg_cntl->funcs->init_pg_status)
 			dc->res_pool->pg_cntl->funcs->init_pg_status(dc->res_pool->pg_cntl);
+
+		if (dc->res_pool->pg_cntl->funcs->set_force_poweron_domain22)
+			dc->res_pool->pg_cntl->funcs->set_force_poweron_domain22(dc->res_pool->pg_cntl, false);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h
index 13f12f2a3f8133..ce2f0c0e82bd65 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h
@@ -141,6 +141,11 @@ struct dccg_funcs {
 			enum physymclk_clock_source clk_src,
 			bool force_enable);
 
+	void (*set_physymclk_root_clock_gating)(
+			struct dccg *dccg,
+			int phy_inst,
+			bool enable);
+
 	void (*set_dtbclk_dto)(
 			struct dccg *dccg,
 			const struct dtbclk_dto_params *params);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
index d7b8d586b5237e..4b27f29d0d80d9 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
@@ -76,6 +76,8 @@ union dsc_enc_slice_caps {
 		uint8_t NUM_SLICES_3 : 1; /* This one is not per DSC spec, but our encoder supports it */
 		uint8_t NUM_SLICES_4 : 1;
 		uint8_t NUM_SLICES_8 : 1;
+		uint8_t NUM_SLICES_12 : 1;
+		uint8_t NUM_SLICES_16 : 1;
 	} bits;
 	uint8_t raw;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/optc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/optc.h
new file mode 100644
index 00000000000000..9a8bf6ec70ea66
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/optc.h
@@ -0,0 +1,219 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright 2023 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+/**
+ * DOC: overview
+ *
+ * Output Pipe Timing Combiner (OPTC) includes two major functional blocks:
+ * Output Data Mapper (ODM) and Output Timing Generator (OTG).
+ *
+ * - ODM: It is Output Data Mapping block. It can combine input data from
+ *   multiple OPP data pipes into one single data stream or split data from one
+ *   OPP data pipe into multiple data streams or just bypass OPP data to DIO.
+ * - OTG: It is Output Timing Generator. It generates display timing signals to
+ *   drive the display output.
+ */
+
+#ifndef __DC_OPTC_H__
+#define __DC_OPTC_H__
+
+#include "timing_generator.h"
+
+struct optc {
+	struct timing_generator base;
+
+	const struct dcn_optc_registers *tg_regs;
+	const struct dcn_optc_shift *tg_shift;
+	const struct dcn_optc_mask *tg_mask;
+
+	int opp_count;
+
+	uint32_t max_h_total;
+	uint32_t max_v_total;
+
+	uint32_t min_h_blank;
+
+	uint32_t min_h_sync_width;
+	uint32_t min_v_sync_width;
+	uint32_t min_v_blank;
+	uint32_t min_v_blank_interlace;
+
+	int vstartup_start;
+	int vupdate_offset;
+	int vupdate_width;
+	int vready_offset;
+	struct dc_crtc_timing orginal_patched_timing;
+	enum signal_type signal;
+};
+
+struct dcn_otg_state {
+	uint32_t v_blank_start;
+	uint32_t v_blank_end;
+	uint32_t v_sync_a_pol;
+	uint32_t v_total;
+	uint32_t v_total_max;
+	uint32_t v_total_min;
+	uint32_t v_total_min_sel;
+	uint32_t v_total_max_sel;
+	uint32_t v_sync_a_start;
+	uint32_t v_sync_a_end;
+	uint32_t h_blank_start;
+	uint32_t h_blank_end;
+	uint32_t h_sync_a_start;
+	uint32_t h_sync_a_end;
+	uint32_t h_sync_a_pol;
+	uint32_t h_total;
+	uint32_t underflow_occurred_status;
+	uint32_t otg_enabled;
+	uint32_t blank_enabled;
+	uint32_t vertical_interrupt1_en;
+	uint32_t vertical_interrupt1_line;
+	uint32_t vertical_interrupt2_en;
+	uint32_t vertical_interrupt2_line;
+};
+
+void optc1_read_otg_state(struct optc *optc1, struct dcn_otg_state *s);
+
+bool optc1_get_hw_timing(struct timing_generator *tg, struct dc_crtc_timing *hw_crtc_timing);
+
+bool optc1_validate_timing(struct timing_generator *optc,
+			   const struct dc_crtc_timing *timing);
+
+void optc1_program_timing(struct timing_generator *optc,
+			  const struct dc_crtc_timing *dc_crtc_timing,
+			  int vready_offset,
+			  int vstartup_start,
+			  int vupdate_offset,
+			  int vupdate_width,
+			  const enum signal_type signal,
+			  bool use_vbios);
+
+void optc1_setup_vertical_interrupt0(struct timing_generator *optc,
+				     uint32_t start_line,
+				     uint32_t end_line);
+
+void optc1_setup_vertical_interrupt1(struct timing_generator *optc,
+				     uint32_t start_line);
+
+void optc1_setup_vertical_interrupt2(struct timing_generator *optc,
+				     uint32_t start_line);
+
+void optc1_program_global_sync(struct timing_generator *optc,
+			       int vready_offset,
+			       int vstartup_start,
+			       int vupdate_offset,
+			       int vupdate_width);
+
+bool optc1_disable_crtc(struct timing_generator *optc);
+
+bool optc1_is_counter_moving(struct timing_generator *optc);
+
+void optc1_get_position(struct timing_generator *optc,
+			struct crtc_position *position);
+
+uint32_t optc1_get_vblank_counter(struct timing_generator *optc);
+
+void optc1_get_crtc_scanoutpos(struct timing_generator *optc,
+			       uint32_t *v_blank_start,
+			       uint32_t *v_blank_end,
+			       uint32_t *h_position,
+			       uint32_t *v_position);
+
+void optc1_set_early_control(struct timing_generator *optc,
+			     uint32_t early_cntl);
+
+void optc1_wait_for_state(struct timing_generator *optc,
+			  enum crtc_state state);
+
+void optc1_set_blank(struct timing_generator *optc,
+		     bool enable_blanking);
+
+bool optc1_is_blanked(struct timing_generator *optc);
+
+void optc1_program_blank_color(struct timing_generator *optc,
+			       const struct tg_color *black_color);
+
+bool optc1_did_triggered_reset_occur(struct timing_generator *optc);
+
+void optc1_enable_reset_trigger(struct timing_generator *optc, int source_tg_inst);
+
+void optc1_disable_reset_trigger(struct timing_generator *optc);
+
+void optc1_lock(struct timing_generator *optc);
+
+void optc1_unlock(struct timing_generator *optc);
+
+void optc1_enable_optc_clock(struct timing_generator *optc, bool enable);
+
+void optc1_set_drr(struct timing_generator *optc,
+		   const struct drr_params *params);
+
+void optc1_set_vtotal_min_max(struct timing_generator *optc, int vtotal_min, int vtotal_max);
+
+void optc1_set_static_screen_control(struct timing_generator *optc,
+				     uint32_t event_triggers,
+				     uint32_t num_frames);
+
+void optc1_program_stereo(struct timing_generator *optc,
+			  const struct dc_crtc_timing *timing,
+			  struct crtc_stereo_flags *flags);
+
+bool optc1_is_stereo_left_eye(struct timing_generator *optc);
+
+void optc1_clear_optc_underflow(struct timing_generator *optc);
+
+void optc1_tg_init(struct timing_generator *optc);
+
+bool optc1_is_tg_enabled(struct timing_generator *optc);
+
+bool optc1_is_optc_underflow_occurred(struct timing_generator *optc);
+
+void optc1_set_blank_data_double_buffer(struct timing_generator *optc, bool enable);
+
+void optc1_set_timing_double_buffer(struct timing_generator *optc, bool enable);
+
+bool optc1_get_otg_active_size(struct timing_generator *optc,
+			       uint32_t *otg_active_width,
+			       uint32_t *otg_active_height);
+
+void optc1_enable_crtc_reset(struct timing_generator *optc,
+			     int source_tg_inst,
+			     struct crtc_trigger_info *crtc_tp);
+
+bool optc1_configure_crc(struct timing_generator *optc, const struct crc_params *params);
+
+bool optc1_get_crc(struct timing_generator *optc,
+		   uint32_t *r_cr,
+		   uint32_t *g_y,
+		   uint32_t *b_cb);
+
+bool optc1_is_two_pixels_per_containter(const struct dc_crtc_timing *timing);
+
+void optc1_set_vtg_params(struct timing_generator *optc,
+			  const struct dc_crtc_timing *dc_crtc_timing,
+			  bool program_fp2);
+
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h
index 00ea3864dd4df4..b9812afb886be1 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h
@@ -47,6 +47,8 @@ struct pg_cntl_funcs {
 	void (*optc_pg_control)(struct pg_cntl *pg_cntl, unsigned int optc_inst, bool power_on);
 	void (*dwb_pg_control)(struct pg_cntl *pg_cntl, bool power_on);
 	void (*init_pg_status)(struct pg_cntl *pg_cntl);
+
+	void (*set_force_poweron_domain22)(struct pg_cntl *pg_cntl, bool power_on);
 };
 
 #endif //__DC_PG_CNTL_H__
diff --git a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c
index 21a39afd274bb6..2d152b68a501f4 100644
--- a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c
+++ b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c
@@ -53,6 +53,7 @@ static enum dc_link_rate get_link_rate_from_test_link_rate(uint8_t test_rate)
 		return LINK_RATE_UHBR10;
 	case DP_TEST_LINK_RATE_UHBR20:
 		return LINK_RATE_UHBR20;
+	case DP_TEST_LINK_RATE_UHBR13_5_LEGACY:
 	case DP_TEST_LINK_RATE_UHBR13_5:
 		return LINK_RATE_UHBR13_5;
 	default:
@@ -119,6 +120,11 @@ static void dp_test_send_link_training(struct dc_link *link)
 			1);
 	link_settings.link_rate = get_link_rate_from_test_link_rate(test_rate);
 
+	if (link_settings.link_rate == LINK_RATE_UNKNOWN) {
+		DC_LOG_ERROR("%s: Invalid test link rate.", __func__);
+		ASSERT(0);
+	}
+
 	/* Set preferred link settings */
 	link->verified_link_cap.lane_count = link_settings.lane_count;
 	link->verified_link_cap.link_rate = link_settings.link_rate;
@@ -457,7 +463,7 @@ static void set_crtc_test_pattern(struct dc_link *link,
 			controller_color_space = pipe_ctx->stream_res.test_pattern_params.color_space;
 
 			if (controller_color_space == CONTROLLER_DP_COLOR_SPACE_UDEFINED) {
-				DC_LOG_WARNING("%s: Color space must be defined for test pattern", __func__);
+				DC_LOG_ERROR("%s: Color space must be defined for test pattern", __func__);
 				ASSERT(0);
 			}
 
@@ -592,6 +598,7 @@ bool dp_set_test_pattern(
 	const unsigned char *p_custom_pattern,
 	unsigned int cust_pattern_size)
 {
+	const struct link_hwss *link_hwss;
 	struct pipe_ctx *pipes = link->dc->current_state->res_ctx.pipe_ctx;
 	struct pipe_ctx *pipe_ctx = NULL;
 	unsigned int lane;
@@ -828,11 +835,9 @@ bool dp_set_test_pattern(
 
 		pipe_ctx->stream_res.tg->funcs->lock(pipe_ctx->stream_res.tg);
 		/* update MSA to requested color space */
-		pipe_ctx->stream_res.stream_enc->funcs->dp_set_stream_attribute(pipe_ctx->stream_res.stream_enc,
-				&pipe_ctx->stream->timing,
-				color_space,
-				pipe_ctx->stream->use_vsc_sdp_for_colorimetry,
-				link->dpcd_caps.dprx_feature.bits.SST_SPLIT_SDP_CAP);
+		link_hwss = get_link_hwss(link, &pipe_ctx->link_res);
+		pipe_ctx->stream->output_color_space = color_space;
+		link_hwss->setup_stream_attribute(pipe_ctx);
 
 		if (pipe_ctx->stream->use_vsc_sdp_for_colorimetry) {
 			if (test_pattern == DP_TEST_PATTERN_COLOR_SQUARES_CEA)
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
index d6f0f857c05af8..24153b0df503dd 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
@@ -879,7 +879,7 @@ static bool detect_link_and_local_sink(struct dc_link *link,
 			(link->dpcd_sink_ext_caps.bits.oled == 1)) {
 			dpcd_set_source_specific_data(link);
 			msleep(post_oui_delay);
-			set_cached_brightness_aux(link);
+			set_default_brightness_aux(link);
 		}
 
 		return true;
@@ -1088,6 +1088,9 @@ static bool detect_link_and_local_sink(struct dc_link *link,
 		if (sink->edid_caps.panel_patch.skip_scdc_overwrite)
 			link->ctx->dc->debug.hdmi20_disable = true;
 
+		if (sink->edid_caps.panel_patch.remove_sink_ext_caps)
+			link->dpcd_sink_ext_caps.raw = 0;
+
 		if (dc_is_hdmi_signal(link->connector_signal))
 			read_scdc_caps(link->ddc, link->local_sink);
 
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index 34a4a8c0e18c3f..f8e01ca09d9646 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -2142,8 +2142,7 @@ static enum dc_status enable_link_dp(struct dc_state *state,
 	if (link->dpcd_sink_ext_caps.bits.oled == 1 ||
 		link->dpcd_sink_ext_caps.bits.sdr_aux_backlight_control == 1 ||
 		link->dpcd_sink_ext_caps.bits.hdr_aux_backlight_control == 1) {
-		set_cached_brightness_aux(link);
-
+		set_default_brightness_aux(link);
 		if (link->dpcd_sink_ext_caps.bits.oled == 1)
 			msleep(bl_oled_enable_delay);
 		edp_backlight_enable_aux(link, true);
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c
index 34bf8a9ef73809..0c00e94e90b1d5 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c
@@ -184,14 +184,17 @@ static bool handle_hpd_irq_psr_sink(struct dc_link *link)
 	return false;
 }
 
-static bool handle_hpd_irq_replay_sink(struct dc_link *link)
+static void handle_hpd_irq_replay_sink(struct dc_link *link)
 {
 	union dpcd_replay_configuration replay_configuration;
 	/*AMD Replay version reuse DP_PSR_ERROR_STATUS for REPLAY_ERROR status.*/
 	union psr_error_status replay_error_status;
 
+	if (link->replay_settings.config.force_disable_desync_error_check)
+		return;
+
 	if (!link->replay_settings.replay_feature_enabled)
-		return false;
+		return;
 
 	dm_helpers_dp_read_dpcd(
 		link->ctx,
@@ -207,6 +210,9 @@ static bool handle_hpd_irq_replay_sink(struct dc_link *link)
 		&replay_error_status.raw,
 		sizeof(replay_error_status.raw));
 
+	if (replay_configuration.bits.DESYNC_ERROR_STATUS)
+		link->replay_settings.config.received_desync_error_hpd = 1;
+
 	link->replay_settings.config.replay_error_status.bits.LINK_CRC_ERROR =
 		replay_error_status.bits.LINK_CRC_ERROR;
 	link->replay_settings.config.replay_error_status.bits.DESYNC_ERROR =
@@ -243,7 +249,6 @@ static bool handle_hpd_irq_replay_sink(struct dc_link *link)
 			edp_set_replay_allow_active(link, &allow_active, true, false, NULL);
 		}
 	}
-	return true;
 }
 
 void dp_handle_link_loss(struct dc_link *link)
@@ -424,9 +429,7 @@ bool dp_handle_hpd_rx_irq(struct dc_link *link,
 		/* PSR-related error was detected and handled */
 		return true;
 
-	if (handle_hpd_irq_replay_sink(link))
-		/* Replay-related error was detected and handled */
-		return true;
+	handle_hpd_irq_replay_sink(link);
 
 	/* If PSR-related error handled, Main link may be off,
 	 * so do not handle as a normal sink status change interrupt.
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c
index fd8f6f19814617..68096d12f52fd6 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c
@@ -115,7 +115,7 @@ static enum link_training_result perform_fixed_vs_pe_nontransparent_training_seq
 		lt_settings->cr_pattern_time = 16000;
 
 	/* Fixed VS/PE specific: Toggle link rate */
-	apply_toggle_rate_wa = (link->vendor_specific_lttpr_link_rate_wa == target_rate);
+	apply_toggle_rate_wa = ((link->vendor_specific_lttpr_link_rate_wa == target_rate) || (link->vendor_specific_lttpr_link_rate_wa == 0));
 	target_rate = get_dpcd_link_rate(&lt_settings->link_settings);
 	toggle_rate = (target_rate == 0x6) ? 0xA : 0x6;
 
@@ -271,7 +271,7 @@ enum link_training_result dp_perform_fixed_vs_pe_training_sequence_legacy(
 	/* Vendor specific: Toggle link rate */
 	toggle_rate = (rate == 0x6) ? 0xA : 0x6;
 
-	if (link->vendor_specific_lttpr_link_rate_wa == rate) {
+	if (link->vendor_specific_lttpr_link_rate_wa == rate || link->vendor_specific_lttpr_link_rate_wa == 0) {
 		core_link_write_dpcd(
 				link,
 				DP_LINK_BW_SET,
@@ -617,7 +617,7 @@ enum link_training_result dp_perform_fixed_vs_pe_training_sequence(
 	/* Vendor specific: Toggle link rate */
 	toggle_rate = (rate == 0x6) ? 0xA : 0x6;
 
-	if (link->vendor_specific_lttpr_link_rate_wa == rate) {
+	if (link->vendor_specific_lttpr_link_rate_wa == rate || link->vendor_specific_lttpr_link_rate_wa == 0) {
 		core_link_write_dpcd(
 				link,
 				DP_LINK_BW_SET,
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index e32a7974a4bc68..e5cfaaef70b3f7 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -170,7 +170,6 @@ bool edp_set_backlight_level_nits(struct dc_link *link,
 	*(uint32_t *)&dpcd_backlight_set.backlight_level_millinits = backlight_millinits;
 	*(uint16_t *)&dpcd_backlight_set.backlight_transition_time_ms = (uint16_t)transition_time_in_ms;
 
-	link->backlight_settings.backlight_millinits = backlight_millinits;
 
 	if (!link->dpcd_caps.panel_luminance_control) {
 		if (core_link_write_dpcd(link, DP_SOURCE_BACKLIGHT_LEVEL,
@@ -290,7 +289,7 @@ bool set_default_brightness_aux(struct dc_link *link)
 			default_backlight = 150000;
 		// if < 1 nits or > 5000, it might be wrong readback
 		if (default_backlight < 1000 || default_backlight > 5000000)
-			default_backlight = 150000; //
+			default_backlight = 150000;
 
 		return edp_set_backlight_level_nits(link, true,
 				default_backlight, 0);
@@ -298,15 +297,6 @@ bool set_default_brightness_aux(struct dc_link *link)
 	return false;
 }
 
-bool set_cached_brightness_aux(struct dc_link *link)
-{
-	if (link->backlight_settings.backlight_millinits)
-		return edp_set_backlight_level_nits(link, true,
-						    link->backlight_settings.backlight_millinits, 0);
-	else
-		return set_default_brightness_aux(link);
-	return false;
-}
 bool edp_is_ilr_optimization_enabled(struct dc_link *link)
 {
 	if (link->dpcd_caps.edp_supported_link_rates_count == 0 || !link->panel_config.ilr.optimize_edp_link_rate)
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h
index ebf7deb63d136e..a034288ad75d4a 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h
@@ -30,7 +30,6 @@
 enum dp_panel_mode dp_get_panel_mode(struct dc_link *link);
 void dp_set_panel_mode(struct dc_link *link, enum dp_panel_mode panel_mode);
 bool set_default_brightness_aux(struct dc_link *link);
-bool set_cached_brightness_aux(struct dc_link *link);
 void edp_panel_backlight_power_on(struct dc_link *link, bool wait_for_hpd);
 int edp_get_backlight_level(const struct dc_link *link);
 bool edp_get_backlight_level_nits(struct dc_link *link,
diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
index 9665ada0f894b2..df63aa8f01e98d 100644
--- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
@@ -195,6 +195,7 @@ struct dmub_srv_region_params {
 	uint32_t vbios_size;
 	const uint8_t *fw_inst_const;
 	const uint8_t *fw_bss_data;
+	bool is_mailbox_in_inbox;
 };
 
 /**
@@ -214,20 +215,25 @@ struct dmub_srv_region_params {
  */
 struct dmub_srv_region_info {
 	uint32_t fb_size;
+	uint32_t inbox_size;
 	uint8_t num_regions;
 	struct dmub_region regions[DMUB_WINDOW_TOTAL];
 };
 
 /**
- * struct dmub_srv_fb_params - parameters used for driver fb setup
+ * struct dmub_srv_memory_params - parameters used for driver fb setup
  * @region_info: region info calculated by dmub service
- * @cpu_addr: base cpu address for the framebuffer
- * @gpu_addr: base gpu virtual address for the framebuffer
+ * @cpu_fb_addr: base cpu address for the framebuffer
+ * @cpu_inbox_addr: base cpu address for the gart
+ * @gpu_fb_addr: base gpu virtual address for the framebuffer
+ * @gpu_inbox_addr: base gpu virtual address for the gart
  */
-struct dmub_srv_fb_params {
+struct dmub_srv_memory_params {
 	const struct dmub_srv_region_info *region_info;
-	void *cpu_addr;
-	uint64_t gpu_addr;
+	void *cpu_fb_addr;
+	void *cpu_inbox_addr;
+	uint64_t gpu_fb_addr;
+	uint64_t gpu_inbox_addr;
 };
 
 /**
@@ -563,8 +569,8 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub,
  *   DMUB_STATUS_OK - success
  *   DMUB_STATUS_INVALID - unspecified error
  */
-enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub,
-				       const struct dmub_srv_fb_params *params,
+enum dmub_status dmub_srv_calc_mem_info(struct dmub_srv *dmub,
+				       const struct dmub_srv_memory_params *params,
 				       struct dmub_srv_fb_info *out);
 
 /**
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index bc907ae2052d5e..ed4379c047151a 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -583,6 +583,7 @@ union dmub_fw_boot_status {
 		uint32_t fams_enabled : 1; /**< 1 if VBIOS data is deferred programmed */
 		uint32_t detection_required: 1; /**<  if detection need to be triggered by driver */
 		uint32_t hw_power_init_done: 1; /**< 1 if hw power init is completed */
+		uint32_t ono_regions_enabled: 1; /**< 1 if ONO regions are enabled */
 	} bits; /**< status bits */
 	uint32_t all; /**< 32-bit access to status bits */
 };
@@ -599,6 +600,7 @@ enum dmub_fw_boot_status_bit {
 	DMUB_FW_BOOT_STATUS_BIT_FAMS_ENABLED = (1 << 5), /**< 1 if FAMS is enabled*/
 	DMUB_FW_BOOT_STATUS_BIT_DETECTION_REQUIRED = (1 << 6), /**< 1 if detection need to be triggered by driver*/
 	DMUB_FW_BOOT_STATUS_BIT_HW_POWER_INIT_DONE = (1 << 7), /**< 1 if hw power init is completed */
+	DMUB_FW_BOOT_STATUS_BIT_ONO_REGIONS_ENABLED = (1 << 8), /**< 1 if ONO regions are enabled */
 };
 
 /* Register bit definition for SCRATCH5 */
@@ -617,9 +619,12 @@ enum dmub_lvtma_status_bit {
 };
 
 enum dmub_ips_disable_type {
-	DMUB_IPS_DISABLE_IPS1 = 1,
-	DMUB_IPS_DISABLE_IPS2 = 2,
-	DMUB_IPS_DISABLE_IPS2_Z10 = 3,
+	DMUB_IPS_ENABLE = 0,
+	DMUB_IPS_DISABLE_ALL = 1,
+	DMUB_IPS_DISABLE_IPS1 = 2,
+	DMUB_IPS_DISABLE_IPS2 = 3,
+	DMUB_IPS_DISABLE_IPS2_Z10 = 4,
+	DMUB_IPS_DISABLE_DYNAMIC = 5,
 };
 
 #define DMUB_IPS1_ALLOW_MASK 0x00000001
@@ -653,8 +658,8 @@ union dmub_fw_boot_options {
 		uint32_t disable_clk_ds: 1; /* 1 if disallow dispclk_ds and dppclk_ds*/
 		uint32_t disable_timeout_recovery : 1; /* 1 if timeout recovery should be disabled */
 		uint32_t ips_pg_disable: 1; /* 1 to disable ONO domains power gating*/
-		uint32_t ips_disable: 2; /* options to disable ips support*/
-		uint32_t reserved : 10; /**< reserved */
+		uint32_t ips_disable: 3; /* options to disable ips support*/
+		uint32_t reserved : 9; /**< reserved */
 	} bits; /**< boot bits */
 	uint32_t all; /**< 32-bit access to bits */
 };
@@ -2098,7 +2103,7 @@ enum psr_version {
 	/**
 	 * PSR not supported.
 	 */
-	PSR_VERSION_UNSUPPORTED			= 0xFFFFFFFF,
+	PSR_VERSION_UNSUPPORTED			= 0xFF,	// psr_version field is only 8 bits wide
 };
 
 /**
@@ -3620,7 +3625,6 @@ struct dmub_cmd_abm_pause_data {
 	uint8_t pad[1];
 };
 
-
 /**
  * Definition of a DMUB_CMD__ABM_PAUSE command.
  */
@@ -4046,6 +4050,7 @@ union dmub_rb_cmd {
 	 * Definition of a DMUB_CMD__MALL command.
 	 */
 	struct dmub_rb_cmd_mall mall;
+
 	/**
 	 * Definition of a DMUB_CMD__CAB command.
 	 */
@@ -4067,6 +4072,7 @@ union dmub_rb_cmd {
 	 * Definition of DMUB_CMD__PANEL_CNTL commands.
 	 */
 	struct dmub_rb_cmd_panel_cntl panel_cntl;
+
 	/**
 	 * Definition of a DMUB_CMD__ABM_SET_PIPE command.
 	 */
@@ -4470,10 +4476,6 @@ static inline void dmub_rb_flush_pending(const struct dmub_rb *rb)
 		uint64_t *data = (uint64_t *)((uint8_t *)(rb->base_address) + rptr);
 		uint8_t i;
 
-		/* Don't remove this.
-		 * The contents need to actually be read from the ring buffer
-		 * for this function to be effective.
-		 */
 		for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++)
 			(void)READ_ONCE(*data++);
 
@@ -4522,5 +4524,4 @@ static inline void dmub_rb_get_return_data(struct dmub_rb *rb,
 //==============================================================================
 //</DMUB_RB>====================================================================
 //==============================================================================
-
 #endif /* _DMUB_CMD_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
index e43e8d4bfe375e..38360adc53d973 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
@@ -434,7 +434,7 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub,
 	uint32_t fw_state_size = DMUB_FW_STATE_SIZE;
 	uint32_t trace_buffer_size = DMUB_TRACE_BUFFER_SIZE;
 	uint32_t scratch_mem_size = DMUB_SCRATCH_MEM_SIZE;
-
+	uint32_t previous_top = 0;
 	if (!dmub->sw_init)
 		return DMUB_STATUS_INVALID;
 
@@ -459,8 +459,15 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub,
 	bios->base = dmub_align(stack->top, 256);
 	bios->top = bios->base + params->vbios_size;
 
-	mail->base = dmub_align(bios->top, 256);
-	mail->top = mail->base + DMUB_MAILBOX_SIZE;
+	if (params->is_mailbox_in_inbox) {
+		mail->base = 0;
+		mail->top = mail->base + DMUB_MAILBOX_SIZE;
+		previous_top = bios->top;
+	} else {
+		mail->base = dmub_align(bios->top, 256);
+		mail->top = mail->base + DMUB_MAILBOX_SIZE;
+		previous_top = mail->top;
+	}
 
 	fw_info = dmub_get_fw_meta_info(params);
 
@@ -479,7 +486,7 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub,
 			dmub->fw_version = fw_info->fw_version;
 	}
 
-	trace_buff->base = dmub_align(mail->top, 256);
+	trace_buff->base = dmub_align(previous_top, 256);
 	trace_buff->top = trace_buff->base + dmub_align(trace_buffer_size, 64);
 
 	fw_state->base = dmub_align(trace_buff->top, 256);
@@ -490,11 +497,14 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub,
 
 	out->fb_size = dmub_align(scratch_mem->top, 4096);
 
+	if (params->is_mailbox_in_inbox)
+		out->inbox_size = dmub_align(mail->top, 4096);
+
 	return DMUB_STATUS_OK;
 }
 
-enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub,
-				       const struct dmub_srv_fb_params *params,
+enum dmub_status dmub_srv_calc_mem_info(struct dmub_srv *dmub,
+				       const struct dmub_srv_memory_params *params,
 				       struct dmub_srv_fb_info *out)
 {
 	uint8_t *cpu_base;
@@ -509,8 +519,8 @@ enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub,
 	if (params->region_info->num_regions != DMUB_NUM_WINDOWS)
 		return DMUB_STATUS_INVALID;
 
-	cpu_base = (uint8_t *)params->cpu_addr;
-	gpu_base = params->gpu_addr;
+	cpu_base = (uint8_t *)params->cpu_fb_addr;
+	gpu_base = params->gpu_fb_addr;
 
 	for (i = 0; i < DMUB_NUM_WINDOWS; ++i) {
 		const struct dmub_region *reg =
@@ -518,6 +528,12 @@ enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub,
 
 		out->fb[i].cpu_addr = cpu_base + reg->base;
 		out->fb[i].gpu_addr = gpu_base + reg->base;
+
+		if (i == DMUB_WINDOW_4_MAILBOX && params->cpu_inbox_addr != 0) {
+			out->fb[i].cpu_addr = (uint8_t *)params->cpu_inbox_addr + reg->base;
+			out->fb[i].gpu_addr = params->gpu_inbox_addr + reg->base;
+		}
+
 		out->fb[i].size = reg->top - reg->base;
 	}
 
@@ -707,9 +723,16 @@ enum dmub_status dmub_srv_sync_inbox1(struct dmub_srv *dmub)
 		return DMUB_STATUS_INVALID;
 
 	if (dmub->hw_funcs.get_inbox1_rptr && dmub->hw_funcs.get_inbox1_wptr) {
-		dmub->inbox1_rb.rptr = dmub->hw_funcs.get_inbox1_rptr(dmub);
-		dmub->inbox1_rb.wrpt = dmub->hw_funcs.get_inbox1_wptr(dmub);
-		dmub->inbox1_last_wptr = dmub->inbox1_rb.wrpt;
+		uint32_t rptr = dmub->hw_funcs.get_inbox1_rptr(dmub);
+		uint32_t wptr = dmub->hw_funcs.get_inbox1_wptr(dmub);
+
+		if (rptr > dmub->inbox1_rb.capacity || wptr > dmub->inbox1_rb.capacity) {
+			return DMUB_STATUS_HW_FAILURE;
+		} else {
+			dmub->inbox1_rb.rptr = rptr;
+			dmub->inbox1_rb.wrpt = wptr;
+			dmub->inbox1_last_wptr = dmub->inbox1_rb.wrpt;
+		}
 	}
 
 	return DMUB_STATUS_OK;
@@ -743,6 +766,11 @@ enum dmub_status dmub_srv_cmd_queue(struct dmub_srv *dmub,
 	if (!dmub->hw_init)
 		return DMUB_STATUS_INVALID;
 
+	if (dmub->inbox1_rb.rptr > dmub->inbox1_rb.capacity ||
+	    dmub->inbox1_rb.wrpt > dmub->inbox1_rb.capacity) {
+		return DMUB_STATUS_HW_FAILURE;
+	}
+
 	if (dmub_rb_push_front(&dmub->inbox1_rb, cmd))
 		return DMUB_STATUS_OK;
 
@@ -1049,6 +1077,7 @@ enum dmub_status dmub_srv_wait_for_inbox0_ack(struct dmub_srv *dmub, uint32_t ti
 		ack = dmub->hw_funcs.read_inbox0_ack_register(dmub);
 		if (ack)
 			return DMUB_STATUS_OK;
+		udelay(1);
 	}
 	return DMUB_STATUS_TIMEOUT;
 }
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
index bc96d021136080..813463ffe15c52 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
@@ -417,6 +417,8 @@ struct integrated_info {
 	/* V2.1 */
 	struct edp_info edp1_info;
 	struct edp_info edp2_info;
+	uint32_t gpuclk_ss_percentage;
+	uint32_t gpuclk_ss_type;
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index a522a7c0291108..1675314a3ff208 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -839,6 +839,8 @@ bool is_psr_su_specific_panel(struct dc_link *link)
 				((dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x08) ||
 				(dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x07)))
 				isPSRSUSupported = false;
+			else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03)
+				isPSRSUSupported = false;
 			else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1)
 				isPSRSUSupported = true;
 		}
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h
index c92c4b83253f81..4bff1ef8a9a640 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h
@@ -6369,6 +6369,8 @@
 #define regTCP_INVALIDATE_BASE_IDX                                                                      1
 #define regTCP_STATUS                                                                                   0x19a1
 #define regTCP_STATUS_BASE_IDX                                                                          1
+#define regTCP_CNTL                                                                                     0x19a2
+#define regTCP_CNTL_BASE_IDX                                                                            1
 #define regTCP_CNTL2                                                                                    0x19a3
 #define regTCP_CNTL2_BASE_IDX                                                                           1
 #define regTCP_DEBUG_INDEX                                                                              0x19a5
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
index ff30f04be59120..7ee3d291120d54 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
@@ -781,6 +781,8 @@
 #define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_CNTL2_BASE_IDX                                              5
 #define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1                                             0x420187
 #define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1_BASE_IDX                                    5
+#define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3                                                  0x4201c6
+#define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3_BASE_IDX                                         5
 
 
 // addressBlock: nbio_nbif0_bif_cfg_dev0_rc_bifcfgdecp
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h
index 7f131999a263d1..eb8c556d9c9300 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h
@@ -24646,6 +24646,35 @@
 //BIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1
 #define BIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN_MASK                                  0x00000001L
 #define BIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN_MASK                               0x00000008L
+//BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_PAYLOAD_SIZE_MODE__SHIFT                     0x8
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_PRIV_MAX_PAYLOAD_SIZE__SHIFT                     0x9
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_10BIT_TAG_EN_OVERRIDE__SHIFT                          0xb
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_10BIT_TAG_EN_OVERRIDE__SHIFT                     0xd
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__MST_DROP_SYNC_FLOOD_EN__SHIFT                            0xf
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_PAYLOAD_SIZE_MODE__SHIFT                          0x10
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_PRIV_MAX_PAYLOAD_SIZE__SHIFT                          0x11
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_READ_REQUEST_SIZE_MODE__SHIFT                     0x14
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_PRIV_MAX_READ_REQUEST_SIZE__SHIFT                     0x15
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_READ_SAFE_MODE__SHIFT                             0x18
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_EXTENDED_TAG_EN_OVERRIDE__SHIFT                       0x19
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_READ_REQUEST_SIZE_MODE__SHIFT                0x1b
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_READ_REQUEST_SIZE_PRIV__SHIFT                0x1c
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_EXTENDED_TAG_EN_OVERRIDE__SHIFT                  0x1e
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_PAYLOAD_SIZE_MODE_MASK                       0x00000100L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_PRIV_MAX_PAYLOAD_SIZE_MASK                       0x00000600L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_10BIT_TAG_EN_OVERRIDE_MASK                            0x00001800L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_10BIT_TAG_EN_OVERRIDE_MASK                       0x00006000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__MST_DROP_SYNC_FLOOD_EN_MASK                              0x00008000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_PAYLOAD_SIZE_MODE_MASK                            0x00010000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_PRIV_MAX_PAYLOAD_SIZE_MASK                            0x000E0000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_READ_REQUEST_SIZE_MODE_MASK                       0x00100000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_PRIV_MAX_READ_REQUEST_SIZE_MASK                       0x00E00000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_READ_SAFE_MODE_MASK                               0x01000000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_EXTENDED_TAG_EN_OVERRIDE_MASK                         0x06000000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_READ_REQUEST_SIZE_MODE_MASK                  0x08000000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_READ_REQUEST_SIZE_PRIV_MASK                  0x30000000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_EXTENDED_TAG_EN_OVERRIDE_MASK                    0xC0000000L
 
 // addressBlock: nbio_nbif0_bif_cfg_dev0_rc_bifcfgdecp
 //BIF_CFG_DEV0_RC0_VENDOR_ID
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index cd3c40a860293c..1c5049e894e30e 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -444,6 +444,7 @@ struct amd_pm_funcs {
 				   struct dpm_clocks *clock_table);
 	int (*get_smu_prv_buf_details)(void *handle, void **addr, size_t *size);
 	void (*pm_compute_clocks)(void *handle);
+	int (*notify_rlc_state)(void *handle, bool en);
 };
 
 struct metrics_table_header {
@@ -1084,6 +1085,10 @@ struct gpu_metrics_v3_0 {
 	uint16_t			average_dram_reads;
 	/* time filtered DRAM write bandwidth [MB/sec] */
 	uint16_t			average_dram_writes;
+	/* time filtered IPU read bandwidth [MB/sec] */
+	uint16_t			average_ipu_reads;
+	/* time filtered IPU write bandwidth [MB/sec] */
+	uint16_t			average_ipu_writes;
 
 	/* Driver attached timestamp (in ns) */
 	uint64_t			system_clock_counter;
@@ -1103,6 +1108,8 @@ struct gpu_metrics_v3_0 {
 	uint32_t			average_all_core_power;
 	/* calculated core power [mW] */
 	uint16_t			average_core_power[16];
+	/* time filtered total system power [mW] */
+	uint16_t			average_sys_power;
 	/* maximum IRM defined STAPM power limit [mW] */
 	uint16_t			stapm_power_limit;
 	/* time filtered STAPM power limit [mW] */
@@ -1115,6 +1122,8 @@ struct gpu_metrics_v3_0 {
 	uint16_t			average_ipuclk_frequency;
 	uint16_t			average_fclk_frequency;
 	uint16_t			average_vclk_frequency;
+	uint16_t			average_uclk_frequency;
+	uint16_t			average_mpipu_frequency;
 
 	/* Current clocks */
 	/* target core frequency [MHz] */
@@ -1124,6 +1133,15 @@ struct gpu_metrics_v3_0 {
 	/* GFXCLK frequency limit enforced on GFX [MHz] */
 	uint16_t			current_gfx_maxfreq;
 
+	/* Throttle Residency (ASIC dependent) */
+	uint32_t			throttle_residency_prochot;
+	uint32_t			throttle_residency_spl;
+	uint32_t			throttle_residency_fppt;
+	uint32_t			throttle_residency_sppt;
+	uint32_t			throttle_residency_thm_core;
+	uint32_t			throttle_residency_thm_gfx;
+	uint32_t			throttle_residency_thm_soc;
+
 	/* Metrics table alpha filter time constant [us] */
 	uint32_t			time_filter_alphavalue;
 };
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index acf3527fff2dbf..8ec11da0319ffd 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -181,6 +181,24 @@ int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 	return ret;
 }
 
+int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en)
+{
+	int ret = 0;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (pp_funcs && pp_funcs->notify_rlc_state) {
+		mutex_lock(&adev->pm.mutex);
+
+		ret = pp_funcs->notify_rlc_state(
+				adev->powerplay.pp_handle,
+				en);
+
+		mutex_unlock(&adev->pm.mutex);
+	}
+
+	return ret;
+}
+
 bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev)
 {
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
@@ -491,7 +509,7 @@ int amdgpu_dpm_read_sensor(struct amdgpu_device *adev, enum amd_pp_sensors senso
 int amdgpu_dpm_get_apu_thermal_limit(struct amdgpu_device *adev, uint32_t *limit)
 {
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-	int ret = -EINVAL;
+	int ret = -EOPNOTSUPP;
 
 	if (pp_funcs && pp_funcs->get_apu_thermal_limit) {
 		mutex_lock(&adev->pm.mutex);
@@ -505,7 +523,7 @@ int amdgpu_dpm_get_apu_thermal_limit(struct amdgpu_device *adev, uint32_t *limit
 int amdgpu_dpm_set_apu_thermal_limit(struct amdgpu_device *adev, uint32_t limit)
 {
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-	int ret = -EINVAL;
+	int ret = -EOPNOTSUPP;
 
 	if (pp_funcs && pp_funcs->set_apu_thermal_limit) {
 		mutex_lock(&adev->pm.mutex);
@@ -1182,7 +1200,7 @@ int amdgpu_dpm_get_sclk_od(struct amdgpu_device *adev)
 	int ret = 0;
 
 	if (!pp_funcs->get_sclk_od)
-		return 0;
+		return -EOPNOTSUPP;
 
 	mutex_lock(&adev->pm.mutex);
 	ret = pp_funcs->get_sclk_od(adev->powerplay.pp_handle);
@@ -1196,7 +1214,7 @@ int amdgpu_dpm_set_sclk_od(struct amdgpu_device *adev, uint32_t value)
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
 
 	if (is_support_sw_smu(adev))
-		return 0;
+		return -EOPNOTSUPP;
 
 	mutex_lock(&adev->pm.mutex);
 	if (pp_funcs->set_sclk_od)
@@ -1219,7 +1237,7 @@ int amdgpu_dpm_get_mclk_od(struct amdgpu_device *adev)
 	int ret = 0;
 
 	if (!pp_funcs->get_mclk_od)
-		return 0;
+		return -EOPNOTSUPP;
 
 	mutex_lock(&adev->pm.mutex);
 	ret = pp_funcs->get_mclk_od(adev->powerplay.pp_handle);
@@ -1233,7 +1251,7 @@ int amdgpu_dpm_set_mclk_od(struct amdgpu_device *adev, uint32_t value)
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
 
 	if (is_support_sw_smu(adev))
-		return 0;
+		return -EOPNOTSUPP;
 
 	mutex_lock(&adev->pm.mutex);
 	if (pp_funcs->set_mclk_od)
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 4ba9195c83c5d8..49028dde0f87b1 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -989,12 +989,13 @@ static ssize_t amdgpu_get_pp_features(struct device *dev,
  * Reading back the files will show you the available power levels within
  * the power state and the clock information for those levels. If deep sleep is
  * applied to a clock, the level will be denoted by a special level 'S:'
- * E.g.,
- *	S: 19Mhz *
- *	0: 615Mhz
- *	1: 800Mhz
- *	2: 888Mhz
- *	3: 1000Mhz
+ * E.g., ::
+ *
+ *  S: 19Mhz *
+ *  0: 615Mhz
+ *  1: 800Mhz
+ *  2: 888Mhz
+ *  3: 1000Mhz
  *
  *
  * To manually adjust these states, first select manual using
@@ -2197,6 +2198,22 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 	} else if (DEVICE_ATTR_IS(xgmi_plpd_policy)) {
 		if (amdgpu_dpm_get_xgmi_plpd_mode(adev, NULL) == XGMI_PLPD_NONE)
 			*states = ATTR_STATE_UNSUPPORTED;
+	} else if (DEVICE_ATTR_IS(pp_mclk_od)) {
+		if (amdgpu_dpm_get_mclk_od(adev) == -EOPNOTSUPP)
+			*states = ATTR_STATE_UNSUPPORTED;
+	} else if (DEVICE_ATTR_IS(pp_sclk_od)) {
+		if (amdgpu_dpm_get_sclk_od(adev) == -EOPNOTSUPP)
+			*states = ATTR_STATE_UNSUPPORTED;
+	} else if (DEVICE_ATTR_IS(apu_thermal_cap)) {
+		u32 limit;
+
+		if (amdgpu_dpm_get_apu_thermal_limit(adev, &limit) ==
+		    -EOPNOTSUPP)
+			*states = ATTR_STATE_UNSUPPORTED;
+	} else if (DEVICE_ATTR_IS(pp_dpm_pcie)) {
+		if (gc_ver == IP_VERSION(9, 4, 2) ||
+		    gc_ver == IP_VERSION(9, 4, 3))
+			*states = ATTR_STATE_UNSUPPORTED;
 	}
 
 	switch (gc_ver) {
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index feccd2a7120dcd..482ea30147ab64 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -415,6 +415,8 @@ int amdgpu_dpm_mode1_reset(struct amdgpu_device *adev);
 int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 			     enum pp_mp1_state mp1_state);
 
+int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en);
+
 int amdgpu_dpm_set_gfx_power_up_by_imu(struct amdgpu_device *adev);
 
 int amdgpu_dpm_baco_exit(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 23b00eddc1af2c..e1a5ee911dbbc6 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1710,7 +1710,18 @@ static int smu_disable_dpms(struct smu_context *smu)
 		}
 	}
 
+	/* Notify SMU RLC is going to be off, stop RLC and SMU interaction.
+	 * otherwise SMU will hang while interacting with RLC if RLC is halted
+	 * this is a WA for Vangogh asic which fix the SMU hang issue.
+	 */
+	ret = smu_notify_rlc_state(smu, false);
+	if (ret) {
+		dev_err(adev->dev, "Fail to notify rlc status!\n");
+		return ret;
+	}
+
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(9, 4, 2) &&
+	    !((adev->flags & AMD_IS_APU) && adev->gfx.imu.funcs) &&
 	    !amdgpu_sriov_vf(adev) && adev->gfx.rlc.funcs->stop)
 		adev->gfx.rlc.funcs->stop(adev);
 
@@ -2747,7 +2758,7 @@ unlock:
 
 static int smu_get_apu_thermal_limit(void *handle, uint32_t *limit)
 {
-	int ret = -EINVAL;
+	int ret = -EOPNOTSUPP;
 	struct smu_context *smu = handle;
 
 	if (smu->ppt_funcs && smu->ppt_funcs->get_apu_thermal_limit)
@@ -2758,7 +2769,7 @@ static int smu_get_apu_thermal_limit(void *handle, uint32_t *limit)
 
 static int smu_set_apu_thermal_limit(void *handle, uint32_t limit)
 {
-	int ret = -EINVAL;
+	int ret = -EOPNOTSUPP;
 	struct smu_context *smu = handle;
 
 	if (smu->ppt_funcs && smu->ppt_funcs->set_apu_thermal_limit)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 8def291b18bcda..f8b2e6cc256888 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -1360,6 +1360,11 @@ struct pptable_funcs {
 	 *                       management.
 	 */
 	int (*dpm_set_umsch_mm_enable)(struct smu_context *smu, bool enable);
+
+	/**
+	 * @notify_rlc_state: Notify RLC power state to SMU.
+	 */
+	int (*notify_rlc_state)(struct smu_context *smu, bool en);
 };
 
 typedef enum {
@@ -1403,6 +1408,16 @@ typedef enum {
 	METRICS_PCIE_WIDTH,
 	METRICS_CURR_FANPWM,
 	METRICS_CURR_SOCKETPOWER,
+	METRICS_AVERAGE_VPECLK,
+	METRICS_AVERAGE_IPUCLK,
+	METRICS_AVERAGE_MPIPUCLK,
+	METRICS_THROTTLER_RESIDENCY_PROCHOT,
+	METRICS_THROTTLER_RESIDENCY_SPL,
+	METRICS_THROTTLER_RESIDENCY_FPPT,
+	METRICS_THROTTLER_RESIDENCY_SPPT,
+	METRICS_THROTTLER_RESIDENCY_THM_CORE,
+	METRICS_THROTTLER_RESIDENCY_THM_GFX,
+	METRICS_THROTTLER_RESIDENCY_THM_SOC,
 } MetricsMember_t;
 
 enum smu_cmn2asic_mapping_type {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h
index 22f88842a7fd21..8f42771e1f0a28 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h
@@ -27,7 +27,7 @@
 // *** IMPORTANT ***
 // SMU TEAM: Always increment the interface version if
 // any structure is changed in this file
-#define PMFW_DRIVER_IF_VERSION 6
+#define PMFW_DRIVER_IF_VERSION 7
 
 typedef struct {
   int32_t value;
@@ -150,37 +150,50 @@ typedef struct {
 } DpmClocks_t;
 
 typedef struct {
-  uint16_t CoreFrequency[16];        //Target core frequency [MHz]
-  uint16_t CorePower[16];            //CAC calculated core power [mW]
-  uint16_t CoreTemperature[16];      //TSEN measured core temperature [centi-C]
-  uint16_t GfxTemperature;           //TSEN measured GFX temperature [centi-C]
-  uint16_t SocTemperature;           //TSEN measured SOC temperature [centi-C]
-  uint16_t StapmOpnLimit;            //Maximum IRM defined STAPM power limit [mW]
-  uint16_t StapmCurrentLimit;        //Time filtered STAPM power limit [mW]
-  uint16_t InfrastructureCpuMaxFreq; //CCLK frequency limit enforced on classic cores [MHz]
-  uint16_t InfrastructureGfxMaxFreq; //GFXCLK frequency limit enforced on GFX [MHz]
-  uint16_t SkinTemp;                 //Maximum skin temperature reported by APU and HS2 chassis sensors [centi-C]
-  uint16_t GfxclkFrequency;          //Time filtered target GFXCLK frequency [MHz]
-  uint16_t FclkFrequency;            //Time filtered target FCLK frequency [MHz]
-  uint16_t GfxActivity;              //Time filtered GFX busy % [0-100]
-  uint16_t SocclkFrequency;          //Time filtered target SOCCLK frequency [MHz]
-  uint16_t VclkFrequency;            //Time filtered target VCLK frequency [MHz]
-  uint16_t VcnActivity;              //Time filtered VCN busy % [0-100]
-  uint16_t VpeclkFrequency;          //Time filtered target VPECLK frequency [MHz]
-  uint16_t IpuclkFrequency;          //Time filtered target IPUCLK frequency [MHz]
-  uint16_t IpuBusy[8];               //Time filtered IPU per-column busy % [0-100]
-  uint16_t DRAMReads;                //Time filtered DRAM read bandwidth [MB/sec]
-  uint16_t DRAMWrites;               //Time filtered DRAM write bandwidth [MB/sec]
-  uint16_t CoreC0Residency[16];      //Time filtered per-core C0 residency % [0-100]
-  uint16_t IpuPower;                 //Time filtered IPU power [mW]
-  uint32_t ApuPower;                 //Time filtered APU power [mW]
-  uint32_t GfxPower;                 //Time filtered GFX power [mW]
-  uint32_t dGpuPower;                //Time filtered dGPU power [mW]
-  uint32_t SocketPower;              //Time filtered power used for PPT/STAPM [APU+dGPU] [mW]
-  uint32_t AllCorePower;             //Time filtered sum of core power across all cores in the socket [mW]
-  uint32_t FilterAlphaValue;         //Metrics table alpha filter time constant [us]
-  uint32_t MetricsCounter;           //Counter that is incremented on every metrics table update [PM_TIMER cycles]
-  uint32_t spare[16];
+  uint16_t CoreFrequency[16];          //Target core frequency [MHz]
+  uint16_t CorePower[16];              //CAC calculated core power [mW]
+  uint16_t CoreTemperature[16];        //TSEN measured core temperature [centi-C]
+  uint16_t GfxTemperature;             //TSEN measured GFX temperature [centi-C]
+  uint16_t SocTemperature;             //TSEN measured SOC temperature [centi-C]
+  uint16_t StapmOpnLimit;              //Maximum IRM defined STAPM power limit [mW]
+  uint16_t StapmCurrentLimit;          //Time filtered STAPM power limit [mW]
+  uint16_t InfrastructureCpuMaxFreq;   //CCLK frequency limit enforced on classic cores [MHz]
+  uint16_t InfrastructureGfxMaxFreq;   //GFXCLK frequency limit enforced on GFX [MHz]
+  uint16_t SkinTemp;                   //Maximum skin temperature reported by APU and HS2 chassis sensors [centi-C]
+  uint16_t GfxclkFrequency;            //Time filtered target GFXCLK frequency [MHz]
+  uint16_t FclkFrequency;              //Time filtered target FCLK frequency [MHz]
+  uint16_t GfxActivity;                //Time filtered GFX busy % [0-100]
+  uint16_t SocclkFrequency;            //Time filtered target SOCCLK frequency [MHz]
+  uint16_t VclkFrequency;              //Time filtered target VCLK frequency [MHz]
+  uint16_t VcnActivity;                //Time filtered VCN busy % [0-100]
+  uint16_t VpeclkFrequency;            //Time filtered target VPECLK frequency [MHz]
+  uint16_t IpuclkFrequency;            //Time filtered target IPUCLK frequency [MHz]
+  uint16_t IpuBusy[8];                 //Time filtered IPU per-column busy % [0-100]
+  uint16_t DRAMReads;                  //Time filtered DRAM read bandwidth [MB/sec]
+  uint16_t DRAMWrites;                 //Time filtered DRAM write bandwidth [MB/sec]
+  uint16_t CoreC0Residency[16];        //Time filtered per-core C0 residency % [0-100]
+  uint16_t IpuPower;                   //Time filtered IPU power [mW]
+  uint32_t ApuPower;                   //Time filtered APU power [mW]
+  uint32_t GfxPower;                   //Time filtered GFX power [mW]
+  uint32_t dGpuPower;                  //Time filtered dGPU power [mW]
+  uint32_t SocketPower;                //Time filtered power used for PPT/STAPM [APU+dGPU] [mW]
+  uint32_t AllCorePower;               //Time filtered sum of core power across all cores in the socket [mW]
+  uint32_t FilterAlphaValue;           //Metrics table alpha filter time constant [us]
+  uint32_t MetricsCounter;             //Counter that is incremented on every metrics table update [PM_TIMER cycles]
+  uint16_t MemclkFrequency;            //Time filtered target MEMCLK frequency [MHz]
+  uint16_t MpipuclkFrequency;          //Time filtered target MPIPUCLK frequency [MHz]
+  uint16_t IpuReads;                   //Time filtered IPU read bandwidth [MB/sec]
+  uint16_t IpuWrites;                  //Time filtered IPU write bandwidth [MB/sec]
+  uint32_t ThrottleResidency_PROCHOT;  //Counter that is incremented on every metrics table update when PROCHOT was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_SPL;      //Counter that is incremented on every metrics table update when SPL was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_FPPT;     //Counter that is incremented on every metrics table update when fast PPT was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_SPPT;     //Counter that is incremented on every metrics table update when slow PPT was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_THM_CORE; //Counter that is incremented on every metrics table update when CORE thermal throttling was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_THM_GFX;  //Counter that is incremented on every metrics table update when GFX thermal throttling was engaged [PM_TIMER cycles]
+  uint32_t ThrottleResidency_THM_SOC;  //Counter that is incremented on every metrics table update when SOC thermal throttling was engaged [PM_TIMER cycles]
+  uint16_t Psys;                       //Time filtered Psys power [mW]
+  uint16_t spare1;
+  uint32_t spare[6];
 } SmuMetrics_t;
 
 //ISP tile definitions
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h
index dab35d878a905c..fef2d290f3f252 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h
@@ -123,7 +123,7 @@ typedef enum {
   VOLTAGE_GUARDBAND_COUNT
 } GFX_GUARDBAND_e;
 
-#define SMU_METRICS_TABLE_VERSION 0x8
+#define SMU_METRICS_TABLE_VERSION 0x9
 
 typedef struct __attribute__((packed, aligned(4))) {
   uint32_t AccumulationCounter;
@@ -211,6 +211,14 @@ typedef struct __attribute__((packed, aligned(4))) {
   //XGMI Data tranfser size
   uint64_t XgmiReadDataSizeAcc[8];//in KByte
   uint64_t XgmiWriteDataSizeAcc[8];//in KByte
+
+  //PCIE BW Data and error count
+  uint32_t PcieBandwidth[4];
+  uint32_t PCIeL0ToRecoveryCountAcc;      // The Pcie counter itself is accumulated
+  uint32_t PCIenReplayAAcc;               // The Pcie counter itself is accumulated
+  uint32_t PCIenReplayARolloverCountAcc;  // The Pcie counter itself is accumulated
+  uint32_t PCIeNAKSentCountAcc;           // The Pcie counter itself is accumulated
+  uint32_t PCIeNAKReceivedCountAcc;       // The Pcie counter itself is accumulated
 } MetricsTable_t;
 
 #define SMU_VF_METRICS_TABLE_VERSION 0x3
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 762b31455a0b6c..2ff6deedef955e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -2193,8 +2193,7 @@ static int vangogh_get_dpm_clock_table(struct smu_context *smu, struct dpm_clock
 	return 0;
 }
 
-
-static int vangogh_system_features_control(struct smu_context *smu, bool en)
+static int vangogh_notify_rlc_state(struct smu_context *smu, bool en)
 {
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
@@ -2523,7 +2522,7 @@ static const struct pptable_funcs vangogh_ppt_funcs = {
 	.print_clk_levels = vangogh_common_print_clk_levels,
 	.set_default_dpm_table = vangogh_set_default_dpm_tables,
 	.set_fine_grain_gfx_freq_parameters = vangogh_set_fine_grain_gfx_freq_parameters,
-	.system_features_control = vangogh_system_features_control,
+	.notify_rlc_state = vangogh_notify_rlc_state,
 	.feature_is_enabled = smu_cmn_feature_is_enabled,
 	.set_power_profile_mode = vangogh_set_power_profile_mode,
 	.get_power_profile_mode = vangogh_get_power_profile_mode,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index 1a6675d70a4bc4..f1440869d1ce05 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -257,8 +257,11 @@ static int aldebaran_tables_init(struct smu_context *smu)
 	}
 
 	smu_table->ecc_table = kzalloc(tables[SMU_TABLE_ECCINFO].size, GFP_KERNEL);
-	if (!smu_table->ecc_table)
+	if (!smu_table->ecc_table) {
+		kfree(smu_table->metrics_table);
+		kfree(smu_table->gpu_metrics_table);
 		return -ENOMEM;
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 20f66e696f8739..900a2d9e6d8548 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -48,6 +48,7 @@
 #include "smu_cmn.h"
 #include "mp/mp_13_0_6_offset.h"
 #include "mp/mp_13_0_6_sh_mask.h"
+#include "umc_v12_0.h"
 
 #undef MP1_Public
 #undef smnMP1_FIRMWARE_FLAGS
@@ -94,22 +95,11 @@ MODULE_FIRMWARE("amdgpu/smu_13_0_6.bin");
 #define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT 0x5
 #define LINK_SPEED_MAX				4
 
-#define SMU_13_0_6_DSCLK_THRESHOLD 100
+#define SMU_13_0_6_DSCLK_THRESHOLD 140
 
 #define MCA_BANK_IPID(_ip, _hwid, _type) \
 	[AMDGPU_MCA_IP_##_ip] = { .hwid = _hwid, .mcatype = _type, }
 
-enum mca_reg_idx {
-	MCA_REG_IDX_CONTROL		= 0,
-	MCA_REG_IDX_STATUS		= 1,
-	MCA_REG_IDX_ADDR		= 2,
-	MCA_REG_IDX_MISC0		= 3,
-	MCA_REG_IDX_CONFIG		= 4,
-	MCA_REG_IDX_IPID		= 5,
-	MCA_REG_IDX_SYND		= 6,
-	MCA_REG_IDX_COUNT		= 16,
-};
-
 struct mca_bank_ipid {
 	enum amdgpu_mca_ip ip;
 	uint16_t hwid;
@@ -122,7 +112,9 @@ struct mca_ras_info {
 	int *err_code_array;
 	int err_code_count;
 	int (*get_err_count)(const struct mca_ras_info *mca_ras, struct amdgpu_device *adev,
-			     enum amdgpu_mca_error_type type, int idx, uint32_t *count);
+			     enum amdgpu_mca_error_type type, struct mca_bank_entry *entry, uint32_t *count);
+	bool (*bank_is_valid)(const struct mca_ras_info *mca_ras, struct amdgpu_device *adev,
+			      enum amdgpu_mca_error_type type, struct mca_bank_entry *entry);
 };
 
 #define P2S_TABLE_ID_A 0x50325341
@@ -1462,7 +1454,7 @@ static int smu_v13_0_6_register_irq_handler(struct smu_context *smu)
 
 static int smu_v13_0_6_notify_unload(struct smu_context *smu)
 {
-	if (smu->smc_fw_version <= 0x553500)
+	if (amdgpu_in_reset(smu->adev))
 		return 0;
 
 	dev_dbg(smu->adev->dev, "Notify PMFW about driver unload");
@@ -2103,6 +2095,14 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 			smu_v13_0_6_get_current_pcie_link_speed(smu);
 		gpu_metrics->pcie_bandwidth_acc =
 				SMUQ10_ROUND(metrics->PcieBandwidthAcc[0]);
+		gpu_metrics->pcie_bandwidth_inst =
+				SMUQ10_ROUND(metrics->PcieBandwidth[0]);
+		gpu_metrics->pcie_l0_to_recov_count_acc =
+				metrics->PCIeL0ToRecoveryCountAcc;
+		gpu_metrics->pcie_replay_count_acc =
+				metrics->PCIenReplayAAcc;
+		gpu_metrics->pcie_replay_rover_count_acc =
+				metrics->PCIenReplayARolloverCountAcc;
 	}
 
 	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
@@ -2305,7 +2305,7 @@ static int smu_v13_0_6_post_init(struct smu_context *smu)
 	struct amdgpu_device *adev = smu->adev;
 
 	if (!amdgpu_sriov_vf(adev) && adev->ras_enabled)
-		return smu_v13_0_6_mca_set_debug_mode(smu, true);
+		return smu_v13_0_6_mca_set_debug_mode(smu, false);
 
 	return 0;
 }
@@ -2387,6 +2387,7 @@ static const struct mca_bank_ipid smu_v13_0_6_mca_ipid_table[AMDGPU_MCA_IP_COUNT
 	MCA_BANK_IPID(UMC, 0x96, 0x0),
 	MCA_BANK_IPID(SMU, 0x01, 0x1),
 	MCA_BANK_IPID(MP5, 0x01, 0x2),
+	MCA_BANK_IPID(PCS_XGMI, 0x50, 0x0),
 };
 
 static void mca_bank_entry_info_decode(struct mca_bank_entry *entry, struct mca_bank_info *info)
@@ -2448,53 +2449,60 @@ static int mca_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_error_t
 	return 0;
 }
 
-static int mca_decode_mca_ipid(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, int idx, int *ip)
+static int mca_decode_ipid_to_hwip(uint64_t val)
 {
 	const struct mca_bank_ipid *ipid;
-	uint64_t val;
 	uint16_t hwid, mcatype;
-	int i, ret;
-
-	ret = mca_bank_read_reg(adev, type, idx, MCA_REG_IDX_IPID, &val);
-	if (ret)
-		return ret;
+	int i;
 
 	hwid = REG_GET_FIELD(val, MCMP1_IPIDT0, HardwareID);
 	mcatype = REG_GET_FIELD(val, MCMP1_IPIDT0, McaType);
 
-	if (hwid) {
-		for (i = 0; i < ARRAY_SIZE(smu_v13_0_6_mca_ipid_table); i++) {
-			ipid = &smu_v13_0_6_mca_ipid_table[i];
+	for (i = 0; i < ARRAY_SIZE(smu_v13_0_6_mca_ipid_table); i++) {
+		ipid = &smu_v13_0_6_mca_ipid_table[i];
 
-			if (!ipid->hwid)
-				continue;
+		if (!ipid->hwid)
+			continue;
 
-			if (ipid->hwid == hwid && ipid->mcatype == mcatype) {
-				*ip = i;
-				return 0;
-			}
-		}
+		if (ipid->hwid == hwid && ipid->mcatype == mcatype)
+			return i;
+	}
+
+	return AMDGPU_MCA_IP_UNKNOW;
+}
+
+static int mca_umc_mca_get_err_count(const struct mca_ras_info *mca_ras, struct amdgpu_device *adev,
+				     enum amdgpu_mca_error_type type, struct mca_bank_entry *entry, uint32_t *count)
+{
+	uint64_t status0;
+
+	status0 = entry->regs[MCA_REG_IDX_STATUS];
+
+	if (!REG_GET_FIELD(status0, MCMP1_STATUST0, Val)) {
+		*count = 0;
+		return 0;
 	}
 
-	*ip = AMDGPU_MCA_IP_UNKNOW;
+	if (type == AMDGPU_MCA_ERROR_TYPE_UE && umc_v12_0_is_uncorrectable_error(status0))
+		*count = 1;
+	else if (type == AMDGPU_MCA_ERROR_TYPE_CE && umc_v12_0_is_correctable_error(status0))
+		*count = 1;
 
 	return 0;
 }
 
-static int mca_normal_mca_get_err_count(const struct mca_ras_info *mca_ras, struct amdgpu_device *adev,
-					enum amdgpu_mca_error_type type, int idx, uint32_t *count)
+static int mca_pcs_xgmi_mca_get_err_count(const struct mca_ras_info *mca_ras, struct amdgpu_device *adev,
+					  enum amdgpu_mca_error_type type, struct mca_bank_entry *entry,
+					  uint32_t *count)
 {
-	uint64_t status0;
-	int ret;
+	u32 ext_error_code;
 
-	ret = mca_bank_read_reg(adev, type, idx, MCA_REG_IDX_STATUS, &status0);
-	if (ret)
-		return ret;
+	ext_error_code = MCA_REG__STATUS__ERRORCODEEXT(entry->regs[MCA_REG_IDX_STATUS]);
 
-	if (REG_GET_FIELD(status0, MCMP1_STATUST0, Val))
+	if (type == AMDGPU_MCA_ERROR_TYPE_UE && ext_error_code == 0)
+		*count = 1;
+	else if (type == AMDGPU_MCA_ERROR_TYPE_CE && ext_error_code == 6)
 		*count = 1;
-	else
-		*count = 0;
 
 	return 0;
 }
@@ -2515,70 +2523,41 @@ static bool mca_smu_check_error_code(struct amdgpu_device *adev, const struct mc
 	return false;
 }
 
-static int mca_mp5_mca_get_err_count(const struct mca_ras_info *mca_ras, struct amdgpu_device *adev,
-				     enum amdgpu_mca_error_type type, int idx, uint32_t *count)
+static int mca_gfx_mca_get_err_count(const struct mca_ras_info *mca_ras, struct amdgpu_device *adev,
+				     enum amdgpu_mca_error_type type, struct mca_bank_entry *entry, uint32_t *count)
 {
-	uint64_t status0 = 0, misc0 = 0;
-	uint32_t errcode;
-	int ret;
-
-	if (mca_ras->ip != AMDGPU_MCA_IP_MP5)
-		return -EINVAL;
-
-	ret = mca_bank_read_reg(adev, type, idx, MCA_REG_IDX_STATUS, &status0);
-	if (ret)
-		return ret;
+	uint64_t status0, misc0;
 
+	status0 = entry->regs[MCA_REG_IDX_STATUS];
 	if (!REG_GET_FIELD(status0, MCMP1_STATUST0, Val)) {
 		*count = 0;
 		return 0;
 	}
 
-	errcode = REG_GET_FIELD(status0, MCMP1_STATUST0, ErrorCode);
-	if (!mca_smu_check_error_code(adev, mca_ras, errcode))
-		return 0;
-
 	if (type == AMDGPU_MCA_ERROR_TYPE_UE &&
 	    REG_GET_FIELD(status0, MCMP1_STATUST0, UC) == 1 &&
 	    REG_GET_FIELD(status0, MCMP1_STATUST0, PCC) == 1) {
-		if (count)
-			*count = 1;
+		*count = 1;
 		return 0;
-	}
-
-	ret = mca_bank_read_reg(adev, type, idx, MCA_REG_IDX_MISC0, &misc0);
-	if (ret)
-		return ret;
-
-	if (count)
+	} else {
+		misc0 = entry->regs[MCA_REG_IDX_MISC0];
 		*count = REG_GET_FIELD(misc0, MCMP1_MISC0T0, ErrCnt);
+	}
 
 	return 0;
 }
 
 static int mca_smu_mca_get_err_count(const struct mca_ras_info *mca_ras, struct amdgpu_device *adev,
-				     enum amdgpu_mca_error_type type, int idx, uint32_t *count)
+				     enum amdgpu_mca_error_type type, struct mca_bank_entry *entry, uint32_t *count)
 {
-	uint64_t status0 = 0, misc0 = 0;
-	uint32_t errcode;
-	int ret;
-
-	if (mca_ras->ip != AMDGPU_MCA_IP_SMU)
-		return -EINVAL;
-
-	ret = mca_bank_read_reg(adev, type, idx, MCA_REG_IDX_STATUS, &status0);
-	if (ret)
-		return ret;
+	uint64_t status0, misc0;
 
+	status0 = entry->regs[MCA_REG_IDX_STATUS];
 	if (!REG_GET_FIELD(status0, MCMP1_STATUST0, Val)) {
 		*count = 0;
 		return 0;
 	}
 
-	errcode = REG_GET_FIELD(status0, MCMP1_STATUST0, ErrorCode);
-	if (!mca_smu_check_error_code(adev, mca_ras, errcode))
-		return 0;
-
 	if (type == AMDGPU_MCA_ERROR_TYPE_UE &&
 	    REG_GET_FIELD(status0, MCMP1_STATUST0, UC) == 1 &&
 	    REG_GET_FIELD(status0, MCMP1_STATUST0, PCC) == 1) {
@@ -2587,16 +2566,50 @@ static int mca_smu_mca_get_err_count(const struct mca_ras_info *mca_ras, struct
 		return 0;
 	}
 
-	ret = mca_bank_read_reg(adev, type, idx, MCA_REG_IDX_MISC0, &misc0);
-	if (ret)
-		return ret;
-
-	if (count)
-		*count = REG_GET_FIELD(misc0, MCMP1_MISC0T0, ErrCnt);
+	misc0 = entry->regs[MCA_REG_IDX_MISC0];
+	*count = REG_GET_FIELD(misc0, MCMP1_MISC0T0, ErrCnt);
 
 	return 0;
 }
 
+static bool mca_gfx_smu_bank_is_valid(const struct mca_ras_info *mca_ras, struct amdgpu_device *adev,
+				      enum amdgpu_mca_error_type type, struct mca_bank_entry *entry)
+{
+	uint32_t instlo;
+
+	instlo = REG_GET_FIELD(entry->regs[MCA_REG_IDX_IPID], MCMP1_IPIDT0, InstanceIdLo);
+	switch (instlo) {
+	case 0x36430400: /* SMNAID XCD 0 */
+	case 0x38430400: /* SMNAID XCD 1 */
+	case 0x40430400: /* SMNXCD XCD 0, NOTE: FIXME: fix this error later */
+		return true;
+	default:
+		return false;
+	}
+
+	return false;
+};
+
+static bool mca_smu_bank_is_valid(const struct mca_ras_info *mca_ras, struct amdgpu_device *adev,
+				  enum amdgpu_mca_error_type type, struct mca_bank_entry *entry)
+{
+	struct smu_context *smu = adev->powerplay.pp_handle;
+	uint32_t errcode, instlo;
+
+	instlo = REG_GET_FIELD(entry->regs[MCA_REG_IDX_IPID], MCMP1_IPIDT0, InstanceIdLo);
+	if (instlo != 0x03b30400)
+		return false;
+
+	if (!(adev->flags & AMD_IS_APU) && smu->smc_fw_version >= 0x00555600) {
+		errcode = MCA_REG__SYND__ERRORINFORMATION(entry->regs[MCA_REG_IDX_SYND]);
+		errcode &= 0xff;
+	} else {
+		errcode = REG_GET_FIELD(entry->regs[MCA_REG_IDX_STATUS], MCMP1_STATUST0, ErrorCode);
+	}
+
+	return mca_smu_check_error_code(adev, mca_ras, errcode);
+}
+
 static int sdma_err_codes[] = { CODE_SDMA0, CODE_SDMA1, CODE_SDMA2, CODE_SDMA3 };
 static int mmhub_err_codes[] = {
 	CODE_DAGB0, CODE_DAGB0 + 1, CODE_DAGB0 + 2, CODE_DAGB0 + 3, CODE_DAGB0 + 4, /* DAGB0-4 */
@@ -2608,23 +2621,30 @@ static const struct mca_ras_info mca_ras_table[] = {
 	{
 		.blkid = AMDGPU_RAS_BLOCK__UMC,
 		.ip = AMDGPU_MCA_IP_UMC,
-		.get_err_count = mca_normal_mca_get_err_count,
+		.get_err_count = mca_umc_mca_get_err_count,
 	}, {
 		.blkid = AMDGPU_RAS_BLOCK__GFX,
-		.ip = AMDGPU_MCA_IP_MP5,
-		.get_err_count = mca_mp5_mca_get_err_count,
+		.ip = AMDGPU_MCA_IP_SMU,
+		.get_err_count = mca_gfx_mca_get_err_count,
+		.bank_is_valid = mca_gfx_smu_bank_is_valid,
 	}, {
 		.blkid = AMDGPU_RAS_BLOCK__SDMA,
 		.ip = AMDGPU_MCA_IP_SMU,
 		.err_code_array = sdma_err_codes,
 		.err_code_count = ARRAY_SIZE(sdma_err_codes),
 		.get_err_count = mca_smu_mca_get_err_count,
+		.bank_is_valid = mca_smu_bank_is_valid,
 	}, {
 		.blkid = AMDGPU_RAS_BLOCK__MMHUB,
 		.ip = AMDGPU_MCA_IP_SMU,
 		.err_code_array = mmhub_err_codes,
 		.err_code_count = ARRAY_SIZE(mmhub_err_codes),
 		.get_err_count = mca_smu_mca_get_err_count,
+		.bank_is_valid = mca_smu_bank_is_valid,
+	}, {
+		.blkid = AMDGPU_RAS_BLOCK__XGMI_WAFL,
+		.ip = AMDGPU_MCA_IP_PCS_XGMI,
+		.get_err_count = mca_pcs_xgmi_mca_get_err_count,
 	},
 };
 
@@ -2659,130 +2679,84 @@ static int mca_get_valid_mca_count(struct amdgpu_device *adev, enum amdgpu_mca_e
 }
 
 static bool mca_bank_is_valid(struct amdgpu_device *adev, const struct mca_ras_info *mca_ras,
-			      enum amdgpu_mca_error_type type, int idx)
+			      enum amdgpu_mca_error_type type, struct mca_bank_entry *entry)
 {
-	int ret, ip = AMDGPU_MCA_IP_UNKNOW;
-
-	ret = mca_decode_mca_ipid(adev, type, idx, &ip);
-	if (ret)
-		return false;
-
-	if (ip == AMDGPU_MCA_IP_UNKNOW)
+	if (mca_decode_ipid_to_hwip(entry->regs[MCA_REG_IDX_IPID]) != mca_ras->ip)
 		return false;
 
-	return ip == mca_ras->ip;
-}
+	if (mca_ras->bank_is_valid)
+		return mca_ras->bank_is_valid(mca_ras, adev, type, entry);
 
-static int mca_get_valid_mca_idx(struct amdgpu_device *adev, const struct mca_ras_info *mca_ras,
-				 enum amdgpu_mca_error_type type,
-				 uint32_t mca_cnt, int *idx_array, int idx_array_size)
-{
-	int i, idx_cnt = 0;
-
-	for (i = 0; i < mca_cnt; i++) {
-		if (!mca_bank_is_valid(adev, mca_ras, type, i))
-			continue;
-
-		if (idx_array) {
-			if (idx_cnt < idx_array_size)
-				idx_array[idx_cnt] = i;
-			else
-				return -EINVAL;
-		}
-
-		idx_cnt++;
-	}
-
-	return idx_cnt;
+	return true;
 }
 
-static int __mca_smu_get_error_count(struct amdgpu_device *adev, const struct mca_ras_info *mca_ras, enum amdgpu_mca_error_type type, uint32_t *count)
+static int __mca_smu_get_ras_mca_set(struct amdgpu_device *adev, const struct mca_ras_info *mca_ras,
+				     enum amdgpu_mca_error_type type, struct mca_bank_set *mca_set)
 {
-	uint32_t result, mca_cnt, total = 0;
-	int idx_array[16];
-	int i, ret, idx_cnt = 0;
+	struct mca_bank_entry entry;
+	uint32_t mca_cnt;
+	int i, ret;
 
 	ret = mca_get_valid_mca_count(adev, type, &mca_cnt);
 	if (ret)
 		return ret;
 
 	/* if valid mca bank count is 0, the driver can return 0 directly */
-	if (!mca_cnt) {
-		*count = 0;
+	if (!mca_cnt)
 		return 0;
-	}
 
-	if (!mca_ras->get_err_count)
-		return -EINVAL;
+	for (i = 0; i < mca_cnt; i++) {
+		memset(&entry, 0, sizeof(entry));
+		ret = mca_get_mca_entry(adev, type, i, &entry);
+		if (ret)
+			return ret;
 
-	idx_cnt = mca_get_valid_mca_idx(adev, mca_ras, type, mca_cnt, idx_array, ARRAY_SIZE(idx_array));
-	if (idx_cnt < 0)
-		return -EINVAL;
+		if (mca_ras && !mca_bank_is_valid(adev, mca_ras, type, &entry))
+			continue;
 
-	for (i = 0; i < idx_cnt; i++) {
-		result = 0;
-		ret = mca_ras->get_err_count(mca_ras, adev, type, idx_array[i], &result);
+		ret = amdgpu_mca_bank_set_add_entry(mca_set, &entry);
 		if (ret)
 			return ret;
-
-		total += result;
 	}
 
-	*count = total;
-
 	return 0;
 }
 
-static int mca_smu_get_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
-				   enum amdgpu_mca_error_type type, uint32_t *count)
+static int mca_smu_get_ras_mca_set(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
+				   enum amdgpu_mca_error_type type, struct mca_bank_set *mca_set)
 {
-	const struct mca_ras_info *mca_ras;
+	const struct mca_ras_info *mca_ras = NULL;
 
-	if (!count)
+	if (!mca_set)
 		return -EINVAL;
 
-	mca_ras = mca_get_mca_ras_info(adev, blk);
-	if (!mca_ras)
-		return -EOPNOTSUPP;
-
-	return __mca_smu_get_error_count(adev, mca_ras, type, count);
-}
-
-static int __mca_smu_get_ras_mca_idx_array(struct amdgpu_device *adev, const struct mca_ras_info *mca_ras,
-					   enum amdgpu_mca_error_type type, int *idx_array, int *idx_array_size)
-{
-	uint32_t mca_cnt = 0;
-	int ret, idx_cnt = 0;
-
-	ret = mca_get_valid_mca_count(adev, type, &mca_cnt);
-	if (ret)
-		return ret;
-
-	/* if valid mca bank count is 0, the driver can return 0 directly */
-	if (!mca_cnt) {
-		*idx_array_size = 0;
-		return 0;
+	if (blk != AMDGPU_RAS_BLOCK_COUNT) {
+		mca_ras = mca_get_mca_ras_info(adev, blk);
+		if (!mca_ras)
+			return -EOPNOTSUPP;
 	}
 
-	idx_cnt = mca_get_valid_mca_idx(adev, mca_ras, type, mca_cnt, idx_array, *idx_array_size);
-	if (idx_cnt < 0)
-		return -EINVAL;
-
-	*idx_array_size = idx_cnt;
-
-	return 0;
+	return __mca_smu_get_ras_mca_set(adev, mca_ras, type, mca_set);
 }
 
-static int mca_smu_get_ras_mca_idx_array(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
-					 enum amdgpu_mca_error_type type, int *idx_array, int *idx_array_size)
+static int mca_smu_parse_mca_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type,
+					 struct mca_bank_entry *entry, uint32_t *count)
 {
 	const struct mca_ras_info *mca_ras;
 
+	if (!entry || !count)
+		return -EINVAL;
+
 	mca_ras = mca_get_mca_ras_info(adev, blk);
 	if (!mca_ras)
 		return -EOPNOTSUPP;
 
-	return __mca_smu_get_ras_mca_idx_array(adev, mca_ras, type, idx_array, idx_array_size);
+	if (!mca_bank_is_valid(adev, mca_ras, type, entry)) {
+		*count = 0;
+		return 0;
+	}
+
+	return mca_ras->get_err_count(mca_ras, adev, type, entry, count);
 }
 
 static int mca_smu_get_mca_entry(struct amdgpu_device *adev,
@@ -2801,10 +2775,10 @@ static const struct amdgpu_mca_smu_funcs smu_v13_0_6_mca_smu_funcs = {
 	.max_ue_count = 12,
 	.max_ce_count = 12,
 	.mca_set_debug_mode = mca_smu_set_debug_mode,
-	.mca_get_error_count = mca_smu_get_error_count,
+	.mca_get_ras_mca_set = mca_smu_get_ras_mca_set,
+	.mca_parse_mca_error_count = mca_smu_parse_mca_error_count,
 	.mca_get_mca_entry = mca_smu_get_mca_entry,
 	.mca_get_valid_mca_count = mca_smu_get_valid_mca_count,
-	.mca_get_ras_mca_idx_array = mca_smu_get_ras_mca_idx_array,
 };
 
 static int smu_v13_0_6_select_xgmi_plpd_policy(struct smu_context *smu,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index 03b38c3a996843..94ccdbfd709092 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -246,11 +246,20 @@ static int smu_v14_0_0_get_smu_metrics_data(struct smu_context *smu,
 		*value = 0;
 		break;
 	case METRICS_AVERAGE_UCLK:
-		*value = 0;
+		*value = metrics->MemclkFrequency;
 		break;
 	case METRICS_AVERAGE_FCLK:
 		*value = metrics->FclkFrequency;
 		break;
+	case METRICS_AVERAGE_VPECLK:
+		*value = metrics->VpeclkFrequency;
+		break;
+	case METRICS_AVERAGE_IPUCLK:
+		*value = metrics->IpuclkFrequency;
+		break;
+	case METRICS_AVERAGE_MPIPUCLK:
+		*value = metrics->MpipuclkFrequency;
+		break;
 	case METRICS_AVERAGE_GFXACTIVITY:
 		*value = metrics->GfxActivity / 100;
 		break;
@@ -270,8 +279,26 @@ static int smu_v14_0_0_get_smu_metrics_data(struct smu_context *smu,
 		*value = metrics->SocTemperature / 100 *
 		SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 		break;
-	case METRICS_THROTTLER_STATUS:
-		*value = 0;
+	case METRICS_THROTTLER_RESIDENCY_PROCHOT:
+		*value = metrics->ThrottleResidency_PROCHOT;
+		break;
+	case METRICS_THROTTLER_RESIDENCY_SPL:
+		*value = metrics->ThrottleResidency_SPL;
+		break;
+	case METRICS_THROTTLER_RESIDENCY_FPPT:
+		*value = metrics->ThrottleResidency_FPPT;
+		break;
+	case METRICS_THROTTLER_RESIDENCY_SPPT:
+		*value = metrics->ThrottleResidency_SPPT;
+		break;
+	case METRICS_THROTTLER_RESIDENCY_THM_CORE:
+		*value = metrics->ThrottleResidency_THM_CORE;
+		break;
+	case METRICS_THROTTLER_RESIDENCY_THM_GFX:
+		*value = metrics->ThrottleResidency_THM_GFX;
+		break;
+	case METRICS_THROTTLER_RESIDENCY_THM_SOC:
+		*value = metrics->ThrottleResidency_THM_SOC;
 		break;
 	case METRICS_VOLTAGE_VDDGFX:
 		*value = 0;
@@ -498,6 +525,8 @@ static ssize_t smu_v14_0_0_get_gpu_metrics(struct smu_context *smu,
 		sizeof(uint16_t) * 16);
 	gpu_metrics->average_dram_reads = metrics.DRAMReads;
 	gpu_metrics->average_dram_writes = metrics.DRAMWrites;
+	gpu_metrics->average_ipu_reads = metrics.IpuReads;
+	gpu_metrics->average_ipu_writes = metrics.IpuWrites;
 
 	gpu_metrics->average_socket_power = metrics.SocketPower;
 	gpu_metrics->average_ipu_power = metrics.IpuPower;
@@ -505,6 +534,7 @@ static ssize_t smu_v14_0_0_get_gpu_metrics(struct smu_context *smu,
 	gpu_metrics->average_gfx_power = metrics.GfxPower;
 	gpu_metrics->average_dgpu_power = metrics.dGpuPower;
 	gpu_metrics->average_all_core_power = metrics.AllCorePower;
+	gpu_metrics->average_sys_power = metrics.Psys;
 	memcpy(&gpu_metrics->average_core_power[0],
 		&metrics.CorePower[0],
 		sizeof(uint16_t) * 16);
@@ -515,6 +545,8 @@ static ssize_t smu_v14_0_0_get_gpu_metrics(struct smu_context *smu,
 	gpu_metrics->average_fclk_frequency = metrics.FclkFrequency;
 	gpu_metrics->average_vclk_frequency = metrics.VclkFrequency;
 	gpu_metrics->average_ipuclk_frequency = metrics.IpuclkFrequency;
+	gpu_metrics->average_uclk_frequency = metrics.MemclkFrequency;
+	gpu_metrics->average_mpipu_frequency = metrics.MpipuclkFrequency;
 
 	memcpy(&gpu_metrics->current_coreclk[0],
 		&metrics.CoreFrequency[0],
@@ -522,6 +554,14 @@ static ssize_t smu_v14_0_0_get_gpu_metrics(struct smu_context *smu,
 	gpu_metrics->current_core_maxfreq = metrics.InfrastructureCpuMaxFreq;
 	gpu_metrics->current_gfx_maxfreq = metrics.InfrastructureGfxMaxFreq;
 
+	gpu_metrics->throttle_residency_prochot = metrics.ThrottleResidency_PROCHOT;
+	gpu_metrics->throttle_residency_spl = metrics.ThrottleResidency_SPL;
+	gpu_metrics->throttle_residency_fppt = metrics.ThrottleResidency_FPPT;
+	gpu_metrics->throttle_residency_sppt = metrics.ThrottleResidency_SPPT;
+	gpu_metrics->throttle_residency_thm_core = metrics.ThrottleResidency_THM_CORE;
+	gpu_metrics->throttle_residency_thm_gfx = metrics.ThrottleResidency_THM_GFX;
+	gpu_metrics->throttle_residency_thm_soc = metrics.ThrottleResidency_THM_SOC;
+
 	gpu_metrics->time_filter_alphavalue = metrics.FilterAlphaValue;
 	gpu_metrics->system_clock_counter = ktime_get_boottime_ns();
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
index 80b3c3efc006de..64766ac69c53bf 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
@@ -97,6 +97,7 @@
 #define smu_get_default_config_table_settings(smu, config_table)	smu_ppt_funcs(get_default_config_table_settings, -EOPNOTSUPP, smu, config_table)
 #define smu_set_config_table(smu, config_table)				smu_ppt_funcs(set_config_table, -EOPNOTSUPP, smu, config_table)
 #define smu_init_pptable_microcode(smu)					smu_ppt_funcs(init_pptable_microcode, 0, smu)
+#define smu_notify_rlc_state(smu, en)					smu_ppt_funcs(notify_rlc_state, 0, smu, en)
 
 #endif
 #endif
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 2aee32344f4a25..772f3b049c1694 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -174,6 +174,17 @@ to_ast_sil164_connector(struct drm_connector *connector)
 	return container_of(connector, struct ast_sil164_connector, base);
 }
 
+struct ast_bmc_connector {
+	struct drm_connector base;
+	struct drm_connector *physical_connector;
+};
+
+static inline struct ast_bmc_connector *
+to_ast_bmc_connector(struct drm_connector *connector)
+{
+	return container_of(connector, struct ast_bmc_connector, base);
+}
+
 /*
  * Device
  */
@@ -218,7 +229,7 @@ struct ast_device {
 		} astdp;
 		struct {
 			struct drm_encoder encoder;
-			struct drm_connector connector;
+			struct ast_bmc_connector bmc_connector;
 		} bmc;
 	} output;
 
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index cb96149842851a..c20534d0ef7c8a 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -1767,6 +1767,30 @@ static const struct drm_encoder_funcs ast_bmc_encoder_funcs = {
 	.destroy = drm_encoder_cleanup,
 };
 
+static int ast_bmc_connector_helper_detect_ctx(struct drm_connector *connector,
+					       struct drm_modeset_acquire_ctx *ctx,
+					       bool force)
+{
+	struct ast_bmc_connector *bmc_connector = to_ast_bmc_connector(connector);
+	struct drm_connector *physical_connector = bmc_connector->physical_connector;
+
+	/*
+	 * Most user-space compositors cannot handle more than one connected
+	 * connector per CRTC. Hence, we only mark the BMC as connected if the
+	 * physical connector is disconnected. If the physical connector's status
+	 * is connected or unknown, the BMC remains disconnected. This has no
+	 * effect on the output of the BMC.
+	 *
+	 * FIXME: Remove this logic once user-space compositors can handle more
+	 *        than one connector per CRTC. The BMC should always be connected.
+	 */
+
+	if (physical_connector && physical_connector->status == connector_status_disconnected)
+		return connector_status_connected;
+
+	return connector_status_disconnected;
+}
+
 static int ast_bmc_connector_helper_get_modes(struct drm_connector *connector)
 {
 	return drm_add_modes_noedid(connector, 4096, 4096);
@@ -1774,6 +1798,7 @@ static int ast_bmc_connector_helper_get_modes(struct drm_connector *connector)
 
 static const struct drm_connector_helper_funcs ast_bmc_connector_helper_funcs = {
 	.get_modes = ast_bmc_connector_helper_get_modes,
+	.detect_ctx = ast_bmc_connector_helper_detect_ctx,
 };
 
 static const struct drm_connector_funcs ast_bmc_connector_funcs = {
@@ -1784,12 +1809,33 @@ static const struct drm_connector_funcs ast_bmc_connector_funcs = {
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
-static int ast_bmc_output_init(struct ast_device *ast)
+static int ast_bmc_connector_init(struct drm_device *dev,
+				  struct ast_bmc_connector *bmc_connector,
+				  struct drm_connector *physical_connector)
+{
+	struct drm_connector *connector = &bmc_connector->base;
+	int ret;
+
+	ret = drm_connector_init(dev, connector, &ast_bmc_connector_funcs,
+				 DRM_MODE_CONNECTOR_VIRTUAL);
+	if (ret)
+		return ret;
+
+	drm_connector_helper_add(connector, &ast_bmc_connector_helper_funcs);
+
+	bmc_connector->physical_connector = physical_connector;
+
+	return 0;
+}
+
+static int ast_bmc_output_init(struct ast_device *ast,
+			       struct drm_connector *physical_connector)
 {
 	struct drm_device *dev = &ast->base;
 	struct drm_crtc *crtc = &ast->crtc;
 	struct drm_encoder *encoder = &ast->output.bmc.encoder;
-	struct drm_connector *connector = &ast->output.bmc.connector;
+	struct ast_bmc_connector *bmc_connector = &ast->output.bmc.bmc_connector;
+	struct drm_connector *connector = &bmc_connector->base;
 	int ret;
 
 	ret = drm_encoder_init(dev, encoder,
@@ -1799,13 +1845,10 @@ static int ast_bmc_output_init(struct ast_device *ast)
 		return ret;
 	encoder->possible_crtcs = drm_crtc_mask(crtc);
 
-	ret = drm_connector_init(dev, connector, &ast_bmc_connector_funcs,
-				 DRM_MODE_CONNECTOR_VIRTUAL);
+	ret = ast_bmc_connector_init(dev, bmc_connector, physical_connector);
 	if (ret)
 		return ret;
 
-	drm_connector_helper_add(connector, &ast_bmc_connector_helper_funcs);
-
 	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret)
 		return ret;
@@ -1864,6 +1907,7 @@ static const struct drm_mode_config_funcs ast_mode_config_funcs = {
 int ast_mode_config_init(struct ast_device *ast)
 {
 	struct drm_device *dev = &ast->base;
+	struct drm_connector *physical_connector = NULL;
 	int ret;
 
 	ret = drmm_mode_config_init(dev);
@@ -1904,23 +1948,27 @@ int ast_mode_config_init(struct ast_device *ast)
 		ret = ast_vga_output_init(ast);
 		if (ret)
 			return ret;
+		physical_connector = &ast->output.vga.vga_connector.base;
 	}
 	if (ast->tx_chip_types & AST_TX_SIL164_BIT) {
 		ret = ast_sil164_output_init(ast);
 		if (ret)
 			return ret;
+		physical_connector = &ast->output.sil164.sil164_connector.base;
 	}
 	if (ast->tx_chip_types & AST_TX_DP501_BIT) {
 		ret = ast_dp501_output_init(ast);
 		if (ret)
 			return ret;
+		physical_connector = &ast->output.dp501.connector;
 	}
 	if (ast->tx_chip_types & AST_TX_ASTDP_BIT) {
 		ret = ast_astdp_output_init(ast);
 		if (ret)
 			return ret;
+		physical_connector = &ast->output.astdp.connector;
 	}
-	ret = ast_bmc_output_init(ast);
+	ret = ast_bmc_output_init(ast, physical_connector);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index ba82a1142adf73..3e6a4e2044c0eb 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -313,6 +313,7 @@ config DRM_TOSHIBA_TC358768
 	select REGMAP_I2C
 	select DRM_PANEL
 	select DRM_MIPI_DSI
+	select VIDEOMODE_HELPERS
 	help
 	  Toshiba TC358768AXBG/TC358778XBG DSI bridge chip driver.
 
diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c
index e48823a4f1edef..7f41525f7a6e61 100644
--- a/drivers/gpu/drm/bridge/panel.c
+++ b/drivers/gpu/drm/bridge/panel.c
@@ -4,8 +4,6 @@
  * Copyright (C) 2017 Broadcom
  */
 
-#include <linux/device.h>
-
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_bridge.h>
 #include <drm/drm_connector.h>
@@ -21,7 +19,6 @@ struct panel_bridge {
 	struct drm_bridge bridge;
 	struct drm_connector connector;
 	struct drm_panel *panel;
-	struct device_link *link;
 	u32 connector_type;
 };
 
@@ -63,24 +60,13 @@ static int panel_bridge_attach(struct drm_bridge *bridge,
 {
 	struct panel_bridge *panel_bridge = drm_bridge_to_panel_bridge(bridge);
 	struct drm_connector *connector = &panel_bridge->connector;
-	struct drm_panel *panel = panel_bridge->panel;
-	struct drm_device *drm_dev = bridge->dev;
 	int ret;
 
-	panel_bridge->link = device_link_add(drm_dev->dev, panel->dev,
-					     DL_FLAG_STATELESS);
-	if (!panel_bridge->link) {
-		DRM_ERROR("Failed to add device link between %s and %s\n",
-			  dev_name(drm_dev->dev), dev_name(panel->dev));
-		return -EINVAL;
-	}
-
 	if (flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR)
 		return 0;
 
 	if (!bridge->encoder) {
 		DRM_ERROR("Missing encoder\n");
-		device_link_del(panel_bridge->link);
 		return -ENODEV;
 	}
 
@@ -92,7 +78,6 @@ static int panel_bridge_attach(struct drm_bridge *bridge,
 				 panel_bridge->connector_type);
 	if (ret) {
 		DRM_ERROR("Failed to initialize connector\n");
-		device_link_del(panel_bridge->link);
 		return ret;
 	}
 
@@ -115,8 +100,6 @@ static void panel_bridge_detach(struct drm_bridge *bridge)
 	struct panel_bridge *panel_bridge = drm_bridge_to_panel_bridge(bridge);
 	struct drm_connector *connector = &panel_bridge->connector;
 
-	device_link_del(panel_bridge->link);
-
 	/*
 	 * Cleanup the connector if we know it was initialized.
 	 *
diff --git a/drivers/gpu/drm/ci/xfails/requirements.txt b/drivers/gpu/drm/ci/xfails/requirements.txt
index d8856d1581fdb3..e9994c9db799bf 100644
--- a/drivers/gpu/drm/ci/xfails/requirements.txt
+++ b/drivers/gpu/drm/ci/xfails/requirements.txt
@@ -5,7 +5,7 @@ termcolor==2.3.0
 certifi==2023.7.22
 charset-normalizer==3.2.0
 idna==3.4
-pip==23.2.1
+pip==23.3
 python-gitlab==3.15.0
 requests==2.31.0
 requests-toolbelt==1.0.0
@@ -13,5 +13,5 @@ ruamel.yaml==0.17.32
 ruamel.yaml.clib==0.2.7
 setuptools==68.0.0
 tenacity==8.2.3
-urllib3==2.0.4
-wheel==0.41.1
\ No newline at end of file
+urllib3==2.0.7
+wheel==0.41.1
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 2444fc33dd7c77..68ffcc0b00dca1 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -2012,7 +2012,7 @@ int drm_atomic_helper_commit(struct drm_device *dev,
 			return ret;
 
 		drm_atomic_helper_async_commit(dev, state);
-		drm_atomic_helper_cleanup_planes(dev, state);
+		drm_atomic_helper_unprepare_planes(dev, state);
 
 		return 0;
 	}
@@ -2072,7 +2072,7 @@ int drm_atomic_helper_commit(struct drm_device *dev,
 	return 0;
 
 err:
-	drm_atomic_helper_cleanup_planes(dev, state);
+	drm_atomic_helper_unprepare_planes(dev, state);
 	return ret;
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit);
@@ -2650,6 +2650,39 @@ fail_prepare_fb:
 }
 EXPORT_SYMBOL(drm_atomic_helper_prepare_planes);
 
+/**
+ * drm_atomic_helper_unprepare_planes - release plane resources on aborts
+ * @dev: DRM device
+ * @state: atomic state object with old state structures
+ *
+ * This function cleans up plane state, specifically framebuffers, from the
+ * atomic state. It undoes the effects of drm_atomic_helper_prepare_planes()
+ * when aborting an atomic commit. For cleaning up after a successful commit
+ * use drm_atomic_helper_cleanup_planes().
+ */
+void drm_atomic_helper_unprepare_planes(struct drm_device *dev,
+					struct drm_atomic_state *state)
+{
+	struct drm_plane *plane;
+	struct drm_plane_state *new_plane_state;
+	int i;
+
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
+
+		if (funcs->end_fb_access)
+			funcs->end_fb_access(plane, new_plane_state);
+	}
+
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
+
+		if (funcs->cleanup_fb)
+			funcs->cleanup_fb(plane, new_plane_state);
+	}
+}
+EXPORT_SYMBOL(drm_atomic_helper_unprepare_planes);
+
 static bool plane_crtc_active(const struct drm_plane_state *state)
 {
 	return state->crtc && state->crtc->state->active;
@@ -2784,6 +2817,17 @@ void drm_atomic_helper_commit_planes(struct drm_device *dev,
 
 		funcs->atomic_flush(crtc, old_state);
 	}
+
+	/*
+	 * Signal end of framebuffer access here before hw_done. After hw_done,
+	 * a later commit might have already released the plane state.
+	 */
+	for_each_old_plane_in_state(old_state, plane, old_plane_state, i) {
+		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
+
+		if (funcs->end_fb_access)
+			funcs->end_fb_access(plane, old_plane_state);
+	}
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit_planes);
 
@@ -2911,40 +2955,22 @@ EXPORT_SYMBOL(drm_atomic_helper_disable_planes_on_crtc);
  * configuration. Hence the old configuration must be perserved in @old_state to
  * be able to call this function.
  *
- * This function must also be called on the new state when the atomic update
- * fails at any point after calling drm_atomic_helper_prepare_planes().
+ * This function may not be called on the new state when the atomic update
+ * fails at any point after calling drm_atomic_helper_prepare_planes(). Use
+ * drm_atomic_helper_unprepare_planes() in this case.
  */
 void drm_atomic_helper_cleanup_planes(struct drm_device *dev,
 				      struct drm_atomic_state *old_state)
 {
 	struct drm_plane *plane;
-	struct drm_plane_state *old_plane_state, *new_plane_state;
+	struct drm_plane_state *old_plane_state;
 	int i;
 
-	for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) {
+	for_each_old_plane_in_state(old_state, plane, old_plane_state, i) {
 		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
 
-		if (funcs->end_fb_access)
-			funcs->end_fb_access(plane, new_plane_state);
-	}
-
-	for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) {
-		const struct drm_plane_helper_funcs *funcs;
-		struct drm_plane_state *plane_state;
-
-		/*
-		 * This might be called before swapping when commit is aborted,
-		 * in which case we have to cleanup the new state.
-		 */
-		if (old_plane_state == plane->state)
-			plane_state = new_plane_state;
-		else
-			plane_state = old_plane_state;
-
-		funcs = plane->helper_private;
-
 		if (funcs->cleanup_fb)
-			funcs->cleanup_fb(plane, plane_state);
+			funcs->cleanup_fb(plane, old_plane_state);
 	}
 }
 EXPORT_SYMBOL(drm_atomic_helper_cleanup_planes);
diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c
index 2ed2585ded3784..6899b3dc1f12a5 100644
--- a/drivers/gpu/drm/drm_auth.c
+++ b/drivers/gpu/drm/drm_auth.c
@@ -236,7 +236,7 @@ static int
 drm_master_check_perm(struct drm_device *dev, struct drm_file *file_priv)
 {
 	if (file_priv->was_master &&
-	    rcu_access_pointer(file_priv->pid) == task_pid(current))
+	    rcu_access_pointer(file_priv->pid) == task_tgid(current))
 		return 0;
 
 	if (!capable(CAP_SYS_ADMIN))
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index df9bf3c9206e71..cb90e70d85e862 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -715,8 +715,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 	struct drm_mode_set set;
 	uint32_t __user *set_connectors_ptr;
 	struct drm_modeset_acquire_ctx ctx;
-	int ret;
-	int i;
+	int ret, i, num_connectors = 0;
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
@@ -871,6 +870,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 					connector->name);
 
 			connector_set[i] = connector;
+			num_connectors++;
 		}
 	}
 
@@ -879,7 +879,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 	set.y = crtc_req->y;
 	set.mode = mode;
 	set.connectors = connector_set;
-	set.num_connectors = crtc_req->count_connectors;
+	set.num_connectors = num_connectors;
 	set.fb = fb;
 
 	if (drm_drv_uses_atomic_modeset(dev))
@@ -892,7 +892,7 @@ out:
 		drm_framebuffer_put(fb);
 
 	if (connector_set) {
-		for (i = 0; i < crtc_req->count_connectors; i++) {
+		for (i = 0; i < num_connectors; i++) {
 			if (connector_set[i])
 				drm_connector_put(connector_set[i]);
 		}
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 39db08f803eac2..3b40650998728c 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -2309,7 +2309,8 @@ int drm_edid_override_connector_update(struct drm_connector *connector)
 
 	override = drm_edid_override_get(connector);
 	if (override) {
-		num_modes = drm_edid_connector_update(connector, override);
+		if (drm_edid_connector_update(connector, override) == 0)
+			num_modes = drm_edid_connector_add_modes(connector);
 
 		drm_edid_free(override);
 
diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c
index 08c088319652e6..b80d4e1cc9b7f1 100644
--- a/drivers/gpu/drm/drm_gpuvm.c
+++ b/drivers/gpu/drm/drm_gpuvm.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0 OR MIT
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Copyright (c) 2022 Red Hat.
  *
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index d5c15292ae9378..3d92f66e550c38 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -336,6 +336,12 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "IdeaPad Duet 3 10IGL5"),
 		},
 		.driver_data = (void *)&lcd1200x1920_rightside_up,
+	}, {	/* Lenovo Legion Go 8APU1 */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Legion Go 8APU1"),
+		},
+		.driver_data = (void *)&lcd1600x2560_leftside_up,
 	}, {	/* Lenovo Yoga Book X90F / X90L */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 63b709a67471b9..834a5e28abbe59 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -278,7 +278,7 @@ void drm_gem_dmabuf_release(struct dma_buf *dma_buf)
 }
 EXPORT_SYMBOL(drm_gem_dmabuf_release);
 
-/*
+/**
  * drm_gem_prime_fd_to_handle - PRIME import function for GEM drivers
  * @dev: drm_device to import into
  * @file_priv: drm file-private structure
@@ -292,9 +292,9 @@ EXPORT_SYMBOL(drm_gem_dmabuf_release);
  *
  * Returns 0 on success or a negative error code on failure.
  */
-static int drm_gem_prime_fd_to_handle(struct drm_device *dev,
-				      struct drm_file *file_priv, int prime_fd,
-				      uint32_t *handle)
+int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+			       struct drm_file *file_priv, int prime_fd,
+			       uint32_t *handle)
 {
 	struct dma_buf *dma_buf;
 	struct drm_gem_object *obj;
@@ -360,6 +360,7 @@ out_put:
 	dma_buf_put(dma_buf);
 	return ret;
 }
+EXPORT_SYMBOL(drm_gem_prime_fd_to_handle);
 
 int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv)
@@ -408,7 +409,7 @@ static struct dma_buf *export_and_register_object(struct drm_device *dev,
 	return dmabuf;
 }
 
-/*
+/**
  * drm_gem_prime_handle_to_fd - PRIME export function for GEM drivers
  * @dev: dev to export the buffer from
  * @file_priv: drm file-private structure
@@ -421,10 +422,10 @@ static struct dma_buf *export_and_register_object(struct drm_device *dev,
  * The actual exporting from GEM object to a dma-buf is done through the
  * &drm_gem_object_funcs.export callback.
  */
-static int drm_gem_prime_handle_to_fd(struct drm_device *dev,
-				      struct drm_file *file_priv, uint32_t handle,
-				      uint32_t flags,
-				      int *prime_fd)
+int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+			       struct drm_file *file_priv, uint32_t handle,
+			       uint32_t flags,
+			       int *prime_fd)
 {
 	struct drm_gem_object *obj;
 	int ret = 0;
@@ -506,6 +507,7 @@ out_unlock:
 
 	return ret;
 }
+EXPORT_SYMBOL(drm_gem_prime_handle_to_fd);
 
 int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv)
@@ -864,9 +866,9 @@ EXPORT_SYMBOL(drm_prime_get_contiguous_size);
  * @obj: GEM object to export
  * @flags: flags like DRM_CLOEXEC and DRM_RDWR
  *
- * This is the implementation of the &drm_gem_object_funcs.export functions
- * for GEM drivers using the PRIME helpers. It is used as the default for
- * drivers that do not set their own.
+ * This is the implementation of the &drm_gem_object_funcs.export functions for GEM drivers
+ * using the PRIME helpers. It is used as the default in
+ * drm_gem_prime_handle_to_fd().
  */
 struct dma_buf *drm_gem_prime_export(struct drm_gem_object *obj,
 				     int flags)
@@ -962,9 +964,10 @@ EXPORT_SYMBOL(drm_gem_prime_import_dev);
  * @dev: drm_device to import into
  * @dma_buf: dma-buf object to import
  *
- * This is the implementation of the gem_prime_import functions for GEM
- * drivers using the PRIME helpers. It is the default for drivers that do
- * not set their own &drm_driver.gem_prime_import.
+ * This is the implementation of the gem_prime_import functions for GEM drivers
+ * using the PRIME helpers. Drivers can use this as their
+ * &drm_driver.gem_prime_import implementation. It is used as the default
+ * implementation in drm_gem_prime_fd_to_handle().
  *
  * Drivers must arrange to call drm_prime_gem_destroy() from their
  * &drm_gem_object_funcs.free hook when using this function.
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index f7003d1ec5ef1e..01da6789d04409 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -1069,7 +1069,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 		fence = drm_syncobj_fence_get(syncobjs[i]);
 		if (!fence || dma_fence_chain_find_seqno(&fence, points[i])) {
 			dma_fence_put(fence);
-			if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) {
+			if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT |
+				     DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) {
 				continue;
 			} else {
 				timeout = -EINVAL;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c
index a971590b813230..e2c7373f20c6b7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dma.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c
@@ -107,18 +107,16 @@ int exynos_drm_register_dma(struct drm_device *drm, struct device *dev,
 		return 0;
 
 	if (!priv->mapping) {
-		void *mapping;
+		void *mapping = NULL;
 
 		if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU))
 			mapping = arm_iommu_create_mapping(&platform_bus_type,
 				EXYNOS_DEV_ADDR_START, EXYNOS_DEV_ADDR_SIZE);
 		else if (IS_ENABLED(CONFIG_IOMMU_DMA))
 			mapping = iommu_get_domain_for_dev(priv->dma_dev);
-		else
-			mapping = ERR_PTR(-ENODEV);
 
-		if (IS_ERR(mapping))
-			return PTR_ERR(mapping);
+		if (!mapping)
+			return -ENODEV;
 		priv->mapping = mapping;
 	}
 
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index f3aaa4ea3e6820..dd9903eab563ee 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -1861,6 +1861,8 @@ static int hdmi_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 
 	crtc = exynos_drm_crtc_get_by_type(drm_dev, EXYNOS_DISPLAY_TYPE_HDMI);
+	if (IS_ERR(crtc))
+		return PTR_ERR(crtc);
 	crtc->pipe_clk = &hdata->phy_clk;
 
 	ret = hdmi_create_connector(encoder);
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index c4585e445198d3..67143a0f518930 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1440,6 +1440,13 @@ static void gen11_dsi_post_disable(struct intel_atomic_state *state,
 static enum drm_mode_status gen11_dsi_mode_valid(struct drm_connector *connector,
 						 struct drm_display_mode *mode)
 {
+	struct drm_i915_private *i915 = to_i915(connector->dev);
+	enum drm_mode_status status;
+
+	status = intel_cpu_transcoder_mode_valid(i915, mode);
+	if (status != MODE_OK)
+		return status;
+
 	/* FIXME: DSC? */
 	return intel_dsi_mode_valid(connector, mode);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 6d7ba4d0f13068..c4839c67cb0f06 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -2750,6 +2750,18 @@ static int intel_compute_min_cdclk(struct intel_cdclk_state *cdclk_state)
 	for_each_pipe(dev_priv, pipe)
 		min_cdclk = max(cdclk_state->min_cdclk[pipe], min_cdclk);
 
+	/*
+	 * Avoid glk_force_audio_cdclk() causing excessive screen
+	 * blinking when multiple pipes are active by making sure
+	 * CDCLK frequency is always high enough for audio. With a
+	 * single active pipe we can always change CDCLK frequency
+	 * by changing the cd2x divider (see glk_cdclk_table[]) and
+	 * thus a full modeset won't be needed then.
+	 */
+	if (IS_GEMINILAKE(dev_priv) && cdclk_state->active_pipes &&
+	    !is_power_of_2(cdclk_state->active_pipes))
+		min_cdclk = max(2 * 96000, min_cdclk);
+
 	if (min_cdclk > dev_priv->display.cdclk.max_cdclk_freq) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "required cdclk (%d kHz) exceeds max (%d kHz)\n",
diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c
index 913e5d230a4df9..6f6b348b8a4054 100644
--- a/drivers/gpu/drm/i915/display/intel_crt.c
+++ b/drivers/gpu/drm/i915/display/intel_crt.c
@@ -348,8 +348,13 @@ intel_crt_mode_valid(struct drm_connector *connector,
 	struct drm_device *dev = connector->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	int max_dotclk = dev_priv->max_dotclk_freq;
+	enum drm_mode_status status;
 	int max_clock;
 
+	status = intel_cpu_transcoder_mode_valid(dev_priv, mode);
+	if (status != MODE_OK)
+		return status;
+
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
 
diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
index d414f6b7f993c2..ccf225afeb2ad3 100644
--- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
@@ -2465,7 +2465,8 @@ static void intel_program_port_clock_ctl(struct intel_encoder *encoder,
 
 	val |= XELPDP_FORWARD_CLOCK_UNGATE;
 
-	if (is_hdmi_frl(crtc_state->port_clock))
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI) &&
+	    is_hdmi_frl(crtc_state->port_clock))
 		val |= XELPDP_DDI_CLOCK_SELECT(XELPDP_DDI_CLOCK_SELECT_DIV18CLK);
 	else
 		val |= XELPDP_DDI_CLOCK_SELECT(XELPDP_DDI_CLOCK_SELECT_MAXPCLK);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 28d85e1e858eaa..df582ff81b45fa 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -906,12 +906,18 @@ static bool needs_async_flip_vtd_wa(const struct intel_crtc_state *crtc_state)
 static bool planes_enabling(const struct intel_crtc_state *old_crtc_state,
 			    const struct intel_crtc_state *new_crtc_state)
 {
+	if (!new_crtc_state->hw.active)
+		return false;
+
 	return is_enabling(active_planes, old_crtc_state, new_crtc_state);
 }
 
 static bool planes_disabling(const struct intel_crtc_state *old_crtc_state,
 			     const struct intel_crtc_state *new_crtc_state)
 {
+	if (!old_crtc_state->hw.active)
+		return false;
+
 	return is_disabling(active_planes, old_crtc_state, new_crtc_state);
 }
 
@@ -928,6 +934,9 @@ static bool vrr_params_changed(const struct intel_crtc_state *old_crtc_state,
 static bool vrr_enabling(const struct intel_crtc_state *old_crtc_state,
 			 const struct intel_crtc_state *new_crtc_state)
 {
+	if (!new_crtc_state->hw.active)
+		return false;
+
 	return is_enabling(vrr.enable, old_crtc_state, new_crtc_state) ||
 		(new_crtc_state->vrr.enable &&
 		 (new_crtc_state->update_m_n || new_crtc_state->update_lrr ||
@@ -937,6 +946,9 @@ static bool vrr_enabling(const struct intel_crtc_state *old_crtc_state,
 static bool vrr_disabling(const struct intel_crtc_state *old_crtc_state,
 			  const struct intel_crtc_state *new_crtc_state)
 {
+	if (!old_crtc_state->hw.active)
+		return false;
+
 	return is_disabling(vrr.enable, old_crtc_state, new_crtc_state) ||
 		(old_crtc_state->vrr.enable &&
 		 (new_crtc_state->update_m_n || new_crtc_state->update_lrr ||
@@ -3735,8 +3747,8 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc,
 	if (!active)
 		goto out;
 
-	intel_dsc_get_config(pipe_config);
 	intel_bigjoiner_get_config(pipe_config);
+	intel_dsc_get_config(pipe_config);
 
 	if (!transcoder_is_dsi(pipe_config->cpu_transcoder) ||
 	    DISPLAY_VER(dev_priv) >= 11)
@@ -6021,6 +6033,17 @@ static int intel_async_flip_check_uapi(struct intel_atomic_state *state,
 		return -EINVAL;
 	}
 
+	/*
+	 * FIXME: Bigjoiner+async flip is busted currently.
+	 * Remove this check once the issues are fixed.
+	 */
+	if (new_crtc_state->bigjoiner_pipes) {
+		drm_dbg_kms(&i915->drm,
+			    "[CRTC:%d:%s] async flip disallowed with bigjoiner\n",
+			    crtc->base.base.id, crtc->base.name);
+		return -EINVAL;
+	}
+
 	for_each_oldnew_intel_plane_in_state(state, plane, old_plane_state,
 					     new_plane_state, i) {
 		if (plane->pipe != crtc->pipe)
@@ -6853,10 +6876,11 @@ static void intel_commit_modeset_disables(struct intel_atomic_state *state)
 		if (!intel_crtc_needs_modeset(new_crtc_state))
 			continue;
 
+		intel_pre_plane_update(state, crtc);
+
 		if (!old_crtc_state->hw.active)
 			continue;
 
-		intel_pre_plane_update(state, crtc);
 		intel_crtc_disable_planes(state, crtc);
 	}
 
@@ -7475,7 +7499,7 @@ int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *_state,
 		for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i)
 			intel_color_cleanup_commit(new_crtc_state);
 
-		drm_atomic_helper_cleanup_planes(dev, &state->base);
+		drm_atomic_helper_unprepare_planes(dev, &state->base);
 		intel_runtime_pm_put(&dev_priv->runtime_pm, state->wakeref);
 		return ret;
 	}
@@ -7856,6 +7880,16 @@ enum drm_mode_status intel_mode_valid(struct drm_device *dev,
 	    mode->vtotal > vtotal_max)
 		return MODE_V_ILLEGAL;
 
+	return MODE_OK;
+}
+
+enum drm_mode_status intel_cpu_transcoder_mode_valid(struct drm_i915_private *dev_priv,
+						     const struct drm_display_mode *mode)
+{
+	/*
+	 * Additional transcoder timing limits,
+	 * excluding BXT/GLK DSI transcoders.
+	 */
 	if (DISPLAY_VER(dev_priv) >= 5) {
 		if (mode->hdisplay < 64 ||
 		    mode->htotal - mode->hdisplay < 32)
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 0e5dffe8f0189e..a05c7e2b782eac 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -403,6 +403,9 @@ enum drm_mode_status
 intel_mode_valid_max_plane_size(struct drm_i915_private *dev_priv,
 				const struct drm_display_mode *mode,
 				bool bigjoiner);
+enum drm_mode_status
+intel_cpu_transcoder_mode_valid(struct drm_i915_private *i915,
+				const struct drm_display_mode *mode);
 enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port);
 bool is_trans_port_sync_mode(const struct intel_crtc_state *state);
 bool is_trans_port_sync_master(const struct intel_crtc_state *state);
diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c
index 63e080e0702368..073b85b57679a5 100644
--- a/drivers/gpu/drm/i915/display/intel_dmc.c
+++ b/drivers/gpu/drm/i915/display/intel_dmc.c
@@ -389,7 +389,7 @@ disable_all_flip_queue_events(struct drm_i915_private *i915)
 	enum intel_dmc_id dmc_id;
 
 	/* TODO: check if the following applies to all D13+ platforms. */
-	if (!IS_DG2(i915) && !IS_TIGERLAKE(i915))
+	if (!IS_TIGERLAKE(i915))
 		return;
 
 	for_each_dmc_id(dmc_id) {
@@ -493,6 +493,45 @@ void intel_dmc_disable_pipe(struct drm_i915_private *i915, enum pipe pipe)
 		intel_de_rmw(i915, PIPEDMC_CONTROL(pipe), PIPEDMC_ENABLE, 0);
 }
 
+static bool is_dmc_evt_ctl_reg(struct drm_i915_private *i915,
+			       enum intel_dmc_id dmc_id, i915_reg_t reg)
+{
+	u32 offset = i915_mmio_reg_offset(reg);
+	u32 start = i915_mmio_reg_offset(DMC_EVT_CTL(i915, dmc_id, 0));
+	u32 end = i915_mmio_reg_offset(DMC_EVT_CTL(i915, dmc_id, DMC_EVENT_HANDLER_COUNT_GEN12));
+
+	return offset >= start && offset < end;
+}
+
+static bool disable_dmc_evt(struct drm_i915_private *i915,
+			    enum intel_dmc_id dmc_id,
+			    i915_reg_t reg, u32 data)
+{
+	if (!is_dmc_evt_ctl_reg(i915, dmc_id, reg))
+		return false;
+
+	/* keep all pipe DMC events disabled by default */
+	if (dmc_id != DMC_FW_MAIN)
+		return true;
+
+	return false;
+}
+
+static u32 dmc_mmiodata(struct drm_i915_private *i915,
+			struct intel_dmc *dmc,
+			enum intel_dmc_id dmc_id, int i)
+{
+	if (disable_dmc_evt(i915, dmc_id,
+			    dmc->dmc_info[dmc_id].mmioaddr[i],
+			    dmc->dmc_info[dmc_id].mmiodata[i]))
+		return REG_FIELD_PREP(DMC_EVT_CTL_TYPE_MASK,
+				      DMC_EVT_CTL_TYPE_EDGE_0_1) |
+			REG_FIELD_PREP(DMC_EVT_CTL_EVENT_ID_MASK,
+				       DMC_EVT_CTL_EVENT_ID_FALSE);
+	else
+		return dmc->dmc_info[dmc_id].mmiodata[i];
+}
+
 /**
  * intel_dmc_load_program() - write the firmware from memory to register.
  * @i915: i915 drm device.
@@ -532,7 +571,7 @@ void intel_dmc_load_program(struct drm_i915_private *i915)
 	for_each_dmc_id(dmc_id) {
 		for (i = 0; i < dmc->dmc_info[dmc_id].mmio_count; i++) {
 			intel_de_write(i915, dmc->dmc_info[dmc_id].mmioaddr[i],
-				       dmc->dmc_info[dmc_id].mmiodata[i]);
+				       dmc_mmiodata(i915, dmc, dmc_id, i));
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 1891c0cc187d11..b21bcd40f11100 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -430,7 +430,7 @@ static int mtl_max_source_rate(struct intel_dp *intel_dp)
 	enum phy phy = intel_port_to_phy(i915, dig_port->base.port);
 
 	if (intel_is_c10phy(i915, phy))
-		return intel_dp_is_edp(intel_dp) ? 675000 : 810000;
+		return 810000;
 
 	return 2000000;
 }
@@ -1172,6 +1172,10 @@ intel_dp_mode_valid(struct drm_connector *_connector,
 	enum drm_mode_status status;
 	bool dsc = false, bigjoiner = false;
 
+	status = intel_cpu_transcoder_mode_valid(dev_priv, mode);
+	if (status != MODE_OK)
+		return status;
+
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		return MODE_H_ILLEGAL;
 
@@ -6037,8 +6041,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	 * (eg. Acer Chromebook C710), so we'll check it only if multiple
 	 * ports are attempting to use the same AUX CH, according to VBT.
 	 */
-	if (intel_bios_dp_has_shared_aux_ch(encoder->devdata) &&
-	    !intel_digital_port_connected(encoder)) {
+	if (intel_bios_dp_has_shared_aux_ch(encoder->devdata)) {
 		/*
 		 * If this fails, presume the DPCD answer came
 		 * from some other port using the same AUX CH.
@@ -6046,10 +6049,27 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 		 * FIXME maybe cleaner to check this before the
 		 * DPCD read? Would need sort out the VDD handling...
 		 */
-		drm_info(&dev_priv->drm,
-			 "[ENCODER:%d:%s] HPD is down, disabling eDP\n",
-			 encoder->base.base.id, encoder->base.name);
-		goto out_vdd_off;
+		if (!intel_digital_port_connected(encoder)) {
+			drm_info(&dev_priv->drm,
+				 "[ENCODER:%d:%s] HPD is down, disabling eDP\n",
+				 encoder->base.base.id, encoder->base.name);
+			goto out_vdd_off;
+		}
+
+		/*
+		 * Unfortunately even the HPD based detection fails on
+		 * eg. Asus B360M-A (CFL+CNP), so as a last resort fall
+		 * back to checking for a VGA branch device. Only do this
+		 * on known affected platforms to minimize false positives.
+		 */
+		if (DISPLAY_VER(dev_priv) == 9 && drm_dp_is_branch(intel_dp->dpcd) &&
+		    (intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK) ==
+		    DP_DWN_STRM_PORT_TYPE_ANALOG) {
+			drm_info(&dev_priv->drm,
+				 "[ENCODER:%d:%s] VGA converter detected, disabling eDP\n",
+				 encoder->base.base.id, encoder->base.name);
+			goto out_vdd_off;
+		}
 	}
 
 	mutex_lock(&dev_priv->drm.mode_config.mutex);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index dbc1b66c8ee485..1abfafbbfa7571 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -650,19 +650,30 @@ intel_dp_update_link_bw_set(struct intel_dp *intel_dp,
 			    const struct intel_crtc_state *crtc_state,
 			    u8 link_bw, u8 rate_select)
 {
-	u8 link_config[2];
+	u8 lane_count = crtc_state->lane_count;
 
-	/* Write the link configuration data */
-	link_config[0] = link_bw;
-	link_config[1] = crtc_state->lane_count;
 	if (crtc_state->enhanced_framing)
-		link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
-	drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, 2);
+		lane_count |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
+
+	if (link_bw) {
+		/* DP and eDP v1.3 and earlier link bw set method. */
+		u8 link_config[] = { link_bw, lane_count };
 
-	/* eDP 1.4 rate select method. */
-	if (!link_bw)
-		drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_RATE_SET,
-				  &rate_select, 1);
+		drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config,
+				  ARRAY_SIZE(link_config));
+	} else {
+		/*
+		 * eDP v1.4 and later link rate set method.
+		 *
+		 * eDP v1.4x sinks shall ignore DP_LINK_RATE_SET if
+		 * DP_LINK_BW_SET is set. Avoid writing DP_LINK_BW_SET.
+		 *
+		 * eDP v1.5 sinks allow choosing either, and the last choice
+		 * shall be active.
+		 */
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_LANE_COUNT_SET, lane_count);
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_LINK_RATE_SET, rate_select);
+	}
 }
 
 /*
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 7b4628f4f12404..aa10612626136d 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -959,6 +959,10 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector,
 		return 0;
 	}
 
+	*status = intel_cpu_transcoder_mode_valid(dev_priv, mode);
+	if (*status != MODE_OK)
+		return 0;
+
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN) {
 		*status = MODE_NO_DBLESCAN;
 		return 0;
@@ -993,6 +997,10 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector,
 	if (intel_dp_need_bigjoiner(intel_dp, mode->hdisplay, target_clock)) {
 		bigjoiner = true;
 		max_dotclk *= 2;
+
+		/* TODO: add support for bigjoiner */
+		*status = MODE_CLOCK_HIGH;
+		return 0;
 	}
 
 	if (DISPLAY_VER(dev_priv) >= 10 &&
@@ -1027,11 +1035,15 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector,
 	 * Big joiner configuration needs DSC for TGL which is not true for
 	 * XE_LPD where uncompressed joiner is supported.
 	 */
-	if (DISPLAY_VER(dev_priv) < 13 && bigjoiner && !dsc)
-		return MODE_CLOCK_HIGH;
+	if (DISPLAY_VER(dev_priv) < 13 && bigjoiner && !dsc) {
+		*status = MODE_CLOCK_HIGH;
+		return 0;
+	}
 
-	if (mode_rate > max_rate && !dsc)
-		return MODE_CLOCK_HIGH;
+	if (mode_rate > max_rate && !dsc) {
+		*status = MODE_CLOCK_HIGH;
+		return 0;
+	}
 
 	*status = intel_mode_valid_max_plane_size(dev_priv, mode, false);
 	return 0;
@@ -1161,6 +1173,14 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 	intel_connector->port = port;
 	drm_dp_mst_get_port_malloc(port);
 
+	/*
+	 * TODO: set the AUX for the actual MST port decompressing the stream.
+	 * At the moment the driver only supports enabling this globally in the
+	 * first downstream MST branch, via intel_dp's (root port) AUX.
+	 */
+	intel_connector->dp.dsc_decompression_aux = &intel_dp->aux;
+	intel_dp_mst_read_decompression_port_dsc_caps(intel_dp, intel_connector);
+
 	connector = &intel_connector->base;
 	ret = drm_connector_init(dev, connector, &intel_dp_mst_connector_funcs,
 				 DRM_MODE_CONNECTOR_DisplayPort);
@@ -1172,14 +1192,6 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 
 	drm_connector_helper_add(connector, &intel_dp_mst_connector_helper_funcs);
 
-	/*
-	 * TODO: set the AUX for the actual MST port decompressing the stream.
-	 * At the moment the driver only supports enabling this globally in the
-	 * first downstream MST branch, via intel_dp's (root port) AUX.
-	 */
-	intel_connector->dp.dsc_decompression_aux = &intel_dp->aux;
-	intel_dp_mst_read_decompression_port_dsc_caps(intel_dp, intel_connector);
-
 	for_each_pipe(dev_priv, pipe) {
 		struct drm_encoder *enc =
 			&intel_dp->mst_encoders[pipe]->base.base;
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index 78b6fe24dcd8bb..7fd6280c54a79a 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -340,7 +340,7 @@ static int intel_dsb_dewake_scanline(const struct intel_crtc_state *crtc_state)
 }
 
 static void _intel_dsb_commit(struct intel_dsb *dsb, u32 ctrl,
-			      unsigned int dewake_scanline)
+			      int dewake_scanline)
 {
 	struct intel_crtc *crtc = dsb->crtc;
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c
index 55d6743374bdd6..9111e9d46486d8 100644
--- a/drivers/gpu/drm/i915/display/intel_dvo.c
+++ b/drivers/gpu/drm/i915/display/intel_dvo.c
@@ -217,11 +217,17 @@ intel_dvo_mode_valid(struct drm_connector *_connector,
 		     struct drm_display_mode *mode)
 {
 	struct intel_connector *connector = to_intel_connector(_connector);
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
 	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
 	const struct drm_display_mode *fixed_mode =
 		intel_panel_fixed_mode(connector, mode);
 	int max_dotclk = to_i915(connector->base.dev)->max_dotclk_freq;
 	int target_clock = mode->clock;
+	enum drm_mode_status status;
+
+	status = intel_cpu_transcoder_mode_valid(i915, mode);
+	if (status != MODE_OK)
+		return status;
 
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c
index 19b35ece31f1b7..646f367a13f5a0 100644
--- a/drivers/gpu/drm/i915/display/intel_fb.c
+++ b/drivers/gpu/drm/i915/display/intel_fb.c
@@ -1374,7 +1374,8 @@ plane_view_scanout_stride(const struct intel_framebuffer *fb, int color_plane,
 	struct drm_i915_private *i915 = to_i915(fb->base.dev);
 	unsigned int stride_tiles;
 
-	if (IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14)
+	if ((IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) &&
+	    src_stride_tiles < dst_stride_tiles)
 		stride_tiles = src_stride_tiles;
 	else
 		stride_tiles = dst_stride_tiles;
@@ -1501,8 +1502,20 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p
 
 			size += remap_info->size;
 		} else {
-			unsigned int dst_stride = plane_view_dst_stride_tiles(fb, color_plane,
-									      remap_info->width);
+			unsigned int dst_stride;
+
+			/*
+			 * The hardware automagically calculates the CCS AUX surface
+			 * stride from the main surface stride so can't really remap a
+			 * smaller subset (unless we'd remap in whole AUX page units).
+			 */
+			if (intel_fb_needs_pot_stride_remap(fb) &&
+			    intel_fb_is_ccs_modifier(fb->base.modifier))
+				dst_stride = remap_info->src_stride;
+			else
+				dst_stride = remap_info->width;
+
+			dst_stride = plane_view_dst_stride_tiles(fb, color_plane, dst_stride);
 
 			assign_chk_ovf(i915, remap_info->dst_stride, dst_stride);
 			color_plane_info->mapping_stride = dst_stride *
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index ac315f8e782017..bfa456fa7d25c9 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -1983,6 +1983,10 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
 	bool ycbcr_420_only;
 	enum intel_output_format sink_format;
 
+	status = intel_cpu_transcoder_mode_valid(dev_priv, mode);
+	if (status != MODE_OK)
+		return status;
+
 	if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
 		clock *= 2;
 
diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c
index 2a4ca7e65775e5..bcbdd1984fd908 100644
--- a/drivers/gpu/drm/i915/display/intel_lvds.c
+++ b/drivers/gpu/drm/i915/display/intel_lvds.c
@@ -389,11 +389,16 @@ intel_lvds_mode_valid(struct drm_connector *_connector,
 		      struct drm_display_mode *mode)
 {
 	struct intel_connector *connector = to_intel_connector(_connector);
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
 	const struct drm_display_mode *fixed_mode =
 		intel_panel_fixed_mode(connector, mode);
 	int max_pixclk = to_i915(connector->base.dev)->max_dotclk_freq;
 	enum drm_mode_status status;
 
+	status = intel_cpu_transcoder_mode_valid(i915, mode);
+	if (status != MODE_OK)
+		return status;
+
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
 
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index a636f42ceae555..a9ac7d45d1f332 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -1921,13 +1921,19 @@ static enum drm_mode_status
 intel_sdvo_mode_valid(struct drm_connector *connector,
 		      struct drm_display_mode *mode)
 {
+	struct drm_i915_private *i915 = to_i915(connector->dev);
 	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(connector);
-	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 	bool has_hdmi_sink = intel_has_hdmi_sink(intel_sdvo_connector, connector->state);
+	int max_dotclk = i915->max_dotclk_freq;
+	enum drm_mode_status status;
 	int clock = mode->clock;
 
+	status = intel_cpu_transcoder_mode_valid(i915, mode);
+	if (status != MODE_OK)
+		return status;
+
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
 
diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 37b0f8529b4f9a..f64d348a969efa 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -58,7 +58,7 @@ struct intel_tc_port {
 	struct delayed_work link_reset_work;
 	int link_refcount;
 	bool legacy_port:1;
-	char port_name[8];
+	const char *port_name;
 	enum tc_port_mode mode;
 	enum tc_port_mode init_mode;
 	enum phy_fia phy_fia;
@@ -1875,8 +1875,12 @@ int intel_tc_port_init(struct intel_digital_port *dig_port, bool is_legacy)
 	else
 		tc->phy_ops = &icl_tc_phy_ops;
 
-	snprintf(tc->port_name, sizeof(tc->port_name),
-		 "%c/TC#%d", port_name(port), tc_port + 1);
+	tc->port_name = kasprintf(GFP_KERNEL, "%c/TC#%d", port_name(port),
+				  tc_port + 1);
+	if (!tc->port_name) {
+		kfree(tc);
+		return -ENOMEM;
+	}
 
 	mutex_init(&tc->lock);
 	/* TODO: Combine the two works */
@@ -1897,6 +1901,7 @@ void intel_tc_port_cleanup(struct intel_digital_port *dig_port)
 {
 	intel_tc_port_suspend(dig_port);
 
+	kfree(dig_port->tc->port_name);
 	kfree(dig_port->tc);
 	dig_port->tc = NULL;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index 31a79fdfc81284..2ee4f0d9585136 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -958,8 +958,14 @@ static enum drm_mode_status
 intel_tv_mode_valid(struct drm_connector *connector,
 		    struct drm_display_mode *mode)
 {
+	struct drm_i915_private *i915 = to_i915(connector->dev);
 	const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state);
-	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
+	int max_dotclk = i915->max_dotclk_freq;
+	enum drm_mode_status status;
+
+	status = intel_cpu_transcoder_mode_valid(i915, mode);
+	if (status != MODE_OK)
+		return status;
 
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c
index 1e7c97243fcf55..8a934bada6245d 100644
--- a/drivers/gpu/drm/i915/display/skl_scaler.c
+++ b/drivers/gpu/drm/i915/display/skl_scaler.c
@@ -504,7 +504,6 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv,
 {
 	struct drm_plane *plane = NULL;
 	struct intel_plane *intel_plane;
-	struct intel_plane_state *plane_state = NULL;
 	struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
 	struct drm_atomic_state *drm_state = crtc_state->uapi.state;
@@ -536,6 +535,7 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv,
 
 	/* walkthrough scaler_users bits and start assigning scalers */
 	for (i = 0; i < sizeof(scaler_state->scaler_users) * 8; i++) {
+		struct intel_plane_state *plane_state = NULL;
 		int *scaler_id;
 		const char *name;
 		int idx, ret;
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index 55da627a8b8d22..f488394d3108e4 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -1541,9 +1541,25 @@ static const struct drm_encoder_funcs intel_dsi_funcs = {
 	.destroy = intel_dsi_encoder_destroy,
 };
 
+static enum drm_mode_status vlv_dsi_mode_valid(struct drm_connector *connector,
+					       struct drm_display_mode *mode)
+{
+	struct drm_i915_private *i915 = to_i915(connector->dev);
+
+	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) {
+		enum drm_mode_status status;
+
+		status = intel_cpu_transcoder_mode_valid(i915, mode);
+		if (status != MODE_OK)
+			return status;
+	}
+
+	return intel_dsi_mode_valid(connector, mode);
+}
+
 static const struct drm_connector_helper_funcs intel_dsi_connector_helper_funcs = {
 	.get_modes = intel_dsi_get_modes,
-	.mode_valid = intel_dsi_mode_valid,
+	.mode_valid = vlv_dsi_mode_valid,
 	.atomic_check = intel_digital_connector_atomic_check,
 };
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 9a9ff84c90d7e6..e38f06a6e56ebc 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -844,6 +844,7 @@ static int set_proto_ctx_sseu(struct drm_i915_file_private *fpriv,
 		if (idx >= pc->num_user_engines)
 			return -EINVAL;
 
+		idx = array_index_nospec(idx, pc->num_user_engines);
 		pe = &pc->user_engines[idx];
 
 		/* Only render engine supports RPCS configuration. */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c
index 118164ddbb2e85..833987015b8bbc 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_user.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c
@@ -41,12 +41,15 @@ void intel_engine_add_user(struct intel_engine_cs *engine)
 	llist_add(&engine->uabi_llist, &engine->i915->uabi_engines_llist);
 }
 
-static const u8 uabi_classes[] = {
+#define I915_NO_UABI_CLASS ((u16)(-1))
+
+static const u16 uabi_classes[] = {
 	[RENDER_CLASS] = I915_ENGINE_CLASS_RENDER,
 	[COPY_ENGINE_CLASS] = I915_ENGINE_CLASS_COPY,
 	[VIDEO_DECODE_CLASS] = I915_ENGINE_CLASS_VIDEO,
 	[VIDEO_ENHANCEMENT_CLASS] = I915_ENGINE_CLASS_VIDEO_ENHANCE,
 	[COMPUTE_CLASS] = I915_ENGINE_CLASS_COMPUTE,
+	[OTHER_CLASS] = I915_NO_UABI_CLASS, /* Not exposed to users, no uabi class. */
 };
 
 static int engine_cmp(void *priv, const struct list_head *A,
@@ -200,6 +203,7 @@ static void engine_rename(struct intel_engine_cs *engine, const char *name, u16
 
 void intel_engines_driver_register(struct drm_i915_private *i915)
 {
+	u16 name_instance, other_instance = 0;
 	struct legacy_ring ring = {};
 	struct list_head *it, *next;
 	struct rb_node **p, *prev;
@@ -216,27 +220,28 @@ void intel_engines_driver_register(struct drm_i915_private *i915)
 		if (intel_gt_has_unrecoverable_error(engine->gt))
 			continue; /* ignore incomplete engines */
 
-		/*
-		 * We don't want to expose the GSC engine to the users, but we
-		 * still rename it so it is easier to identify in the debug logs
-		 */
-		if (engine->id == GSC0) {
-			engine_rename(engine, "gsc", 0);
-			continue;
-		}
-
 		GEM_BUG_ON(engine->class >= ARRAY_SIZE(uabi_classes));
 		engine->uabi_class = uabi_classes[engine->class];
+		if (engine->uabi_class == I915_NO_UABI_CLASS) {
+			name_instance = other_instance++;
+		} else {
+			GEM_BUG_ON(engine->uabi_class >=
+				   ARRAY_SIZE(i915->engine_uabi_class_count));
+			name_instance =
+				i915->engine_uabi_class_count[engine->uabi_class]++;
+		}
+		engine->uabi_instance = name_instance;
 
-		GEM_BUG_ON(engine->uabi_class >=
-			   ARRAY_SIZE(i915->engine_uabi_class_count));
-		engine->uabi_instance =
-			i915->engine_uabi_class_count[engine->uabi_class]++;
-
-		/* Replace the internal name with the final user facing name */
+		/*
+		 * Replace the internal name with the final user and log facing
+		 * name.
+		 */
 		engine_rename(engine,
 			      intel_engine_class_repr(engine->class),
-			      engine->uabi_instance);
+			      name_instance);
+
+		if (engine->uabi_class == I915_NO_UABI_CLASS)
+			continue;
 
 		rb_link_node(&engine->uabi_node, prev, p);
 		rb_insert_color(&engine->uabi_node, &i915->uabi_engines);
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index 1c93e84278a037..15fc8e4703f483 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -195,6 +195,21 @@ void gen6_ggtt_invalidate(struct i915_ggtt *ggtt)
 	spin_unlock_irq(&uncore->lock);
 }
 
+static bool needs_wc_ggtt_mapping(struct drm_i915_private *i915)
+{
+	/*
+	 * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range
+	 * will be dropped. For WC mappings in general we have 64 byte burst
+	 * writes when the WC buffer is flushed, so we can't use it, but have to
+	 * resort to an uncached mapping. The WC issue is easily caught by the
+	 * readback check when writing GTT PTE entries.
+	 */
+	if (!IS_GEN9_LP(i915) && GRAPHICS_VER(i915) < 11)
+		return true;
+
+	return false;
+}
+
 static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt)
 {
 	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
@@ -202,8 +217,12 @@ static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt)
 	/*
 	 * Note that as an uncached mmio write, this will flush the
 	 * WCB of the writes into the GGTT before it triggers the invalidate.
+	 *
+	 * Only perform this when GGTT is mapped as WC, see ggtt_probe_common().
 	 */
-	intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
+	if (needs_wc_ggtt_mapping(ggtt->vm.i915))
+		intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6,
+				      GFX_FLSH_CNTL_EN);
 }
 
 static void guc_ggtt_ct_invalidate(struct intel_gt *gt)
@@ -1140,17 +1159,11 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 	GEM_WARN_ON(pci_resource_len(pdev, GEN4_GTTMMADR_BAR) != gen6_gttmmadr_size(i915));
 	phys_addr = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) + gen6_gttadr_offset(i915);
 
-	/*
-	 * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range
-	 * will be dropped. For WC mappings in general we have 64 byte burst
-	 * writes when the WC buffer is flushed, so we can't use it, but have to
-	 * resort to an uncached mapping. The WC issue is easily caught by the
-	 * readback check when writing GTT PTE entries.
-	 */
-	if (IS_GEN9_LP(i915) || GRAPHICS_VER(i915) >= 11)
-		ggtt->gsm = ioremap(phys_addr, size);
-	else
+	if (needs_wc_ggtt_mapping(i915))
 		ggtt->gsm = ioremap_wc(phys_addr, size);
+	else
+		ggtt->gsm = ioremap(phys_addr, size);
+
 	if (!ggtt->gsm) {
 		drm_err(&i915->drm, "Failed to map the ggtt page table\n");
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index ed32bf5b15464e..ba1186fc524f84 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -982,8 +982,6 @@ int intel_gt_probe_all(struct drm_i915_private *i915)
 
 err:
 	i915_probe_error(i915, "Failed to initialize %s! (%d)\n", gtdef->name, ret);
-	intel_gt_release_all(i915);
-
 	return ret;
 }
 
@@ -1002,15 +1000,6 @@ int intel_gt_tiles_init(struct drm_i915_private *i915)
 	return 0;
 }
 
-void intel_gt_release_all(struct drm_i915_private *i915)
-{
-	struct intel_gt *gt;
-	unsigned int id;
-
-	for_each_gt(gt, i915, id)
-		i915->gt[id] = NULL;
-}
-
 void intel_gt_info_print(const struct intel_gt_info *info,
 			 struct drm_printer *p)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
index 8b67abd720be86..7090e4be29cb69 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.c
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -581,19 +581,23 @@ static void __intel_rc6_disable(struct intel_rc6 *rc6)
 
 static void rc6_res_reg_init(struct intel_rc6 *rc6)
 {
-	memset(rc6->res_reg, INVALID_MMIO_REG.reg, sizeof(rc6->res_reg));
+	i915_reg_t res_reg[INTEL_RC6_RES_MAX] = {
+		[0 ... INTEL_RC6_RES_MAX - 1] = INVALID_MMIO_REG,
+	};
 
 	switch (rc6_to_gt(rc6)->type) {
 	case GT_MEDIA:
-		rc6->res_reg[INTEL_RC6_RES_RC6] = MTL_MEDIA_MC6;
+		res_reg[INTEL_RC6_RES_RC6] = MTL_MEDIA_MC6;
 		break;
 	default:
-		rc6->res_reg[INTEL_RC6_RES_RC6_LOCKED] = GEN6_GT_GFX_RC6_LOCKED;
-		rc6->res_reg[INTEL_RC6_RES_RC6] = GEN6_GT_GFX_RC6;
-		rc6->res_reg[INTEL_RC6_RES_RC6p] = GEN6_GT_GFX_RC6p;
-		rc6->res_reg[INTEL_RC6_RES_RC6pp] = GEN6_GT_GFX_RC6pp;
+		res_reg[INTEL_RC6_RES_RC6_LOCKED] = GEN6_GT_GFX_RC6_LOCKED;
+		res_reg[INTEL_RC6_RES_RC6] = GEN6_GT_GFX_RC6;
+		res_reg[INTEL_RC6_RES_RC6p] = GEN6_GT_GFX_RC6p;
+		res_reg[INTEL_RC6_RES_RC6pp] = GEN6_GT_GFX_RC6pp;
 		break;
 	}
+
+	memcpy(rc6->res_reg, res_reg, sizeof(res_reg));
 }
 
 void intel_rc6_init(struct intel_rc6 *rc6)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index d5ed904f355d5a..6801f8b95c53d1 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -1293,7 +1293,7 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg)
 	if (msg)
 		drm_notice(&engine->i915->drm,
 			   "Resetting %s for %s\n", engine->name, msg);
-	atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]);
+	i915_increase_reset_engine_count(&engine->i915->gpu_error, engine);
 
 	ret = intel_gt_reset_engine(engine);
 	if (ret) {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index d37698bd6b91ae..17df71117cc70d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -5001,7 +5001,8 @@ static void capture_error_state(struct intel_guc *guc,
 			if (match) {
 				intel_engine_set_hung_context(e, ce);
 				engine_mask |= e->mask;
-				atomic_inc(&i915->gpu_error.reset_engine_count[e->uabi_class]);
+				i915_increase_reset_engine_count(&i915->gpu_error,
+								 e);
 			}
 		}
 
@@ -5013,7 +5014,7 @@ static void capture_error_state(struct intel_guc *guc,
 	} else {
 		intel_engine_set_hung_context(ce->engine, ce);
 		engine_mask = ce->engine->mask;
-		atomic_inc(&i915->gpu_error.reset_engine_count[ce->engine->uabi_class]);
+		i915_increase_reset_engine_count(&i915->gpu_error, ce->engine);
 	}
 
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
diff --git a/drivers/gpu/drm/i915/i915_debugfs_params.c b/drivers/gpu/drm/i915/i915_debugfs_params.c
index 614bde321589dd..8bca02025e0933 100644
--- a/drivers/gpu/drm/i915/i915_debugfs_params.c
+++ b/drivers/gpu/drm/i915/i915_debugfs_params.c
@@ -38,10 +38,13 @@ static int i915_param_int_open(struct inode *inode, struct file *file)
 
 static int notify_guc(struct drm_i915_private *i915)
 {
-	int ret = 0;
+	struct intel_gt *gt;
+	int i, ret = 0;
 
-	if (intel_uc_uses_guc_submission(&to_gt(i915)->uc))
-		ret = intel_guc_global_policies_update(&to_gt(i915)->uc.guc);
+	for_each_gt(gt, i915, i) {
+		if (intel_uc_uses_guc_submission(&gt->uc))
+			ret = intel_guc_global_policies_update(&gt->uc.guc);
+	}
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index 8a0e2c745e1f9e..802de2c6decb7b 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -782,7 +782,7 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	ret = i915_driver_mmio_probe(i915);
 	if (ret < 0)
-		goto out_tiles_cleanup;
+		goto out_runtime_pm_put;
 
 	ret = i915_driver_hw_probe(i915);
 	if (ret < 0)
@@ -842,8 +842,6 @@ out_cleanup_hw:
 	i915_ggtt_driver_late_release(i915);
 out_cleanup_mmio:
 	i915_driver_mmio_release(i915);
-out_tiles_cleanup:
-	intel_gt_release_all(i915);
 out_runtime_pm_put:
 	enable_rpm_wakeref_asserts(&i915->runtime_pm);
 	i915_driver_late_release(i915);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 9f5971f5e98014..48f6c00402c47a 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -16,6 +16,7 @@
 
 #include "display/intel_display_device.h"
 #include "gt/intel_engine.h"
+#include "gt/intel_engine_types.h"
 #include "gt/intel_gt_types.h"
 #include "gt/uc/intel_uc_fw.h"
 
@@ -232,7 +233,7 @@ struct i915_gpu_error {
 	atomic_t reset_count;
 
 	/** Number of times an engine has been reset */
-	atomic_t reset_engine_count[I915_NUM_ENGINES];
+	atomic_t reset_engine_count[MAX_ENGINE_CLASS];
 };
 
 struct drm_i915_error_state_buf {
@@ -255,7 +256,14 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
 static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
 					  const struct intel_engine_cs *engine)
 {
-	return atomic_read(&error->reset_engine_count[engine->uabi_class]);
+	return atomic_read(&error->reset_engine_count[engine->class]);
+}
+
+static inline void
+i915_increase_reset_engine_count(struct i915_gpu_error *error,
+				 const struct intel_engine_cs *engine)
+{
+	atomic_inc(&error->reset_engine_count[engine->class]);
 }
 
 #define CORE_DUMP_FLAG_NONE           0x0
diff --git a/drivers/gpu/drm/i915/i915_hwmon.c b/drivers/gpu/drm/i915/i915_hwmon.c
index 975da8e7f2a9f8..8c3f443c8347e0 100644
--- a/drivers/gpu/drm/i915/i915_hwmon.c
+++ b/drivers/gpu/drm/i915/i915_hwmon.c
@@ -175,7 +175,7 @@ hwm_power1_max_interval_show(struct device *dev, struct device_attribute *attr,
 	 *     tau4 = (4 | x) << y
 	 * but add 2 when doing the final right shift to account for units
 	 */
-	tau4 = ((1 << x_w) | x) << y;
+	tau4 = (u64)((1 << x_w) | x) << y;
 	/* val in hwmon interface units (millisec) */
 	out = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w);
 
@@ -211,7 +211,7 @@ hwm_power1_max_interval_store(struct device *dev,
 	r = FIELD_PREP(PKG_MAX_WIN, PKG_MAX_WIN_DEFAULT);
 	x = REG_FIELD_GET(PKG_MAX_WIN_X, r);
 	y = REG_FIELD_GET(PKG_MAX_WIN_Y, r);
-	tau4 = ((1 << x_w) | x) << y;
+	tau4 = (u64)((1 << x_w) | x) << y;
 	max_win = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w);
 
 	if (val > max_win)
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 2f3ecd7d4804a2..7b1c8de2f9cb3c 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -4227,11 +4227,8 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 	u32 known_open_flags;
 	int ret;
 
-	if (!perf->i915) {
-		drm_dbg(&perf->i915->drm,
-			"i915 perf interface not available for this system\n");
+	if (!perf->i915)
 		return -ENOTSUPP;
-	}
 
 	known_open_flags = I915_PERF_FLAG_FD_CLOEXEC |
 			   I915_PERF_FLAG_FD_NONBLOCK |
@@ -4607,11 +4604,8 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 	struct i915_oa_reg *regs;
 	int err, id;
 
-	if (!perf->i915) {
-		drm_dbg(&perf->i915->drm,
-			"i915 perf interface not available for this system\n");
+	if (!perf->i915)
 		return -ENOTSUPP;
-	}
 
 	if (!perf->metrics_kobj) {
 		drm_dbg(&perf->i915->drm,
@@ -4773,11 +4767,8 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 	struct i915_oa_config *oa_config;
 	int ret;
 
-	if (!perf->i915) {
-		drm_dbg(&perf->i915->drm,
-			"i915 perf interface not available for this system\n");
+	if (!perf->i915)
 		return -ENOTSUPP;
-	}
 
 	if (i915_perf_stream_paranoid && !perfmon_capable()) {
 		drm_dbg(&perf->i915->drm,
diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.c b/drivers/gpu/drm/i915/selftests/igt_live_test.c
index 4ddc6d902752af..7d41874a49c589 100644
--- a/drivers/gpu/drm/i915/selftests/igt_live_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_live_test.c
@@ -37,8 +37,9 @@ int igt_live_test_begin(struct igt_live_test *t,
 		}
 
 		for_each_engine(engine, gt, id)
-			t->reset_engine[id] =
-			i915_reset_engine_count(&i915->gpu_error, engine);
+			t->reset_engine[i][id] =
+				i915_reset_engine_count(&i915->gpu_error,
+							engine);
 	}
 
 	t->reset_global = i915_reset_count(&i915->gpu_error);
@@ -66,14 +67,14 @@ int igt_live_test_end(struct igt_live_test *t)
 
 	for_each_gt(gt, i915, i) {
 		for_each_engine(engine, gt, id) {
-			if (t->reset_engine[id] ==
+			if (t->reset_engine[i][id] ==
 			    i915_reset_engine_count(&i915->gpu_error, engine))
 				continue;
 
 			gt_err(gt, "%s(%s): engine '%s' was reset %d times!\n",
 			       t->func, t->name, engine->name,
 			       i915_reset_engine_count(&i915->gpu_error, engine) -
-			       t->reset_engine[id]);
+			       t->reset_engine[i][id]);
 			return -EIO;
 		}
 	}
diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.h b/drivers/gpu/drm/i915/selftests/igt_live_test.h
index 36ed42736c5216..83e3ad430922fe 100644
--- a/drivers/gpu/drm/i915/selftests/igt_live_test.h
+++ b/drivers/gpu/drm/i915/selftests/igt_live_test.h
@@ -7,6 +7,7 @@
 #ifndef IGT_LIVE_TEST_H
 #define IGT_LIVE_TEST_H
 
+#include "gt/intel_gt_defines.h" /* for I915_MAX_GT */
 #include "gt/intel_engine.h" /* for I915_NUM_ENGINES */
 
 struct drm_i915_private;
@@ -17,7 +18,7 @@ struct igt_live_test {
 	const char *name;
 
 	unsigned int reset_global;
-	unsigned int reset_engine[I915_NUM_ENGINES];
+	unsigned int reset_engine[I915_MAX_GT][I915_NUM_ENGINES];
 };
 
 /*
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c
index f81dc34c9c3ef4..c1bc8b00d9380c 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c
@@ -203,7 +203,7 @@ void mtk_gamma_set(struct device *dev, struct drm_crtc_state *state)
 	/* Disable RELAY mode to pass the processed image */
 	cfg_val &= ~GAMMA_RELAY_MODE;
 
-	cfg_val = readl(gamma->regs + DISP_GAMMA_CFG);
+	writel(cfg_val, gamma->regs + DISP_GAMMA_CFG);
 }
 
 void mtk_gamma_config(struct device *dev, unsigned int w,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index c277b9fae95020..db43f9dff912e4 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -788,6 +788,7 @@ static void mtk_drm_crtc_atomic_begin(struct drm_crtc *crtc,
 									  crtc);
 	struct mtk_crtc_state *mtk_crtc_state = to_mtk_crtc_state(crtc_state);
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
+	unsigned long flags;
 
 	if (mtk_crtc->event && mtk_crtc_state->base.event)
 		DRM_ERROR("new event while there is still a pending event\n");
@@ -795,7 +796,11 @@ static void mtk_drm_crtc_atomic_begin(struct drm_crtc *crtc,
 	if (mtk_crtc_state->base.event) {
 		mtk_crtc_state->base.event->pipe = drm_crtc_index(crtc);
 		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
+
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
 		mtk_crtc->event = mtk_crtc_state->base.event;
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+
 		mtk_crtc_state->base.event = NULL;
 	}
 }
@@ -921,7 +926,14 @@ static int mtk_drm_crtc_init_comp_planes(struct drm_device *drm_dev,
 
 struct device *mtk_drm_crtc_dma_dev_get(struct drm_crtc *crtc)
 {
-	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
+	struct mtk_drm_crtc *mtk_crtc = NULL;
+
+	if (!crtc)
+		return NULL;
+
+	mtk_crtc = to_mtk_crtc(crtc);
+	if (!mtk_crtc)
+		return NULL;
 
 	return mtk_crtc->dma_dev;
 }
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 2dfaa613276a6d..2b0c35cacbc6da 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -443,6 +443,7 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 	struct mtk_drm_private *private = drm->dev_private;
 	struct mtk_drm_private *priv_n;
 	struct device *dma_dev = NULL;
+	struct drm_crtc *crtc;
 	int ret, i, j;
 
 	if (drm_firmware_drivers_only())
@@ -519,7 +520,9 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 	}
 
 	/* Use OVL device for all DMA memory allocations */
-	dma_dev = mtk_drm_crtc_dma_dev_get(drm_crtc_from_index(drm, 0));
+	crtc = drm_crtc_from_index(drm, 0);
+	if (crtc)
+		dma_dev = mtk_drm_crtc_dma_dev_get(crtc);
 	if (!dma_dev) {
 		ret = -ENODEV;
 		dev_err(drm->dev, "Need at least one OVL device\n");
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
index 1ccd1edd693c54..4c0528794e7a7e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
@@ -406,6 +406,7 @@ static const struct dpu_perf_cfg sc8280xp_perf_data = {
 	.min_llcc_ib = 0,
 	.min_dram_ib = 800000,
 	.danger_lut_tbl = {0xf, 0xffff, 0x0},
+	.safe_lut_tbl = {0xfe00, 0xfe00, 0xffff},
 	.qos_lut_tbl = {
 		{.nentry = ARRAY_SIZE(sc8180x_qos_linear),
 		.entries = sc8180x_qos_linear
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 11d9fc2c6bf5e0..ec933d597e20cf 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -844,8 +844,7 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev)
 
 	return 0;
 fail:
-	if (mdp5_kms)
-		mdp5_destroy(mdp5_kms);
+	mdp5_destroy(mdp5_kms);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index e329e03e068d52..1b88fb52726f24 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -365,9 +365,11 @@ static int dp_display_send_hpd_notification(struct dp_display_private *dp,
 	/* reset video pattern flag on disconnect */
 	if (!hpd) {
 		dp->panel->video_test = false;
-		drm_dp_set_subconnector_property(dp->dp_display.connector,
-						 connector_status_disconnected,
-						 dp->panel->dpcd, dp->panel->downstream_ports);
+		if (!dp->dp_display.is_edp)
+			drm_dp_set_subconnector_property(dp->dp_display.connector,
+							 connector_status_disconnected,
+							 dp->panel->dpcd,
+							 dp->panel->downstream_ports);
 	}
 
 	dp->dp_display.is_connected = hpd;
@@ -396,8 +398,11 @@ static int dp_display_process_hpd_high(struct dp_display_private *dp)
 
 	dp_link_process_request(dp->link);
 
-	drm_dp_set_subconnector_property(dp->dp_display.connector, connector_status_connected,
-					 dp->panel->dpcd, dp->panel->downstream_ports);
+	if (!dp->dp_display.is_edp)
+		drm_dp_set_subconnector_property(dp->dp_display.connector,
+						 connector_status_connected,
+						 dp->panel->dpcd,
+						 dp->panel->downstream_ports);
 
 	edid = dp->panel->edid;
 
diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c
index 40e7344180e3e0..e3bdd7dd4cdc7d 100644
--- a/drivers/gpu/drm/msm/dp/dp_drm.c
+++ b/drivers/gpu/drm/msm/dp/dp_drm.c
@@ -345,6 +345,9 @@ struct drm_connector *dp_drm_connector_init(struct msm_dp *dp_display, struct dr
 	if (IS_ERR(connector))
 		return connector;
 
+	if (!dp_display->is_edp)
+		drm_connector_attach_dp_subconnector_property(connector);
+
 	drm_connector_attach_encoder(connector, encoder);
 
 	return connector;
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 3b1ed02f644d28..89a6344bc8653d 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -918,7 +918,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 	if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2)) {
 		if (phy->cphy_mode) {
 			vreg_ctrl_0 = 0x45;
-			vreg_ctrl_1 = 0x45;
+			vreg_ctrl_1 = 0x41;
 			glbl_rescode_top_ctrl = 0x00;
 			glbl_rescode_bot_ctrl = 0x00;
 		} else {
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 2aae7d107f3356..3f217b57829347 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -288,8 +288,6 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 	if (ret)
 		goto err_msm_uninit;
 
-	drm_kms_helper_poll_init(ddev);
-
 	if (priv->kms_init) {
 		drm_kms_helper_poll_init(ddev);
 		msm_fbdev_setup(ddev);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 7840b6428afbe4..118807e38422b6 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -2474,7 +2474,7 @@ nv50_disp_atomic_commit(struct drm_device *dev,
 
 err_cleanup:
 	if (ret)
-		drm_atomic_helper_cleanup_planes(dev, state);
+		drm_atomic_helper_unprepare_planes(dev, state);
 done:
 	pm_runtime_put_autosuspend(dev->dev);
 	return ret;
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/event.h b/drivers/gpu/drm/nouveau/include/nvkm/core/event.h
index 82b267c111470a..460459af272d6f 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/event.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/event.h
@@ -14,7 +14,7 @@ struct nvkm_event {
 	int index_nr;
 
 	spinlock_t refs_lock;
-	spinlock_t list_lock;
+	rwlock_t list_lock;
 	int *refs;
 
 	struct list_head ntfy;
@@ -38,7 +38,7 @@ nvkm_event_init(const struct nvkm_event_func *func, struct nvkm_subdev *subdev,
 		int types_nr, int index_nr, struct nvkm_event *event)
 {
 	spin_lock_init(&event->refs_lock);
-	spin_lock_init(&event->list_lock);
+	rwlock_init(&event->list_lock);
 	return __nvkm_event_init(func, subdev, types_nr, index_nr, event);
 }
 
diff --git a/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/common/shared/msgq/inc/msgq/msgq_priv.h b/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/common/shared/msgq/inc/msgq/msgq_priv.h
index 5a2f273d95c8cf..0e32e71e123f37 100644
--- a/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/common/shared/msgq/inc/msgq/msgq_priv.h
+++ b/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/common/shared/msgq/inc/msgq/msgq_priv.h
@@ -26,6 +26,49 @@
  * DEALINGS IN THE SOFTWARE.
  */
 
+/**
+ * msgqTxHeader -- TX queue data structure
+ * @version: the version of this structure, must be 0
+ * @size: the size of the entire queue, including this header
+ * @msgSize: the padded size of queue element, 16 is minimum
+ * @msgCount: the number of elements in this queue
+ * @writePtr: head index of this queue
+ * @flags: 1 = swap the RX pointers
+ * @rxHdrOff: offset of readPtr in this structure
+ * @entryOff: offset of beginning of queue (msgqRxHeader), relative to
+ *          beginning of this structure
+ *
+ * The command queue is a queue of RPCs that are sent from the driver to the
+ * GSP.  The status queue is a queue of messages/responses from GSP-RM to the
+ * driver.  Although the driver allocates memory for both queues, the command
+ * queue is owned by the driver and the status queue is owned by GSP-RM.  In
+ * addition, the headers of the two queues must not share the same 4K page.
+ *
+ * Each queue is prefixed with this data structure.  The idea is that a queue
+ * and its header are written to only by their owner.  That is, only the
+ * driver writes to the command queue and command queue header, and only the
+ * GSP writes to the status (receive) queue and its header.
+ *
+ * This is enforced by the concept of "swapping" the RX pointers.  This is
+ * why the 'flags' field must be set to 1.  'rxHdrOff' is how the GSP knows
+ * where the where the tail pointer of its status queue.
+ *
+ * When the driver writes a new RPC to the command queue, it updates writePtr.
+ * When it reads a new message from the status queue, it updates readPtr.  In
+ * this way, the GSP knows when a new command is in the queue (it polls
+ * writePtr) and it knows how much free space is in the status queue (it
+ * checks readPtr).  The driver never cares about how much free space is in
+ * the status queue.
+ *
+ * As usual, producers write to the head pointer, and consumers read from the
+ * tail pointer.  When head == tail, the queue is empty.
+ *
+ * So to summarize:
+ * command.writePtr = head of command queue
+ * command.readPtr = tail of status queue
+ * status.writePtr = head of status queue
+ * status.readPtr = tail of command queue
+ */
 typedef struct
 {
     NvU32 version;   // queue version
@@ -38,6 +81,14 @@ typedef struct
     NvU32 entryOff;  // Offset of entries from start of backing store.
 } msgqTxHeader;
 
+/**
+ * msgqRxHeader - RX queue data structure
+ * @readPtr: tail index of the other queue
+ *
+ * Although this is a separate struct, it could easily be merged into
+ * msgqTxHeader.  msgqTxHeader.rxHdrOff is simply the offset of readPtr
+ * from the beginning of msgqTxHeader.
+ */
 typedef struct
 {
     NvU32 readPtr; // message id of last message read
diff --git a/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/nvidia/generated/g_os_nvoc.h b/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/nvidia/generated/g_os_nvoc.h
index 754c6af42f3035..10121218f4d3fa 100644
--- a/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/nvidia/generated/g_os_nvoc.h
+++ b/drivers/gpu/drm/nouveau/include/nvrm/535.113.01/nvidia/generated/g_os_nvoc.h
@@ -38,7 +38,7 @@ typedef struct PACKED_REGISTRY_TABLE
 {
     NvU32                   size;
     NvU32                   numEntries;
-    PACKED_REGISTRY_ENTRY   entries[0];
+    PACKED_REGISTRY_ENTRY   entries[] __counted_by(numEntries);
 } PACKED_REGISTRY_TABLE;
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 0f3bd187ede67d..280d1d9a559bad 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -318,8 +318,9 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain,
 			    (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT))
 				continue;
 
-			if (pi < 0)
-				pi = i;
+			/* pick the last one as it will be smallest. */
+			pi = i;
+
 			/* Stop once the buffer is larger than the current page size. */
 			if (*size >= 1ULL << vmm->page[i].shift)
 				break;
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index d8c92521226d97..f28f9a85745868 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -726,6 +726,11 @@ nouveau_display_create(struct drm_device *dev)
 
 	if (nouveau_modeset != 2) {
 		ret = nvif_disp_ctor(&drm->client.device, "kmsDisp", 0, &disp->disp);
+		/* no display hw */
+		if (ret == -ENODEV) {
+			ret = 0;
+			goto disp_create_err;
+		}
 
 		if (!ret && (disp->disp.outp_mask || drm->vbios.dcb.entries)) {
 			nouveau_display_create_properties(dev);
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/event.c b/drivers/gpu/drm/nouveau/nvkm/core/event.c
index a6c877135598f7..61fed7792e415c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/event.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/event.c
@@ -81,17 +81,17 @@ nvkm_event_ntfy_state(struct nvkm_event_ntfy *ntfy)
 static void
 nvkm_event_ntfy_remove(struct nvkm_event_ntfy *ntfy)
 {
-	spin_lock_irq(&ntfy->event->list_lock);
+	write_lock_irq(&ntfy->event->list_lock);
 	list_del_init(&ntfy->head);
-	spin_unlock_irq(&ntfy->event->list_lock);
+	write_unlock_irq(&ntfy->event->list_lock);
 }
 
 static void
 nvkm_event_ntfy_insert(struct nvkm_event_ntfy *ntfy)
 {
-	spin_lock_irq(&ntfy->event->list_lock);
+	write_lock_irq(&ntfy->event->list_lock);
 	list_add_tail(&ntfy->head, &ntfy->event->ntfy);
-	spin_unlock_irq(&ntfy->event->list_lock);
+	write_unlock_irq(&ntfy->event->list_lock);
 }
 
 static void
@@ -176,7 +176,7 @@ nvkm_event_ntfy(struct nvkm_event *event, int id, u32 bits)
 		return;
 
 	nvkm_trace(event->subdev, "event: ntfy %08x on %d\n", bits, id);
-	spin_lock_irqsave(&event->list_lock, flags);
+	read_lock_irqsave(&event->list_lock, flags);
 
 	list_for_each_entry_safe(ntfy, ntmp, &event->ntfy, head) {
 		if (ntfy->id == id && ntfy->bits & bits) {
@@ -185,7 +185,7 @@ nvkm_event_ntfy(struct nvkm_event *event, int id, u32 bits)
 		}
 	}
 
-	spin_unlock_irqrestore(&event->list_lock, flags);
+	read_unlock_irqrestore(&event->list_lock, flags);
 }
 
 void
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c
index e4279f1772a1b7..377d0e0cef8481 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c
@@ -385,7 +385,7 @@ nvkm_uoutp_mthd_inherit(struct nvkm_outp *outp, void *argv, u32 argc)
 
 	/* Ensure an ior is hooked up to this outp already */
 	ior = outp->func->inherit(outp);
-	if (!ior)
+	if (!ior || !ior->arm.head)
 		return -ENODEV;
 
 	/* With iors, there will be a separate output path for each type of connector - and all of
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
index 3adbb05ff587ba..d088e636edc31c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/r535.c
@@ -539,7 +539,7 @@ r535_fifo_runl_ctor(struct nvkm_fifo *fifo)
 	struct nvkm_runl *runl;
 	struct nvkm_engn *engn;
 	u32 cgids = 2048;
-	u32 chids = 2048 / CHID_PER_USERD;
+	u32 chids = 2048;
 	int ret;
 	NV2080_CTRL_FIFO_GET_DEVICE_INFO_TABLE_PARAMS *ctrl;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index e31f9641114b71..44fb86841c058a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -365,10 +365,8 @@ r535_gsp_rpc_send(struct nvkm_gsp *gsp, void *argv, bool wait, u32 repc)
 	}
 
 	ret = r535_gsp_cmdq_push(gsp, rpc);
-	if (ret) {
-		mutex_unlock(&gsp->cmdq.mutex);
+	if (ret)
 		return ERR_PTR(ret);
-	}
 
 	if (wait) {
 		msg = r535_gsp_msg_recv(gsp, fn, repc);
@@ -689,8 +687,8 @@ r535_gsp_rpc_get(struct nvkm_gsp *gsp, u32 fn, u32 argc)
 	struct nvfw_gsp_rpc *rpc;
 
 	rpc = r535_gsp_cmdq_get(gsp, ALIGN(sizeof(*rpc) + argc, sizeof(u64)));
-	if (!rpc)
-		return NULL;
+	if (IS_ERR(rpc))
+		return ERR_CAST(rpc);
 
 	rpc->header_version = 0x03000000;
 	rpc->signature = ('C' << 24) | ('P' << 16) | ('R' << 8) | 'V';
@@ -1048,7 +1046,7 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp)
 	char *strings;
 	int str_offset;
 	int i;
-	size_t rpc_size = sizeof(*rpc) + sizeof(rpc->entries[0]) * NV_GSP_REG_NUM_ENTRIES;
+	size_t rpc_size = struct_size(rpc, entries, NV_GSP_REG_NUM_ENTRIES);
 
 	/* add strings + null terminator */
 	for (i = 0; i < NV_GSP_REG_NUM_ENTRIES; i++)
@@ -1159,7 +1157,7 @@ static void
 r535_gsp_acpi_mux_id(acpi_handle handle, u32 id, MUX_METHOD_DATA_ELEMENT *mode,
 						 MUX_METHOD_DATA_ELEMENT *part)
 {
-	acpi_handle iter = NULL, handle_mux;
+	acpi_handle iter = NULL, handle_mux = NULL;
 	acpi_status status;
 	unsigned long long value;
 
@@ -1379,6 +1377,13 @@ r535_gsp_msg_post_event(void *priv, u32 fn, void *repv, u32 repc)
 	return 0;
 }
 
+/**
+ * r535_gsp_msg_run_cpu_sequencer() -- process I/O commands from the GSP
+ *
+ * The GSP sequencer is a list of I/O commands that the GSP can send to
+ * the driver to perform for various purposes.  The most common usage is to
+ * perform a special mid-initialization reset.
+ */
 static int
 r535_gsp_msg_run_cpu_sequencer(void *priv, u32 fn, void *repv, u32 repc)
 {
@@ -1718,6 +1723,23 @@ r535_gsp_libos_id8(const char *name)
 	return id;
 }
 
+/**
+ * create_pte_array() - creates a PTE array of a physically contiguous buffer
+ * @ptes: pointer to the array
+ * @addr: base address of physically contiguous buffer (GSP_PAGE_SIZE aligned)
+ * @size: size of the buffer
+ *
+ * GSP-RM sometimes expects physically-contiguous buffers to have an array of
+ * "PTEs" for each page in that buffer.  Although in theory that allows for
+ * the buffer to be physically discontiguous, GSP-RM does not currently
+ * support that.
+ *
+ * In this case, the PTEs are DMA addresses of each page of the buffer.  Since
+ * the buffer is physically contiguous, calculating all the PTEs is simple
+ * math.
+ *
+ * See memdescGetPhysAddrsForGpu()
+ */
 static void create_pte_array(u64 *ptes, dma_addr_t addr, size_t size)
 {
 	unsigned int num_pages = DIV_ROUND_UP_ULL(size, GSP_PAGE_SIZE);
@@ -1727,6 +1749,35 @@ static void create_pte_array(u64 *ptes, dma_addr_t addr, size_t size)
 		ptes[i] = (u64)addr + (i << GSP_PAGE_SHIFT);
 }
 
+/**
+ * r535_gsp_libos_init() -- create the libos arguments structure
+ *
+ * The logging buffers are byte queues that contain encoded printf-like
+ * messages from GSP-RM.  They need to be decoded by a special application
+ * that can parse the buffers.
+ *
+ * The 'loginit' buffer contains logs from early GSP-RM init and
+ * exception dumps.  The 'logrm' buffer contains the subsequent logs. Both are
+ * written to directly by GSP-RM and can be any multiple of GSP_PAGE_SIZE.
+ *
+ * The physical address map for the log buffer is stored in the buffer
+ * itself, starting with offset 1. Offset 0 contains the "put" pointer.
+ *
+ * The GSP only understands 4K pages (GSP_PAGE_SIZE), so even if the kernel is
+ * configured for a larger page size (e.g. 64K pages), we need to give
+ * the GSP an array of 4K pages. Fortunately, since the buffer is
+ * physically contiguous, it's simple math to calculate the addresses.
+ *
+ * The buffers must be a multiple of GSP_PAGE_SIZE.  GSP-RM also currently
+ * ignores the @kind field for LOGINIT, LOGINTR, and LOGRM, but expects the
+ * buffers to be physically contiguous anyway.
+ *
+ * The memory allocated for the arguments must remain until the GSP sends the
+ * init_done RPC.
+ *
+ * See _kgspInitLibosLoggingStructures (allocates memory for buffers)
+ * See kgspSetupLibosInitArgs_IMPL (creates pLibosInitArgs[] array)
+ */
 static int
 r535_gsp_libos_init(struct nvkm_gsp *gsp)
 {
@@ -1837,6 +1888,35 @@ nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
 		nvkm_gsp_mem_dtor(gsp, &rx3->mem[i]);
 }
 
+/**
+ * nvkm_gsp_radix3_sg - build a radix3 table from a S/G list
+ *
+ * The GSP uses a three-level page table, called radix3, to map the firmware.
+ * Each 64-bit "pointer" in the table is either the bus address of an entry in
+ * the next table (for levels 0 and 1) or the bus address of the next page in
+ * the GSP firmware image itself.
+ *
+ * Level 0 contains a single entry in one page that points to the first page
+ * of level 1.
+ *
+ * Level 1, since it's also only one page in size, contains up to 512 entries,
+ * one for each page in Level 2.
+ *
+ * Level 2 can be up to 512 pages in size, and each of those entries points to
+ * the next page of the firmware image.  Since there can be up to 512*512
+ * pages, that limits the size of the firmware to 512*512*GSP_PAGE_SIZE = 1GB.
+ *
+ * Internally, the GSP has its window into system memory, but the base
+ * physical address of the aperture is not 0.  In fact, it varies depending on
+ * the GPU architecture.  Since the GPU is a PCI device, this window is
+ * accessed via DMA and is therefore bound by IOMMU translation.  The end
+ * result is that GSP-RM must translate the bus addresses in the table to GSP
+ * physical addresses.  All this should happen transparently.
+ *
+ * Returns 0 on success, or negative error code
+ *
+ * See kgspCreateRadix3_IMPL
+ */
 static int
 nvkm_gsp_radix3_sg(struct nvkm_device *device, struct sg_table *sgt, u64 size,
 		   struct nvkm_gsp_radix3 *rx3)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c
index 1b811d6972a16d..201022ae9214a0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c
@@ -49,14 +49,14 @@
 #include <subdev/mmu.h>
 
 struct gk20a_instobj {
-	struct nvkm_memory memory;
+	struct nvkm_instobj base;
 	struct nvkm_mm_node *mn;
 	struct gk20a_instmem *imem;
 
 	/* CPU mapping */
 	u32 *vaddr;
 };
-#define gk20a_instobj(p) container_of((p), struct gk20a_instobj, memory)
+#define gk20a_instobj(p) container_of((p), struct gk20a_instobj, base.memory)
 
 /*
  * Used for objects allocated using the DMA API
@@ -148,7 +148,7 @@ gk20a_instobj_iommu_recycle_vaddr(struct gk20a_instobj_iommu *obj)
 	list_del(&obj->vaddr_node);
 	vunmap(obj->base.vaddr);
 	obj->base.vaddr = NULL;
-	imem->vaddr_use -= nvkm_memory_size(&obj->base.memory);
+	imem->vaddr_use -= nvkm_memory_size(&obj->base.base.memory);
 	nvkm_debug(&imem->base.subdev, "vaddr used: %x/%x\n", imem->vaddr_use,
 		   imem->vaddr_max);
 }
@@ -283,7 +283,7 @@ gk20a_instobj_map(struct nvkm_memory *memory, u64 offset, struct nvkm_vmm *vmm,
 {
 	struct gk20a_instobj *node = gk20a_instobj(memory);
 	struct nvkm_vmm_map map = {
-		.memory = &node->memory,
+		.memory = &node->base.memory,
 		.offset = offset,
 		.mem = node->mn,
 	};
@@ -391,8 +391,8 @@ gk20a_instobj_ctor_dma(struct gk20a_instmem *imem, u32 npages, u32 align,
 		return -ENOMEM;
 	*_node = &node->base;
 
-	nvkm_memory_ctor(&gk20a_instobj_func_dma, &node->base.memory);
-	node->base.memory.ptrs = &gk20a_instobj_ptrs;
+	nvkm_memory_ctor(&gk20a_instobj_func_dma, &node->base.base.memory);
+	node->base.base.memory.ptrs = &gk20a_instobj_ptrs;
 
 	node->base.vaddr = dma_alloc_attrs(dev, npages << PAGE_SHIFT,
 					   &node->handle, GFP_KERNEL,
@@ -438,8 +438,8 @@ gk20a_instobj_ctor_iommu(struct gk20a_instmem *imem, u32 npages, u32 align,
 	*_node = &node->base;
 	node->dma_addrs = (void *)(node->pages + npages);
 
-	nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.memory);
-	node->base.memory.ptrs = &gk20a_instobj_ptrs;
+	nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.base.memory);
+	node->base.base.memory.ptrs = &gk20a_instobj_ptrs;
 
 	/* Allocate backing memory */
 	for (i = 0; i < npages; i++) {
@@ -533,7 +533,7 @@ gk20a_instobj_new(struct nvkm_instmem *base, u32 size, u32 align, bool zero,
 	else
 		ret = gk20a_instobj_ctor_dma(imem, size >> PAGE_SHIFT,
 					     align, &node);
-	*pmemory = node ? &node->memory : NULL;
+	*pmemory = node ? &node->base.memory : NULL;
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c
index e34bc60764010f..8379e72d77ab2b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmtu102.c
@@ -31,7 +31,7 @@ tu102_vmm_flush(struct nvkm_vmm *vmm, int depth)
 
 	type |= 0x00000001; /* PAGE_ALL */
 	if (atomic_read(&vmm->engref[NVKM_SUBDEV_BAR]))
-		type |= 0x00000004; /* HUB_ONLY */
+		type |= 0x00000006; /* HUB_ONLY | ALL PDB (hack) */
 
 	mutex_lock(&vmm->mmu->mutex);
 
diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
index 9323e7b9e38493..c4c0f08e92026d 100644
--- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
+++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
@@ -1709,6 +1709,7 @@ static const struct panel_desc auo_b101uan08_3_desc = {
 	.mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
 		      MIPI_DSI_MODE_LPM,
 	.init_cmds = auo_b101uan08_3_init_cmd,
+	.lp11_before_reset = true,
 };
 
 static const struct drm_display_mode boe_tv105wum_nw0_default_mode = {
@@ -1763,14 +1764,15 @@ static const struct panel_desc starry_qfh032011_53g_desc = {
 	.mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
 		      MIPI_DSI_MODE_LPM,
 	.init_cmds = starry_qfh032011_53g_init_cmd,
+	.lp11_before_reset = true,
 };
 
 static const struct drm_display_mode starry_himax83102_j02_default_mode = {
-	.clock = 161600,
+	.clock = 162850,
 	.hdisplay = 1200,
-	.hsync_start = 1200 + 40,
-	.hsync_end = 1200 + 40 + 20,
-	.htotal = 1200 + 40 + 20 + 40,
+	.hsync_start = 1200 + 50,
+	.hsync_end = 1200 + 50 + 20,
+	.htotal = 1200 + 50 + 20 + 50,
 	.vdisplay = 1920,
 	.vsync_start = 1920 + 116,
 	.vsync_end = 1920 + 116 + 8,
diff --git a/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c b/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c
index 6e3670508e3a5a..30919c872ac8d5 100644
--- a/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c
+++ b/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c
@@ -326,7 +326,7 @@ static const struct drm_display_mode ltk050h3148w_mode = {
 static const struct ltk050h3146w_desc ltk050h3148w_data = {
 	.mode = &ltk050h3148w_mode,
 	.init = ltk050h3148w_init_sequence,
-	.mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE,
+	.mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE | MIPI_DSI_MODE_VIDEO_BURST,
 };
 
 static int ltk050h3146w_init_sequence(struct ltk050h3146w *ctx)
diff --git a/drivers/gpu/drm/panel/panel-novatek-nt36523.c b/drivers/gpu/drm/panel/panel-novatek-nt36523.c
index 9b9a7eb1bc606a..a189ce23632856 100644
--- a/drivers/gpu/drm/panel/panel-novatek-nt36523.c
+++ b/drivers/gpu/drm/panel/panel-novatek-nt36523.c
@@ -1254,9 +1254,9 @@ static int nt36523_probe(struct mipi_dsi_device *dsi)
 			return dev_err_probe(dev, -EPROBE_DEFER, "cannot get secondary DSI host\n");
 
 		pinfo->dsi[1] = mipi_dsi_device_register_full(dsi1_host, info);
-		if (!pinfo->dsi[1]) {
+		if (IS_ERR(pinfo->dsi[1])) {
 			dev_err(dev, "cannot get secondary DSI device\n");
-			return -ENODEV;
+			return PTR_ERR(pinfo->dsi[1]);
 		}
 	}
 
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 6cd32b90908765..9367a4572dcf64 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -2379,13 +2379,13 @@ static const struct panel_desc innolux_g070y2_t02 = {
 static const struct display_timing innolux_g101ice_l01_timing = {
 	.pixelclock = { 60400000, 71100000, 74700000 },
 	.hactive = { 1280, 1280, 1280 },
-	.hfront_porch = { 41, 80, 100 },
-	.hback_porch = { 40, 79, 99 },
-	.hsync_len = { 1, 1, 1 },
+	.hfront_porch = { 30, 60, 70 },
+	.hback_porch = { 30, 60, 70 },
+	.hsync_len = { 22, 40, 60 },
 	.vactive = { 800, 800, 800 },
-	.vfront_porch = { 5, 11, 14 },
-	.vback_porch = { 4, 11, 14 },
-	.vsync_len = { 1, 1, 1 },
+	.vfront_porch = { 3, 8, 14 },
+	.vback_porch = { 3, 8, 14 },
+	.vsync_len = { 4, 7, 12 },
 	.flags = DISPLAY_FLAGS_DE_HIGH,
 };
 
@@ -2402,6 +2402,7 @@ static const struct panel_desc innolux_g101ice_l01 = {
 		.disable = 200,
 	},
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH,
 	.connector_type = DRM_MODE_CONNECTOR_LVDS,
 };
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index f59c82ea887013..2d30da38c2c3e4 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -29,14 +29,20 @@ static void panfrost_devfreq_update_utilization(struct panfrost_devfreq *pfdevfr
 static int panfrost_devfreq_target(struct device *dev, unsigned long *freq,
 				   u32 flags)
 {
+	struct panfrost_device *ptdev = dev_get_drvdata(dev);
 	struct dev_pm_opp *opp;
+	int err;
 
 	opp = devfreq_recommended_opp(dev, freq, flags);
 	if (IS_ERR(opp))
 		return PTR_ERR(opp);
 	dev_pm_opp_put(opp);
 
-	return dev_pm_opp_set_rate(dev, *freq);
+	err =  dev_pm_opp_set_rate(dev, *freq);
+	if (!err)
+		ptdev->pfdevfreq.current_frequency = *freq;
+
+	return err;
 }
 
 static void panfrost_devfreq_reset(struct panfrost_devfreq *pfdevfreq)
@@ -58,7 +64,6 @@ static int panfrost_devfreq_get_dev_status(struct device *dev,
 	spin_lock_irqsave(&pfdevfreq->lock, irqflags);
 
 	panfrost_devfreq_update_utilization(pfdevfreq);
-	pfdevfreq->current_frequency = status->current_frequency;
 
 	status->total_time = ktime_to_ns(ktime_add(pfdevfreq->busy_time,
 						   pfdevfreq->idle_time));
@@ -165,6 +170,14 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 	panfrost_devfreq_profile.initial_freq = cur_freq;
 
 	/*
+	 * We could wait until panfrost_devfreq_target() to set this value, but
+	 * since the simple_ondemand governor works asynchronously, there's a
+	 * chance by the time someone opens the device's fdinfo file, current
+	 * frequency hasn't been updated yet, so let's just do an early set.
+	 */
+	pfdevfreq->current_frequency = cur_freq;
+
+	/*
 	 * Set the recommend OPP this will enable and configure the regulator
 	 * if any and will avoid a switch off by regulator_late_cleanup()
 	 */
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index 0cf64456e29a4f..d47b40b82b0bc4 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -200,7 +200,7 @@ static enum drm_gem_object_status panfrost_gem_status(struct drm_gem_object *obj
 	struct panfrost_gem_object *bo = to_panfrost_bo(obj);
 	enum drm_gem_object_status res = 0;
 
-	if (bo->base.pages)
+	if (bo->base.base.import_attach || bo->base.pages)
 		res |= DRM_GEM_OBJECT_RESIDENT;
 
 	if (bo->base.madv == PANFROST_MADV_DONTNEED)
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 6492a70e3c396a..404b0483bb7cb9 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -1229,6 +1229,9 @@ int qxl_destroy_monitors_object(struct qxl_device *qdev)
 	if (!qdev->monitors_config_bo)
 		return 0;
 
+	kfree(qdev->dumb_heads);
+	qdev->dumb_heads = NULL;
+
 	qdev->monitors_config = NULL;
 	qdev->ram_header->monitors_config = 0;
 
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 066299894d0480..a13473b2d54c40 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -247,14 +247,22 @@ static inline void vop_cfg_done(struct vop *vop)
 	VOP_REG_SET(vop, common, cfg_done, 1);
 }
 
-static bool has_rb_swapped(uint32_t format)
+static bool has_rb_swapped(uint32_t version, uint32_t format)
 {
 	switch (format) {
 	case DRM_FORMAT_XBGR8888:
 	case DRM_FORMAT_ABGR8888:
-	case DRM_FORMAT_BGR888:
 	case DRM_FORMAT_BGR565:
 		return true;
+	/*
+	 * full framework (IP version 3.x) only need rb swapped for RGB888 and
+	 * little framework (IP version 2.x) only need rb swapped for BGR888,
+	 * check for 3.x to also only rb swap BGR888 for unknown vop version
+	 */
+	case DRM_FORMAT_RGB888:
+		return VOP_MAJOR(version) == 3;
+	case DRM_FORMAT_BGR888:
+		return VOP_MAJOR(version) != 3;
 	default:
 		return false;
 	}
@@ -1030,7 +1038,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 	VOP_WIN_SET(vop, win, dsp_info, dsp_info);
 	VOP_WIN_SET(vop, win, dsp_st, dsp_st);
 
-	rb_swap = has_rb_swapped(fb->format->format);
+	rb_swap = has_rb_swapped(vop->data->version, fb->format->format);
 	VOP_WIN_SET(vop, win, rb_swap, rb_swap);
 
 	/*
diff --git a/drivers/gpu/drm/vc4/tests/vc4_mock_crtc.c b/drivers/gpu/drm/vc4/tests/vc4_mock_crtc.c
index 5d12d7beef0eb3..ade3309ae042f1 100644
--- a/drivers/gpu/drm/vc4/tests/vc4_mock_crtc.c
+++ b/drivers/gpu/drm/vc4/tests/vc4_mock_crtc.c
@@ -26,7 +26,7 @@ struct vc4_dummy_crtc *vc4_mock_pv(struct kunit *test,
 	struct vc4_crtc *vc4_crtc;
 	int ret;
 
-	dummy_crtc = kunit_kzalloc(test, sizeof(*dummy_crtc), GFP_KERNEL);
+	dummy_crtc = drmm_kzalloc(drm, sizeof(*dummy_crtc), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_NULL(test, dummy_crtc);
 
 	vc4_crtc = &dummy_crtc->crtc;
diff --git a/drivers/gpu/drm/vc4/tests/vc4_mock_output.c b/drivers/gpu/drm/vc4/tests/vc4_mock_output.c
index 6e11fcc9ef45e0..e70d7c3076acf1 100644
--- a/drivers/gpu/drm/vc4/tests/vc4_mock_output.c
+++ b/drivers/gpu/drm/vc4/tests/vc4_mock_output.c
@@ -32,7 +32,7 @@ struct vc4_dummy_output *vc4_dummy_output(struct kunit *test,
 	struct drm_encoder *enc;
 	int ret;
 
-	dummy_output = kunit_kzalloc(test, sizeof(*dummy_output), GFP_KERNEL);
+	dummy_output = drmm_kzalloc(drm, sizeof(*dummy_output), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dummy_output);
 	dummy_output->encoder.type = vc4_encoder_type;
 
diff --git a/drivers/greybus/Kconfig b/drivers/greybus/Kconfig
index 033d31dbf3b8cf..ab81ceceb3371d 100644
--- a/drivers/greybus/Kconfig
+++ b/drivers/greybus/Kconfig
@@ -20,6 +20,7 @@ if GREYBUS
 config GREYBUS_BEAGLEPLAY
 	tristate "Greybus BeaglePlay driver"
 	depends on SERIAL_DEV_BUS
+	select CRC_CCITT
 	help
 	  Select this option if you have a BeaglePlay where CC1352
 	  co-processor acts as Greybus SVC.
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 3ca45975c686ee..b9c7c0ed7bcc37 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -345,6 +345,10 @@ static const struct apple_non_apple_keyboard non_apple_keyboards[] = {
 	{ "AONE" },
 	{ "GANSS" },
 	{ "Hailuck" },
+	{ "Jamesdonkey" },
+	{ "A3R" },
+	{ "hfd.cn" },
+	{ "WKB603" },
 };
 
 static bool apple_is_non_apple_keyboard(struct hid_device *hdev)
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index fd61dba882338e..78cdfb8b9a7aeb 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -381,7 +381,7 @@ static int asus_raw_event(struct hid_device *hdev,
 	return 0;
 }
 
-static int asus_kbd_set_report(struct hid_device *hdev, u8 *buf, size_t buf_size)
+static int asus_kbd_set_report(struct hid_device *hdev, const u8 *buf, size_t buf_size)
 {
 	unsigned char *dmabuf;
 	int ret;
@@ -404,7 +404,7 @@ static int asus_kbd_set_report(struct hid_device *hdev, u8 *buf, size_t buf_size
 
 static int asus_kbd_init(struct hid_device *hdev)
 {
-	u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x41, 0x53, 0x55, 0x53, 0x20, 0x54,
+	const u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x41, 0x53, 0x55, 0x53, 0x20, 0x54,
 		     0x65, 0x63, 0x68, 0x2e, 0x49, 0x6e, 0x63, 0x2e, 0x00 };
 	int ret;
 
@@ -418,7 +418,7 @@ static int asus_kbd_init(struct hid_device *hdev)
 static int asus_kbd_get_functions(struct hid_device *hdev,
 				  unsigned char *kbd_func)
 {
-	u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x05, 0x20, 0x31, 0x00, 0x08 };
+	const u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x05, 0x20, 0x31, 0x00, 0x08 };
 	u8 *readbuf;
 	int ret;
 
@@ -449,7 +449,7 @@ static int asus_kbd_get_functions(struct hid_device *hdev,
 
 static int rog_nkey_led_init(struct hid_device *hdev)
 {
-	u8 buf_init_start[] = { FEATURE_KBD_LED_REPORT_ID1, 0xB9 };
+	const u8 buf_init_start[] = { FEATURE_KBD_LED_REPORT_ID1, 0xB9 };
 	u8 buf_init2[] = { FEATURE_KBD_LED_REPORT_ID1, 0x41, 0x53, 0x55, 0x53, 0x20,
 				0x54, 0x65, 0x63, 0x68, 0x2e, 0x49, 0x6e, 0x63, 0x2e, 0x00 };
 	u8 buf_init3[] = { FEATURE_KBD_LED_REPORT_ID1,
@@ -1000,6 +1000,24 @@ static int asus_start_multitouch(struct hid_device *hdev)
 	return 0;
 }
 
+static int __maybe_unused asus_resume(struct hid_device *hdev) {
+	struct asus_drvdata *drvdata = hid_get_drvdata(hdev);
+	int ret = 0;
+
+	if (drvdata->kbd_backlight) {
+		const u8 buf[] = { FEATURE_KBD_REPORT_ID, 0xba, 0xc5, 0xc4,
+				drvdata->kbd_backlight->cdev.brightness };
+		ret = asus_kbd_set_report(hdev, buf, sizeof(buf));
+		if (ret < 0) {
+			hid_err(hdev, "Asus failed to set keyboard backlight: %d\n", ret);
+			goto asus_resume_err;
+		}
+	}
+
+asus_resume_err:
+	return ret;
+}
+
 static int __maybe_unused asus_reset_resume(struct hid_device *hdev)
 {
 	struct asus_drvdata *drvdata = hid_get_drvdata(hdev);
@@ -1294,6 +1312,7 @@ static struct hid_driver asus_driver = {
 	.input_configured       = asus_input_configured,
 #ifdef CONFIG_PM
 	.reset_resume           = asus_reset_resume,
+	.resume					= asus_resume,
 #endif
 	.event			= asus_event,
 	.raw_event		= asus_raw_event
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 8992e3c1e7698e..e0181218ad8578 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -702,15 +702,22 @@ static void hid_close_report(struct hid_device *device)
  * Free a device structure, all reports, and all fields.
  */
 
-static void hid_device_release(struct device *dev)
+void hiddev_free(struct kref *ref)
 {
-	struct hid_device *hid = to_hid_device(dev);
+	struct hid_device *hid = container_of(ref, struct hid_device, ref);
 
 	hid_close_report(hid);
 	kfree(hid->dev_rdesc);
 	kfree(hid);
 }
 
+static void hid_device_release(struct device *dev)
+{
+	struct hid_device *hid = to_hid_device(dev);
+
+	kref_put(&hid->ref, hiddev_free);
+}
+
 /*
  * Fetch a report description item from the data stream. We support long
  * items, though they are not used yet.
@@ -2846,6 +2853,7 @@ struct hid_device *hid_allocate_device(void)
 	spin_lock_init(&hdev->debug_list_lock);
 	sema_init(&hdev->driver_input_lock, 1);
 	mutex_init(&hdev->ll_open_lock);
+	kref_init(&hdev->ref);
 
 	hid_bpf_device_init(hdev);
 
diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index e7ef1ea107c9e6..7dd83ec74f8a9d 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -1135,6 +1135,7 @@ static int hid_debug_events_open(struct inode *inode, struct file *file)
 		goto out;
 	}
 	list->hdev = (struct hid_device *) inode->i_private;
+	kref_get(&list->hdev->ref);
 	file->private_data = list;
 	mutex_init(&list->read_mutex);
 
@@ -1227,6 +1228,8 @@ static int hid_debug_events_release(struct inode *inode, struct file *file)
 	list_del(&list->node);
 	spin_unlock_irqrestore(&list->hdev->debug_list_lock, flags);
 	kfifo_free(&list->hid_debug_fifo);
+
+	kref_put(&list->hdev->ref, hiddev_free);
 	kfree(list);
 
 	return 0;
diff --git a/drivers/hid/hid-glorious.c b/drivers/hid/hid-glorious.c
index 558eb08c19ef9d..281b3a7187cec2 100644
--- a/drivers/hid/hid-glorious.c
+++ b/drivers/hid/hid-glorious.c
@@ -21,6 +21,10 @@ MODULE_DESCRIPTION("HID driver for Glorious PC Gaming Race mice");
  * Glorious Model O and O- specify the const flag in the consumer input
  * report descriptor, which leads to inputs being ignored. Fix this
  * by patching the descriptor.
+ *
+ * Glorious Model I incorrectly specifes the Usage Minimum for its
+ * keyboard HID report, causing keycodes to be misinterpreted.
+ * Fix this by setting Usage Minimum to 0 in that report.
  */
 static __u8 *glorious_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
@@ -32,6 +36,10 @@ static __u8 *glorious_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		rdesc[85] = rdesc[113] = rdesc[141] = \
 			HID_MAIN_ITEM_VARIABLE | HID_MAIN_ITEM_RELATIVE;
 	}
+	if (*rsize == 156 && rdesc[41] == 1) {
+		hid_info(hdev, "patching Glorious Model I keyboard report descriptor\n");
+		rdesc[41] = 0;
+	}
 	return rdesc;
 }
 
@@ -44,6 +52,8 @@ static void glorious_update_name(struct hid_device *hdev)
 		model = "Model O"; break;
 	case USB_DEVICE_ID_GLORIOUS_MODEL_D:
 		model = "Model D"; break;
+	case USB_DEVICE_ID_GLORIOUS_MODEL_I:
+		model = "Model I"; break;
 	}
 
 	snprintf(hdev->name, sizeof(hdev->name), "%s %s", "Glorious", model);
@@ -66,10 +76,12 @@ static int glorious_probe(struct hid_device *hdev,
 }
 
 static const struct hid_device_id glorious_devices[] = {
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLORIOUS,
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SINOWEALTH,
 		USB_DEVICE_ID_GLORIOUS_MODEL_O) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLORIOUS,
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SINOWEALTH,
 		USB_DEVICE_ID_GLORIOUS_MODEL_D) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LAVIEW,
+		USB_DEVICE_ID_GLORIOUS_MODEL_I) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, glorious_devices);
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index f7973ccd84a287..72046039d1be75 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -511,10 +511,6 @@
 #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_010A 0x010a
 #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100 0xe100
 
-#define USB_VENDOR_ID_GLORIOUS  0x258a
-#define USB_DEVICE_ID_GLORIOUS_MODEL_D 0x0033
-#define USB_DEVICE_ID_GLORIOUS_MODEL_O 0x0036
-
 #define I2C_VENDOR_ID_GOODIX		0x27c6
 #define I2C_DEVICE_ID_GOODIX_01F0	0x01f0
 
@@ -744,6 +740,10 @@
 
 #define USB_VENDOR_ID_LABTEC		0x1020
 #define USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD	0x0006
+#define USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE	0x8888
+
+#define USB_VENDOR_ID_LAVIEW		0x22D4
+#define USB_DEVICE_ID_GLORIOUS_MODEL_I	0x1503
 
 #define USB_VENDOR_ID_LCPOWER		0x1241
 #define USB_DEVICE_ID_LCPOWER_LC1000	0xf767
@@ -869,7 +869,6 @@
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_2		0xc534
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1	0xc539
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_1	0xc53f
-#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_2	0xc547
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_POWERPLAY	0xc53a
 #define USB_DEVICE_ID_SPACETRAVELLER	0xc623
 #define USB_DEVICE_ID_SPACENAVIGATOR	0xc626
@@ -1160,6 +1159,10 @@
 #define USB_VENDOR_ID_SIGMATEL		0x066F
 #define USB_DEVICE_ID_SIGMATEL_STMP3780	0x3780
 
+#define USB_VENDOR_ID_SINOWEALTH  0x258a
+#define USB_DEVICE_ID_GLORIOUS_MODEL_D 0x0033
+#define USB_DEVICE_ID_GLORIOUS_MODEL_O 0x0036
+
 #define USB_VENDOR_ID_SIS_TOUCH		0x0457
 #define USB_DEVICE_ID_SIS9200_TOUCH	0x9200
 #define USB_DEVICE_ID_SIS817_TOUCH	0x0817
diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index 7c1b33be9d1343..149a3c74346b4f 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -692,7 +692,8 @@ static int lenovo_event_cptkbd(struct hid_device *hdev,
 		 * so set middlebutton_state to 3
 		 * to never apply workaround anymore
 		 */
-		if (cptkbd_data->middlebutton_state == 1 &&
+		if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD &&
+				cptkbd_data->middlebutton_state == 1 &&
 				usage->type == EV_REL &&
 				(usage->code == REL_X || usage->code == REL_Y)) {
 			cptkbd_data->middlebutton_state = 3;
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index 8afe3be683ba25..e6a8b6d8eab707 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -1695,12 +1695,11 @@ static int logi_dj_raw_event(struct hid_device *hdev,
 		}
 		/*
 		 * Mouse-only receivers send unnumbered mouse data. The 27 MHz
-		 * receiver uses 6 byte packets, the nano receiver 8 bytes,
-		 * the lightspeed receiver (Pro X Superlight) 13 bytes.
+		 * receiver uses 6 byte packets, the nano receiver 8 bytes.
 		 */
 		if (djrcv_dev->unnumbered_application == HID_GD_MOUSE &&
-		    size <= 13){
-			u8 mouse_report[14];
+		    size <= 8) {
+			u8 mouse_report[9];
 
 			/* Prepend report id */
 			mouse_report[0] = REPORT_TYPE_MOUSE;
@@ -1984,10 +1983,6 @@ static const struct hid_device_id logi_dj_receivers[] = {
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
 		USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_1),
 	 .driver_data = recvr_type_gaming_hidpp},
-	{ /* Logitech lightspeed receiver (0xc547) */
-	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
-		USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_2),
-	 .driver_data = recvr_type_gaming_hidpp},
 
 	{ /* Logitech 27 MHz HID++ 1.0 receiver (0xc513) */
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER),
diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c
index 72883e0ce75758..aef0785c91cc2d 100644
--- a/drivers/hid/hid-mcp2221.c
+++ b/drivers/hid/hid-mcp2221.c
@@ -1142,6 +1142,8 @@ static int mcp2221_probe(struct hid_device *hdev,
 	if (ret)
 		return ret;
 
+	hid_device_io_start(hdev);
+
 	/* Set I2C bus clock diviser */
 	if (i2c_clk_freq > 400)
 		i2c_clk_freq = 400;
@@ -1157,12 +1159,12 @@ static int mcp2221_probe(struct hid_device *hdev,
 	snprintf(mcp->adapter.name, sizeof(mcp->adapter.name),
 			"MCP2221 usb-i2c bridge");
 
+	i2c_set_adapdata(&mcp->adapter, mcp);
 	ret = devm_i2c_add_adapter(&hdev->dev, &mcp->adapter);
 	if (ret) {
 		hid_err(hdev, "can't add usb-i2c adapter: %d\n", ret);
 		return ret;
 	}
-	i2c_set_adapdata(&mcp->adapter, mcp);
 
 #if IS_REACHABLE(CONFIG_GPIOLIB)
 	/* Setup GPIO chip */
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index e098cc7b394437..fd5b0637dad683 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -2046,6 +2046,11 @@ static const struct hid_device_id mt_devices[] = {
 		MT_USB_DEVICE(USB_VENDOR_ID_HANVON_ALT,
 			USB_DEVICE_ID_HANVON_ALT_MULTITOUCH) },
 
+	/* HONOR GLO-GXXX panel */
+	{ .driver_data = MT_CLS_VTL,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			0x347d, 0x7853) },
+
 	/* Ilitek dual touch panel */
 	{  .driver_data = MT_CLS_NSMU,
 		MT_USB_DEVICE(USB_VENDOR_ID_ILITEK,
diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c
index 138f154fecef34..997c3a1adacab2 100644
--- a/drivers/hid/hid-nintendo.c
+++ b/drivers/hid/hid-nintendo.c
@@ -325,28 +325,28 @@ struct joycon_imu_cal {
  * All the controller's button values are stored in a u32.
  * They can be accessed with bitwise ANDs.
  */
-static const u32 JC_BTN_Y	= BIT(0);
-static const u32 JC_BTN_X	= BIT(1);
-static const u32 JC_BTN_B	= BIT(2);
-static const u32 JC_BTN_A	= BIT(3);
-static const u32 JC_BTN_SR_R	= BIT(4);
-static const u32 JC_BTN_SL_R	= BIT(5);
-static const u32 JC_BTN_R	= BIT(6);
-static const u32 JC_BTN_ZR	= BIT(7);
-static const u32 JC_BTN_MINUS	= BIT(8);
-static const u32 JC_BTN_PLUS	= BIT(9);
-static const u32 JC_BTN_RSTICK	= BIT(10);
-static const u32 JC_BTN_LSTICK	= BIT(11);
-static const u32 JC_BTN_HOME	= BIT(12);
-static const u32 JC_BTN_CAP	= BIT(13); /* capture button */
-static const u32 JC_BTN_DOWN	= BIT(16);
-static const u32 JC_BTN_UP	= BIT(17);
-static const u32 JC_BTN_RIGHT	= BIT(18);
-static const u32 JC_BTN_LEFT	= BIT(19);
-static const u32 JC_BTN_SR_L	= BIT(20);
-static const u32 JC_BTN_SL_L	= BIT(21);
-static const u32 JC_BTN_L	= BIT(22);
-static const u32 JC_BTN_ZL	= BIT(23);
+#define JC_BTN_Y	 BIT(0)
+#define JC_BTN_X	 BIT(1)
+#define JC_BTN_B	 BIT(2)
+#define JC_BTN_A	 BIT(3)
+#define JC_BTN_SR_R	 BIT(4)
+#define JC_BTN_SL_R	 BIT(5)
+#define JC_BTN_R	 BIT(6)
+#define JC_BTN_ZR	 BIT(7)
+#define JC_BTN_MINUS	 BIT(8)
+#define JC_BTN_PLUS	 BIT(9)
+#define JC_BTN_RSTICK	 BIT(10)
+#define JC_BTN_LSTICK	 BIT(11)
+#define JC_BTN_HOME	 BIT(12)
+#define JC_BTN_CAP	 BIT(13) /* capture button */
+#define JC_BTN_DOWN	 BIT(16)
+#define JC_BTN_UP	 BIT(17)
+#define JC_BTN_RIGHT	 BIT(18)
+#define JC_BTN_LEFT	 BIT(19)
+#define JC_BTN_SR_L	 BIT(20)
+#define JC_BTN_SL_L	 BIT(21)
+#define JC_BTN_L	 BIT(22)
+#define JC_BTN_ZL	 BIT(23)
 
 enum joycon_msg_type {
 	JOYCON_MSG_TYPE_NONE,
@@ -927,14 +927,27 @@ static int joycon_request_calibration(struct joycon_ctlr *ctlr)
  */
 static void joycon_calc_imu_cal_divisors(struct joycon_ctlr *ctlr)
 {
-	int i;
+	int i, divz = 0;
 
 	for (i = 0; i < 3; i++) {
 		ctlr->imu_cal_accel_divisor[i] = ctlr->accel_cal.scale[i] -
 						ctlr->accel_cal.offset[i];
 		ctlr->imu_cal_gyro_divisor[i] = ctlr->gyro_cal.scale[i] -
 						ctlr->gyro_cal.offset[i];
+
+		if (ctlr->imu_cal_accel_divisor[i] == 0) {
+			ctlr->imu_cal_accel_divisor[i] = 1;
+			divz++;
+		}
+
+		if (ctlr->imu_cal_gyro_divisor[i] == 0) {
+			ctlr->imu_cal_gyro_divisor[i] = 1;
+			divz++;
+		}
 	}
+
+	if (divz)
+		hid_warn(ctlr->hdev, "inaccurate IMU divisors (%d)\n", divz);
 }
 
 static const s16 DFLT_ACCEL_OFFSET /*= 0*/;
@@ -1163,16 +1176,16 @@ static void joycon_parse_imu_report(struct joycon_ctlr *ctlr,
 		    JC_IMU_SAMPLES_PER_DELTA_AVG) {
 			ctlr->imu_avg_delta_ms = ctlr->imu_delta_samples_sum /
 						 ctlr->imu_delta_samples_count;
-			/* don't ever want divide by zero shenanigans */
-			if (ctlr->imu_avg_delta_ms == 0) {
-				ctlr->imu_avg_delta_ms = 1;
-				hid_warn(ctlr->hdev,
-					 "calculated avg imu delta of 0\n");
-			}
 			ctlr->imu_delta_samples_count = 0;
 			ctlr->imu_delta_samples_sum = 0;
 		}
 
+		/* don't ever want divide by zero shenanigans */
+		if (ctlr->imu_avg_delta_ms == 0) {
+			ctlr->imu_avg_delta_ms = 1;
+			hid_warn(ctlr->hdev, "calculated avg imu delta of 0\n");
+		}
+
 		/* useful for debugging IMU sample rate */
 		hid_dbg(ctlr->hdev,
 			"imu_report: ms=%u last_ms=%u delta=%u avg_delta=%u\n",
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 5a48fcaa32f007..e0bbf0c6345d68 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -33,6 +33,7 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AKAI, USB_DEVICE_ID_AKAI_MPKMINI2), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ALPS, USB_DEVICE_ID_IBM_GAMEPAD), HID_QUIRK_BADPAD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AMI, USB_DEVICE_ID_AMI_VIRT_KEYBOARD_AND_MOUSE), HID_QUIRK_ALWAYS_POLL },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ANSI), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_2PORTKVM), HID_QUIRK_NOGET },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVMC), HID_QUIRK_NOGET },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVM), HID_QUIRK_NOGET },
@@ -120,6 +121,7 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M406XE), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_T609A), HID_QUIRK_MULTI_INPUT },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019), HID_QUIRK_ALWAYS_POLL },
diff --git a/drivers/hid/i2c-hid/i2c-hid-acpi.c b/drivers/hid/i2c-hid/i2c-hid-acpi.c
index ac918a9ea8d344..1b49243adb16a5 100644
--- a/drivers/hid/i2c-hid/i2c-hid-acpi.c
+++ b/drivers/hid/i2c-hid/i2c-hid-acpi.c
@@ -40,6 +40,11 @@ static const struct acpi_device_id i2c_hid_acpi_blacklist[] = {
 	 * ICN8505 controller, has a _CID of PNP0C50 but is not HID compatible.
 	 */
 	{ "CHPN0001" },
+	/*
+	 * The IDEA5002 ACPI device causes high interrupt usage and spurious
+	 * wakeups from suspend.
+	 */
+	{ "IDEA5002" },
 	{ }
 };
 
diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c
index 8db740214ffda9..703666b95bf49b 100644
--- a/drivers/hwmon/acpi_power_meter.c
+++ b/drivers/hwmon/acpi_power_meter.c
@@ -31,6 +31,7 @@
 #define POWER_METER_CAN_NOTIFY	(1 << 3)
 #define POWER_METER_IS_BATTERY	(1 << 8)
 #define UNKNOWN_HYSTERESIS	0xFFFFFFFF
+#define UNKNOWN_POWER		0xFFFFFFFF
 
 #define METER_NOTIFY_CONFIG	0x80
 #define METER_NOTIFY_TRIP	0x81
@@ -348,6 +349,9 @@ static ssize_t show_power(struct device *dev,
 	update_meter(resource);
 	mutex_unlock(&resource->lock);
 
+	if (resource->power == UNKNOWN_POWER)
+		return -ENODATA;
+
 	return sprintf(buf, "%llu\n", resource->power * 1000);
 }
 
diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c
index 904890598c116b..2c7c92272fe399 100644
--- a/drivers/hwmon/corsair-psu.c
+++ b/drivers/hwmon/corsair-psu.c
@@ -899,7 +899,23 @@ static struct hid_driver corsairpsu_driver = {
 	.reset_resume	= corsairpsu_resume,
 #endif
 };
-module_hid_driver(corsairpsu_driver);
+
+static int __init corsair_init(void)
+{
+	return hid_register_driver(&corsairpsu_driver);
+}
+
+static void __exit corsair_exit(void)
+{
+	hid_unregister_driver(&corsairpsu_driver);
+}
+
+/*
+ * With module_init() the driver would load before the HID bus when
+ * built-in, so use late_initcall() instead.
+ */
+late_initcall(corsair_init);
+module_exit(corsair_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Wilken Gottwalt <wilken.gottwalt@posteo.net>");
diff --git a/drivers/hwmon/ltc2991.c b/drivers/hwmon/ltc2991.c
index bd63c61129a94a..fc53fdcb2b6caa 100644
--- a/drivers/hwmon/ltc2991.c
+++ b/drivers/hwmon/ltc2991.c
@@ -373,7 +373,7 @@ static int ltc2991_init(struct ltc2991_state *st)
 			   LTC2991_REPEAT_ACQ_EN);
 	if (ret)
 		return dev_err_probe(st->dev, ret,
-				     "Error: Failed to set contiuous mode.\n");
+				     "Error: Failed to set continuous mode.\n");
 
 	/* Enable all channels and trigger conversions */
 	return regmap_write(st->regmap, LTC2991_CH_EN_TRIGGER,
diff --git a/drivers/hwmon/max31827.c b/drivers/hwmon/max31827.c
index fd1fed1a797cd4..a1ce6514566912 100644
--- a/drivers/hwmon/max31827.c
+++ b/drivers/hwmon/max31827.c
@@ -12,6 +12,7 @@
 #include <linux/i2c.h>
 #include <linux/mutex.h>
 #include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
 
 #define MAX31827_T_REG			0x0
 #define MAX31827_CONFIGURATION_REG	0x2
diff --git a/drivers/hwmon/nzxt-kraken2.c b/drivers/hwmon/nzxt-kraken2.c
index 428c77b5fce5a2..7caf387eb1449f 100644
--- a/drivers/hwmon/nzxt-kraken2.c
+++ b/drivers/hwmon/nzxt-kraken2.c
@@ -161,13 +161,13 @@ static int kraken2_probe(struct hid_device *hdev,
 	ret = hid_hw_start(hdev, HID_CONNECT_HIDRAW);
 	if (ret) {
 		hid_err(hdev, "hid hw start failed with %d\n", ret);
-		goto fail_and_stop;
+		return ret;
 	}
 
 	ret = hid_hw_open(hdev);
 	if (ret) {
 		hid_err(hdev, "hid hw open failed with %d\n", ret);
-		goto fail_and_close;
+		goto fail_and_stop;
 	}
 
 	priv->hwmon_dev = hwmon_device_register_with_info(&hdev->dev, "kraken2",
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 5ca6278baff4fa..89e8ed214ea496 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -493,7 +493,7 @@ static void etm_event_start(struct perf_event *event, int flags)
 		goto fail_end_stop;
 
 	/* Finally enable the tracer */
-	if (coresight_enable_source(csdev, CS_MODE_PERF, event))
+	if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF))
 		goto fail_disable_path;
 
 	/*
@@ -587,7 +587,7 @@ static void etm_event_stop(struct perf_event *event, int mode)
 		return;
 
 	/* stop tracer */
-	coresight_disable_source(csdev, event);
+	source_ops(csdev)->disable(csdev, event);
 
 	/* tell the core */
 	event->hw.state = PERF_HES_STOPPED;
diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c
index 77b0271ce6eb98..34aee59dd14739 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x-core.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c
@@ -2224,7 +2224,7 @@ static void clear_etmdrvdata(void *info)
 	per_cpu(delayed_probe, cpu) = NULL;
 }
 
-static void __exit etm4_remove_dev(struct etmv4_drvdata *drvdata)
+static void etm4_remove_dev(struct etmv4_drvdata *drvdata)
 {
 	bool had_delayed_probe;
 	/*
@@ -2253,7 +2253,7 @@ static void __exit etm4_remove_dev(struct etmv4_drvdata *drvdata)
 	}
 }
 
-static void __exit etm4_remove_amba(struct amba_device *adev)
+static void etm4_remove_amba(struct amba_device *adev)
 {
 	struct etmv4_drvdata *drvdata = dev_get_drvdata(&adev->dev);
 
@@ -2261,7 +2261,7 @@ static void __exit etm4_remove_amba(struct amba_device *adev)
 		etm4_remove_dev(drvdata);
 }
 
-static int __exit etm4_remove_platform_dev(struct platform_device *pdev)
+static int etm4_remove_platform_dev(struct platform_device *pdev)
 {
 	struct etmv4_drvdata *drvdata = dev_get_drvdata(&pdev->dev);
 
diff --git a/drivers/hwtracing/coresight/ultrasoc-smb.c b/drivers/hwtracing/coresight/ultrasoc-smb.c
index e9a32a97fbee69..6e32d31a95fe08 100644
--- a/drivers/hwtracing/coresight/ultrasoc-smb.c
+++ b/drivers/hwtracing/coresight/ultrasoc-smb.c
@@ -99,7 +99,7 @@ static int smb_open(struct inode *inode, struct file *file)
 					struct smb_drv_data, miscdev);
 	int ret = 0;
 
-	mutex_lock(&drvdata->mutex);
+	spin_lock(&drvdata->spinlock);
 
 	if (drvdata->reading) {
 		ret = -EBUSY;
@@ -115,7 +115,7 @@ static int smb_open(struct inode *inode, struct file *file)
 
 	drvdata->reading = true;
 out:
-	mutex_unlock(&drvdata->mutex);
+	spin_unlock(&drvdata->spinlock);
 
 	return ret;
 }
@@ -132,10 +132,8 @@ static ssize_t smb_read(struct file *file, char __user *data, size_t len,
 	if (!len)
 		return 0;
 
-	mutex_lock(&drvdata->mutex);
-
 	if (!sdb->data_size)
-		goto out;
+		return 0;
 
 	to_copy = min(sdb->data_size, len);
 
@@ -145,20 +143,15 @@ static ssize_t smb_read(struct file *file, char __user *data, size_t len,
 
 	if (copy_to_user(data, sdb->buf_base + sdb->buf_rdptr, to_copy)) {
 		dev_dbg(dev, "Failed to copy data to user\n");
-		to_copy = -EFAULT;
-		goto out;
+		return -EFAULT;
 	}
 
 	*ppos += to_copy;
-
 	smb_update_read_ptr(drvdata, to_copy);
-
-	dev_dbg(dev, "%zu bytes copied\n", to_copy);
-out:
 	if (!sdb->data_size)
 		smb_reset_buffer(drvdata);
-	mutex_unlock(&drvdata->mutex);
 
+	dev_dbg(dev, "%zu bytes copied\n", to_copy);
 	return to_copy;
 }
 
@@ -167,9 +160,9 @@ static int smb_release(struct inode *inode, struct file *file)
 	struct smb_drv_data *drvdata = container_of(file->private_data,
 					struct smb_drv_data, miscdev);
 
-	mutex_lock(&drvdata->mutex);
+	spin_lock(&drvdata->spinlock);
 	drvdata->reading = false;
-	mutex_unlock(&drvdata->mutex);
+	spin_unlock(&drvdata->spinlock);
 
 	return 0;
 }
@@ -262,7 +255,7 @@ static int smb_enable(struct coresight_device *csdev, enum cs_mode mode,
 	struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent);
 	int ret = 0;
 
-	mutex_lock(&drvdata->mutex);
+	spin_lock(&drvdata->spinlock);
 
 	/* Do nothing, the trace data is reading by other interface now */
 	if (drvdata->reading) {
@@ -294,7 +287,7 @@ static int smb_enable(struct coresight_device *csdev, enum cs_mode mode,
 
 	dev_dbg(&csdev->dev, "Ultrasoc SMB enabled\n");
 out:
-	mutex_unlock(&drvdata->mutex);
+	spin_unlock(&drvdata->spinlock);
 
 	return ret;
 }
@@ -304,7 +297,7 @@ static int smb_disable(struct coresight_device *csdev)
 	struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent);
 	int ret = 0;
 
-	mutex_lock(&drvdata->mutex);
+	spin_lock(&drvdata->spinlock);
 
 	if (drvdata->reading) {
 		ret = -EBUSY;
@@ -327,7 +320,7 @@ static int smb_disable(struct coresight_device *csdev)
 
 	dev_dbg(&csdev->dev, "Ultrasoc SMB disabled\n");
 out:
-	mutex_unlock(&drvdata->mutex);
+	spin_unlock(&drvdata->spinlock);
 
 	return ret;
 }
@@ -408,7 +401,7 @@ static unsigned long smb_update_buffer(struct coresight_device *csdev,
 	if (!buf)
 		return 0;
 
-	mutex_lock(&drvdata->mutex);
+	spin_lock(&drvdata->spinlock);
 
 	/* Don't do anything if another tracer is using this sink. */
 	if (atomic_read(&csdev->refcnt) != 1)
@@ -432,7 +425,7 @@ static unsigned long smb_update_buffer(struct coresight_device *csdev,
 	if (!buf->snapshot && lost)
 		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 out:
-	mutex_unlock(&drvdata->mutex);
+	spin_unlock(&drvdata->spinlock);
 
 	return data_size;
 }
@@ -484,7 +477,6 @@ static int smb_init_data_buffer(struct platform_device *pdev,
 static void smb_init_hw(struct smb_drv_data *drvdata)
 {
 	smb_disable_hw(drvdata);
-	smb_reset_buffer(drvdata);
 
 	writel(SMB_LB_CFG_LO_DEFAULT, drvdata->base + SMB_LB_CFG_LO_REG);
 	writel(SMB_LB_CFG_HI_DEFAULT, drvdata->base + SMB_LB_CFG_HI_REG);
@@ -590,37 +582,33 @@ static int smb_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	mutex_init(&drvdata->mutex);
+	ret = smb_config_inport(dev, true);
+	if (ret)
+		return ret;
+
+	smb_reset_buffer(drvdata);
+	platform_set_drvdata(pdev, drvdata);
+	spin_lock_init(&drvdata->spinlock);
 	drvdata->pid = -1;
 
 	ret = smb_register_sink(pdev, drvdata);
 	if (ret) {
+		smb_config_inport(&pdev->dev, false);
 		dev_err(dev, "Failed to register SMB sink\n");
 		return ret;
 	}
 
-	ret = smb_config_inport(dev, true);
-	if (ret) {
-		smb_unregister_sink(drvdata);
-		return ret;
-	}
-
-	platform_set_drvdata(pdev, drvdata);
-
 	return 0;
 }
 
 static int smb_remove(struct platform_device *pdev)
 {
 	struct smb_drv_data *drvdata = platform_get_drvdata(pdev);
-	int ret;
-
-	ret = smb_config_inport(&pdev->dev, false);
-	if (ret)
-		return ret;
 
 	smb_unregister_sink(drvdata);
 
+	smb_config_inport(&pdev->dev, false);
+
 	return 0;
 }
 
diff --git a/drivers/hwtracing/coresight/ultrasoc-smb.h b/drivers/hwtracing/coresight/ultrasoc-smb.h
index d2e14e8d2c8a8c..82a44c14a8829c 100644
--- a/drivers/hwtracing/coresight/ultrasoc-smb.h
+++ b/drivers/hwtracing/coresight/ultrasoc-smb.h
@@ -8,7 +8,7 @@
 #define _ULTRASOC_SMB_H
 
 #include <linux/miscdevice.h>
-#include <linux/mutex.h>
+#include <linux/spinlock.h>
 
 /* Offset of SMB global registers */
 #define SMB_GLB_CFG_REG		0x00
@@ -105,7 +105,7 @@ struct smb_data_buffer {
  * @csdev:	Component vitals needed by the framework.
  * @sdb:	Data buffer for SMB.
  * @miscdev:	Specifics to handle "/dev/xyz.smb" entry.
- * @mutex:	Control data access to one at a time.
+ * @spinlock:	Control data access to one at a time.
  * @reading:	Synchronise user space access to SMB buffer.
  * @pid:	Process ID of the process being monitored by the
  *		session that is using this component.
@@ -116,7 +116,7 @@ struct smb_drv_data {
 	struct coresight_device	*csdev;
 	struct smb_data_buffer sdb;
 	struct miscdevice miscdev;
-	struct mutex mutex;
+	spinlock_t spinlock;
 	bool reading;
 	pid_t pid;
 	enum cs_mode mode;
diff --git a/drivers/hwtracing/ptt/hisi_ptt.c b/drivers/hwtracing/ptt/hisi_ptt.c
index 49ea1b0f748903..a991ecb7515a34 100644
--- a/drivers/hwtracing/ptt/hisi_ptt.c
+++ b/drivers/hwtracing/ptt/hisi_ptt.c
@@ -342,9 +342,9 @@ static int hisi_ptt_register_irq(struct hisi_ptt *hisi_ptt)
 		return ret;
 
 	hisi_ptt->trace_irq = pci_irq_vector(pdev, HISI_PTT_TRACE_DMA_IRQ);
-	ret = devm_request_threaded_irq(&pdev->dev, hisi_ptt->trace_irq,
-					NULL, hisi_ptt_isr, 0,
-					DRV_NAME, hisi_ptt);
+	ret = devm_request_irq(&pdev->dev, hisi_ptt->trace_irq, hisi_ptt_isr,
+				IRQF_NOBALANCING | IRQF_NO_THREAD, DRV_NAME,
+				hisi_ptt);
 	if (ret) {
 		pci_err(pdev, "failed to request irq %d, ret = %d\n",
 			hisi_ptt->trace_irq, ret);
@@ -1000,6 +1000,9 @@ static int hisi_ptt_pmu_event_init(struct perf_event *event)
 		return -EOPNOTSUPP;
 	}
 
+	if (event->attach_state & PERF_ATTACH_TASK)
+		return -EOPNOTSUPP;
+
 	if (event->attr.type != hisi_ptt->hisi_ptt_pmu.type)
 		return -ENOENT;
 
@@ -1178,6 +1181,10 @@ static void hisi_ptt_pmu_del(struct perf_event *event, int flags)
 	hisi_ptt_pmu_stop(event, PERF_EF_UPDATE);
 }
 
+static void hisi_ptt_pmu_read(struct perf_event *event)
+{
+}
+
 static void hisi_ptt_remove_cpuhp_instance(void *hotplug_node)
 {
 	cpuhp_state_remove_instance_nocalls(hisi_ptt_pmu_online, hotplug_node);
@@ -1221,6 +1228,7 @@ static int hisi_ptt_register_pmu(struct hisi_ptt *hisi_ptt)
 		.stop		= hisi_ptt_pmu_stop,
 		.add		= hisi_ptt_pmu_add,
 		.del		= hisi_ptt_pmu_del,
+		.read		= hisi_ptt_pmu_read,
 	};
 
 	reg = readl(hisi_ptt->iobase + HISI_PTT_LOCATION);
diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c
index 28e2a5fc45282d..5511fd46a65eae 100644
--- a/drivers/i2c/busses/i2c-aspeed.c
+++ b/drivers/i2c/busses/i2c-aspeed.c
@@ -249,18 +249,46 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status)
 	if (!slave)
 		return 0;
 
-	command = readl(bus->base + ASPEED_I2C_CMD_REG);
+	/*
+	 * Handle stop conditions early, prior to SLAVE_MATCH. Some masters may drive
+	 * transfers with low enough latency between the nak/stop phase of the current
+	 * command and the start/address phase of the following command that the
+	 * interrupts are coalesced by the time we process them.
+	 */
+	if (irq_status & ASPEED_I2CD_INTR_NORMAL_STOP) {
+		irq_handled |= ASPEED_I2CD_INTR_NORMAL_STOP;
+		bus->slave_state = ASPEED_I2C_SLAVE_STOP;
+	}
+
+	if (irq_status & ASPEED_I2CD_INTR_TX_NAK &&
+	    bus->slave_state == ASPEED_I2C_SLAVE_READ_PROCESSED) {
+		irq_handled |= ASPEED_I2CD_INTR_TX_NAK;
+		bus->slave_state = ASPEED_I2C_SLAVE_STOP;
+	}
+
+	/* Propagate any stop conditions to the slave implementation. */
+	if (bus->slave_state == ASPEED_I2C_SLAVE_STOP) {
+		i2c_slave_event(slave, I2C_SLAVE_STOP, &value);
+		bus->slave_state = ASPEED_I2C_SLAVE_INACTIVE;
+	}
 
-	/* Slave was requested, restart state machine. */
+	/*
+	 * Now that we've dealt with any potentially coalesced stop conditions,
+	 * address any start conditions.
+	 */
 	if (irq_status & ASPEED_I2CD_INTR_SLAVE_MATCH) {
 		irq_handled |= ASPEED_I2CD_INTR_SLAVE_MATCH;
 		bus->slave_state = ASPEED_I2C_SLAVE_START;
 	}
 
-	/* Slave is not currently active, irq was for someone else. */
+	/*
+	 * If the slave has been stopped and not started then slave interrupt
+	 * handling is complete.
+	 */
 	if (bus->slave_state == ASPEED_I2C_SLAVE_INACTIVE)
 		return irq_handled;
 
+	command = readl(bus->base + ASPEED_I2C_CMD_REG);
 	dev_dbg(bus->dev, "slave irq status 0x%08x, cmd 0x%08x\n",
 		irq_status, command);
 
@@ -279,17 +307,6 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status)
 		irq_handled |= ASPEED_I2CD_INTR_RX_DONE;
 	}
 
-	/* Slave was asked to stop. */
-	if (irq_status & ASPEED_I2CD_INTR_NORMAL_STOP) {
-		irq_handled |= ASPEED_I2CD_INTR_NORMAL_STOP;
-		bus->slave_state = ASPEED_I2C_SLAVE_STOP;
-	}
-	if (irq_status & ASPEED_I2CD_INTR_TX_NAK &&
-	    bus->slave_state == ASPEED_I2C_SLAVE_READ_PROCESSED) {
-		irq_handled |= ASPEED_I2CD_INTR_TX_NAK;
-		bus->slave_state = ASPEED_I2C_SLAVE_STOP;
-	}
-
 	switch (bus->slave_state) {
 	case ASPEED_I2C_SLAVE_READ_REQUESTED:
 		if (unlikely(irq_status & ASPEED_I2CD_INTR_TX_ACK))
@@ -324,8 +341,7 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status)
 		i2c_slave_event(slave, I2C_SLAVE_WRITE_RECEIVED, &value);
 		break;
 	case ASPEED_I2C_SLAVE_STOP:
-		i2c_slave_event(slave, I2C_SLAVE_STOP, &value);
-		bus->slave_state = ASPEED_I2C_SLAVE_INACTIVE;
+		/* Stop event handling is done early. Unreachable. */
 		break;
 	case ASPEED_I2C_SLAVE_START:
 		/* Slave was just started. Waiting for the next event. */;
diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c
index affcfb243f0f52..35f762872b8a58 100644
--- a/drivers/i2c/busses/i2c-designware-common.c
+++ b/drivers/i2c/busses/i2c-designware-common.c
@@ -63,7 +63,7 @@ static int dw_reg_read(void *context, unsigned int reg, unsigned int *val)
 {
 	struct dw_i2c_dev *dev = context;
 
-	*val = readl_relaxed(dev->base + reg);
+	*val = readl(dev->base + reg);
 
 	return 0;
 }
@@ -72,7 +72,7 @@ static int dw_reg_write(void *context, unsigned int reg, unsigned int val)
 {
 	struct dw_i2c_dev *dev = context;
 
-	writel_relaxed(val, dev->base + reg);
+	writel(val, dev->base + reg);
 
 	return 0;
 }
@@ -81,7 +81,7 @@ static int dw_reg_read_swab(void *context, unsigned int reg, unsigned int *val)
 {
 	struct dw_i2c_dev *dev = context;
 
-	*val = swab32(readl_relaxed(dev->base + reg));
+	*val = swab32(readl(dev->base + reg));
 
 	return 0;
 }
@@ -90,7 +90,7 @@ static int dw_reg_write_swab(void *context, unsigned int reg, unsigned int val)
 {
 	struct dw_i2c_dev *dev = context;
 
-	writel_relaxed(swab32(val), dev->base + reg);
+	writel(swab32(val), dev->base + reg);
 
 	return 0;
 }
@@ -99,8 +99,8 @@ static int dw_reg_read_word(void *context, unsigned int reg, unsigned int *val)
 {
 	struct dw_i2c_dev *dev = context;
 
-	*val = readw_relaxed(dev->base + reg) |
-		(readw_relaxed(dev->base + reg + 2) << 16);
+	*val = readw(dev->base + reg) |
+		(readw(dev->base + reg + 2) << 16);
 
 	return 0;
 }
@@ -109,8 +109,8 @@ static int dw_reg_write_word(void *context, unsigned int reg, unsigned int val)
 {
 	struct dw_i2c_dev *dev = context;
 
-	writew_relaxed(val, dev->base + reg);
-	writew_relaxed(val >> 16, dev->base + reg + 2);
+	writew(val, dev->base + reg);
+	writew(val >> 16, dev->base + reg + 2);
 
 	return 0;
 }
diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c
index 041a76f71a49cc..e106af83cef4da 100644
--- a/drivers/i2c/busses/i2c-ocores.c
+++ b/drivers/i2c/busses/i2c-ocores.c
@@ -771,8 +771,8 @@ static int ocores_i2c_resume(struct device *dev)
 	return ocores_init(dev, i2c);
 }
 
-static DEFINE_SIMPLE_DEV_PM_OPS(ocores_i2c_pm,
-				ocores_i2c_suspend, ocores_i2c_resume);
+static DEFINE_NOIRQ_DEV_PM_OPS(ocores_i2c_pm,
+			       ocores_i2c_suspend, ocores_i2c_resume);
 
 static struct platform_driver ocores_i2c_driver = {
 	.probe   = ocores_i2c_probe,
diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c
index 1d764824274921..76f79b68cef845 100644
--- a/drivers/i2c/busses/i2c-pxa.c
+++ b/drivers/i2c/busses/i2c-pxa.c
@@ -265,6 +265,9 @@ struct pxa_i2c {
 	u32			hs_mask;
 
 	struct i2c_bus_recovery_info recovery;
+	struct pinctrl		*pinctrl;
+	struct pinctrl_state	*pinctrl_default;
+	struct pinctrl_state	*pinctrl_recovery;
 };
 
 #define _IBMR(i2c)	((i2c)->reg_ibmr)
@@ -1299,12 +1302,13 @@ static void i2c_pxa_prepare_recovery(struct i2c_adapter *adap)
 	 */
 	gpiod_set_value(i2c->recovery.scl_gpiod, ibmr & IBMR_SCLS);
 	gpiod_set_value(i2c->recovery.sda_gpiod, ibmr & IBMR_SDAS);
+
+	WARN_ON(pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_recovery));
 }
 
 static void i2c_pxa_unprepare_recovery(struct i2c_adapter *adap)
 {
 	struct pxa_i2c *i2c = adap->algo_data;
-	struct i2c_bus_recovery_info *bri = adap->bus_recovery_info;
 	u32 isr;
 
 	/*
@@ -1318,7 +1322,7 @@ static void i2c_pxa_unprepare_recovery(struct i2c_adapter *adap)
 		i2c_pxa_do_reset(i2c);
 	}
 
-	WARN_ON(pinctrl_select_state(bri->pinctrl, bri->pins_default));
+	WARN_ON(pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_default));
 
 	dev_dbg(&i2c->adap.dev, "recovery: IBMR 0x%08x ISR 0x%08x\n",
 	        readl(_IBMR(i2c)), readl(_ISR(i2c)));
@@ -1340,20 +1344,76 @@ static int i2c_pxa_init_recovery(struct pxa_i2c *i2c)
 	if (IS_ENABLED(CONFIG_I2C_PXA_SLAVE))
 		return 0;
 
-	bri->pinctrl = devm_pinctrl_get(dev);
-	if (PTR_ERR(bri->pinctrl) == -ENODEV) {
-		bri->pinctrl = NULL;
+	i2c->pinctrl = devm_pinctrl_get(dev);
+	if (PTR_ERR(i2c->pinctrl) == -ENODEV)
+		i2c->pinctrl = NULL;
+	if (IS_ERR(i2c->pinctrl))
+		return PTR_ERR(i2c->pinctrl);
+
+	if (!i2c->pinctrl)
+		return 0;
+
+	i2c->pinctrl_default = pinctrl_lookup_state(i2c->pinctrl,
+						    PINCTRL_STATE_DEFAULT);
+	i2c->pinctrl_recovery = pinctrl_lookup_state(i2c->pinctrl, "recovery");
+
+	if (IS_ERR(i2c->pinctrl_default) || IS_ERR(i2c->pinctrl_recovery)) {
+		dev_info(dev, "missing pinmux recovery information: %ld %ld\n",
+			 PTR_ERR(i2c->pinctrl_default),
+			 PTR_ERR(i2c->pinctrl_recovery));
+		return 0;
+	}
+
+	/*
+	 * Claiming GPIOs can influence the pinmux state, and may glitch the
+	 * I2C bus. Do this carefully.
+	 */
+	bri->scl_gpiod = devm_gpiod_get(dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN);
+	if (bri->scl_gpiod == ERR_PTR(-EPROBE_DEFER))
+		return -EPROBE_DEFER;
+	if (IS_ERR(bri->scl_gpiod)) {
+		dev_info(dev, "missing scl gpio recovery information: %pe\n",
+			 bri->scl_gpiod);
+		return 0;
+	}
+
+	/*
+	 * We have SCL. Pull SCL low and wait a bit so that SDA glitches
+	 * have no effect.
+	 */
+	gpiod_direction_output(bri->scl_gpiod, 0);
+	udelay(10);
+	bri->sda_gpiod = devm_gpiod_get(dev, "sda", GPIOD_OUT_HIGH_OPEN_DRAIN);
+
+	/* Wait a bit in case of a SDA glitch, and then release SCL. */
+	udelay(10);
+	gpiod_direction_output(bri->scl_gpiod, 1);
+
+	if (bri->sda_gpiod == ERR_PTR(-EPROBE_DEFER))
+		return -EPROBE_DEFER;
+
+	if (IS_ERR(bri->sda_gpiod)) {
+		dev_info(dev, "missing sda gpio recovery information: %pe\n",
+			 bri->sda_gpiod);
 		return 0;
 	}
-	if (IS_ERR(bri->pinctrl))
-		return PTR_ERR(bri->pinctrl);
 
 	bri->prepare_recovery = i2c_pxa_prepare_recovery;
 	bri->unprepare_recovery = i2c_pxa_unprepare_recovery;
+	bri->recover_bus = i2c_generic_scl_recovery;
 
 	i2c->adap.bus_recovery_info = bri;
 
-	return 0;
+	/*
+	 * Claiming GPIOs can change the pinmux state, which confuses the
+	 * pinctrl since pinctrl's idea of the current setting is unaffected
+	 * by the pinmux change caused by claiming the GPIO. Work around that
+	 * by switching pinctrl to the GPIO state here. We do it this way to
+	 * avoid glitching the I2C bus.
+	 */
+	pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_recovery);
+
+	return pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_default);
 }
 
 static int i2c_pxa_probe(struct platform_device *dev)
diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
index 6d829ed2f868f7..0d2e7171e3a6f9 100644
--- a/drivers/i2c/busses/i2c-qcom-geni.c
+++ b/drivers/i2c/busses/i2c-qcom-geni.c
@@ -858,6 +858,7 @@ static int geni_i2c_probe(struct platform_device *pdev)
 	ret = geni_se_resources_on(&gi2c->se);
 	if (ret) {
 		dev_err(dev, "Error turning on resources %d\n", ret);
+		clk_disable_unprepare(gi2c->core_clk);
 		return ret;
 	}
 	proto = geni_se_read_proto(&gi2c->se);
@@ -877,8 +878,11 @@ static int geni_i2c_probe(struct platform_device *pdev)
 		/* FIFO is disabled, so we can only use GPI DMA */
 		gi2c->gpi_mode = true;
 		ret = setup_gpi_dma(gi2c);
-		if (ret)
+		if (ret) {
+			geni_se_resources_off(&gi2c->se);
+			clk_disable_unprepare(gi2c->core_clk);
 			return dev_err_probe(dev, ret, "Failed to setup GPI DMA mode\n");
+		}
 
 		dev_dbg(dev, "Using GPI DMA mode for I2C\n");
 	} else {
@@ -891,6 +895,8 @@ static int geni_i2c_probe(struct platform_device *pdev)
 
 		if (!tx_depth) {
 			dev_err(dev, "Invalid TX FIFO depth\n");
+			geni_se_resources_off(&gi2c->se);
+			clk_disable_unprepare(gi2c->core_clk);
 			return -EINVAL;
 		}
 
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
index a044ca0c35a193..4362db7c57892c 100644
--- a/drivers/i2c/busses/i2c-rk3x.c
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -178,6 +178,7 @@ struct rk3x_i2c_soc_data {
  * @clk: function clk for rk3399 or function & Bus clks for others
  * @pclk: Bus clk for rk3399
  * @clk_rate_nb: i2c clk rate change notify
+ * @irq: irq number
  * @t: I2C known timing information
  * @lock: spinlock for the i2c bus
  * @wait: the waitqueue to wait for i2c transfer
@@ -200,6 +201,7 @@ struct rk3x_i2c {
 	struct clk *clk;
 	struct clk *pclk;
 	struct notifier_block clk_rate_nb;
+	int irq;
 
 	/* Settings */
 	struct i2c_timings t;
@@ -1087,13 +1089,18 @@ static int rk3x_i2c_xfer_common(struct i2c_adapter *adap,
 
 		spin_unlock_irqrestore(&i2c->lock, flags);
 
-		rk3x_i2c_start(i2c);
-
 		if (!polling) {
+			rk3x_i2c_start(i2c);
+
 			timeout = wait_event_timeout(i2c->wait, !i2c->busy,
 						     msecs_to_jiffies(WAIT_TIMEOUT));
 		} else {
+			disable_irq(i2c->irq);
+			rk3x_i2c_start(i2c);
+
 			timeout = rk3x_i2c_wait_xfer_poll(i2c);
+
+			enable_irq(i2c->irq);
 		}
 
 		spin_lock_irqsave(&i2c->lock, flags);
@@ -1310,6 +1317,8 @@ static int rk3x_i2c_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	i2c->irq = irq;
+
 	platform_set_drvdata(pdev, i2c);
 
 	if (i2c->soc_data->calc_timings == rk3x_i2c_v0_calc_timings) {
diff --git a/drivers/iio/accel/kionix-kx022a.c b/drivers/iio/accel/kionix-kx022a.c
index 60864be3a66712..53d59a04ae15e9 100644
--- a/drivers/iio/accel/kionix-kx022a.c
+++ b/drivers/iio/accel/kionix-kx022a.c
@@ -393,17 +393,17 @@ static const unsigned int kx022a_odrs[] = {
  *	(range / 2^bits) * g = (range / 2^bits) * 9.80665 m/s^2
  *	=> KX022A uses 16 bit (HiRes mode - assume the low 8 bits are zeroed
  *	in low-power mode(?) )
- *	=> +/-2G  => 4 / 2^16 * 9,80665 * 10^6 (to scale to micro)
- *	=> +/-2G  - 598.550415
- *	   +/-4G  - 1197.10083
- *	   +/-8G  - 2394.20166
- *	   +/-16G - 4788.40332
+ *	=> +/-2G  => 4 / 2^16 * 9,80665
+ *	=> +/-2G  - 0.000598550415
+ *	   +/-4G  - 0.00119710083
+ *	   +/-8G  - 0.00239420166
+ *	   +/-16G - 0.00478840332
  */
 static const int kx022a_scale_table[][2] = {
-	{ 598, 550415 },
-	{ 1197, 100830 },
-	{ 2394, 201660 },
-	{ 4788, 403320 },
+	{ 0, 598550 },
+	{ 0, 1197101 },
+	{ 0, 2394202 },
+	{ 0, 4788403 },
 };
 
 static int kx022a_read_avail(struct iio_dev *indio_dev,
@@ -422,7 +422,7 @@ static int kx022a_read_avail(struct iio_dev *indio_dev,
 		*vals = (const int *)kx022a_scale_table;
 		*length = ARRAY_SIZE(kx022a_scale_table) *
 			  ARRAY_SIZE(kx022a_scale_table[0]);
-		*type = IIO_VAL_INT_PLUS_MICRO;
+		*type = IIO_VAL_INT_PLUS_NANO;
 		return IIO_AVAIL_LIST;
 	default:
 		return -EINVAL;
@@ -485,6 +485,20 @@ static int kx022a_turn_on_unlock(struct kx022a_data *data)
 	return ret;
 }
 
+static int kx022a_write_raw_get_fmt(struct iio_dev *idev,
+				    struct iio_chan_spec const *chan,
+				    long mask)
+{
+	switch (mask) {
+	case IIO_CHAN_INFO_SCALE:
+		return IIO_VAL_INT_PLUS_NANO;
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		return IIO_VAL_INT_PLUS_MICRO;
+	default:
+		return -EINVAL;
+	}
+}
+
 static int kx022a_write_raw(struct iio_dev *idev,
 			    struct iio_chan_spec const *chan,
 			    int val, int val2, long mask)
@@ -629,7 +643,7 @@ static int kx022a_read_raw(struct iio_dev *idev,
 
 		kx022a_reg2scale(regval, val, val2);
 
-		return IIO_VAL_INT_PLUS_MICRO;
+		return IIO_VAL_INT_PLUS_NANO;
 	}
 
 	return -EINVAL;
@@ -856,6 +870,7 @@ static int kx022a_fifo_flush(struct iio_dev *idev, unsigned int samples)
 static const struct iio_info kx022a_info = {
 	.read_raw = &kx022a_read_raw,
 	.write_raw = &kx022a_write_raw,
+	.write_raw_get_fmt = &kx022a_write_raw_get_fmt,
 	.read_avail = &kx022a_read_avail,
 
 	.validate_trigger	= iio_validate_own_trigger,
diff --git a/drivers/iio/adc/imx93_adc.c b/drivers/iio/adc/imx93_adc.c
index 9bb1e4ba1aeed8..4ccf4819f1f131 100644
--- a/drivers/iio/adc/imx93_adc.c
+++ b/drivers/iio/adc/imx93_adc.c
@@ -93,6 +93,10 @@ static const struct iio_chan_spec imx93_adc_iio_channels[] = {
 	IMX93_ADC_CHAN(1),
 	IMX93_ADC_CHAN(2),
 	IMX93_ADC_CHAN(3),
+	IMX93_ADC_CHAN(4),
+	IMX93_ADC_CHAN(5),
+	IMX93_ADC_CHAN(6),
+	IMX93_ADC_CHAN(7),
 };
 
 static void imx93_adc_power_down(struct imx93_adc *adc)
diff --git a/drivers/iio/adc/mcp3564.c b/drivers/iio/adc/mcp3564.c
index e3f1de5fcc5abd..311b613b605754 100644
--- a/drivers/iio/adc/mcp3564.c
+++ b/drivers/iio/adc/mcp3564.c
@@ -918,7 +918,7 @@ static int mcp3564_write_raw(struct iio_dev *indio_dev,
 		mutex_unlock(&adc->lock);
 		return ret;
 	case IIO_CHAN_INFO_CALIBBIAS:
-		if (val < mcp3564_calib_bias[0] && val > mcp3564_calib_bias[2])
+		if (val < mcp3564_calib_bias[0] || val > mcp3564_calib_bias[2])
 			return -EINVAL;
 
 		mutex_lock(&adc->lock);
@@ -928,7 +928,7 @@ static int mcp3564_write_raw(struct iio_dev *indio_dev,
 		mutex_unlock(&adc->lock);
 		return ret;
 	case IIO_CHAN_INFO_CALIBSCALE:
-		if (val < mcp3564_calib_scale[0] && val > mcp3564_calib_scale[2])
+		if (val < mcp3564_calib_scale[0] || val > mcp3564_calib_scale[2])
 			return -EINVAL;
 
 		if (adc->calib_scale == val)
@@ -1122,7 +1122,7 @@ static int mcp3564_config(struct iio_dev *indio_dev)
 	enum mcp3564_ids ids;
 	int ret = 0;
 	unsigned int tmp = 0x01;
-	bool err = true;
+	bool err = false;
 
 	/*
 	 * The address is set on a per-device basis by fuses in the factory,
@@ -1509,5 +1509,5 @@ static struct spi_driver mcp3564_driver = {
 module_spi_driver(mcp3564_driver);
 
 MODULE_AUTHOR("Marius Cristea <marius.cristea@microchip.com>");
-MODULE_DESCRIPTION("Microchip MCP346x/MCP346xR and MCP356x/MCP346xR ADCs");
+MODULE_DESCRIPTION("Microchip MCP346x/MCP346xR and MCP356x/MCP356xR ADCs");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/iio/adc/meson_saradc.c b/drivers/iio/adc/meson_saradc.c
index 950ff13e6dde80..13b473d8c6c788 100644
--- a/drivers/iio/adc/meson_saradc.c
+++ b/drivers/iio/adc/meson_saradc.c
@@ -1241,6 +1241,20 @@ static const struct meson_sar_adc_param meson_sar_adc_gxl_param = {
 	.cmv_select = 1,
 };
 
+static const struct meson_sar_adc_param meson_sar_adc_axg_param = {
+	.has_bl30_integration = true,
+	.clock_rate = 1200000,
+	.bandgap_reg = MESON_SAR_ADC_REG11,
+	.regmap_config = &meson_sar_adc_regmap_config_gxbb,
+	.resolution = 12,
+	.disable_ring_counter = 1,
+	.has_reg11 = true,
+	.vref_volatge = 1,
+	.has_vref_select = true,
+	.vref_select = VREF_VDDA,
+	.cmv_select = 1,
+};
+
 static const struct meson_sar_adc_param meson_sar_adc_g12a_param = {
 	.has_bl30_integration = false,
 	.clock_rate = 1200000,
@@ -1285,7 +1299,7 @@ static const struct meson_sar_adc_data meson_sar_adc_gxm_data = {
 };
 
 static const struct meson_sar_adc_data meson_sar_adc_axg_data = {
-	.param = &meson_sar_adc_gxl_param,
+	.param = &meson_sar_adc_axg_param,
 	.name = "meson-axg-saradc",
 };
 
diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c
index c755e8cd52205c..95fa857e8aadfe 100644
--- a/drivers/iio/adc/ti_am335x_adc.c
+++ b/drivers/iio/adc/ti_am335x_adc.c
@@ -670,8 +670,10 @@ static int tiadc_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, indio_dev);
 
 	err = tiadc_request_dma(pdev, adc_dev);
-	if (err && err == -EPROBE_DEFER)
+	if (err && err != -ENODEV) {
+		dev_err_probe(&pdev->dev, err, "DMA request failed\n");
 		goto err_dma;
+	}
 
 	return 0;
 
diff --git a/drivers/iio/buffer/industrialio-triggered-buffer.c b/drivers/iio/buffer/industrialio-triggered-buffer.c
index c7671b1f5eadac..c06515987e7a7c 100644
--- a/drivers/iio/buffer/industrialio-triggered-buffer.c
+++ b/drivers/iio/buffer/industrialio-triggered-buffer.c
@@ -46,6 +46,16 @@ int iio_triggered_buffer_setup_ext(struct iio_dev *indio_dev,
 	struct iio_buffer *buffer;
 	int ret;
 
+	/*
+	 * iio_triggered_buffer_cleanup() assumes that the buffer allocated here
+	 * is assigned to indio_dev->buffer but this is only the case if this
+	 * function is the first caller to iio_device_attach_buffer(). If
+	 * indio_dev->buffer is already set then we can't proceed otherwise the
+	 * cleanup function will try to free a buffer that was not allocated here.
+	 */
+	if (indio_dev->buffer)
+		return -EADDRINUSE;
+
 	buffer = iio_kfifo_allocate();
 	if (!buffer) {
 		ret = -ENOMEM;
diff --git a/drivers/iio/common/ms_sensors/ms_sensors_i2c.c b/drivers/iio/common/ms_sensors/ms_sensors_i2c.c
index 6633b35a94e69a..9c9bc77003c7ff 100644
--- a/drivers/iio/common/ms_sensors/ms_sensors_i2c.c
+++ b/drivers/iio/common/ms_sensors/ms_sensors_i2c.c
@@ -15,8 +15,8 @@
 /* Conversion times in us */
 static const u16 ms_sensors_ht_t_conversion_time[] = { 50000, 25000,
 						       13000, 7000 };
-static const u16 ms_sensors_ht_h_conversion_time[] = { 16000, 3000,
-						       5000, 8000 };
+static const u16 ms_sensors_ht_h_conversion_time[] = { 16000, 5000,
+						       3000, 8000 };
 static const u16 ms_sensors_tp_conversion_time[] = { 500, 1100, 2100,
 						     4100, 8220, 16440 };
 
diff --git a/drivers/iio/imu/adis16475.c b/drivers/iio/imu/adis16475.c
index b7cbe1565aee02..64be656f0b8052 100644
--- a/drivers/iio/imu/adis16475.c
+++ b/drivers/iio/imu/adis16475.c
@@ -70,8 +70,8 @@
 #define ADIS16475_MAX_SCAN_DATA		20
 /* spi max speed in brust mode */
 #define ADIS16475_BURST_MAX_SPEED	1000000
-#define ADIS16475_LSB_DEC_MASK		BIT(0)
-#define ADIS16475_LSB_FIR_MASK		BIT(1)
+#define ADIS16475_LSB_DEC_MASK		0
+#define ADIS16475_LSB_FIR_MASK		1
 #define ADIS16500_BURST_DATA_SEL_0_CHN_MASK	GENMASK(5, 0)
 #define ADIS16500_BURST_DATA_SEL_1_CHN_MASK	GENMASK(12, 7)
 
@@ -1406,50 +1406,6 @@ static int adis16475_config_irq_pin(struct adis16475 *st)
 	return 0;
 }
 
-static const struct of_device_id adis16475_of_match[] = {
-	{ .compatible = "adi,adis16470",
-		.data = &adis16475_chip_info[ADIS16470] },
-	{ .compatible = "adi,adis16475-1",
-		.data = &adis16475_chip_info[ADIS16475_1] },
-	{ .compatible = "adi,adis16475-2",
-		.data = &adis16475_chip_info[ADIS16475_2] },
-	{ .compatible = "adi,adis16475-3",
-		.data = &adis16475_chip_info[ADIS16475_3] },
-	{ .compatible = "adi,adis16477-1",
-		.data = &adis16475_chip_info[ADIS16477_1] },
-	{ .compatible = "adi,adis16477-2",
-		.data = &adis16475_chip_info[ADIS16477_2] },
-	{ .compatible = "adi,adis16477-3",
-		.data = &adis16475_chip_info[ADIS16477_3] },
-	{ .compatible = "adi,adis16465-1",
-		.data = &adis16475_chip_info[ADIS16465_1] },
-	{ .compatible = "adi,adis16465-2",
-		.data = &adis16475_chip_info[ADIS16465_2] },
-	{ .compatible = "adi,adis16465-3",
-		.data = &adis16475_chip_info[ADIS16465_3] },
-	{ .compatible = "adi,adis16467-1",
-		.data = &adis16475_chip_info[ADIS16467_1] },
-	{ .compatible = "adi,adis16467-2",
-		.data = &adis16475_chip_info[ADIS16467_2] },
-	{ .compatible = "adi,adis16467-3",
-		.data = &adis16475_chip_info[ADIS16467_3] },
-	{ .compatible = "adi,adis16500",
-		.data = &adis16475_chip_info[ADIS16500] },
-	{ .compatible = "adi,adis16505-1",
-		.data = &adis16475_chip_info[ADIS16505_1] },
-	{ .compatible = "adi,adis16505-2",
-		.data = &adis16475_chip_info[ADIS16505_2] },
-	{ .compatible = "adi,adis16505-3",
-		.data = &adis16475_chip_info[ADIS16505_3] },
-	{ .compatible = "adi,adis16507-1",
-		.data = &adis16475_chip_info[ADIS16507_1] },
-	{ .compatible = "adi,adis16507-2",
-		.data = &adis16475_chip_info[ADIS16507_2] },
-	{ .compatible = "adi,adis16507-3",
-		.data = &adis16475_chip_info[ADIS16507_3] },
-	{ },
-};
-MODULE_DEVICE_TABLE(of, adis16475_of_match);
 
 static int adis16475_probe(struct spi_device *spi)
 {
@@ -1463,7 +1419,7 @@ static int adis16475_probe(struct spi_device *spi)
 
 	st = iio_priv(indio_dev);
 
-	st->info = device_get_match_data(&spi->dev);
+	st->info = spi_get_device_match_data(spi);
 	if (!st->info)
 		return -EINVAL;
 
@@ -1503,12 +1459,83 @@ static int adis16475_probe(struct spi_device *spi)
 	return 0;
 }
 
+static const struct of_device_id adis16475_of_match[] = {
+	{ .compatible = "adi,adis16470",
+		.data = &adis16475_chip_info[ADIS16470] },
+	{ .compatible = "adi,adis16475-1",
+		.data = &adis16475_chip_info[ADIS16475_1] },
+	{ .compatible = "adi,adis16475-2",
+		.data = &adis16475_chip_info[ADIS16475_2] },
+	{ .compatible = "adi,adis16475-3",
+		.data = &adis16475_chip_info[ADIS16475_3] },
+	{ .compatible = "adi,adis16477-1",
+		.data = &adis16475_chip_info[ADIS16477_1] },
+	{ .compatible = "adi,adis16477-2",
+		.data = &adis16475_chip_info[ADIS16477_2] },
+	{ .compatible = "adi,adis16477-3",
+		.data = &adis16475_chip_info[ADIS16477_3] },
+	{ .compatible = "adi,adis16465-1",
+		.data = &adis16475_chip_info[ADIS16465_1] },
+	{ .compatible = "adi,adis16465-2",
+		.data = &adis16475_chip_info[ADIS16465_2] },
+	{ .compatible = "adi,adis16465-3",
+		.data = &adis16475_chip_info[ADIS16465_3] },
+	{ .compatible = "adi,adis16467-1",
+		.data = &adis16475_chip_info[ADIS16467_1] },
+	{ .compatible = "adi,adis16467-2",
+		.data = &adis16475_chip_info[ADIS16467_2] },
+	{ .compatible = "adi,adis16467-3",
+		.data = &adis16475_chip_info[ADIS16467_3] },
+	{ .compatible = "adi,adis16500",
+		.data = &adis16475_chip_info[ADIS16500] },
+	{ .compatible = "adi,adis16505-1",
+		.data = &adis16475_chip_info[ADIS16505_1] },
+	{ .compatible = "adi,adis16505-2",
+		.data = &adis16475_chip_info[ADIS16505_2] },
+	{ .compatible = "adi,adis16505-3",
+		.data = &adis16475_chip_info[ADIS16505_3] },
+	{ .compatible = "adi,adis16507-1",
+		.data = &adis16475_chip_info[ADIS16507_1] },
+	{ .compatible = "adi,adis16507-2",
+		.data = &adis16475_chip_info[ADIS16507_2] },
+	{ .compatible = "adi,adis16507-3",
+		.data = &adis16475_chip_info[ADIS16507_3] },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, adis16475_of_match);
+
+static const struct spi_device_id adis16475_ids[] = {
+	{ "adis16470", (kernel_ulong_t)&adis16475_chip_info[ADIS16470] },
+	{ "adis16475-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_1] },
+	{ "adis16475-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_2] },
+	{ "adis16475-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_3] },
+	{ "adis16477-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_1] },
+	{ "adis16477-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_2] },
+	{ "adis16477-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_3] },
+	{ "adis16465-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_1] },
+	{ "adis16465-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_2] },
+	{ "adis16465-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_3] },
+	{ "adis16467-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_1] },
+	{ "adis16467-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_2] },
+	{ "adis16467-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_3] },
+	{ "adis16500", (kernel_ulong_t)&adis16475_chip_info[ADIS16500] },
+	{ "adis16505-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_1] },
+	{ "adis16505-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_2] },
+	{ "adis16505-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_3] },
+	{ "adis16507-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_1] },
+	{ "adis16507-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_2] },
+	{ "adis16507-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_3] },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, adis16475_ids);
+
 static struct spi_driver adis16475_driver = {
 	.driver = {
 		.name = "adis16475",
 		.of_match_table = adis16475_of_match,
 	},
 	.probe = adis16475_probe,
+	.id_table = adis16475_ids,
 };
 module_spi_driver(adis16475_driver);
 
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index 3fbeef1a70186b..6b034dccc3b17e 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -750,13 +750,13 @@ inv_mpu6050_read_raw(struct iio_dev *indio_dev,
 			ret = inv_mpu6050_sensor_show(st, st->reg->gyro_offset,
 						chan->channel2, val);
 			mutex_unlock(&st->lock);
-			return IIO_VAL_INT;
+			return ret;
 		case IIO_ACCEL:
 			mutex_lock(&st->lock);
 			ret = inv_mpu6050_sensor_show(st, st->reg->accl_offset,
 						chan->channel2, val);
 			mutex_unlock(&st->lock);
-			return IIO_VAL_INT;
+			return ret;
 
 		default:
 			return -EINVAL;
diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c
index f17304b5446839..5cd27f04b45e6d 100644
--- a/drivers/iio/light/hid-sensor-als.c
+++ b/drivers/iio/light/hid-sensor-als.c
@@ -14,11 +14,8 @@
 #include "../common/hid-sensors/hid-sensor-trigger.h"
 
 enum {
-	CHANNEL_SCAN_INDEX_INTENSITY,
-	CHANNEL_SCAN_INDEX_ILLUM,
-	CHANNEL_SCAN_INDEX_COLOR_TEMP,
-	CHANNEL_SCAN_INDEX_CHROMATICITY_X,
-	CHANNEL_SCAN_INDEX_CHROMATICITY_Y,
+	CHANNEL_SCAN_INDEX_INTENSITY = 0,
+	CHANNEL_SCAN_INDEX_ILLUM = 1,
 	CHANNEL_SCAN_INDEX_MAX
 };
 
@@ -68,40 +65,6 @@ static const struct iio_chan_spec als_channels[] = {
 		BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE),
 		.scan_index = CHANNEL_SCAN_INDEX_ILLUM,
 	},
-	{
-		.type = IIO_COLORTEMP,
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
-		BIT(IIO_CHAN_INFO_SCALE) |
-		BIT(IIO_CHAN_INFO_SAMP_FREQ) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE),
-		.scan_index = CHANNEL_SCAN_INDEX_COLOR_TEMP,
-	},
-	{
-		.type = IIO_CHROMATICITY,
-		.modified = 1,
-		.channel2 = IIO_MOD_X,
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
-		BIT(IIO_CHAN_INFO_SCALE) |
-		BIT(IIO_CHAN_INFO_SAMP_FREQ) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE),
-		.scan_index = CHANNEL_SCAN_INDEX_CHROMATICITY_X,
-	},
-	{
-		.type = IIO_CHROMATICITY,
-		.modified = 1,
-		.channel2 = IIO_MOD_Y,
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
-		BIT(IIO_CHAN_INFO_SCALE) |
-		BIT(IIO_CHAN_INFO_SAMP_FREQ) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE),
-		.scan_index = CHANNEL_SCAN_INDEX_CHROMATICITY_Y,
-	},
 	IIO_CHAN_SOFT_TIMESTAMP(CHANNEL_SCAN_INDEX_TIMESTAMP)
 };
 
@@ -140,21 +103,6 @@ static int als_read_raw(struct iio_dev *indio_dev,
 			min = als_state->als[chan->scan_index].logical_minimum;
 			address = HID_USAGE_SENSOR_LIGHT_ILLUM;
 			break;
-		case  CHANNEL_SCAN_INDEX_COLOR_TEMP:
-			report_id = als_state->als[chan->scan_index].report_id;
-			min = als_state->als[chan->scan_index].logical_minimum;
-			address = HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE;
-			break;
-		case  CHANNEL_SCAN_INDEX_CHROMATICITY_X:
-			report_id = als_state->als[chan->scan_index].report_id;
-			min = als_state->als[chan->scan_index].logical_minimum;
-			address = HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X;
-			break;
-		case  CHANNEL_SCAN_INDEX_CHROMATICITY_Y:
-			report_id = als_state->als[chan->scan_index].report_id;
-			min = als_state->als[chan->scan_index].logical_minimum;
-			address = HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y;
-			break;
 		default:
 			report_id = -1;
 			break;
@@ -275,18 +223,6 @@ static int als_capture_sample(struct hid_sensor_hub_device *hsdev,
 		als_state->scan.illum[CHANNEL_SCAN_INDEX_ILLUM] = sample_data;
 		ret = 0;
 		break;
-	case HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE:
-		als_state->scan.illum[CHANNEL_SCAN_INDEX_COLOR_TEMP] = sample_data;
-		ret = 0;
-		break;
-	case HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X:
-		als_state->scan.illum[CHANNEL_SCAN_INDEX_CHROMATICITY_X] = sample_data;
-		ret = 0;
-		break;
-	case HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y:
-		als_state->scan.illum[CHANNEL_SCAN_INDEX_CHROMATICITY_Y] = sample_data;
-		ret = 0;
-		break;
 	case HID_USAGE_SENSOR_TIME_TIMESTAMP:
 		als_state->timestamp = hid_sensor_convert_timestamp(&als_state->common_attributes,
 								    *(s64 *)raw_data);
@@ -322,38 +258,6 @@ static int als_parse_report(struct platform_device *pdev,
 			st->als[i].report_id);
 	}
 
-	ret = sensor_hub_input_get_attribute_info(hsdev, HID_INPUT_REPORT,
-				usage_id,
-				HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE,
-				&st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP]);
-	if (ret < 0)
-		return ret;
-	als_adjust_channel_bit_mask(channels, CHANNEL_SCAN_INDEX_COLOR_TEMP,
-				st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].size);
-
-	dev_dbg(&pdev->dev, "als %x:%x\n",
-		st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].index,
-		st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].report_id);
-
-	for (i = 0; i < 2; i++) {
-		int next_scan_index = CHANNEL_SCAN_INDEX_CHROMATICITY_X + i;
-
-		ret = sensor_hub_input_get_attribute_info(hsdev,
-				HID_INPUT_REPORT, usage_id,
-				HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X + i,
-				&st->als[next_scan_index]);
-		if (ret < 0)
-			return ret;
-
-		als_adjust_channel_bit_mask(channels,
-					CHANNEL_SCAN_INDEX_CHROMATICITY_X + i,
-					st->als[next_scan_index].size);
-
-		dev_dbg(&pdev->dev, "als %x:%x\n",
-			st->als[next_scan_index].index,
-			st->als[next_scan_index].report_id);
-	}
-
 	st->scale_precision = hid_sensor_format_scale(usage_id,
 				&st->als[CHANNEL_SCAN_INDEX_INTENSITY],
 				&st->scale_pre_decml, &st->scale_post_decml);
diff --git a/drivers/iio/magnetometer/tmag5273.c b/drivers/iio/magnetometer/tmag5273.c
index c5e5c4ad681e64..e8c4ca142d21d6 100644
--- a/drivers/iio/magnetometer/tmag5273.c
+++ b/drivers/iio/magnetometer/tmag5273.c
@@ -356,7 +356,7 @@ static int tmag5273_read_raw(struct iio_dev *indio_dev,
 	case IIO_CHAN_INFO_OFFSET:
 		switch (chan->type) {
 		case IIO_TEMP:
-			*val = -266314;
+			*val = -16005;
 			return IIO_VAL_INT;
 		default:
 			return -EINVAL;
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index f9ab671c8eda55..07c571c7b69992 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -96,12 +96,6 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 		return page_size;
 	}
 
-	/* rdma_for_each_block() has a bug if the page size is smaller than the
-	 * page size used to build the umem. For now prevent smaller page sizes
-	 * from being returned.
-	 */
-	pgsz_bitmap &= GENMASK(BITS_PER_LONG - 1, PAGE_SHIFT);
-
 	/* The best result is the smallest page size that results in the minimum
 	 * number of required pages. Compute the largest page size that could
 	 * work based on VA address bits that don't change.
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 8a6da87f464b0d..94a7f3b0c71cc2 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1971,7 +1971,7 @@ int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width)
 	int rc;
 	u32 netdev_speed;
 	struct net_device *netdev;
-	struct ethtool_link_ksettings lksettings;
+	struct ethtool_link_ksettings lksettings = {};
 
 	if (rdma_port_get_link_layer(dev, port_num) != IB_LINK_LAYER_ETHERNET)
 		return -EINVAL;
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index f79369c8360a5f..a99c68247af0cc 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -71,7 +71,7 @@ static char version[] =
 		BNXT_RE_DESC "\n";
 
 MODULE_AUTHOR("Eddie Wai <eddie.wai@broadcom.com>");
-MODULE_DESCRIPTION(BNXT_RE_DESC " Driver");
+MODULE_DESCRIPTION(BNXT_RE_DESC);
 MODULE_LICENSE("Dual BSD/GPL");
 
 /* globals */
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 0cd2612a49870f..2bca9560f32ddd 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -4760,10 +4760,15 @@ static int check_cong_type(struct ib_qp *ibqp,
 		cong_alg->wnd_mode_sel = WND_LIMIT;
 		break;
 	default:
-		ibdev_err(&hr_dev->ib_dev,
-			  "error type(%u) for congestion selection.\n",
-			  hr_dev->caps.cong_type);
-		return -EINVAL;
+		ibdev_warn(&hr_dev->ib_dev,
+			   "invalid type(%u) for congestion selection.\n",
+			   hr_dev->caps.cong_type);
+		hr_dev->caps.cong_type = CONG_TYPE_DCQCN;
+		cong_alg->alg_sel = CONG_DCQCN;
+		cong_alg->alg_sub_sel = UNSUPPORT_CONG_LEVEL;
+		cong_alg->dip_vld = DIP_INVALID;
+		cong_alg->wnd_mode_sel = WND_LIMIT;
+		break;
 	}
 
 	return 0;
diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c
index 8fa7e4a18e737a..bd4b2b89644442 100644
--- a/drivers/infiniband/hw/irdma/hw.c
+++ b/drivers/infiniband/hw/irdma/hw.c
@@ -321,7 +321,11 @@ static void irdma_process_aeq(struct irdma_pci_f *rf)
 			break;
 		case IRDMA_AE_QP_SUSPEND_COMPLETE:
 			if (iwqp->iwdev->vsi.tc_change_pending) {
-				atomic_dec(&iwqp->sc_qp.vsi->qp_suspend_reqs);
+				if (!atomic_dec_return(&qp->vsi->qp_suspend_reqs))
+					wake_up(&iwqp->iwdev->suspend_wq);
+			}
+			if (iwqp->suspend_pending) {
+				iwqp->suspend_pending = false;
 				wake_up(&iwqp->iwdev->suspend_wq);
 			}
 			break;
@@ -581,9 +585,6 @@ static void irdma_destroy_cqp(struct irdma_pci_f *rf)
 	struct irdma_cqp *cqp = &rf->cqp;
 	int status = 0;
 
-	if (rf->cqp_cmpl_wq)
-		destroy_workqueue(rf->cqp_cmpl_wq);
-
 	status = irdma_sc_cqp_destroy(dev->cqp);
 	if (status)
 		ibdev_dbg(to_ibdev(dev), "ERR: Destroy CQP failed %d\n", status);
@@ -748,6 +749,9 @@ static void irdma_destroy_ccq(struct irdma_pci_f *rf)
 	struct irdma_ccq *ccq = &rf->ccq;
 	int status = 0;
 
+	if (rf->cqp_cmpl_wq)
+		destroy_workqueue(rf->cqp_cmpl_wq);
+
 	if (!rf->reset)
 		status = irdma_sc_ccq_destroy(dev->ccq, 0, true);
 	if (status)
@@ -1180,7 +1184,6 @@ static int irdma_create_ceq(struct irdma_pci_f *rf, struct irdma_ceq *iwceq,
 	int status;
 	struct irdma_ceq_init_info info = {};
 	struct irdma_sc_dev *dev = &rf->sc_dev;
-	u64 scratch;
 	u32 ceq_size;
 
 	info.ceq_id = ceq_id;
@@ -1201,14 +1204,13 @@ static int irdma_create_ceq(struct irdma_pci_f *rf, struct irdma_ceq *iwceq,
 	iwceq->sc_ceq.ceq_id = ceq_id;
 	info.dev = dev;
 	info.vsi = vsi;
-	scratch = (uintptr_t)&rf->cqp.sc_cqp;
 	status = irdma_sc_ceq_init(&iwceq->sc_ceq, &info);
 	if (!status) {
 		if (dev->ceq_valid)
 			status = irdma_cqp_ceq_cmd(&rf->sc_dev, &iwceq->sc_ceq,
 						   IRDMA_OP_CEQ_CREATE);
 		else
-			status = irdma_sc_cceq_create(&iwceq->sc_ceq, scratch);
+			status = irdma_sc_cceq_create(&iwceq->sc_ceq, 0);
 	}
 
 	if (status) {
diff --git a/drivers/infiniband/hw/irdma/main.c b/drivers/infiniband/hw/irdma/main.c
index 9ac48b4dab413d..3f13200ff71bc0 100644
--- a/drivers/infiniband/hw/irdma/main.c
+++ b/drivers/infiniband/hw/irdma/main.c
@@ -48,7 +48,7 @@ static void irdma_prep_tc_change(struct irdma_device *iwdev)
 	/* Wait for all qp's to suspend */
 	wait_event_timeout(iwdev->suspend_wq,
 			   !atomic_read(&iwdev->vsi.qp_suspend_reqs),
-			   IRDMA_EVENT_TIMEOUT);
+			   msecs_to_jiffies(IRDMA_EVENT_TIMEOUT_MS));
 	irdma_ws_reset(&iwdev->vsi);
 }
 
diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h
index d66d87bb8bc4d8..b65bc2ea542f56 100644
--- a/drivers/infiniband/hw/irdma/main.h
+++ b/drivers/infiniband/hw/irdma/main.h
@@ -78,7 +78,7 @@ extern struct auxiliary_driver i40iw_auxiliary_drv;
 
 #define MAX_DPC_ITERATIONS	128
 
-#define IRDMA_EVENT_TIMEOUT		50000
+#define IRDMA_EVENT_TIMEOUT_MS		5000
 #define IRDMA_VCHNL_EVENT_TIMEOUT	100000
 #define IRDMA_RST_TIMEOUT_HZ		4
 
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 2138f0a2ff859e..b5eb8d421988c1 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -1157,6 +1157,21 @@ exit:
 	return prio;
 }
 
+static int irdma_wait_for_suspend(struct irdma_qp *iwqp)
+{
+	if (!wait_event_timeout(iwqp->iwdev->suspend_wq,
+				!iwqp->suspend_pending,
+				msecs_to_jiffies(IRDMA_EVENT_TIMEOUT_MS))) {
+		iwqp->suspend_pending = false;
+		ibdev_warn(&iwqp->iwdev->ibdev,
+			   "modify_qp timed out waiting for suspend. qp_id = %d, last_ae = 0x%x\n",
+			   iwqp->ibqp.qp_num, iwqp->last_aeq);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
 /**
  * irdma_modify_qp_roce - modify qp request
  * @ibqp: qp's pointer for modify
@@ -1420,17 +1435,11 @@ int irdma_modify_qp_roce(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 
 			info.next_iwarp_state = IRDMA_QP_STATE_SQD;
 			issue_modify_qp = 1;
+			iwqp->suspend_pending = true;
 			break;
 		case IB_QPS_SQE:
 		case IB_QPS_ERR:
 		case IB_QPS_RESET:
-			if (iwqp->iwarp_state == IRDMA_QP_STATE_RTS) {
-				spin_unlock_irqrestore(&iwqp->lock, flags);
-				info.next_iwarp_state = IRDMA_QP_STATE_SQD;
-				irdma_hw_modify_qp(iwdev, iwqp, &info, true);
-				spin_lock_irqsave(&iwqp->lock, flags);
-			}
-
 			if (iwqp->iwarp_state == IRDMA_QP_STATE_ERROR) {
 				spin_unlock_irqrestore(&iwqp->lock, flags);
 				if (udata && udata->inlen) {
@@ -1467,6 +1476,11 @@ int irdma_modify_qp_roce(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 			ctx_info->rem_endpoint_idx = udp_info->arp_idx;
 			if (irdma_hw_modify_qp(iwdev, iwqp, &info, true))
 				return -EINVAL;
+			if (info.next_iwarp_state == IRDMA_QP_STATE_SQD) {
+				ret = irdma_wait_for_suspend(iwqp);
+				if (ret)
+					return ret;
+			}
 			spin_lock_irqsave(&iwqp->lock, flags);
 			if (iwqp->iwarp_state == info.curr_iwarp_state) {
 				iwqp->iwarp_state = info.next_iwarp_state;
@@ -2900,7 +2914,7 @@ static struct irdma_mr *irdma_alloc_iwmr(struct ib_umem *region,
 	iwmr->type = reg_type;
 
 	pgsz_bitmap = (reg_type == IRDMA_MEMREG_TYPE_MEM) ?
-		iwdev->rf->sc_dev.hw_attrs.page_size_cap : PAGE_SIZE;
+		iwdev->rf->sc_dev.hw_attrs.page_size_cap : SZ_4K;
 
 	iwmr->page_size = ib_umem_find_best_pgsz(region, pgsz_bitmap, virt);
 	if (unlikely(!iwmr->page_size)) {
@@ -2932,6 +2946,11 @@ static int irdma_reg_user_mr_type_qp(struct irdma_mem_reg_req req,
 	int err;
 	u8 lvl;
 
+	/* iWarp: Catch page not starting on OS page boundary */
+	if (!rdma_protocol_roce(&iwdev->ibdev, 1) &&
+	    ib_umem_offset(iwmr->region))
+		return -EINVAL;
+
 	total = req.sq_pages + req.rq_pages + 1;
 	if (total > iwmr->page_cnt)
 		return -EINVAL;
diff --git a/drivers/infiniband/hw/irdma/verbs.h b/drivers/infiniband/hw/irdma/verbs.h
index c42ac22de00e93..cfa140b36395ae 100644
--- a/drivers/infiniband/hw/irdma/verbs.h
+++ b/drivers/infiniband/hw/irdma/verbs.h
@@ -198,6 +198,7 @@ struct irdma_qp {
 	u8 flush_issued : 1;
 	u8 sig_all : 1;
 	u8 pau_mode : 1;
+	u8 suspend_pending : 1;
 	u8 rsvd : 1;
 	u8 iwarp_state;
 	u16 term_sq_flush_code;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 07261523c55473..7f3167ce297224 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -384,7 +384,7 @@ static void complete_rdma_req(struct rtrs_clt_io_req *req, int errno,
 	struct rtrs_clt_path *clt_path;
 	int err;
 
-	if (WARN_ON(!req->in_use))
+	if (!req->in_use)
 		return;
 	if (WARN_ON(!req->con))
 		return;
@@ -1699,7 +1699,7 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
 		clt_path->s.dev_ref++;
 		max_send_wr = min_t(int, wr_limit,
 			      /* QD * (REQ + RSP + FR REGS or INVS) + drain */
-			      clt_path->queue_depth * 3 + 1);
+			      clt_path->queue_depth * 4 + 1);
 		max_recv_wr = min_t(int, wr_limit,
 			      clt_path->queue_depth * 3 + 1);
 		max_send_sge = 2;
@@ -2350,8 +2350,6 @@ static int init_conns(struct rtrs_clt_path *clt_path)
 	if (err)
 		goto destroy;
 
-	rtrs_start_hb(&clt_path->s);
-
 	return 0;
 
 destroy:
@@ -2625,6 +2623,7 @@ static int init_path(struct rtrs_clt_path *clt_path)
 		goto out;
 	}
 	rtrs_clt_path_up(clt_path);
+	rtrs_start_hb(&clt_path->s);
 out:
 	mutex_unlock(&clt_path->init_mutex);
 
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
index 75e56604e46286..1d33efb8fb03be 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
@@ -65,8 +65,9 @@ static bool rtrs_srv_change_state(struct rtrs_srv_path *srv_path,
 {
 	enum rtrs_srv_state old_state;
 	bool changed = false;
+	unsigned long flags;
 
-	spin_lock_irq(&srv_path->state_lock);
+	spin_lock_irqsave(&srv_path->state_lock, flags);
 	old_state = srv_path->state;
 	switch (new_state) {
 	case RTRS_SRV_CONNECTED:
@@ -87,7 +88,7 @@ static bool rtrs_srv_change_state(struct rtrs_srv_path *srv_path,
 	}
 	if (changed)
 		srv_path->state = new_state;
-	spin_unlock_irq(&srv_path->state_lock);
+	spin_unlock_irqrestore(&srv_path->state_lock, flags);
 
 	return changed;
 }
@@ -550,7 +551,10 @@ static void unmap_cont_bufs(struct rtrs_srv_path *srv_path)
 		struct rtrs_srv_mr *srv_mr;
 
 		srv_mr = &srv_path->mrs[i];
-		rtrs_iu_free(srv_mr->iu, srv_path->s.dev->ib_dev, 1);
+
+		if (always_invalidate)
+			rtrs_iu_free(srv_mr->iu, srv_path->s.dev->ib_dev, 1);
+
 		ib_dereg_mr(srv_mr->mr);
 		ib_dma_unmap_sg(srv_path->s.dev->ib_dev, srv_mr->sgt.sgl,
 				srv_mr->sgt.nents, DMA_BIDIRECTIONAL);
@@ -709,20 +713,23 @@ static void rtrs_srv_info_rsp_done(struct ib_cq *cq, struct ib_wc *wc)
 	WARN_ON(wc->opcode != IB_WC_SEND);
 }
 
-static void rtrs_srv_path_up(struct rtrs_srv_path *srv_path)
+static int rtrs_srv_path_up(struct rtrs_srv_path *srv_path)
 {
 	struct rtrs_srv_sess *srv = srv_path->srv;
 	struct rtrs_srv_ctx *ctx = srv->ctx;
-	int up;
+	int up, ret = 0;
 
 	mutex_lock(&srv->paths_ev_mutex);
 	up = ++srv->paths_up;
 	if (up == 1)
-		ctx->ops.link_ev(srv, RTRS_SRV_LINK_EV_CONNECTED, NULL);
+		ret = ctx->ops.link_ev(srv, RTRS_SRV_LINK_EV_CONNECTED, NULL);
 	mutex_unlock(&srv->paths_ev_mutex);
 
 	/* Mark session as established */
-	srv_path->established = true;
+	if (!ret)
+		srv_path->established = true;
+
+	return ret;
 }
 
 static void rtrs_srv_path_down(struct rtrs_srv_path *srv_path)
@@ -851,7 +858,12 @@ static int process_info_req(struct rtrs_srv_con *con,
 		goto iu_free;
 	kobject_get(&srv_path->kobj);
 	get_device(&srv_path->srv->dev);
-	rtrs_srv_change_state(srv_path, RTRS_SRV_CONNECTED);
+	err = rtrs_srv_change_state(srv_path, RTRS_SRV_CONNECTED);
+	if (!err) {
+		rtrs_err(s, "rtrs_srv_change_state(), err: %d\n", err);
+		goto iu_free;
+	}
+
 	rtrs_srv_start_hb(srv_path);
 
 	/*
@@ -860,7 +872,11 @@ static int process_info_req(struct rtrs_srv_con *con,
 	 * all connections are successfully established.  Thus, simply notify
 	 * listener with a proper event if we are the first path.
 	 */
-	rtrs_srv_path_up(srv_path);
+	err = rtrs_srv_path_up(srv_path);
+	if (err) {
+		rtrs_err(s, "rtrs_srv_path_up(), err: %d\n", err);
+		goto iu_free;
+	}
 
 	ib_dma_sync_single_for_device(srv_path->s.dev->ib_dev,
 				      tx_iu->dma_addr,
@@ -1516,7 +1532,6 @@ static void rtrs_srv_close_work(struct work_struct *work)
 
 	srv_path = container_of(work, typeof(*srv_path), close_work);
 
-	rtrs_srv_destroy_path_files(srv_path);
 	rtrs_srv_stop_hb(srv_path);
 
 	for (i = 0; i < srv_path->s.con_num; i++) {
@@ -1536,6 +1551,8 @@ static void rtrs_srv_close_work(struct work_struct *work)
 	/* Wait for all completion */
 	wait_for_completion(&srv_path->complete_done);
 
+	rtrs_srv_destroy_path_files(srv_path);
+
 	/* Notify upper layer if we are the last path */
 	rtrs_srv_path_down(srv_path);
 
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index f5c21565bb3cec..e2c1848182de9a 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -286,6 +286,7 @@ static const struct xpad_device {
 	{ 0x146b, 0x0604, "Bigben Interactive DAIJA Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
 	{ 0x1532, 0x0a00, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
 	{ 0x1532, 0x0a03, "Razer Wildcat", 0, XTYPE_XBOXONE },
+	{ 0x1532, 0x0a29, "Razer Wolverine V2", 0, XTYPE_XBOXONE },
 	{ 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 },
 	{ 0x15e4, 0x3f0a, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 },
 	{ 0x15e4, 0x3f10, "Batarang Xbox 360 controller", 0, XTYPE_XBOX360 },
diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index c92e544c792df8..786f00f6b7fd8b 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -765,6 +765,44 @@ static void atkbd_deactivate(struct atkbd *atkbd)
 			ps2dev->serio->phys);
 }
 
+#ifdef CONFIG_X86
+static bool atkbd_is_portable_device(void)
+{
+	static const char * const chassis_types[] = {
+		"8",	/* Portable */
+		"9",	/* Laptop */
+		"10",	/* Notebook */
+		"14",	/* Sub-Notebook */
+		"31",	/* Convertible */
+		"32",	/* Detachable */
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(chassis_types); i++)
+		if (dmi_match(DMI_CHASSIS_TYPE, chassis_types[i]))
+			return true;
+
+	return false;
+}
+
+/*
+ * On many modern laptops ATKBD_CMD_GETID may cause problems, on these laptops
+ * the controller is always in translated mode. In this mode mice/touchpads will
+ * not work. So in this case simply assume a keyboard is connected to avoid
+ * confusing some laptop keyboards.
+ *
+ * Skipping ATKBD_CMD_GETID ends up using a fake keyboard id. Using a fake id is
+ * ok in translated mode, only atkbd_select_set() checks atkbd->id and in
+ * translated mode that is a no-op.
+ */
+static bool atkbd_skip_getid(struct atkbd *atkbd)
+{
+	return atkbd->translated && atkbd_is_portable_device();
+}
+#else
+static inline bool atkbd_skip_getid(struct atkbd *atkbd) { return false; }
+#endif
+
 /*
  * atkbd_probe() probes for an AT keyboard on a serio port.
  */
@@ -794,12 +832,12 @@ static int atkbd_probe(struct atkbd *atkbd)
  */
 
 	param[0] = param[1] = 0xa5;	/* initialize with invalid values */
-	if (ps2_command(ps2dev, param, ATKBD_CMD_GETID)) {
+	if (atkbd_skip_getid(atkbd) || ps2_command(ps2dev, param, ATKBD_CMD_GETID)) {
 
 /*
- * If the get ID command failed, we check if we can at least set the LEDs on
- * the keyboard. This should work on every keyboard out there. It also turns
- * the LEDs off, which we want anyway.
+ * If the get ID command was skipped or failed, we check if we can at least set
+ * the LEDs on the keyboard. This should work on every keyboard out there.
+ * It also turns the LEDs off, which we want anyway.
  */
 		param[0] = 0;
 		if (ps2_command(ps2dev, param, ATKBD_CMD_SETLEDS))
diff --git a/drivers/input/keyboard/ipaq-micro-keys.c b/drivers/input/keyboard/ipaq-micro-keys.c
index 7b509bce2b332f..1d71dd79ffd289 100644
--- a/drivers/input/keyboard/ipaq-micro-keys.c
+++ b/drivers/input/keyboard/ipaq-micro-keys.c
@@ -105,6 +105,9 @@ static int micro_key_probe(struct platform_device *pdev)
 	keys->codes = devm_kmemdup(&pdev->dev, micro_keycodes,
 			   keys->input->keycodesize * keys->input->keycodemax,
 			   GFP_KERNEL);
+	if (!keys->codes)
+		return -ENOMEM;
+
 	keys->input->keycode = keys->codes;
 
 	__set_bit(EV_KEY, keys->input->evbit);
diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c
index 08bcee3d6bccac..f6d060377d1894 100644
--- a/drivers/input/misc/soc_button_array.c
+++ b/drivers/input/misc/soc_button_array.c
@@ -299,6 +299,11 @@ static int soc_button_parse_btn_desc(struct device *dev,
 		info->name = "power";
 		info->event_code = KEY_POWER;
 		info->wakeup = true;
+	} else if (upage == 0x01 && usage == 0xc6) {
+		info->name = "airplane mode switch";
+		info->event_type = EV_SW;
+		info->event_code = SW_RFKILL_ALL;
+		info->active_low = false;
 	} else if (upage == 0x01 && usage == 0xca) {
 		info->name = "rotation lock switch";
 		info->event_type = EV_SW;
diff --git a/drivers/input/mouse/amimouse.c b/drivers/input/mouse/amimouse.c
index a50e5035483231..cda0c3ff5a288d 100644
--- a/drivers/input/mouse/amimouse.c
+++ b/drivers/input/mouse/amimouse.c
@@ -125,16 +125,15 @@ static int __init amimouse_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int __exit amimouse_remove(struct platform_device *pdev)
+static void __exit amimouse_remove(struct platform_device *pdev)
 {
 	struct input_dev *dev = platform_get_drvdata(pdev);
 
 	input_unregister_device(dev);
-	return 0;
 }
 
 static struct platform_driver amimouse_driver = {
-	.remove = __exit_p(amimouse_remove),
+	.remove_new = __exit_p(amimouse_remove),
 	.driver   = {
 		.name	= "amiga-mouse",
 	},
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 22d16d80efb938..7a303a9d6bf72b 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -183,6 +183,7 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN009b", /* T580 */
 	"LEN0402", /* X1 Extreme Gen 2 / P1 Gen 2 */
 	"LEN040f", /* P1 Gen 3 */
+	"LEN0411", /* L14 Gen 1 */
 	"LEN200f", /* T450s */
 	"LEN2044", /* L470  */
 	"LEN2054", /* E480 */
diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index 9c39553d30fa27..b585b1dab870e0 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -361,6 +361,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.driver_data = (void *)(SERIO_QUIRK_DRITEK)
 	},
 	{
+		/* Acer TravelMate P459-G2-M */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate P459-G2-M"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
+	},
+	{
 		/* Amoi M636/A737 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Amoi Electronics CO.,LTD."),
diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index dfab160ca52934..50bac2d79d9b5e 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -395,6 +395,9 @@ struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec)
 	}
 	mutex_unlock(&icc_lock);
 
+	if (!node)
+		return ERR_PTR(-EINVAL);
+
 	if (IS_ERR(node))
 		return ERR_CAST(node);
 
diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c
index 628e651c555cb0..dbacb2a7af508f 100644
--- a/drivers/interconnect/qcom/icc-rpm.c
+++ b/drivers/interconnect/qcom/icc-rpm.c
@@ -307,7 +307,7 @@ static u64 qcom_icc_calc_rate(struct qcom_icc_provider *qp, struct qcom_icc_node
 
 	if (qn->ib_coeff) {
 		agg_peak_rate = qn->max_peak[ctx] * 100;
-		agg_peak_rate = div_u64(qn->max_peak[ctx], qn->ib_coeff);
+		agg_peak_rate = div_u64(agg_peak_rate, qn->ib_coeff);
 	} else {
 		agg_peak_rate = qn->max_peak[ctx];
 	}
diff --git a/drivers/interconnect/qcom/sm8250.c b/drivers/interconnect/qcom/sm8250.c
index 83aeb3eedc1972..02d40eea0d6964 100644
--- a/drivers/interconnect/qcom/sm8250.c
+++ b/drivers/interconnect/qcom/sm8250.c
@@ -1995,6 +1995,7 @@ static struct platform_driver qnoc_driver = {
 	.driver = {
 		.name = "qnoc-sm8250",
 		.of_match_table = qnoc_of_match,
+		.sync_state = icc_sync_state,
 	},
 };
 module_platform_driver(qnoc_driver);
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index a3414afe11b07e..23cb80d62a9ab4 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1522,6 +1522,15 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 {
 	struct qi_desc desc;
 
+	/*
+	 * VT-d spec, section 4.3:
+	 *
+	 * Software is recommended to not submit any Device-TLB invalidation
+	 * requests while address remapping hardware is disabled.
+	 */
+	if (!(iommu->gcmd & DMA_GCMD_TE))
+		return;
+
 	if (mask) {
 		addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
 		desc.qw1 = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
@@ -1587,6 +1596,15 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 	unsigned long mask = 1UL << (VTD_PAGE_SHIFT + size_order - 1);
 	struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0};
 
+	/*
+	 * VT-d spec, section 4.3:
+	 *
+	 * Software is recommended to not submit any Device-TLB invalidation
+	 * requests while address remapping hardware is disabled.
+	 */
+	if (!(iommu->gcmd & DMA_GCMD_TE))
+		return;
+
 	desc.qw0 = QI_DEV_EIOTLB_PASID(pasid) | QI_DEV_EIOTLB_SID(sid) |
 		QI_DEV_EIOTLB_QDEP(qdep) | QI_DEIOTLB_TYPE |
 		QI_DEV_IOTLB_PFSID(pfsid);
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 3531b956556c7d..897159dba47de4 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -299,7 +299,7 @@ static int iommu_skip_te_disable;
 #define IDENTMAP_AZALIA		4
 
 const struct iommu_ops intel_iommu_ops;
-const struct iommu_dirty_ops intel_dirty_ops;
+static const struct iommu_dirty_ops intel_dirty_ops;
 
 static bool translation_pre_enabled(struct intel_iommu *iommu)
 {
@@ -2207,6 +2207,8 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			attr |= DMA_FL_PTE_DIRTY;
 	}
 
+	domain->has_mappings = true;
+
 	pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | attr;
 
 	while (nr_pages > 0) {
@@ -2490,7 +2492,8 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 		return ret;
 	}
 
-	iommu_enable_pci_caps(info);
+	if (sm_supported(info->iommu) || !domain_type_is_si(info->domain))
+		iommu_enable_pci_caps(info);
 
 	return 0;
 }
@@ -3925,8 +3928,8 @@ static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *op
  */
 static void domain_context_clear(struct device_domain_info *info)
 {
-	if (!info->iommu || !info->dev || !dev_is_pci(info->dev))
-		return;
+	if (!dev_is_pci(info->dev))
+		domain_context_clear_one(info, info->bus, info->devfn);
 
 	pci_for_each_dma_alias(to_pci_dev(info->dev),
 			       &domain_context_clear_one_cb, info);
@@ -4360,7 +4363,8 @@ static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
 		return true;
 
 	spin_lock_irqsave(&dmar_domain->lock, flags);
-	if (!domain_support_force_snooping(dmar_domain)) {
+	if (!domain_support_force_snooping(dmar_domain) ||
+	    (!dmar_domain->use_first_level && dmar_domain->has_mappings)) {
 		spin_unlock_irqrestore(&dmar_domain->lock, flags);
 		return false;
 	}
@@ -4925,7 +4929,7 @@ static int intel_iommu_read_and_clear_dirty(struct iommu_domain *domain,
 	return 0;
 }
 
-const struct iommu_dirty_ops intel_dirty_ops = {
+static const struct iommu_dirty_ops intel_dirty_ops = {
 	.set_dirty_tracking = intel_iommu_set_dirty_tracking,
 	.read_and_clear_dirty = intel_iommu_read_and_clear_dirty,
 };
@@ -5073,7 +5077,7 @@ static void quirk_igfx_skip_te_disable(struct pci_dev *dev)
 	ver = (dev->device >> 8) & 0xff;
 	if (ver != 0x45 && ver != 0x46 && ver != 0x4c &&
 	    ver != 0x4e && ver != 0x8a && ver != 0x98 &&
-	    ver != 0x9a && ver != 0xa7)
+	    ver != 0x9a && ver != 0xa7 && ver != 0x7d)
 		return;
 
 	if (risky_device(dev))
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 65d37a138c75d4..ce030c5b5772ab 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -602,6 +602,9 @@ struct dmar_domain {
 					 */
 	u8 dirty_tracking:1;		/* Dirty tracking is enabled */
 	u8 nested_parent:1;		/* Has other domains nested on it */
+	u8 has_mappings:1;		/* Has mappings configured through
+					 * iommu_map() interface.
+					 */
 
 	spinlock_t lock;		/* Protect device tracking lists */
 	struct list_head devices;	/* all devices' list */
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 50a481c895b867..ac12f76c1212ac 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -216,6 +216,27 @@ static void intel_flush_svm_range(struct intel_svm *svm, unsigned long address,
 	rcu_read_unlock();
 }
 
+static void intel_flush_svm_all(struct intel_svm *svm)
+{
+	struct device_domain_info *info;
+	struct intel_svm_dev *sdev;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdev, &svm->devs, list) {
+		info = dev_iommu_priv_get(sdev->dev);
+
+		qi_flush_piotlb(sdev->iommu, sdev->did, svm->pasid, 0, -1UL, 0);
+		if (info->ats_enabled) {
+			qi_flush_dev_iotlb_pasid(sdev->iommu, sdev->sid, info->pfsid,
+						 svm->pasid, sdev->qdep,
+						 0, 64 - VTD_PAGE_SHIFT);
+			quirk_extra_dev_tlb_flush(info, 0, 64 - VTD_PAGE_SHIFT,
+						  svm->pasid, sdev->qdep);
+		}
+	}
+	rcu_read_unlock();
+}
+
 /* Pages have been freed at this point */
 static void intel_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
 					struct mm_struct *mm,
@@ -223,6 +244,11 @@ static void intel_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
 {
 	struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);
 
+	if (start == 0 && end == -1UL) {
+		intel_flush_svm_all(svm);
+		return;
+	}
+
 	intel_flush_svm_range(svm, start,
 			      (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0);
 }
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index f17a1113f3d6a3..33e2a9b5d339e4 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -485,11 +485,12 @@ static void iommu_deinit_device(struct device *dev)
 	dev_iommu_free(dev);
 }
 
+DEFINE_MUTEX(iommu_probe_device_lock);
+
 static int __iommu_probe_device(struct device *dev, struct list_head *group_list)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
 	struct iommu_group *group;
-	static DEFINE_MUTEX(iommu_probe_device_lock);
 	struct group_device *gdev;
 	int ret;
 
@@ -502,17 +503,15 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list
 	 * probably be able to use device_lock() here to minimise the scope,
 	 * but for now enforcing a simple global ordering is fine.
 	 */
-	mutex_lock(&iommu_probe_device_lock);
+	lockdep_assert_held(&iommu_probe_device_lock);
 
 	/* Device is probed already if in a group */
-	if (dev->iommu_group) {
-		ret = 0;
-		goto out_unlock;
-	}
+	if (dev->iommu_group)
+		return 0;
 
 	ret = iommu_init_device(dev, ops);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	group = dev->iommu_group;
 	gdev = iommu_group_alloc_device(group, dev);
@@ -548,7 +547,6 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list
 			list_add_tail(&group->entry, group_list);
 	}
 	mutex_unlock(&group->mutex);
-	mutex_unlock(&iommu_probe_device_lock);
 
 	if (dev_is_pci(dev))
 		iommu_dma_set_pci_32bit_workaround(dev);
@@ -562,8 +560,6 @@ err_put_group:
 	iommu_deinit_device(dev);
 	mutex_unlock(&group->mutex);
 	iommu_group_put(group);
-out_unlock:
-	mutex_unlock(&iommu_probe_device_lock);
 
 	return ret;
 }
@@ -573,7 +569,9 @@ int iommu_probe_device(struct device *dev)
 	const struct iommu_ops *ops;
 	int ret;
 
+	mutex_lock(&iommu_probe_device_lock);
 	ret = __iommu_probe_device(dev, NULL);
+	mutex_unlock(&iommu_probe_device_lock);
 	if (ret)
 		return ret;
 
@@ -1788,7 +1786,7 @@ iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 	 */
 	if (ops->default_domain) {
 		if (req_type)
-			return NULL;
+			return ERR_PTR(-EINVAL);
 		return ops->default_domain;
 	}
 
@@ -1797,15 +1795,15 @@ iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 
 	/* The driver gave no guidance on what type to use, try the default */
 	dom = __iommu_group_alloc_default_domain(group, iommu_def_domain_type);
-	if (dom)
+	if (!IS_ERR(dom))
 		return dom;
 
 	/* Otherwise IDENTITY and DMA_FQ defaults will try DMA */
 	if (iommu_def_domain_type == IOMMU_DOMAIN_DMA)
-		return NULL;
+		return ERR_PTR(-EINVAL);
 	dom = __iommu_group_alloc_default_domain(group, IOMMU_DOMAIN_DMA);
-	if (!dom)
-		return NULL;
+	if (IS_ERR(dom))
+		return dom;
 
 	pr_warn("Failed to allocate default IOMMU domain of type %u for group %s - Falling back to IOMMU_DOMAIN_DMA",
 		iommu_def_domain_type, group->name);
@@ -1822,7 +1820,9 @@ static int probe_iommu_group(struct device *dev, void *data)
 	struct list_head *group_list = data;
 	int ret;
 
+	mutex_lock(&iommu_probe_device_lock);
 	ret = __iommu_probe_device(dev, group_list);
+	mutex_unlock(&iommu_probe_device_lock);
 	if (ret == -ENODEV)
 		ret = 0;
 
@@ -2094,10 +2094,17 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
 	else if (ops->domain_alloc)
 		domain = ops->domain_alloc(alloc_type);
 	else
-		return NULL;
+		return ERR_PTR(-EOPNOTSUPP);
 
+	/*
+	 * Many domain_alloc ops now return ERR_PTR, make things easier for the
+	 * driver by accepting ERR_PTR from all domain_alloc ops instead of
+	 * having two rules.
+	 */
+	if (IS_ERR(domain))
+		return domain;
 	if (!domain)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	domain->type = type;
 	/*
@@ -2110,9 +2117,14 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
 	if (!domain->ops)
 		domain->ops = ops->default_domain_ops;
 
-	if (iommu_is_dma_domain(domain) && iommu_get_dma_cookie(domain)) {
-		iommu_domain_free(domain);
-		domain = NULL;
+	if (iommu_is_dma_domain(domain)) {
+		int rc;
+
+		rc = iommu_get_dma_cookie(domain);
+		if (rc) {
+			iommu_domain_free(domain);
+			return ERR_PTR(rc);
+		}
 	}
 	return domain;
 }
@@ -2129,10 +2141,15 @@ __iommu_group_domain_alloc(struct iommu_group *group, unsigned int type)
 
 struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus)
 {
+	struct iommu_domain *domain;
+
 	if (bus == NULL || bus->iommu_ops == NULL)
 		return NULL;
-	return __iommu_domain_alloc(bus->iommu_ops, NULL,
+	domain = __iommu_domain_alloc(bus->iommu_ops, NULL,
 				    IOMMU_DOMAIN_UNMANAGED);
+	if (IS_ERR(domain))
+		return NULL;
+	return domain;
 }
 EXPORT_SYMBOL_GPL(iommu_domain_alloc);
 
@@ -3041,8 +3058,8 @@ static int iommu_setup_default_domain(struct iommu_group *group,
 		return -EINVAL;
 
 	dom = iommu_group_alloc_default_domain(group, req_type);
-	if (!dom)
-		return -ENODEV;
+	if (IS_ERR(dom))
+		return PTR_ERR(dom);
 
 	if (group->default_domain == dom)
 		return 0;
@@ -3243,21 +3260,23 @@ void iommu_device_unuse_default_domain(struct device *dev)
 
 static int __iommu_group_alloc_blocking_domain(struct iommu_group *group)
 {
+	struct iommu_domain *domain;
+
 	if (group->blocking_domain)
 		return 0;
 
-	group->blocking_domain =
-		__iommu_group_domain_alloc(group, IOMMU_DOMAIN_BLOCKED);
-	if (!group->blocking_domain) {
+	domain = __iommu_group_domain_alloc(group, IOMMU_DOMAIN_BLOCKED);
+	if (IS_ERR(domain)) {
 		/*
 		 * For drivers that do not yet understand IOMMU_DOMAIN_BLOCKED
 		 * create an empty domain instead.
 		 */
-		group->blocking_domain = __iommu_group_domain_alloc(
-			group, IOMMU_DOMAIN_UNMANAGED);
-		if (!group->blocking_domain)
-			return -EINVAL;
+		domain = __iommu_group_domain_alloc(group,
+						    IOMMU_DOMAIN_UNMANAGED);
+		if (IS_ERR(domain))
+			return PTR_ERR(domain);
 	}
+	group->blocking_domain = domain;
 	return 0;
 }
 
diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index 59d3a07300d934..873630c111c1fc 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -571,7 +571,7 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 			continue;
 		destroy_hwpt = (*do_attach)(idev, hwpt);
 		if (IS_ERR(destroy_hwpt)) {
-			iommufd_put_object(&hwpt->obj);
+			iommufd_put_object(idev->ictx, &hwpt->obj);
 			/*
 			 * -EINVAL means the domain is incompatible with the
 			 * device. Other error codes should propagate to
@@ -583,7 +583,7 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 			goto out_unlock;
 		}
 		*pt_id = hwpt->obj.id;
-		iommufd_put_object(&hwpt->obj);
+		iommufd_put_object(idev->ictx, &hwpt->obj);
 		goto out_unlock;
 	}
 
@@ -652,7 +652,7 @@ static int iommufd_device_change_pt(struct iommufd_device *idev, u32 *pt_id,
 		destroy_hwpt = ERR_PTR(-EINVAL);
 		goto out_put_pt_obj;
 	}
-	iommufd_put_object(pt_obj);
+	iommufd_put_object(idev->ictx, pt_obj);
 
 	/* This destruction has to be after we unlock everything */
 	if (destroy_hwpt)
@@ -660,7 +660,7 @@ static int iommufd_device_change_pt(struct iommufd_device *idev, u32 *pt_id,
 	return 0;
 
 out_put_pt_obj:
-	iommufd_put_object(pt_obj);
+	iommufd_put_object(idev->ictx, pt_obj);
 	return PTR_ERR(destroy_hwpt);
 }
 
@@ -792,7 +792,7 @@ static int iommufd_access_change_ioas_id(struct iommufd_access *access, u32 id)
 	if (IS_ERR(ioas))
 		return PTR_ERR(ioas);
 	rc = iommufd_access_change_ioas(access, ioas);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(access->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -941,7 +941,7 @@ void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova,
 
 		access->ops->unmap(access->data, iova, length);
 
-		iommufd_put_object(&access->obj);
+		iommufd_put_object(access->ictx, &access->obj);
 		xa_lock(&ioas->iopt.access_list);
 	}
 	xa_unlock(&ioas->iopt.access_list);
@@ -1243,6 +1243,6 @@ int iommufd_get_hw_info(struct iommufd_ucmd *ucmd)
 out_free:
 	kfree(data);
 out_put:
-	iommufd_put_object(&idev->obj);
+	iommufd_put_object(ucmd->ictx, &idev->obj);
 	return rc;
 }
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index 2abbeafdbd22d8..cbb5df0a6c32f8 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -318,9 +318,9 @@ out_unlock:
 	if (ioas)
 		mutex_unlock(&ioas->mutex);
 out_put_pt:
-	iommufd_put_object(pt_obj);
+	iommufd_put_object(ucmd->ictx, pt_obj);
 out_put_idev:
-	iommufd_put_object(&idev->obj);
+	iommufd_put_object(ucmd->ictx, &idev->obj);
 	return rc;
 }
 
@@ -345,7 +345,7 @@ int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd)
 	rc = iopt_set_dirty_tracking(&ioas->iopt, hwpt_paging->common.domain,
 				     enable);
 
-	iommufd_put_object(&hwpt_paging->common.obj);
+	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
 	return rc;
 }
 
@@ -368,6 +368,6 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd)
 	rc = iopt_read_and_clear_dirty_data(
 		&ioas->iopt, hwpt_paging->common.domain, cmd->flags, cmd);
 
-	iommufd_put_object(&hwpt_paging->common.obj);
+	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
 	return rc;
 }
diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c
index d5624577f79f1b..74224827654815 100644
--- a/drivers/iommu/iommufd/ioas.c
+++ b/drivers/iommu/iommufd/ioas.c
@@ -105,7 +105,7 @@ int iommufd_ioas_iova_ranges(struct iommufd_ucmd *ucmd)
 		rc = -EMSGSIZE;
 out_put:
 	up_read(&ioas->iopt.iova_rwsem);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -175,7 +175,7 @@ out_free:
 		interval_tree_remove(node, &allowed_iova);
 		kfree(container_of(node, struct iopt_allowed, node));
 	}
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -228,7 +228,7 @@ int iommufd_ioas_map(struct iommufd_ucmd *ucmd)
 	cmd->iova = iova;
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 out_put:
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -258,7 +258,7 @@ int iommufd_ioas_copy(struct iommufd_ucmd *ucmd)
 		return PTR_ERR(src_ioas);
 	rc = iopt_get_pages(&src_ioas->iopt, cmd->src_iova, cmd->length,
 			    &pages_list);
-	iommufd_put_object(&src_ioas->obj);
+	iommufd_put_object(ucmd->ictx, &src_ioas->obj);
 	if (rc)
 		return rc;
 
@@ -279,7 +279,7 @@ int iommufd_ioas_copy(struct iommufd_ucmd *ucmd)
 	cmd->dst_iova = iova;
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 out_put_dst:
-	iommufd_put_object(&dst_ioas->obj);
+	iommufd_put_object(ucmd->ictx, &dst_ioas->obj);
 out_pages:
 	iopt_free_pages_list(&pages_list);
 	return rc;
@@ -315,7 +315,7 @@ int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd)
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 
 out_put:
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -393,6 +393,6 @@ int iommufd_ioas_option(struct iommufd_ucmd *ucmd)
 		rc = -EOPNOTSUPP;
 	}
 
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index a74cfefffbc6c5..abae041e256f7e 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -21,6 +21,7 @@ struct iommufd_ctx {
 	struct file *file;
 	struct xarray objects;
 	struct xarray groups;
+	wait_queue_head_t destroy_wait;
 
 	u8 account_mode;
 	/* Compatibility with VFIO no iommu */
@@ -135,7 +136,7 @@ enum iommufd_object_type {
 
 /* Base struct for all objects with a userspace ID handle. */
 struct iommufd_object {
-	struct rw_semaphore destroy_rwsem;
+	refcount_t shortterm_users;
 	refcount_t users;
 	enum iommufd_object_type type;
 	unsigned int id;
@@ -143,10 +144,15 @@ struct iommufd_object {
 
 static inline bool iommufd_lock_obj(struct iommufd_object *obj)
 {
-	if (!down_read_trylock(&obj->destroy_rwsem))
+	if (!refcount_inc_not_zero(&obj->users))
 		return false;
-	if (!refcount_inc_not_zero(&obj->users)) {
-		up_read(&obj->destroy_rwsem);
+	if (!refcount_inc_not_zero(&obj->shortterm_users)) {
+		/*
+		 * If the caller doesn't already have a ref on obj this must be
+		 * called under the xa_lock. Otherwise the caller is holding a
+		 * ref on users. Thus it cannot be one before this decrement.
+		 */
+		refcount_dec(&obj->users);
 		return false;
 	}
 	return true;
@@ -154,10 +160,16 @@ static inline bool iommufd_lock_obj(struct iommufd_object *obj)
 
 struct iommufd_object *iommufd_get_object(struct iommufd_ctx *ictx, u32 id,
 					  enum iommufd_object_type type);
-static inline void iommufd_put_object(struct iommufd_object *obj)
+static inline void iommufd_put_object(struct iommufd_ctx *ictx,
+				      struct iommufd_object *obj)
 {
+	/*
+	 * Users first, then shortterm so that REMOVE_WAIT_SHORTTERM never sees
+	 * a spurious !0 users with a 0 shortterm_users.
+	 */
 	refcount_dec(&obj->users);
-	up_read(&obj->destroy_rwsem);
+	if (refcount_dec_and_test(&obj->shortterm_users))
+		wake_up_interruptible_all(&ictx->destroy_wait);
 }
 
 void iommufd_object_abort(struct iommufd_ctx *ictx, struct iommufd_object *obj);
@@ -165,17 +177,49 @@ void iommufd_object_abort_and_destroy(struct iommufd_ctx *ictx,
 				      struct iommufd_object *obj);
 void iommufd_object_finalize(struct iommufd_ctx *ictx,
 			     struct iommufd_object *obj);
-void __iommufd_object_destroy_user(struct iommufd_ctx *ictx,
-				   struct iommufd_object *obj, bool allow_fail);
+
+enum {
+	REMOVE_WAIT_SHORTTERM = 1,
+};
+int iommufd_object_remove(struct iommufd_ctx *ictx,
+			  struct iommufd_object *to_destroy, u32 id,
+			  unsigned int flags);
+
+/*
+ * The caller holds a users refcount and wants to destroy the object. At this
+ * point the caller has no shortterm_users reference and at least the xarray
+ * will be holding one.
+ */
 static inline void iommufd_object_destroy_user(struct iommufd_ctx *ictx,
 					       struct iommufd_object *obj)
 {
-	__iommufd_object_destroy_user(ictx, obj, false);
+	int ret;
+
+	ret = iommufd_object_remove(ictx, obj, obj->id, REMOVE_WAIT_SHORTTERM);
+
+	/*
+	 * If there is a bug and we couldn't destroy the object then we did put
+	 * back the caller's users refcount and will eventually try to free it
+	 * again during close.
+	 */
+	WARN_ON(ret);
 }
-static inline void iommufd_object_deref_user(struct iommufd_ctx *ictx,
-					     struct iommufd_object *obj)
+
+/*
+ * The HWPT allocated by autodomains is used in possibly many devices and
+ * is automatically destroyed when its refcount reaches zero.
+ *
+ * If userspace uses the HWPT manually, even for a short term, then it will
+ * disrupt this refcounting and the auto-free in the kernel will not work.
+ * Userspace that tries to use the automatically allocated HWPT must be careful
+ * to ensure that it is consistently destroyed, eg by not racing accesses
+ * and by not attaching an automatic HWPT to a device manually.
+ */
+static inline void
+iommufd_object_put_and_try_destroy(struct iommufd_ctx *ictx,
+				   struct iommufd_object *obj)
 {
-	__iommufd_object_destroy_user(ictx, obj, true);
+	iommufd_object_remove(ictx, obj, obj->id, 0);
 }
 
 struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
@@ -311,7 +355,7 @@ static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx,
 		lockdep_assert_not_held(&hwpt_paging->ioas->mutex);
 
 		if (hwpt_paging->auto_domain) {
-			iommufd_object_deref_user(ictx, &hwpt->obj);
+			iommufd_object_put_and_try_destroy(ictx, &hwpt->obj);
 			return;
 		}
 	}
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 45b9d40773b13a..c9091e46d208ab 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -33,7 +33,6 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
 					     size_t size,
 					     enum iommufd_object_type type)
 {
-	static struct lock_class_key obj_keys[IOMMUFD_OBJ_MAX];
 	struct iommufd_object *obj;
 	int rc;
 
@@ -41,15 +40,8 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
 	if (!obj)
 		return ERR_PTR(-ENOMEM);
 	obj->type = type;
-	/*
-	 * In most cases the destroy_rwsem is obtained with try so it doesn't
-	 * interact with lockdep, however on destroy we have to sleep. This
-	 * means if we have to destroy an object while holding a get on another
-	 * object it triggers lockdep. Using one locking class per object type
-	 * is a simple and reasonable way to avoid this.
-	 */
-	__init_rwsem(&obj->destroy_rwsem, "iommufd_object::destroy_rwsem",
-		     &obj_keys[type]);
+	/* Starts out bias'd by 1 until it is removed from the xarray */
+	refcount_set(&obj->shortterm_users, 1);
 	refcount_set(&obj->users, 1);
 
 	/*
@@ -129,92 +121,113 @@ struct iommufd_object *iommufd_get_object(struct iommufd_ctx *ictx, u32 id,
 	return obj;
 }
 
+static int iommufd_object_dec_wait_shortterm(struct iommufd_ctx *ictx,
+					     struct iommufd_object *to_destroy)
+{
+	if (refcount_dec_and_test(&to_destroy->shortterm_users))
+		return 0;
+
+	if (wait_event_timeout(ictx->destroy_wait,
+				refcount_read(&to_destroy->shortterm_users) ==
+					0,
+				msecs_to_jiffies(10000)))
+		return 0;
+
+	pr_crit("Time out waiting for iommufd object to become free\n");
+	refcount_inc(&to_destroy->shortterm_users);
+	return -EBUSY;
+}
+
 /*
  * Remove the given object id from the xarray if the only reference to the
- * object is held by the xarray. The caller must call ops destroy().
+ * object is held by the xarray.
  */
-static struct iommufd_object *iommufd_object_remove(struct iommufd_ctx *ictx,
-						    u32 id, bool extra_put)
+int iommufd_object_remove(struct iommufd_ctx *ictx,
+			  struct iommufd_object *to_destroy, u32 id,
+			  unsigned int flags)
 {
 	struct iommufd_object *obj;
 	XA_STATE(xas, &ictx->objects, id);
-
-	xa_lock(&ictx->objects);
-	obj = xas_load(&xas);
-	if (xa_is_zero(obj) || !obj) {
-		obj = ERR_PTR(-ENOENT);
-		goto out_xa;
-	}
+	bool zerod_shortterm = false;
+	int ret;
 
 	/*
-	 * If the caller is holding a ref on obj we put it here under the
-	 * spinlock.
+	 * The purpose of the shortterm_users is to ensure deterministic
+	 * destruction of objects used by external drivers and destroyed by this
+	 * function. Any temporary increment of the refcount must increment
+	 * shortterm_users, such as during ioctl execution.
 	 */
-	if (extra_put)
+	if (flags & REMOVE_WAIT_SHORTTERM) {
+		ret = iommufd_object_dec_wait_shortterm(ictx, to_destroy);
+		if (ret) {
+			/*
+			 * We have a bug. Put back the callers reference and
+			 * defer cleaning this object until close.
+			 */
+			refcount_dec(&to_destroy->users);
+			return ret;
+		}
+		zerod_shortterm = true;
+	}
+
+	xa_lock(&ictx->objects);
+	obj = xas_load(&xas);
+	if (to_destroy) {
+		/*
+		 * If the caller is holding a ref on obj we put it here under
+		 * the spinlock.
+		 */
 		refcount_dec(&obj->users);
 
+		if (WARN_ON(obj != to_destroy)) {
+			ret = -ENOENT;
+			goto err_xa;
+		}
+	} else if (xa_is_zero(obj) || !obj) {
+		ret = -ENOENT;
+		goto err_xa;
+	}
+
 	if (!refcount_dec_if_one(&obj->users)) {
-		obj = ERR_PTR(-EBUSY);
-		goto out_xa;
+		ret = -EBUSY;
+		goto err_xa;
 	}
 
 	xas_store(&xas, NULL);
 	if (ictx->vfio_ioas == container_of(obj, struct iommufd_ioas, obj))
 		ictx->vfio_ioas = NULL;
-
-out_xa:
 	xa_unlock(&ictx->objects);
 
-	/* The returned object reference count is zero */
-	return obj;
-}
-
-/*
- * The caller holds a users refcount and wants to destroy the object. Returns
- * true if the object was destroyed. In all cases the caller no longer has a
- * reference on obj.
- */
-void __iommufd_object_destroy_user(struct iommufd_ctx *ictx,
-				   struct iommufd_object *obj, bool allow_fail)
-{
-	struct iommufd_object *ret;
-
 	/*
-	 * The purpose of the destroy_rwsem is to ensure deterministic
-	 * destruction of objects used by external drivers and destroyed by this
-	 * function. Any temporary increment of the refcount must hold the read
-	 * side of this, such as during ioctl execution.
-	 */
-	down_write(&obj->destroy_rwsem);
-	ret = iommufd_object_remove(ictx, obj->id, true);
-	up_write(&obj->destroy_rwsem);
-
-	if (allow_fail && IS_ERR(ret))
-		return;
-
-	/*
-	 * If there is a bug and we couldn't destroy the object then we did put
-	 * back the caller's refcount and will eventually try to free it again
-	 * during close.
+	 * Since users is zero any positive users_shortterm must be racing
+	 * iommufd_put_object(), or we have a bug.
 	 */
-	if (WARN_ON(IS_ERR(ret)))
-		return;
+	if (!zerod_shortterm) {
+		ret = iommufd_object_dec_wait_shortterm(ictx, obj);
+		if (WARN_ON(ret))
+			return ret;
+	}
 
 	iommufd_object_ops[obj->type].destroy(obj);
 	kfree(obj);
+	return 0;
+
+err_xa:
+	if (zerod_shortterm) {
+		/* Restore the xarray owned reference */
+		refcount_set(&obj->shortterm_users, 1);
+	}
+	xa_unlock(&ictx->objects);
+
+	/* The returned object reference count is zero */
+	return ret;
 }
 
 static int iommufd_destroy(struct iommufd_ucmd *ucmd)
 {
 	struct iommu_destroy *cmd = ucmd->cmd;
-	struct iommufd_object *obj;
 
-	obj = iommufd_object_remove(ucmd->ictx, cmd->id, false);
-	if (IS_ERR(obj))
-		return PTR_ERR(obj);
-	iommufd_object_ops[obj->type].destroy(obj);
-	kfree(obj);
-	return 0;
+	return iommufd_object_remove(ucmd->ictx, NULL, cmd->id, 0);
 }
 
 static int iommufd_fops_open(struct inode *inode, struct file *filp)
@@ -238,6 +251,7 @@ static int iommufd_fops_open(struct inode *inode, struct file *filp)
 	xa_init_flags(&ictx->objects, XA_FLAGS_ALLOC1 | XA_FLAGS_ACCOUNT);
 	xa_init(&ictx->groups);
 	ictx->file = filp;
+	init_waitqueue_head(&ictx->destroy_wait);
 	filp->private_data = ictx;
 	return 0;
 }
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 5d93434003d8ad..022ef8f55088a6 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -86,7 +86,7 @@ void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd,
 	if (IS_ERR(ioas))
 		return;
 	*iova = iommufd_test_syz_conv_iova(&ioas->iopt, iova);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 }
 
 struct mock_iommu_domain {
@@ -500,7 +500,7 @@ get_md_pagetable(struct iommufd_ucmd *ucmd, u32 mockpt_id,
 		return hwpt;
 	if (hwpt->domain->type != IOMMU_DOMAIN_UNMANAGED ||
 	    hwpt->domain->ops != mock_ops.default_domain_ops) {
-		iommufd_put_object(&hwpt->obj);
+		iommufd_put_object(ucmd->ictx, &hwpt->obj);
 		return ERR_PTR(-EINVAL);
 	}
 	*mock = container_of(hwpt->domain, struct mock_iommu_domain, domain);
@@ -518,7 +518,7 @@ get_md_pagetable_nested(struct iommufd_ucmd *ucmd, u32 mockpt_id,
 		return hwpt;
 	if (hwpt->domain->type != IOMMU_DOMAIN_NESTED ||
 	    hwpt->domain->ops != &domain_nested_ops) {
-		iommufd_put_object(&hwpt->obj);
+		iommufd_put_object(ucmd->ictx, &hwpt->obj);
 		return ERR_PTR(-EINVAL);
 	}
 	*mock_nested = container_of(hwpt->domain,
@@ -681,7 +681,7 @@ static int iommufd_test_mock_domain_replace(struct iommufd_ucmd *ucmd,
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 
 out_dev_obj:
-	iommufd_put_object(dev_obj);
+	iommufd_put_object(ucmd->ictx, dev_obj);
 	return rc;
 }
 
@@ -699,7 +699,7 @@ static int iommufd_test_add_reserved(struct iommufd_ucmd *ucmd,
 	down_write(&ioas->iopt.iova_rwsem);
 	rc = iopt_reserve_iova(&ioas->iopt, start, start + length - 1, NULL);
 	up_write(&ioas->iopt.iova_rwsem);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -754,7 +754,7 @@ static int iommufd_test_md_check_pa(struct iommufd_ucmd *ucmd,
 	rc = 0;
 
 out_put:
-	iommufd_put_object(&hwpt->obj);
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
 	return rc;
 }
 
@@ -1233,7 +1233,7 @@ static int iommufd_test_dirty(struct iommufd_ucmd *ucmd, unsigned int mockpt_id,
 out_free:
 	kvfree(tmp);
 out_put:
-	iommufd_put_object(&hwpt->obj);
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
 	return rc;
 }
 
diff --git a/drivers/iommu/iommufd/vfio_compat.c b/drivers/iommu/iommufd/vfio_compat.c
index 538fbf76354d13..a3ad5f0b6c59dd 100644
--- a/drivers/iommu/iommufd/vfio_compat.c
+++ b/drivers/iommu/iommufd/vfio_compat.c
@@ -41,7 +41,7 @@ int iommufd_vfio_compat_ioas_get_id(struct iommufd_ctx *ictx, u32 *out_ioas_id)
 	if (IS_ERR(ioas))
 		return PTR_ERR(ioas);
 	*out_ioas_id = ioas->obj.id;
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return 0;
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_get_id, IOMMUFD_VFIO);
@@ -98,7 +98,7 @@ int iommufd_vfio_compat_ioas_create(struct iommufd_ctx *ictx)
 
 	if (ictx->vfio_ioas && iommufd_lock_obj(&ictx->vfio_ioas->obj)) {
 		ret = 0;
-		iommufd_put_object(&ictx->vfio_ioas->obj);
+		iommufd_put_object(ictx, &ictx->vfio_ioas->obj);
 		goto out_abort;
 	}
 	ictx->vfio_ioas = ioas;
@@ -133,7 +133,7 @@ int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd)
 		if (IS_ERR(ioas))
 			return PTR_ERR(ioas);
 		cmd->ioas_id = ioas->obj.id;
-		iommufd_put_object(&ioas->obj);
+		iommufd_put_object(ucmd->ictx, &ioas->obj);
 		return iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 
 	case IOMMU_VFIO_IOAS_SET:
@@ -143,7 +143,7 @@ int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd)
 		xa_lock(&ucmd->ictx->objects);
 		ucmd->ictx->vfio_ioas = ioas;
 		xa_unlock(&ucmd->ictx->objects);
-		iommufd_put_object(&ioas->obj);
+		iommufd_put_object(ucmd->ictx, &ioas->obj);
 		return 0;
 
 	case IOMMU_VFIO_IOAS_CLEAR:
@@ -190,7 +190,7 @@ static int iommufd_vfio_map_dma(struct iommufd_ctx *ictx, unsigned int cmd,
 	iova = map.iova;
 	rc = iopt_map_user_pages(ictx, &ioas->iopt, &iova, u64_to_user_ptr(map.vaddr),
 				 map.size, iommu_prot, 0);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
@@ -249,7 +249,7 @@ static int iommufd_vfio_unmap_dma(struct iommufd_ctx *ictx, unsigned int cmd,
 		rc = -EFAULT;
 
 err_put:
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
@@ -272,7 +272,7 @@ static int iommufd_vfio_cc_iommu(struct iommufd_ctx *ictx)
 	}
 	mutex_unlock(&ioas->mutex);
 
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
@@ -349,7 +349,7 @@ static int iommufd_vfio_set_iommu(struct iommufd_ctx *ictx, unsigned long type)
 	 */
 	if (type == VFIO_TYPE1_IOMMU)
 		rc = iopt_disable_large_pages(&ioas->iopt);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
@@ -511,7 +511,7 @@ static int iommufd_vfio_iommu_get_info(struct iommufd_ctx *ictx,
 
 out_put:
 	up_read(&ioas->iopt.iova_rwsem);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 157b286e36bf3a..35ba090f3b5e24 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -112,16 +112,20 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 					   const u32 *id)
 {
 	const struct iommu_ops *ops = NULL;
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct iommu_fwspec *fwspec;
 	int err = NO_IOMMU;
 
 	if (!master_np)
 		return NULL;
 
+	/* Serialise to make dev->iommu stable under our potential fwspec */
+	mutex_lock(&iommu_probe_device_lock);
+	fwspec = dev_iommu_fwspec_get(dev);
 	if (fwspec) {
-		if (fwspec->ops)
+		if (fwspec->ops) {
+			mutex_unlock(&iommu_probe_device_lock);
 			return fwspec->ops;
-
+		}
 		/* In the deferred case, start again from scratch */
 		iommu_fwspec_free(dev);
 	}
@@ -155,6 +159,8 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 		fwspec = dev_iommu_fwspec_get(dev);
 		ops    = fwspec->ops;
 	}
+	mutex_unlock(&iommu_probe_device_lock);
+
 	/*
 	 * If we have reason to believe the IOMMU driver missed the initial
 	 * probe for dev, replay it to get things in order.
@@ -191,7 +197,7 @@ iommu_resv_region_get_type(struct device *dev,
 	if (start == phys->start && end == phys->end)
 		return IOMMU_RESV_DIRECT;
 
-	dev_warn(dev, "treating non-direct mapping [%pr] -> [%pap-%pap] as reservation\n", &phys,
+	dev_warn(dev, "treating non-direct mapping [%pr] -> [%pap-%pap] as reservation\n", phys,
 		 &start, &end);
 	return IOMMU_RESV_RESERVED;
 }
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index a8c89df1a99786..9a7a74239eabb7 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -2379,12 +2379,12 @@ retry_baser:
 		break;
 	}
 
+	if (!shr)
+		gic_flush_dcache_to_poc(base, PAGE_ORDER_TO_SIZE(order));
+
 	its_write_baser(its, baser, val);
 	tmp = baser->val;
 
-	if (its->flags & ITS_FLAGS_FORCE_NON_SHAREABLE)
-		tmp &= ~GITS_BASER_SHAREABILITY_MASK;
-
 	if ((val ^ tmp) & GITS_BASER_SHAREABILITY_MASK) {
 		/*
 		 * Shareability didn't stick. Just use
@@ -2394,10 +2394,9 @@ retry_baser:
 		 * non-cacheable as well.
 		 */
 		shr = tmp & GITS_BASER_SHAREABILITY_MASK;
-		if (!shr) {
+		if (!shr)
 			cache = GITS_BASER_nC;
-			gic_flush_dcache_to_poc(base, PAGE_ORDER_TO_SIZE(order));
-		}
+
 		goto retry_baser;
 	}
 
@@ -2609,6 +2608,11 @@ static int its_alloc_tables(struct its_node *its)
 		/* erratum 24313: ignore memory access type */
 		cache = GITS_BASER_nCnB;
 
+	if (its->flags & ITS_FLAGS_FORCE_NON_SHAREABLE) {
+		cache = GITS_BASER_nC;
+		shr = 0;
+	}
+
 	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
 		struct its_baser *baser = its->tables + i;
 		u64 val = its_read_baser(its, baser);
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 68d11ccee44120..98b0329b7154a4 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -39,8 +39,7 @@
 
 #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996	(1ULL << 0)
 #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539	(1ULL << 1)
-#define FLAGS_WORKAROUND_MTK_GICR_SAVE		(1ULL << 2)
-#define FLAGS_WORKAROUND_ASR_ERRATUM_8601001	(1ULL << 3)
+#define FLAGS_WORKAROUND_ASR_ERRATUM_8601001	(1ULL << 2)
 
 #define GIC_IRQ_TYPE_PARTITION	(GIC_IRQ_TYPE_LPI + 1)
 
@@ -106,7 +105,7 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
  * - Figure 4-7 Secure read of the priority field for a Non-secure Group 1
  *   interrupt.
  */
-DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis);
+static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis);
 
 DEFINE_STATIC_KEY_FALSE(gic_nonsecure_priorities);
 EXPORT_SYMBOL(gic_nonsecure_priorities);
@@ -1779,15 +1778,6 @@ static bool gic_enable_quirk_msm8996(void *data)
 	return true;
 }
 
-static bool gic_enable_quirk_mtk_gicr(void *data)
-{
-	struct gic_chip_data *d = data;
-
-	d->flags |= FLAGS_WORKAROUND_MTK_GICR_SAVE;
-
-	return true;
-}
-
 static bool gic_enable_quirk_cavium_38539(void *data)
 {
 	struct gic_chip_data *d = data;
@@ -1889,11 +1879,6 @@ static const struct gic_quirk gic_quirks[] = {
 		.init	= gic_enable_quirk_asr8601,
 	},
 	{
-		.desc	= "GICv3: Mediatek Chromebook GICR save problem",
-		.property = "mediatek,broken-save-restore-fw",
-		.init	= gic_enable_quirk_mtk_gicr,
-	},
-	{
 		.desc	= "GICv3: HIP06 erratum 161010803",
 		.iidr	= 0x0204043b,
 		.mask	= 0xffffffff,
@@ -1959,11 +1944,6 @@ static void gic_enable_nmi_support(void)
 	if (!gic_prio_masking_enabled())
 		return;
 
-	if (gic_data.flags & FLAGS_WORKAROUND_MTK_GICR_SAVE) {
-		pr_warn("Skipping NMI enable due to firmware issues\n");
-		return;
-	}
-
 	rdist_nmi_refs = kcalloc(gic_data.ppi_nr + SGI_NR,
 				 sizeof(*rdist_nmi_refs), GFP_KERNEL);
 	if (!rdist_nmi_refs)
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 974b84f6bd6af7..ba1be15cfd8ea3 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -75,19 +75,6 @@ static ssize_t max_brightness_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(max_brightness);
 
-static ssize_t color_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	const char *color_text = "invalid";
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-
-	if (led_cdev->color < LED_COLOR_ID_MAX)
-		color_text = led_colors[led_cdev->color];
-
-	return sysfs_emit(buf, "%s\n", color_text);
-}
-static DEVICE_ATTR_RO(color);
-
 #ifdef CONFIG_LEDS_TRIGGERS
 static BIN_ATTR(trigger, 0644, led_trigger_read, led_trigger_write, 0);
 static struct bin_attribute *led_trigger_bin_attrs[] = {
@@ -102,7 +89,6 @@ static const struct attribute_group led_trigger_group = {
 static struct attribute *led_class_attrs[] = {
 	&dev_attr_brightness.attr,
 	&dev_attr_max_brightness.attr,
-	&dev_attr_color.attr,
 	NULL,
 };
 
diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
index e358e77e4b38f9..d76214fa9ad864 100644
--- a/drivers/leds/trigger/ledtrig-netdev.c
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -226,6 +226,11 @@ static int set_device_name(struct led_netdev_data *trigger_data,
 
 	cancel_delayed_work_sync(&trigger_data->work);
 
+	/*
+	 * Take RTNL lock before trigger_data lock to prevent potential
+	 * deadlock with netdev notifier registration.
+	 */
+	rtnl_lock();
 	mutex_lock(&trigger_data->lock);
 
 	if (trigger_data->net_dev) {
@@ -245,16 +250,14 @@ static int set_device_name(struct led_netdev_data *trigger_data,
 	trigger_data->carrier_link_up = false;
 	trigger_data->link_speed = SPEED_UNKNOWN;
 	trigger_data->duplex = DUPLEX_UNKNOWN;
-	if (trigger_data->net_dev != NULL) {
-		rtnl_lock();
+	if (trigger_data->net_dev)
 		get_device_state(trigger_data);
-		rtnl_unlock();
-	}
 
 	trigger_data->last_activity = 0;
 
 	set_baseline_state(trigger_data);
 	mutex_unlock(&trigger_data->lock);
+	rtnl_unlock();
 
 	return 0;
 }
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 2a8b081bce7dd8..3ff87cb4dc4948 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -660,6 +660,7 @@ config DM_ZONED
 
 config DM_AUDIT
 	bool "DM audit events"
+	depends on BLK_DEV_DM
 	depends on AUDIT
 	help
 	  Generate audit events for device-mapper.
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 05be59ae21b29d..6ae2329052c92c 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -265,6 +265,7 @@ struct bcache_device {
 #define BCACHE_DEV_WB_RUNNING		3
 #define BCACHE_DEV_RATE_DW_RUNNING	4
 	int			nr_stripes;
+#define BCH_MIN_STRIPE_SZ		((4 << 20) >> SECTOR_SHIFT)
 	unsigned int		stripe_size;
 	atomic_t		*stripe_sectors_dirty;
 	unsigned long		*full_dirty_stripes;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index ae5cbb55861fdb..196cdacce38f25 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -293,16 +293,16 @@ static void btree_complete_write(struct btree *b, struct btree_write *w)
 	w->journal	= NULL;
 }
 
-static void btree_node_write_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(btree_node_write_unlock)
 {
-	struct btree *b = container_of(cl, struct btree, io);
+	closure_type(b, struct btree, io);
 
 	up(&b->io_mutex);
 }
 
-static void __btree_node_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(__btree_node_write_done)
 {
-	struct btree *b = container_of(cl, struct btree, io);
+	closure_type(b, struct btree, io);
 	struct btree_write *w = btree_prev_write(b);
 
 	bch_bbio_free(b->bio, b->c);
@@ -315,12 +315,12 @@ static void __btree_node_write_done(struct closure *cl)
 	closure_return_with_destructor(cl, btree_node_write_unlock);
 }
 
-static void btree_node_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(btree_node_write_done)
 {
-	struct btree *b = container_of(cl, struct btree, io);
+	closure_type(b, struct btree, io);
 
 	bio_free_pages(b->bio);
-	__btree_node_write_done(cl);
+	__btree_node_write_done(&cl->work);
 }
 
 static void btree_node_write_endio(struct bio *bio)
@@ -1000,6 +1000,9 @@ err:
  *
  * The btree node will have either a read or a write lock held, depending on
  * level and op->lock.
+ *
+ * Note: Only error code or btree pointer will be returned, it is unncessary
+ *       for callers to check NULL pointer.
  */
 struct btree *bch_btree_node_get(struct cache_set *c, struct btree_op *op,
 				 struct bkey *k, int level, bool write,
@@ -1111,6 +1114,10 @@ retry:
 	mutex_unlock(&b->c->bucket_lock);
 }
 
+/*
+ * Only error code or btree pointer will be returned, it is unncessary for
+ * callers to check NULL pointer.
+ */
 struct btree *__bch_btree_node_alloc(struct cache_set *c, struct btree_op *op,
 				     int level, bool wait,
 				     struct btree *parent)
@@ -1368,7 +1375,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
 	memset(new_nodes, 0, sizeof(new_nodes));
 	closure_init_stack(&cl);
 
-	while (nodes < GC_MERGE_NODES && !IS_ERR(r[nodes].b))
+	while (nodes < GC_MERGE_NODES && !IS_ERR_OR_NULL(r[nodes].b))
 		keys += r[nodes++].keys;
 
 	blocks = btree_default_blocks(b->c) * 2 / 3;
@@ -1515,7 +1522,7 @@ out_nocoalesce:
 	bch_keylist_free(&keylist);
 
 	for (i = 0; i < nodes; i++)
-		if (!IS_ERR(new_nodes[i])) {
+		if (!IS_ERR_OR_NULL(new_nodes[i])) {
 			btree_node_free(new_nodes[i]);
 			rw_unlock(true, new_nodes[i]);
 		}
@@ -1532,6 +1539,8 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op,
 		return 0;
 
 	n = btree_node_alloc_replacement(replace, NULL);
+	if (IS_ERR(n))
+		return 0;
 
 	/* recheck reserve after allocating replacement node */
 	if (btree_check_reserve(b, NULL)) {
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index c182c21de2e819..7ff14bd2feb8bb 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -723,11 +723,11 @@ static void journal_write_endio(struct bio *bio)
 	closure_put(&w->c->journal.io);
 }
 
-static void journal_write(struct closure *cl);
+static CLOSURE_CALLBACK(journal_write);
 
-static void journal_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_done)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct journal_write *w = (j->cur == j->w)
 		? &j->w[1]
 		: &j->w[0];
@@ -736,19 +736,19 @@ static void journal_write_done(struct closure *cl)
 	continue_at_nobarrier(cl, journal_write, bch_journal_wq);
 }
 
-static void journal_write_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_unlock)
 	__releases(&c->journal.lock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 
 	c->journal.io_in_flight = 0;
 	spin_unlock(&c->journal.lock);
 }
 
-static void journal_write_unlocked(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_unlocked)
 	__releases(c->journal.lock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 	struct cache *ca = c->cache;
 	struct journal_write *w = c->journal.cur;
 	struct bkey *k = &c->journal.key;
@@ -823,12 +823,12 @@ static void journal_write_unlocked(struct closure *cl)
 	continue_at(cl, journal_write_done, NULL);
 }
 
-static void journal_write(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 
 	spin_lock(&c->journal.lock);
-	journal_write_unlocked(cl);
+	journal_write_unlocked(&cl->work);
 }
 
 static void journal_try_write(struct cache_set *c)
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 9f32901fdad102..ebd500bdf0b2fb 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -35,16 +35,16 @@ static bool moving_pred(struct keybuf *buf, struct bkey *k)
 
 /* Moving GC - IO loop */
 
-static void moving_io_destructor(struct closure *cl)
+static CLOSURE_CALLBACK(moving_io_destructor)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 
 	kfree(io);
 }
 
-static void write_moving_finish(struct closure *cl)
+static CLOSURE_CALLBACK(write_moving_finish)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 	struct bio *bio = &io->bio.bio;
 
 	bio_free_pages(bio);
@@ -89,9 +89,9 @@ static void moving_init(struct moving_io *io)
 	bch_bio_map(bio, NULL);
 }
 
-static void write_moving(struct closure *cl)
+static CLOSURE_CALLBACK(write_moving)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 	struct data_insert_op *op = &io->op;
 
 	if (!op->status) {
@@ -113,9 +113,9 @@ static void write_moving(struct closure *cl)
 	continue_at(cl, write_moving_finish, op->wq);
 }
 
-static void read_moving_submit(struct closure *cl)
+static CLOSURE_CALLBACK(read_moving_submit)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 	struct bio *bio = &io->bio.bio;
 
 	bch_submit_bbio(bio, io->op.c, &io->w->key, 0);
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index a9b1f3896249b3..83d112bd2b1c0e 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -25,7 +25,7 @@
 
 struct kmem_cache *bch_search_cache;
 
-static void bch_data_insert_start(struct closure *cl);
+static CLOSURE_CALLBACK(bch_data_insert_start);
 
 static unsigned int cache_mode(struct cached_dev *dc)
 {
@@ -55,9 +55,9 @@ static void bio_csum(struct bio *bio, struct bkey *k)
 
 /* Insert data into cache */
 
-static void bch_data_insert_keys(struct closure *cl)
+static CLOSURE_CALLBACK(bch_data_insert_keys)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 	atomic_t *journal_ref = NULL;
 	struct bkey *replace_key = op->replace ? &op->replace_key : NULL;
 	int ret;
@@ -136,9 +136,9 @@ out:
 	continue_at(cl, bch_data_insert_keys, op->wq);
 }
 
-static void bch_data_insert_error(struct closure *cl)
+static CLOSURE_CALLBACK(bch_data_insert_error)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 
 	/*
 	 * Our data write just errored, which means we've got a bunch of keys to
@@ -163,7 +163,7 @@ static void bch_data_insert_error(struct closure *cl)
 
 	op->insert_keys.top = dst;
 
-	bch_data_insert_keys(cl);
+	bch_data_insert_keys(&cl->work);
 }
 
 static void bch_data_insert_endio(struct bio *bio)
@@ -184,9 +184,9 @@ static void bch_data_insert_endio(struct bio *bio)
 	bch_bbio_endio(op->c, bio, bio->bi_status, "writing data to cache");
 }
 
-static void bch_data_insert_start(struct closure *cl)
+static CLOSURE_CALLBACK(bch_data_insert_start)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 	struct bio *bio = op->bio, *n;
 
 	if (op->bypass)
@@ -305,16 +305,16 @@ err:
  * If op->bypass is true, instead of inserting the data it invalidates the
  * region of the cache represented by op->bio and op->inode.
  */
-void bch_data_insert(struct closure *cl)
+CLOSURE_CALLBACK(bch_data_insert)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 
 	trace_bcache_write(op->c, op->inode, op->bio,
 			   op->writeback, op->bypass);
 
 	bch_keylist_init(&op->insert_keys);
 	bio_get(op->bio);
-	bch_data_insert_start(cl);
+	bch_data_insert_start(&cl->work);
 }
 
 /*
@@ -575,9 +575,9 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k)
 	return n == bio ? MAP_DONE : MAP_CONTINUE;
 }
 
-static void cache_lookup(struct closure *cl)
+static CLOSURE_CALLBACK(cache_lookup)
 {
-	struct search *s = container_of(cl, struct search, iop.cl);
+	closure_type(s, struct search, iop.cl);
 	struct bio *bio = &s->bio.bio;
 	struct cached_dev *dc;
 	int ret;
@@ -698,9 +698,9 @@ static void do_bio_hook(struct search *s,
 	bio_cnt_set(bio, 3);
 }
 
-static void search_free(struct closure *cl)
+static CLOSURE_CALLBACK(search_free)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 
 	atomic_dec(&s->iop.c->search_inflight);
 
@@ -749,20 +749,20 @@ static inline struct search *search_alloc(struct bio *bio,
 
 /* Cached devices */
 
-static void cached_dev_bio_complete(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_bio_complete)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	cached_dev_put(dc);
-	search_free(cl);
+	search_free(&cl->work);
 }
 
 /* Process reads */
 
-static void cached_dev_read_error_done(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_error_done)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 
 	if (s->iop.replace_collision)
 		bch_mark_cache_miss_collision(s->iop.c, s->d);
@@ -770,12 +770,12 @@ static void cached_dev_read_error_done(struct closure *cl)
 	if (s->iop.bio)
 		bio_free_pages(s->iop.bio);
 
-	cached_dev_bio_complete(cl);
+	cached_dev_bio_complete(&cl->work);
 }
 
-static void cached_dev_read_error(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_error)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct bio *bio = &s->bio.bio;
 
 	/*
@@ -801,9 +801,9 @@ static void cached_dev_read_error(struct closure *cl)
 	continue_at(cl, cached_dev_read_error_done, NULL);
 }
 
-static void cached_dev_cache_miss_done(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_cache_miss_done)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct bcache_device *d = s->d;
 
 	if (s->iop.replace_collision)
@@ -812,13 +812,13 @@ static void cached_dev_cache_miss_done(struct closure *cl)
 	if (s->iop.bio)
 		bio_free_pages(s->iop.bio);
 
-	cached_dev_bio_complete(cl);
+	cached_dev_bio_complete(&cl->work);
 	closure_put(&d->cl);
 }
 
-static void cached_dev_read_done(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_done)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	/*
@@ -858,9 +858,9 @@ static void cached_dev_read_done(struct closure *cl)
 	continue_at(cl, cached_dev_cache_miss_done, NULL);
 }
 
-static void cached_dev_read_done_bh(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_done_bh)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	bch_mark_cache_accounting(s->iop.c, s->d,
@@ -955,13 +955,13 @@ static void cached_dev_read(struct cached_dev *dc, struct search *s)
 
 /* Process writes */
 
-static void cached_dev_write_complete(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_write_complete)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	up_read_non_owner(&dc->writeback_lock);
-	cached_dev_bio_complete(cl);
+	cached_dev_bio_complete(&cl->work);
 }
 
 static void cached_dev_write(struct cached_dev *dc, struct search *s)
@@ -1048,9 +1048,9 @@ insert_data:
 	continue_at(cl, cached_dev_write_complete, NULL);
 }
 
-static void cached_dev_nodata(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_nodata)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct bio *bio = &s->bio.bio;
 
 	if (s->iop.flush_journal)
@@ -1265,9 +1265,9 @@ static int flash_dev_cache_miss(struct btree *b, struct search *s,
 	return MAP_CONTINUE;
 }
 
-static void flash_dev_nodata(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_nodata)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 
 	if (s->iop.flush_journal)
 		bch_journal_meta(s->iop.c, cl);
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index 38ab4856eaab0d..46bbef00aebb9d 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -34,7 +34,7 @@ struct data_insert_op {
 };
 
 unsigned int bch_get_congested(const struct cache_set *c);
-void bch_data_insert(struct closure *cl);
+CLOSURE_CALLBACK(bch_data_insert);
 
 void bch_cached_dev_request_init(struct cached_dev *dc);
 void cached_dev_submit_bio(struct bio *bio);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 8bd899766372af..1402096b8076db 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -327,9 +327,9 @@ static void __write_super(struct cache_sb *sb, struct cache_sb_disk *out,
 	submit_bio(bio);
 }
 
-static void bch_write_bdev_super_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(bch_write_bdev_super_unlock)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, sb_write);
+	closure_type(dc, struct cached_dev, sb_write);
 
 	up(&dc->sb_write_mutex);
 }
@@ -363,9 +363,9 @@ static void write_super_endio(struct bio *bio)
 	closure_put(&ca->set->sb_write);
 }
 
-static void bcache_write_super_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(bcache_write_super_unlock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, sb_write);
+	closure_type(c, struct cache_set, sb_write);
 
 	up(&c->sb_write_mutex);
 }
@@ -407,9 +407,9 @@ static void uuid_endio(struct bio *bio)
 	closure_put(cl);
 }
 
-static void uuid_io_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(uuid_io_unlock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, uuid_write);
+	closure_type(c, struct cache_set, uuid_write);
 
 	up(&c->uuid_write_mutex);
 }
@@ -905,6 +905,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 
 	if (!d->stripe_size)
 		d->stripe_size = 1 << 31;
+	else if (d->stripe_size < BCH_MIN_STRIPE_SZ)
+		d->stripe_size = roundup(BCH_MIN_STRIPE_SZ, d->stripe_size);
 
 	n = DIV_ROUND_UP_ULL(sectors, d->stripe_size);
 	if (!n || n > max_stripes) {
@@ -1342,9 +1344,9 @@ void bch_cached_dev_release(struct kobject *kobj)
 	module_put(THIS_MODULE);
 }
 
-static void cached_dev_free(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_free)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
+	closure_type(dc, struct cached_dev, disk.cl);
 
 	if (test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags))
 		cancel_writeback_rate_update_dwork(dc);
@@ -1376,9 +1378,9 @@ static void cached_dev_free(struct closure *cl)
 	kobject_put(&dc->disk.kobj);
 }
 
-static void cached_dev_flush(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_flush)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
+	closure_type(dc, struct cached_dev, disk.cl);
 	struct bcache_device *d = &dc->disk;
 
 	mutex_lock(&bch_register_lock);
@@ -1497,9 +1499,9 @@ void bch_flash_dev_release(struct kobject *kobj)
 	kfree(d);
 }
 
-static void flash_dev_free(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_free)
 {
-	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+	closure_type(d, struct bcache_device, cl);
 
 	mutex_lock(&bch_register_lock);
 	atomic_long_sub(bcache_dev_sectors_dirty(d),
@@ -1510,9 +1512,9 @@ static void flash_dev_free(struct closure *cl)
 	kobject_put(&d->kobj);
 }
 
-static void flash_dev_flush(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_flush)
 {
-	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+	closure_type(d, struct bcache_device, cl);
 
 	mutex_lock(&bch_register_lock);
 	bcache_device_unlink(d);
@@ -1668,9 +1670,9 @@ void bch_cache_set_release(struct kobject *kobj)
 	module_put(THIS_MODULE);
 }
 
-static void cache_set_free(struct closure *cl)
+static CLOSURE_CALLBACK(cache_set_free)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, cl);
+	closure_type(c, struct cache_set, cl);
 	struct cache *ca;
 
 	debugfs_remove(c->debug);
@@ -1709,9 +1711,9 @@ static void cache_set_free(struct closure *cl)
 	kobject_put(&c->kobj);
 }
 
-static void cache_set_flush(struct closure *cl)
+static CLOSURE_CALLBACK(cache_set_flush)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, caching);
+	closure_type(c, struct cache_set, caching);
 	struct cache *ca = c->cache;
 	struct btree *b;
 
@@ -1806,9 +1808,9 @@ static void conditional_stop_bcache_device(struct cache_set *c,
 	}
 }
 
-static void __cache_set_unregister(struct closure *cl)
+static CLOSURE_CALLBACK(__cache_set_unregister)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, caching);
+	closure_type(c, struct cache_set, caching);
 	struct cached_dev *dc;
 	struct bcache_device *d;
 	size_t i;
@@ -2016,7 +2018,7 @@ static int run_cache_set(struct cache_set *c)
 		c->root = bch_btree_node_get(c, NULL, k,
 					     j->btree_level,
 					     true, NULL);
-		if (IS_ERR_OR_NULL(c->root))
+		if (IS_ERR(c->root))
 			goto err;
 
 		list_del_init(&c->root->list);
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 45d8af755de6d1..a438efb660699b 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -1104,7 +1104,7 @@ SHOW(__bch_cache)
 			sum += INITIAL_PRIO - cached[i];
 
 		if (n)
-			do_div(sum, n);
+			sum = div64_u64(sum, n);
 
 		for (i = 0; i < ARRAY_SIZE(q); i++)
 			q[i] = INITIAL_PRIO - cached[n * (i + 1) /
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 24c049067f61ae..8827a6f130ad7f 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -341,16 +341,16 @@ static void dirty_init(struct keybuf_key *w)
 	bch_bio_map(bio, NULL);
 }
 
-static void dirty_io_destructor(struct closure *cl)
+static CLOSURE_CALLBACK(dirty_io_destructor)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 
 	kfree(io);
 }
 
-static void write_dirty_finish(struct closure *cl)
+static CLOSURE_CALLBACK(write_dirty_finish)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 	struct keybuf_key *w = io->bio.bi_private;
 	struct cached_dev *dc = io->dc;
 
@@ -400,9 +400,9 @@ static void dirty_endio(struct bio *bio)
 	closure_put(&io->cl);
 }
 
-static void write_dirty(struct closure *cl)
+static CLOSURE_CALLBACK(write_dirty)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 	struct keybuf_key *w = io->bio.bi_private;
 	struct cached_dev *dc = io->dc;
 
@@ -462,9 +462,9 @@ static void read_dirty_endio(struct bio *bio)
 	dirty_endio(bio);
 }
 
-static void read_dirty_submit(struct closure *cl)
+static CLOSURE_CALLBACK(read_dirty_submit)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 
 	closure_bio_submit(io->dc->disk.c, &io->bio, cl);
 
@@ -913,7 +913,7 @@ static int bch_dirty_init_thread(void *arg)
 	int cur_idx, prev_idx, skip_nr;
 
 	k = p = NULL;
-	cur_idx = prev_idx = 0;
+	prev_idx = 0;
 
 	bch_btree_iter_init(&c->root->keys, &iter, NULL);
 	k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
@@ -977,24 +977,35 @@ static int bch_btre_dirty_init_thread_nr(void)
 void bch_sectors_dirty_init(struct bcache_device *d)
 {
 	int i;
+	struct btree *b = NULL;
 	struct bkey *k = NULL;
 	struct btree_iter iter;
 	struct sectors_dirty_init op;
 	struct cache_set *c = d->c;
 	struct bch_dirty_init_state state;
 
+retry_lock:
+	b = c->root;
+	rw_lock(0, b, b->level);
+	if (b != c->root) {
+		rw_unlock(0, b);
+		goto retry_lock;
+	}
+
 	/* Just count root keys if no leaf node */
-	rw_lock(0, c->root, c->root->level);
 	if (c->root->level == 0) {
 		bch_btree_op_init(&op.op, -1);
 		op.inode = d->id;
 		op.count = 0;
 
 		for_each_key_filter(&c->root->keys,
-				    k, &iter, bch_ptr_invalid)
+				    k, &iter, bch_ptr_invalid) {
+			if (KEY_INODE(k) != op.inode)
+				continue;
 			sectors_dirty_init_fn(&op.op, c->root, k);
+		}
 
-		rw_unlock(0, c->root);
+		rw_unlock(0, b);
 		return;
 	}
 
@@ -1014,23 +1025,24 @@ void bch_sectors_dirty_init(struct bcache_device *d)
 		if (atomic_read(&state.enough))
 			break;
 
+		atomic_inc(&state.started);
 		state.infos[i].state = &state;
 		state.infos[i].thread =
 			kthread_run(bch_dirty_init_thread, &state.infos[i],
 				    "bch_dirtcnt[%d]", i);
 		if (IS_ERR(state.infos[i].thread)) {
 			pr_err("fails to run thread bch_dirty_init[%d]\n", i);
+			atomic_dec(&state.started);
 			for (--i; i >= 0; i--)
 				kthread_stop(state.infos[i].thread);
 			goto out;
 		}
-		atomic_inc(&state.started);
 	}
 
 out:
 	/* Must wait for all threads to stop. */
 	wait_event(state.wait, atomic_read(&state.started) == 0);
-	rw_unlock(0, c->root);
+	rw_unlock(0, b);
 }
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 62eb27639c9b85..f03d7dba270c52 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -254,7 +254,7 @@ enum evict_result {
 
 typedef enum evict_result (*le_predicate)(struct lru_entry *le, void *context);
 
-static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context)
+static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context, bool no_sleep)
 {
 	unsigned long tested = 0;
 	struct list_head *h = lru->cursor;
@@ -295,7 +295,8 @@ static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *con
 
 		h = h->next;
 
-		cond_resched();
+		if (!no_sleep)
+			cond_resched();
 	}
 
 	return NULL;
@@ -382,7 +383,10 @@ struct dm_buffer {
  */
 
 struct buffer_tree {
-	struct rw_semaphore lock;
+	union {
+		struct rw_semaphore lock;
+		rwlock_t spinlock;
+	} u;
 	struct rb_root root;
 } ____cacheline_aligned_in_smp;
 
@@ -393,9 +397,12 @@ struct dm_buffer_cache {
 	 * on the locks.
 	 */
 	unsigned int num_locks;
+	bool no_sleep;
 	struct buffer_tree trees[];
 };
 
+static DEFINE_STATIC_KEY_FALSE(no_sleep_enabled);
+
 static inline unsigned int cache_index(sector_t block, unsigned int num_locks)
 {
 	return dm_hash_locks_index(block, num_locks);
@@ -403,22 +410,34 @@ static inline unsigned int cache_index(sector_t block, unsigned int num_locks)
 
 static inline void cache_read_lock(struct dm_buffer_cache *bc, sector_t block)
 {
-	down_read(&bc->trees[cache_index(block, bc->num_locks)].lock);
+	if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep)
+		read_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock);
+	else
+		down_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock);
 }
 
 static inline void cache_read_unlock(struct dm_buffer_cache *bc, sector_t block)
 {
-	up_read(&bc->trees[cache_index(block, bc->num_locks)].lock);
+	if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep)
+		read_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock);
+	else
+		up_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock);
 }
 
 static inline void cache_write_lock(struct dm_buffer_cache *bc, sector_t block)
 {
-	down_write(&bc->trees[cache_index(block, bc->num_locks)].lock);
+	if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep)
+		write_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock);
+	else
+		down_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock);
 }
 
 static inline void cache_write_unlock(struct dm_buffer_cache *bc, sector_t block)
 {
-	up_write(&bc->trees[cache_index(block, bc->num_locks)].lock);
+	if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep)
+		write_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock);
+	else
+		up_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock);
 }
 
 /*
@@ -442,18 +461,32 @@ static void lh_init(struct lock_history *lh, struct dm_buffer_cache *cache, bool
 
 static void __lh_lock(struct lock_history *lh, unsigned int index)
 {
-	if (lh->write)
-		down_write(&lh->cache->trees[index].lock);
-	else
-		down_read(&lh->cache->trees[index].lock);
+	if (lh->write) {
+		if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep)
+			write_lock_bh(&lh->cache->trees[index].u.spinlock);
+		else
+			down_write(&lh->cache->trees[index].u.lock);
+	} else {
+		if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep)
+			read_lock_bh(&lh->cache->trees[index].u.spinlock);
+		else
+			down_read(&lh->cache->trees[index].u.lock);
+	}
 }
 
 static void __lh_unlock(struct lock_history *lh, unsigned int index)
 {
-	if (lh->write)
-		up_write(&lh->cache->trees[index].lock);
-	else
-		up_read(&lh->cache->trees[index].lock);
+	if (lh->write) {
+		if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep)
+			write_unlock_bh(&lh->cache->trees[index].u.spinlock);
+		else
+			up_write(&lh->cache->trees[index].u.lock);
+	} else {
+		if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep)
+			read_unlock_bh(&lh->cache->trees[index].u.spinlock);
+		else
+			up_read(&lh->cache->trees[index].u.lock);
+	}
 }
 
 /*
@@ -502,14 +535,18 @@ static struct dm_buffer *list_to_buffer(struct list_head *l)
 	return le_to_buffer(le);
 }
 
-static void cache_init(struct dm_buffer_cache *bc, unsigned int num_locks)
+static void cache_init(struct dm_buffer_cache *bc, unsigned int num_locks, bool no_sleep)
 {
 	unsigned int i;
 
 	bc->num_locks = num_locks;
+	bc->no_sleep = no_sleep;
 
 	for (i = 0; i < bc->num_locks; i++) {
-		init_rwsem(&bc->trees[i].lock);
+		if (no_sleep)
+			rwlock_init(&bc->trees[i].u.spinlock);
+		else
+			init_rwsem(&bc->trees[i].u.lock);
 		bc->trees[i].root = RB_ROOT;
 	}
 
@@ -648,7 +685,7 @@ static struct dm_buffer *__cache_evict(struct dm_buffer_cache *bc, int list_mode
 	struct lru_entry *le;
 	struct dm_buffer *b;
 
-	le = lru_evict(&bc->lru[list_mode], __evict_pred, &w);
+	le = lru_evict(&bc->lru[list_mode], __evict_pred, &w, bc->no_sleep);
 	if (!le)
 		return NULL;
 
@@ -702,7 +739,7 @@ static void __cache_mark_many(struct dm_buffer_cache *bc, int old_mode, int new_
 	struct evict_wrapper w = {.lh = lh, .pred = pred, .context = context};
 
 	while (true) {
-		le = lru_evict(&bc->lru[old_mode], __evict_pred, &w);
+		le = lru_evict(&bc->lru[old_mode], __evict_pred, &w, bc->no_sleep);
 		if (!le)
 			break;
 
@@ -915,10 +952,11 @@ static void cache_remove_range(struct dm_buffer_cache *bc,
 {
 	unsigned int i;
 
+	BUG_ON(bc->no_sleep);
 	for (i = 0; i < bc->num_locks; i++) {
-		down_write(&bc->trees[i].lock);
+		down_write(&bc->trees[i].u.lock);
 		__remove_range(bc, &bc->trees[i].root, begin, end, pred, release);
-		up_write(&bc->trees[i].lock);
+		up_write(&bc->trees[i].u.lock);
 	}
 }
 
@@ -979,8 +1017,6 @@ struct dm_bufio_client {
 	struct dm_buffer_cache cache; /* must be last member */
 };
 
-static DEFINE_STATIC_KEY_FALSE(no_sleep_enabled);
-
 /*----------------------------------------------------------------*/
 
 #define dm_bufio_in_request()	(!!current->bio_list)
@@ -1871,7 +1907,8 @@ static void *new_read(struct dm_bufio_client *c, sector_t block,
 	if (need_submit)
 		submit_io(b, REQ_OP_READ, read_endio);
 
-	wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE);
+	if (nf != NF_GET)	/* we already tested this condition above */
+		wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE);
 
 	if (b->read_error) {
 		int error = blk_status_to_errno(b->read_error);
@@ -2421,7 +2458,7 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
 		r = -ENOMEM;
 		goto bad_client;
 	}
-	cache_init(&c->cache, num_locks);
+	cache_init(&c->cache, num_locks, (flags & DM_BUFIO_CLIENT_NO_SLEEP) != 0);
 
 	c->bdev = bdev;
 	c->block_size = block_size;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 6de107aff33194..2ae8560b6a14ad 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1673,7 +1673,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int size)
 	unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM;
 	unsigned int remaining_size;
-	unsigned int order = MAX_ORDER - 1;
+	unsigned int order = MAX_ORDER;
 
 retry:
 	if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index efd510984e2593..5eabdb06c6498b 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -33,7 +33,7 @@ struct delay_c {
 	struct work_struct flush_expired_bios;
 	struct list_head delayed_bios;
 	struct task_struct *worker;
-	atomic_t may_delay;
+	bool may_delay;
 
 	struct delay_class read;
 	struct delay_class write;
@@ -73,39 +73,6 @@ static inline bool delay_is_fast(struct delay_c *dc)
 	return !!dc->worker;
 }
 
-static void flush_delayed_bios_fast(struct delay_c *dc, bool flush_all)
-{
-	struct dm_delay_info *delayed, *next;
-
-	mutex_lock(&delayed_bios_lock);
-	list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) {
-		if (flush_all || time_after_eq(jiffies, delayed->expires)) {
-			struct bio *bio = dm_bio_from_per_bio_data(delayed,
-						sizeof(struct dm_delay_info));
-			list_del(&delayed->list);
-			dm_submit_bio_remap(bio, NULL);
-			delayed->class->ops--;
-		}
-	}
-	mutex_unlock(&delayed_bios_lock);
-}
-
-static int flush_worker_fn(void *data)
-{
-	struct delay_c *dc = data;
-
-	while (1) {
-		flush_delayed_bios_fast(dc, false);
-		if (unlikely(list_empty(&dc->delayed_bios))) {
-			set_current_state(TASK_INTERRUPTIBLE);
-			schedule();
-		} else
-			cond_resched();
-	}
-
-	return 0;
-}
-
 static void flush_bios(struct bio *bio)
 {
 	struct bio *n;
@@ -118,36 +85,61 @@ static void flush_bios(struct bio *bio)
 	}
 }
 
-static struct bio *flush_delayed_bios(struct delay_c *dc, bool flush_all)
+static void flush_delayed_bios(struct delay_c *dc, bool flush_all)
 {
 	struct dm_delay_info *delayed, *next;
+	struct bio_list flush_bio_list;
 	unsigned long next_expires = 0;
-	unsigned long start_timer = 0;
-	struct bio_list flush_bios = { };
+	bool start_timer = false;
+	bio_list_init(&flush_bio_list);
 
 	mutex_lock(&delayed_bios_lock);
 	list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) {
+		cond_resched();
 		if (flush_all || time_after_eq(jiffies, delayed->expires)) {
 			struct bio *bio = dm_bio_from_per_bio_data(delayed,
 						sizeof(struct dm_delay_info));
 			list_del(&delayed->list);
-			bio_list_add(&flush_bios, bio);
+			bio_list_add(&flush_bio_list, bio);
 			delayed->class->ops--;
 			continue;
 		}
 
-		if (!start_timer) {
-			start_timer = 1;
-			next_expires = delayed->expires;
-		} else
-			next_expires = min(next_expires, delayed->expires);
+		if (!delay_is_fast(dc)) {
+			if (!start_timer) {
+				start_timer = true;
+				next_expires = delayed->expires;
+			} else {
+				next_expires = min(next_expires, delayed->expires);
+			}
+		}
 	}
 	mutex_unlock(&delayed_bios_lock);
 
 	if (start_timer)
 		queue_timeout(dc, next_expires);
 
-	return bio_list_get(&flush_bios);
+	flush_bios(bio_list_get(&flush_bio_list));
+}
+
+static int flush_worker_fn(void *data)
+{
+	struct delay_c *dc = data;
+
+	while (!kthread_should_stop()) {
+		flush_delayed_bios(dc, false);
+		mutex_lock(&delayed_bios_lock);
+		if (unlikely(list_empty(&dc->delayed_bios))) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			mutex_unlock(&delayed_bios_lock);
+			schedule();
+		} else {
+			mutex_unlock(&delayed_bios_lock);
+			cond_resched();
+		}
+	}
+
+	return 0;
 }
 
 static void flush_expired_bios(struct work_struct *work)
@@ -155,10 +147,7 @@ static void flush_expired_bios(struct work_struct *work)
 	struct delay_c *dc;
 
 	dc = container_of(work, struct delay_c, flush_expired_bios);
-	if (delay_is_fast(dc))
-		flush_delayed_bios_fast(dc, false);
-	else
-		flush_bios(flush_delayed_bios(dc, false));
+	flush_delayed_bios(dc, false);
 }
 
 static void delay_dtr(struct dm_target *ti)
@@ -177,8 +166,7 @@ static void delay_dtr(struct dm_target *ti)
 	if (dc->worker)
 		kthread_stop(dc->worker);
 
-	if (!delay_is_fast(dc))
-		mutex_destroy(&dc->timer_lock);
+	mutex_destroy(&dc->timer_lock);
 
 	kfree(dc);
 }
@@ -236,7 +224,8 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	ti->private = dc;
 	INIT_LIST_HEAD(&dc->delayed_bios);
-	atomic_set(&dc->may_delay, 1);
+	mutex_init(&dc->timer_lock);
+	dc->may_delay = true;
 	dc->argc = argc;
 
 	ret = delay_class_ctr(ti, &dc->read, argv);
@@ -282,12 +271,12 @@ out:
 					    "dm-delay-flush-worker");
 		if (IS_ERR(dc->worker)) {
 			ret = PTR_ERR(dc->worker);
+			dc->worker = NULL;
 			goto bad;
 		}
 	} else {
 		timer_setup(&dc->delay_timer, handle_delayed_timer, 0);
 		INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
-		mutex_init(&dc->timer_lock);
 		dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
 		if (!dc->kdelayd_wq) {
 			ret = -EINVAL;
@@ -312,7 +301,7 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio)
 	struct dm_delay_info *delayed;
 	unsigned long expires = 0;
 
-	if (!c->delay || !atomic_read(&dc->may_delay))
+	if (!c->delay)
 		return DM_MAPIO_REMAPPED;
 
 	delayed = dm_per_bio_data(bio, sizeof(struct dm_delay_info));
@@ -321,6 +310,10 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio)
 	delayed->expires = expires = jiffies + msecs_to_jiffies(c->delay);
 
 	mutex_lock(&delayed_bios_lock);
+	if (unlikely(!dc->may_delay)) {
+		mutex_unlock(&delayed_bios_lock);
+		return DM_MAPIO_REMAPPED;
+	}
 	c->ops++;
 	list_add_tail(&delayed->list, &dc->delayed_bios);
 	mutex_unlock(&delayed_bios_lock);
@@ -337,21 +330,20 @@ static void delay_presuspend(struct dm_target *ti)
 {
 	struct delay_c *dc = ti->private;
 
-	atomic_set(&dc->may_delay, 0);
+	mutex_lock(&delayed_bios_lock);
+	dc->may_delay = false;
+	mutex_unlock(&delayed_bios_lock);
 
-	if (delay_is_fast(dc))
-		flush_delayed_bios_fast(dc, true);
-	else {
+	if (!delay_is_fast(dc))
 		del_timer_sync(&dc->delay_timer);
-		flush_bios(flush_delayed_bios(dc, true));
-	}
+	flush_delayed_bios(dc, true);
 }
 
 static void delay_resume(struct dm_target *ti)
 {
 	struct delay_c *dc = ti->private;
 
-	atomic_set(&dc->may_delay, 1);
+	dc->may_delay = true;
 }
 
 static int delay_map(struct dm_target *ti, struct bio *bio)
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 120153e44ae0d3..f57fb821528d7e 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -434,7 +434,7 @@ static struct bio *clone_bio(struct dm_target *ti, struct flakey_c *fc, struct b
 
 	remaining_size = size;
 
-	order = MAX_ORDER - 1;
+	order = MAX_ORDER;
 	while (remaining_size) {
 		struct page *pages;
 		unsigned size_to_add, to_copy;
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index e85c688fd91e90..c5f03aab455256 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -1755,11 +1755,12 @@ static void integrity_metadata(struct work_struct *w)
 		sectors_to_process = dio->range.n_sectors;
 
 		__bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) {
+			struct bio_vec bv_copy = bv;
 			unsigned int pos;
 			char *mem, *checksums_ptr;
 
 again:
-			mem = bvec_kmap_local(&bv);
+			mem = bvec_kmap_local(&bv_copy);
 			pos = 0;
 			checksums_ptr = checksums;
 			do {
@@ -1768,7 +1769,7 @@ again:
 				sectors_to_process -= ic->sectors_per_block;
 				pos += ic->sectors_per_block << SECTOR_SHIFT;
 				sector += ic->sectors_per_block;
-			} while (pos < bv.bv_len && sectors_to_process && checksums != checksums_onstack);
+			} while (pos < bv_copy.bv_len && sectors_to_process && checksums != checksums_onstack);
 			kunmap_local(mem);
 
 			r = dm_integrity_rw_tag(ic, checksums, &dio->metadata_block, &dio->metadata_offset,
@@ -1793,9 +1794,9 @@ again:
 			if (!sectors_to_process)
 				break;
 
-			if (unlikely(pos < bv.bv_len)) {
-				bv.bv_offset += pos;
-				bv.bv_len -= pos;
+			if (unlikely(pos < bv_copy.bv_len)) {
+				bv_copy.bv_offset += pos;
+				bv_copy.bv_len -= pos;
 				goto again;
 			}
 		}
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 91ebdcc6e9a8c5..eb009d6bb03a17 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3317,6 +3317,9 @@ static void raid_dtr(struct dm_target *ti)
 	mddev_lock_nointr(&rs->md);
 	md_stop(&rs->md);
 	mddev_unlock(&rs->md);
+
+	if (work_pending(&rs->md.event_work))
+		flush_work(&rs->md.event_work);
 	raid_set_free(rs);
 }
 
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 3ef9f018da60ce..b475200d8586a6 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -24,7 +24,8 @@ bool verity_fec_is_enabled(struct dm_verity *v)
  */
 static inline struct dm_verity_fec_io *fec_io(struct dm_verity_io *io)
 {
-	return (struct dm_verity_fec_io *) verity_io_digest_end(io->v, io);
+	return (struct dm_verity_fec_io *)
+		((char *)io + io->v->ti->per_io_data_size - sizeof(struct dm_verity_fec_io));
 }
 
 /*
@@ -185,7 +186,7 @@ static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io,
 {
 	if (unlikely(verity_hash(v, verity_io_hash_req(v, io),
 				 data, 1 << v->data_dev_block_bits,
-				 verity_io_real_digest(v, io))))
+				 verity_io_real_digest(v, io), true)))
 		return 0;
 
 	return memcmp(verity_io_real_digest(v, io), want_digest,
@@ -386,7 +387,7 @@ static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io,
 	/* Always re-validate the corrected block against the expected hash */
 	r = verity_hash(v, verity_io_hash_req(v, io), fio->output,
 			1 << v->data_dev_block_bits,
-			verity_io_real_digest(v, io));
+			verity_io_real_digest(v, io), true);
 	if (unlikely(r < 0))
 		return r;
 
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 26adcfea030229..14e58ae705218f 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -135,20 +135,21 @@ static int verity_hash_update(struct dm_verity *v, struct ahash_request *req,
  * Wrapper for crypto_ahash_init, which handles verity salting.
  */
 static int verity_hash_init(struct dm_verity *v, struct ahash_request *req,
-				struct crypto_wait *wait)
+				struct crypto_wait *wait, bool may_sleep)
 {
 	int r;
 
 	ahash_request_set_tfm(req, v->tfm);
-	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP |
-					CRYPTO_TFM_REQ_MAY_BACKLOG,
-					crypto_req_done, (void *)wait);
+	ahash_request_set_callback(req,
+		may_sleep ? CRYPTO_TFM_REQ_MAY_SLEEP | CRYPTO_TFM_REQ_MAY_BACKLOG : 0,
+		crypto_req_done, (void *)wait);
 	crypto_init_wait(wait);
 
 	r = crypto_wait_req(crypto_ahash_init(req), wait);
 
 	if (unlikely(r < 0)) {
-		DMERR("crypto_ahash_init failed: %d", r);
+		if (r != -ENOMEM)
+			DMERR("crypto_ahash_init failed: %d", r);
 		return r;
 	}
 
@@ -179,12 +180,12 @@ out:
 }
 
 int verity_hash(struct dm_verity *v, struct ahash_request *req,
-		const u8 *data, size_t len, u8 *digest)
+		const u8 *data, size_t len, u8 *digest, bool may_sleep)
 {
 	int r;
 	struct crypto_wait wait;
 
-	r = verity_hash_init(v, req, &wait);
+	r = verity_hash_init(v, req, &wait, may_sleep);
 	if (unlikely(r < 0))
 		goto out;
 
@@ -322,7 +323,7 @@ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io,
 
 		r = verity_hash(v, verity_io_hash_req(v, io),
 				data, 1 << v->hash_dev_block_bits,
-				verity_io_real_digest(v, io));
+				verity_io_real_digest(v, io), !io->in_tasklet);
 		if (unlikely(r < 0))
 			goto release_ret_r;
 
@@ -556,7 +557,7 @@ static int verity_verify_io(struct dm_verity_io *io)
 			continue;
 		}
 
-		r = verity_hash_init(v, req, &wait);
+		r = verity_hash_init(v, req, &wait, !io->in_tasklet);
 		if (unlikely(r < 0))
 			return r;
 
@@ -641,7 +642,6 @@ static void verity_work(struct work_struct *w)
 
 	io->in_tasklet = false;
 
-	verity_fec_init_io(io);
 	verity_finish_io(io, errno_to_blk_status(verity_verify_io(io)));
 }
 
@@ -652,7 +652,7 @@ static void verity_tasklet(unsigned long data)
 
 	io->in_tasklet = true;
 	err = verity_verify_io(io);
-	if (err == -EAGAIN) {
+	if (err == -EAGAIN || err == -ENOMEM) {
 		/* fallback to retrying with work-queue */
 		INIT_WORK(&io->work, verity_work);
 		queue_work(io->v->verify_wq, &io->work);
@@ -667,7 +667,9 @@ static void verity_end_io(struct bio *bio)
 	struct dm_verity_io *io = bio->bi_private;
 
 	if (bio->bi_status &&
-	    (!verity_fec_is_enabled(io->v) || verity_is_system_shutting_down())) {
+	    (!verity_fec_is_enabled(io->v) ||
+	     verity_is_system_shutting_down() ||
+	     (bio->bi_opf & REQ_RAHEAD))) {
 		verity_finish_io(io, bio->bi_status);
 		return;
 	}
@@ -791,6 +793,8 @@ static int verity_map(struct dm_target *ti, struct bio *bio)
 	bio->bi_private = io;
 	io->iter = bio->bi_iter;
 
+	verity_fec_init_io(io);
+
 	verity_submit_prefetch(v, io);
 
 	submit_bio_noacct(bio);
@@ -1033,7 +1037,7 @@ static int verity_alloc_zero_digest(struct dm_verity *v)
 		goto out;
 
 	r = verity_hash(v, req, zero_data, 1 << v->data_dev_block_bits,
-			v->zero_digest);
+			v->zero_digest, true);
 
 out:
 	kfree(req);
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index 2f555b4203679a..f9d522c870e616 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -115,12 +115,6 @@ static inline u8 *verity_io_want_digest(struct dm_verity *v,
 	return (u8 *)(io + 1) + v->ahash_reqsize + v->digest_size;
 }
 
-static inline u8 *verity_io_digest_end(struct dm_verity *v,
-				       struct dm_verity_io *io)
-{
-	return verity_io_want_digest(v, io) + v->digest_size;
-}
-
 extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
 			       struct bvec_iter *iter,
 			       int (*process)(struct dm_verity *v,
@@ -128,7 +122,7 @@ extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
 					      u8 *data, size_t len));
 
 extern int verity_hash(struct dm_verity *v, struct ahash_request *req,
-		       const u8 *data, size_t len, u8 *digest);
+		       const u8 *data, size_t len, u8 *digest, bool may_sleep);
 
 extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
 				 sector_t block, u8 *digest, bool *is_zero);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4ee4593c874a76..9bdd57324c3760 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -82,6 +82,14 @@ static struct module *md_cluster_mod;
 
 static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
 static struct workqueue_struct *md_wq;
+
+/*
+ * This workqueue is used for sync_work to register new sync_thread, and for
+ * del_work to remove rdev, and for event_work that is only set by dm-raid.
+ *
+ * Noted that sync_work will grab reconfig_mutex, hence never flush this
+ * workqueue whith reconfig_mutex grabbed.
+ */
 static struct workqueue_struct *md_misc_wq;
 struct workqueue_struct *md_bitmap_wq;
 
@@ -490,7 +498,7 @@ int mddev_suspend(struct mddev *mddev, bool interruptible)
 }
 EXPORT_SYMBOL_GPL(mddev_suspend);
 
-void mddev_resume(struct mddev *mddev)
+static void __mddev_resume(struct mddev *mddev, bool recovery_needed)
 {
 	lockdep_assert_not_held(&mddev->reconfig_mutex);
 
@@ -507,12 +515,18 @@ void mddev_resume(struct mddev *mddev)
 	percpu_ref_resurrect(&mddev->active_io);
 	wake_up(&mddev->sb_wait);
 
-	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	if (recovery_needed)
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
 	mutex_unlock(&mddev->suspend_mutex);
 }
+
+void mddev_resume(struct mddev *mddev)
+{
+	return __mddev_resume(mddev, true);
+}
 EXPORT_SYMBOL_GPL(mddev_resume);
 
 /*
@@ -4840,25 +4854,29 @@ action_show(struct mddev *mddev, char *page)
 	return sprintf(page, "%s\n", type);
 }
 
-static void stop_sync_thread(struct mddev *mddev)
+/**
+ * stop_sync_thread() - wait for sync_thread to stop if it's running.
+ * @mddev:	the array.
+ * @locked:	if set, reconfig_mutex will still be held after this function
+ *		return; if not set, reconfig_mutex will be released after this
+ *		function return.
+ * @check_seq:	if set, only wait for curent running sync_thread to stop, noted
+ *		that new sync_thread can still start.
+ */
+static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq)
 {
-	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		return;
+	int sync_seq;
 
-	if (mddev_lock(mddev))
-		return;
+	if (check_seq)
+		sync_seq = atomic_read(&mddev->sync_seq);
 
-	/*
-	 * Check again in case MD_RECOVERY_RUNNING is cleared before lock is
-	 * held.
-	 */
 	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
-		mddev_unlock(mddev);
+		if (!locked)
+			mddev_unlock(mddev);
 		return;
 	}
 
-	if (work_pending(&mddev->del_work))
-		flush_workqueue(md_misc_wq);
+	mddev_unlock(mddev);
 
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	/*
@@ -4866,21 +4884,28 @@ static void stop_sync_thread(struct mddev *mddev)
 	 * never happen
 	 */
 	md_wakeup_thread_directly(mddev->sync_thread);
+	if (work_pending(&mddev->sync_work))
+		flush_work(&mddev->sync_work);
 
-	mddev_unlock(mddev);
+	wait_event(resync_wait,
+		   !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+		   (check_seq && sync_seq != atomic_read(&mddev->sync_seq)));
+
+	if (locked)
+		mddev_lock_nointr(mddev);
 }
 
 static void idle_sync_thread(struct mddev *mddev)
 {
-	int sync_seq = atomic_read(&mddev->sync_seq);
-
 	mutex_lock(&mddev->sync_mutex);
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	stop_sync_thread(mddev);
 
-	wait_event(resync_wait, sync_seq != atomic_read(&mddev->sync_seq) ||
-			!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+	if (mddev_lock(mddev)) {
+		mutex_unlock(&mddev->sync_mutex);
+		return;
+	}
 
+	stop_sync_thread(mddev, false, true);
 	mutex_unlock(&mddev->sync_mutex);
 }
 
@@ -4888,11 +4913,13 @@ static void frozen_sync_thread(struct mddev *mddev)
 {
 	mutex_lock(&mddev->sync_mutex);
 	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	stop_sync_thread(mddev);
 
-	wait_event(resync_wait, mddev->sync_thread == NULL &&
-			!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+	if (mddev_lock(mddev)) {
+		mutex_unlock(&mddev->sync_mutex);
+		return;
+	}
 
+	stop_sync_thread(mddev, false, false);
 	mutex_unlock(&mddev->sync_mutex);
 }
 
@@ -6264,14 +6291,7 @@ static void md_clean(struct mddev *mddev)
 
 static void __md_stop_writes(struct mddev *mddev)
 {
-	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	if (work_pending(&mddev->del_work))
-		flush_workqueue(md_misc_wq);
-	if (mddev->sync_thread) {
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-		md_reap_sync_thread(mddev);
-	}
-
+	stop_sync_thread(mddev, true, false);
 	del_timer_sync(&mddev->safemode_timer);
 
 	if (mddev->pers && mddev->pers->quiesce) {
@@ -6318,9 +6338,6 @@ static void __md_stop(struct mddev *mddev)
 	struct md_personality *pers = mddev->pers;
 	md_bitmap_destroy(mddev);
 	mddev_detach(mddev);
-	/* Ensure ->event_work is done */
-	if (mddev->event_work.func)
-		flush_workqueue(md_misc_wq);
 	spin_lock(&mddev->lock);
 	mddev->pers = NULL;
 	spin_unlock(&mddev->lock);
@@ -6355,25 +6372,16 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 	int err = 0;
 	int did_freeze = 0;
 
+	if (mddev->external && test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
+		return -EBUSY;
+
 	if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
 		did_freeze = 1;
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
 	}
-	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 
-	/*
-	 * Thread might be blocked waiting for metadata update which will now
-	 * never happen
-	 */
-	md_wakeup_thread_directly(mddev->sync_thread);
-
-	if (mddev->external && test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
-		return -EBUSY;
-	mddev_unlock(mddev);
-	wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING,
-					  &mddev->recovery));
+	stop_sync_thread(mddev, false, false);
 	wait_event(mddev->sb_wait,
 		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 	mddev_lock_nointr(mddev);
@@ -6383,29 +6391,30 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 	    mddev->sync_thread ||
 	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		pr_warn("md: %s still in use.\n",mdname(mddev));
-		if (did_freeze) {
-			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-			md_wakeup_thread(mddev->thread);
-		}
 		err = -EBUSY;
 		goto out;
 	}
+
 	if (mddev->pers) {
 		__md_stop_writes(mddev);
 
-		err  = -ENXIO;
-		if (mddev->ro == MD_RDONLY)
+		if (mddev->ro == MD_RDONLY) {
+			err  = -ENXIO;
 			goto out;
+		}
+
 		mddev->ro = MD_RDONLY;
 		set_disk_ro(mddev->gendisk, 1);
+	}
+
+out:
+	if ((mddev->pers && !err) || did_freeze) {
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
-		err = 0;
 	}
-out:
+
 	mutex_unlock(&mddev->open_mutex);
 	return err;
 }
@@ -6426,20 +6435,8 @@ static int do_md_stop(struct mddev *mddev, int mode,
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
 	}
-	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 
-	/*
-	 * Thread might be blocked waiting for metadata update which will now
-	 * never happen
-	 */
-	md_wakeup_thread_directly(mddev->sync_thread);
-
-	mddev_unlock(mddev);
-	wait_event(resync_wait, (mddev->sync_thread == NULL &&
-				 !test_bit(MD_RECOVERY_RUNNING,
-					   &mddev->recovery)));
-	mddev_lock_nointr(mddev);
+	stop_sync_thread(mddev, true, false);
 
 	mutex_lock(&mddev->open_mutex);
 	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
@@ -8666,7 +8663,8 @@ static void md_end_clone_io(struct bio *bio)
 	struct bio *orig_bio = md_io_clone->orig_bio;
 	struct mddev *mddev = md_io_clone->mddev;
 
-	orig_bio->bi_status = bio->bi_status;
+	if (bio->bi_status && !orig_bio->bi_status)
+		orig_bio->bi_status = bio->bi_status;
 
 	if (md_io_clone->start_time)
 		bio_end_io_acct(orig_bio, md_io_clone->start_time);
@@ -9402,7 +9400,15 @@ static void md_start_sync(struct work_struct *ws)
 		goto not_running;
 	}
 
-	suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
+	mddev_unlock(mddev);
+	/*
+	 * md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should
+	 * not set it again. Otherwise, we may cause issue like this one:
+	 *     https://bugzilla.kernel.org/show_bug.cgi?id=218200
+	 * Therefore, use __mddev_resume(mddev, false).
+	 */
+	if (suspend)
+		__mddev_resume(mddev, false);
 	md_wakeup_thread(mddev->sync_thread);
 	sysfs_notify_dirent_safe(mddev->sysfs_action);
 	md_new_event();
@@ -9414,7 +9420,15 @@ not_running:
 	clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 	clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-	suspend ? mddev_unlock_and_resume(mddev) : mddev_unlock(mddev);
+	mddev_unlock(mddev);
+	/*
+	 * md_start_sync was triggered by MD_RECOVERY_NEEDED, so we should
+	 * not set it again. Otherwise, we may cause issue like this one:
+	 *     https://bugzilla.kernel.org/show_bug.cgi?id=218200
+	 * Therefore, use __mddev_resume(mddev, false).
+	 */
+	if (suspend)
+		__mddev_resume(mddev, false);
 
 	wake_up(&resync_wait);
 	if (test_and_clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery) &&
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index dc031d42f53bc6..26e1e8a5e94191 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5892,11 +5892,11 @@ static bool stripe_ahead_of_reshape(struct mddev *mddev, struct r5conf *conf,
 	int dd_idx;
 
 	for (dd_idx = 0; dd_idx < sh->disks; dd_idx++) {
-		if (dd_idx == sh->pd_idx)
+		if (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx)
 			continue;
 
 		min_sector = min(min_sector, sh->dev[dd_idx].sector);
-		max_sector = min(max_sector, sh->dev[dd_idx].sector);
+		max_sector = max(max_sector, sh->dev[dd_idx].sector);
 	}
 
 	spin_lock_irq(&conf->device_lock);
diff --git a/drivers/media/pci/mgb4/Kconfig b/drivers/media/pci/mgb4/Kconfig
index 13fad15a434c42..f2a05a1c8ffab4 100644
--- a/drivers/media/pci/mgb4/Kconfig
+++ b/drivers/media/pci/mgb4/Kconfig
@@ -2,6 +2,7 @@
 config VIDEO_MGB4
 	tristate "Digiteq Automotive MGB4 support"
 	depends on VIDEO_DEV && PCI && I2C && DMADEVICES && SPI && MTD && IIO
+	depends on COMMON_CLK
 	select VIDEOBUF2_DMA_SG
 	select IIO_BUFFER
 	select IIO_TRIGGERED_BUFFER
diff --git a/drivers/media/pci/mgb4/mgb4_core.c b/drivers/media/pci/mgb4/mgb4_core.c
index 3efb33fbf40ccb..5bfb8a06202e99 100644
--- a/drivers/media/pci/mgb4/mgb4_core.c
+++ b/drivers/media/pci/mgb4/mgb4_core.c
@@ -42,6 +42,10 @@
 
 #define MGB4_USER_IRQS 16
 
+#define DIGITEQ_VID 0x1ed8
+#define T100_DID    0x0101
+#define T200_DID    0x0201
+
 ATTRIBUTE_GROUPS(mgb4_pci);
 
 static int flashid;
@@ -151,7 +155,7 @@ static struct spi_master *get_spi_adap(struct platform_device *pdev)
 	return dev ? container_of(dev, struct spi_master, dev) : NULL;
 }
 
-static int init_spi(struct mgb4_dev *mgbdev)
+static int init_spi(struct mgb4_dev *mgbdev, u32 devid)
 {
 	struct resource spi_resources[] = {
 		{
@@ -213,8 +217,13 @@ static int init_spi(struct mgb4_dev *mgbdev)
 	snprintf(mgbdev->fw_part_name, sizeof(mgbdev->fw_part_name),
 		 "mgb4-fw.%d", flashid);
 	mgbdev->partitions[0].name = mgbdev->fw_part_name;
-	mgbdev->partitions[0].size = 0x400000;
-	mgbdev->partitions[0].offset = 0x400000;
+	if (devid == T200_DID) {
+		mgbdev->partitions[0].size = 0x950000;
+		mgbdev->partitions[0].offset = 0x1000000;
+	} else {
+		mgbdev->partitions[0].size = 0x400000;
+		mgbdev->partitions[0].offset = 0x400000;
+	}
 	mgbdev->partitions[0].mask_flags = 0;
 
 	snprintf(mgbdev->data_part_name, sizeof(mgbdev->data_part_name),
@@ -551,7 +560,7 @@ static int mgb4_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_video_regs;
 
 	/* SPI FLASH */
-	rv = init_spi(mgbdev);
+	rv = init_spi(mgbdev, id->device);
 	if (rv < 0)
 		goto err_cmt_regs;
 
@@ -666,7 +675,8 @@ static void mgb4_remove(struct pci_dev *pdev)
 }
 
 static const struct pci_device_id mgb4_pci_ids[] = {
-	{ PCI_DEVICE(0x1ed8, 0x0101), },
+	{ PCI_DEVICE(DIGITEQ_VID, T100_DID), },
+	{ PCI_DEVICE(DIGITEQ_VID, T200_DID), },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, mgb4_pci_ids);
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_pipe.c b/drivers/media/platform/renesas/vsp1/vsp1_pipe.c
index f8093ba9539e93..68d05243c3ee55 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_pipe.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_pipe.c
@@ -373,7 +373,7 @@ int vsp1_pipeline_stop(struct vsp1_pipeline *pipe)
 			   (7 << VI6_DPR_SMPPT_TGW_SHIFT) |
 			   (VI6_DPR_NODE_UNUSED << VI6_DPR_SMPPT_PT_SHIFT));
 
-	v4l2_subdev_call(&pipe->output->entity.subdev, video, s_stream, 0);
+	vsp1_wpf_stop(pipe->output);
 
 	return ret;
 }
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_rpf.c b/drivers/media/platform/renesas/vsp1/vsp1_rpf.c
index 3b17f5fa4067fb..ea12c3f12c92a3 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_rpf.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_rpf.c
@@ -44,14 +44,6 @@ static inline void vsp1_rpf_write(struct vsp1_rwpf *rpf,
 }
 
 /* -----------------------------------------------------------------------------
- * V4L2 Subdevice Operations
- */
-
-static const struct v4l2_subdev_ops rpf_ops = {
-	.pad    = &vsp1_rwpf_pad_ops,
-};
-
-/* -----------------------------------------------------------------------------
  * VSP1 Entity Operations
  */
 
@@ -411,7 +403,7 @@ struct vsp1_rwpf *vsp1_rpf_create(struct vsp1_device *vsp1, unsigned int index)
 	rpf->entity.index = index;
 
 	sprintf(name, "rpf.%u", index);
-	ret = vsp1_entity_init(vsp1, &rpf->entity, name, 2, &rpf_ops,
+	ret = vsp1_entity_init(vsp1, &rpf->entity, name, 2, &vsp1_rwpf_subdev_ops,
 			       MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER);
 	if (ret < 0)
 		return ERR_PTR(ret);
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_rwpf.c b/drivers/media/platform/renesas/vsp1/vsp1_rwpf.c
index 22a82d218152fd..e0f87c8103ca56 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_rwpf.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_rwpf.c
@@ -24,7 +24,7 @@ struct v4l2_rect *vsp1_rwpf_get_crop(struct vsp1_rwpf *rwpf,
 }
 
 /* -----------------------------------------------------------------------------
- * V4L2 Subdevice Pad Operations
+ * V4L2 Subdevice Operations
  */
 
 static int vsp1_rwpf_enum_mbus_code(struct v4l2_subdev *subdev,
@@ -243,7 +243,7 @@ done:
 	return ret;
 }
 
-const struct v4l2_subdev_pad_ops vsp1_rwpf_pad_ops = {
+static const struct v4l2_subdev_pad_ops vsp1_rwpf_pad_ops = {
 	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = vsp1_rwpf_enum_mbus_code,
 	.enum_frame_size = vsp1_rwpf_enum_frame_size,
@@ -253,6 +253,10 @@ const struct v4l2_subdev_pad_ops vsp1_rwpf_pad_ops = {
 	.set_selection = vsp1_rwpf_set_selection,
 };
 
+const struct v4l2_subdev_ops vsp1_rwpf_subdev_ops = {
+	.pad    = &vsp1_rwpf_pad_ops,
+};
+
 /* -----------------------------------------------------------------------------
  * Controls
  */
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_rwpf.h b/drivers/media/platform/renesas/vsp1/vsp1_rwpf.h
index eac5c04c223934..e0d212c70b2f99 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_rwpf.h
+++ b/drivers/media/platform/renesas/vsp1/vsp1_rwpf.h
@@ -79,9 +79,11 @@ static inline struct vsp1_rwpf *entity_to_rwpf(struct vsp1_entity *entity)
 struct vsp1_rwpf *vsp1_rpf_create(struct vsp1_device *vsp1, unsigned int index);
 struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index);
 
+void vsp1_wpf_stop(struct vsp1_rwpf *wpf);
+
 int vsp1_rwpf_init_ctrls(struct vsp1_rwpf *rwpf, unsigned int ncontrols);
 
-extern const struct v4l2_subdev_pad_ops vsp1_rwpf_pad_ops;
+extern const struct v4l2_subdev_ops vsp1_rwpf_subdev_ops;
 
 struct v4l2_rect *vsp1_rwpf_get_crop(struct vsp1_rwpf *rwpf,
 				     struct v4l2_subdev_state *sd_state);
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_wpf.c b/drivers/media/platform/renesas/vsp1/vsp1_wpf.c
index d0074ca009209c..cab4445eca696e 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_wpf.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_wpf.c
@@ -186,17 +186,13 @@ static int wpf_init_controls(struct vsp1_rwpf *wpf)
 }
 
 /* -----------------------------------------------------------------------------
- * V4L2 Subdevice Core Operations
+ * VSP1 Entity Operations
  */
 
-static int wpf_s_stream(struct v4l2_subdev *subdev, int enable)
+void vsp1_wpf_stop(struct vsp1_rwpf *wpf)
 {
-	struct vsp1_rwpf *wpf = to_rwpf(subdev);
 	struct vsp1_device *vsp1 = wpf->entity.vsp1;
 
-	if (enable)
-		return 0;
-
 	/*
 	 * Write to registers directly when stopping the stream as there will be
 	 * no pipeline run to apply the display list.
@@ -204,27 +200,8 @@ static int wpf_s_stream(struct v4l2_subdev *subdev, int enable)
 	vsp1_write(vsp1, VI6_WPF_IRQ_ENB(wpf->entity.index), 0);
 	vsp1_write(vsp1, wpf->entity.index * VI6_WPF_OFFSET +
 		   VI6_WPF_SRCRPF, 0);
-
-	return 0;
 }
 
-/* -----------------------------------------------------------------------------
- * V4L2 Subdevice Operations
- */
-
-static const struct v4l2_subdev_video_ops wpf_video_ops = {
-	.s_stream = wpf_s_stream,
-};
-
-static const struct v4l2_subdev_ops wpf_ops = {
-	.video	= &wpf_video_ops,
-	.pad    = &vsp1_rwpf_pad_ops,
-};
-
-/* -----------------------------------------------------------------------------
- * VSP1 Entity Operations
- */
-
 static void vsp1_wpf_destroy(struct vsp1_entity *entity)
 {
 	struct vsp1_rwpf *wpf = entity_to_rwpf(entity);
@@ -583,7 +560,7 @@ struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index)
 	wpf->entity.index = index;
 
 	sprintf(name, "wpf.%u", index);
-	ret = vsp1_entity_init(vsp1, &wpf->entity, name, 2, &wpf_ops,
+	ret = vsp1_entity_init(vsp1, &wpf->entity, name, 2, &vsp1_rwpf_subdev_ops,
 			       MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER);
 	if (ret < 0)
 		return ERR_PTR(ret);
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index 9c8fc87938a745..9d090fa07516f0 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -2011,7 +2011,7 @@ ssize_t mei_cl_write(struct mei_cl *cl, struct mei_cl_cb *cb, unsigned long time
 
 	mei_hdr = mei_msg_hdr_init(cb);
 	if (IS_ERR(mei_hdr)) {
-		rets = -PTR_ERR(mei_hdr);
+		rets = PTR_ERR(mei_hdr);
 		mei_hdr = NULL;
 		goto err;
 	}
@@ -2032,7 +2032,7 @@ ssize_t mei_cl_write(struct mei_cl *cl, struct mei_cl_cb *cb, unsigned long time
 
 	hbuf_slots = mei_hbuf_empty_slots(dev);
 	if (hbuf_slots < 0) {
-		rets = -EOVERFLOW;
+		buf_len = -EOVERFLOW;
 		goto out;
 	}
 
diff --git a/drivers/misc/mei/pxp/mei_pxp.c b/drivers/misc/mei/pxp/mei_pxp.c
index f77d78fa50549e..787c6a27a4be60 100644
--- a/drivers/misc/mei/pxp/mei_pxp.c
+++ b/drivers/misc/mei/pxp/mei_pxp.c
@@ -84,9 +84,10 @@ mei_pxp_send_message(struct device *dev, const void *message, size_t size, unsig
 				byte = ret;
 			break;
 		}
+		return byte;
 	}
 
-	return byte;
+	return 0;
 }
 
 /**
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 3a8f27c3e310a5..f9a5cffa64b1fd 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -1482,6 +1482,8 @@ static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req)
 			blk_mq_requeue_request(req, true);
 		else
 			__blk_mq_end_request(req, BLK_STS_OK);
+	} else if (mq->in_recovery) {
+		blk_mq_requeue_request(req, true);
 	} else {
 		blk_mq_end_request(req, BLK_STS_OK);
 	}
@@ -2381,8 +2383,10 @@ enum mmc_issued mmc_blk_mq_issue_rq(struct mmc_queue *mq, struct request *req)
 			}
 			ret = mmc_blk_cqe_issue_flush(mq, req);
 			break;
-		case REQ_OP_READ:
 		case REQ_OP_WRITE:
+			card->written_flag = true;
+			fallthrough;
+		case REQ_OP_READ:
 			if (host->cqe_enabled)
 				ret = mmc_blk_cqe_issue_rw_rq(mq, req);
 			else
diff --git a/drivers/mmc/core/card.h b/drivers/mmc/core/card.h
index 4edf9057fa79d3..b7754a1b8d9788 100644
--- a/drivers/mmc/core/card.h
+++ b/drivers/mmc/core/card.h
@@ -280,4 +280,8 @@ static inline int mmc_card_broken_sd_cache(const struct mmc_card *c)
 	return c->quirks & MMC_QUIRK_BROKEN_SD_CACHE;
 }
 
+static inline int mmc_card_broken_cache_flush(const struct mmc_card *c)
+{
+	return c->quirks & MMC_QUIRK_BROKEN_CACHE_FLUSH;
+}
 #endif
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 3d3e0ca5261481..a8c17b4cd73792 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -551,7 +551,9 @@ int mmc_cqe_recovery(struct mmc_host *host)
 	cmd.flags        = MMC_RSP_R1B | MMC_CMD_AC;
 	cmd.flags       &= ~MMC_RSP_CRC; /* Ignore CRC */
 	cmd.busy_timeout = MMC_CQE_RECOVERY_TIMEOUT;
-	mmc_wait_for_cmd(host, &cmd, 0);
+	mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES);
+
+	mmc_poll_for_busy(host->card, MMC_CQE_RECOVERY_TIMEOUT, true, MMC_BUSY_IO);
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.opcode       = MMC_CMDQ_TASK_MGMT;
@@ -559,10 +561,13 @@ int mmc_cqe_recovery(struct mmc_host *host)
 	cmd.flags        = MMC_RSP_R1B | MMC_CMD_AC;
 	cmd.flags       &= ~MMC_RSP_CRC; /* Ignore CRC */
 	cmd.busy_timeout = MMC_CQE_RECOVERY_TIMEOUT;
-	err = mmc_wait_for_cmd(host, &cmd, 0);
+	err = mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES);
 
 	host->cqe_ops->cqe_recovery_finish(host);
 
+	if (err)
+		err = mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES);
+
 	mmc_retune_release(host);
 
 	return err;
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 8180983bd4029d..705942edacc6a8 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -104,7 +104,7 @@ static int mmc_decode_cid(struct mmc_card *card)
 	case 3: /* MMC v3.1 - v3.3 */
 	case 4: /* MMC v4 */
 		card->cid.manfid	= UNSTUFF_BITS(resp, 120, 8);
-		card->cid.oemid		= UNSTUFF_BITS(resp, 104, 8);
+		card->cid.oemid		= UNSTUFF_BITS(resp, 104, 16);
 		card->cid.prod_name[0]	= UNSTUFF_BITS(resp, 96, 8);
 		card->cid.prod_name[1]	= UNSTUFF_BITS(resp, 88, 8);
 		card->cid.prod_name[2]	= UNSTUFF_BITS(resp, 80, 8);
@@ -2086,13 +2086,17 @@ static int _mmc_flush_cache(struct mmc_host *host)
 {
 	int err = 0;
 
+	if (mmc_card_broken_cache_flush(host->card) && !host->card->written_flag)
+		return 0;
+
 	if (_mmc_cache_enabled(host)) {
 		err = mmc_switch(host->card, EXT_CSD_CMD_SET_NORMAL,
 				 EXT_CSD_FLUSH_CACHE, 1,
 				 CACHE_FLUSH_TIMEOUT_MS);
 		if (err)
-			pr_err("%s: cache flush error %d\n",
-			       mmc_hostname(host), err);
+			pr_err("%s: cache flush error %d\n", mmc_hostname(host), err);
+		else
+			host->card->written_flag = false;
 	}
 
 	return err;
diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h
index 32b64b564fb1fd..cca71867bc4ad6 100644
--- a/drivers/mmc/core/quirks.h
+++ b/drivers/mmc/core/quirks.h
@@ -110,11 +110,12 @@ static const struct mmc_fixup __maybe_unused mmc_blk_fixups[] = {
 		  MMC_QUIRK_TRIM_BROKEN),
 
 	/*
-	 * Micron MTFC4GACAJCN-1M advertises TRIM but it does not seems to
-	 * support being used to offload WRITE_ZEROES.
+	 * Micron MTFC4GACAJCN-1M supports TRIM but does not appear to support
+	 * WRITE_ZEROES offloading. It also supports caching, but the cache can
+	 * only be flushed after a write has occurred.
 	 */
 	MMC_FIXUP("Q2J54A", CID_MANFID_MICRON, 0x014e, add_quirk_mmc,
-		  MMC_QUIRK_TRIM_BROKEN),
+		  MMC_QUIRK_TRIM_BROKEN | MMC_QUIRK_BROKEN_CACHE_FLUSH),
 
 	/*
 	 * Kingston EMMC04G-M627 advertises TRIM but it does not seems to
diff --git a/drivers/mmc/host/cqhci-core.c b/drivers/mmc/host/cqhci-core.c
index b3d7d6d8d65485..41e94cd1410980 100644
--- a/drivers/mmc/host/cqhci-core.c
+++ b/drivers/mmc/host/cqhci-core.c
@@ -942,8 +942,8 @@ static bool cqhci_clear_all_tasks(struct mmc_host *mmc, unsigned int timeout)
 	ret = cqhci_tasks_cleared(cq_host);
 
 	if (!ret)
-		pr_debug("%s: cqhci: Failed to clear tasks\n",
-			 mmc_hostname(mmc));
+		pr_warn("%s: cqhci: Failed to clear tasks\n",
+			mmc_hostname(mmc));
 
 	return ret;
 }
@@ -976,7 +976,7 @@ static bool cqhci_halt(struct mmc_host *mmc, unsigned int timeout)
 	ret = cqhci_halted(cq_host);
 
 	if (!ret)
-		pr_debug("%s: cqhci: Failed to halt\n", mmc_hostname(mmc));
+		pr_warn("%s: cqhci: Failed to halt\n", mmc_hostname(mmc));
 
 	return ret;
 }
@@ -984,10 +984,10 @@ static bool cqhci_halt(struct mmc_host *mmc, unsigned int timeout)
 /*
  * After halting we expect to be able to use the command line. We interpret the
  * failure to halt to mean the data lines might still be in use (and the upper
- * layers will need to send a STOP command), so we set the timeout based on a
- * generous command timeout.
+ * layers will need to send a STOP command), however failing to halt complicates
+ * the recovery, so set a timeout that would reasonably allow I/O to complete.
  */
-#define CQHCI_START_HALT_TIMEOUT	5
+#define CQHCI_START_HALT_TIMEOUT	500
 
 static void cqhci_recovery_start(struct mmc_host *mmc)
 {
@@ -1075,28 +1075,28 @@ static void cqhci_recovery_finish(struct mmc_host *mmc)
 
 	ok = cqhci_halt(mmc, CQHCI_FINISH_HALT_TIMEOUT);
 
-	if (!cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT))
-		ok = false;
-
 	/*
 	 * The specification contradicts itself, by saying that tasks cannot be
 	 * cleared if CQHCI does not halt, but if CQHCI does not halt, it should
 	 * be disabled/re-enabled, but not to disable before clearing tasks.
 	 * Have a go anyway.
 	 */
-	if (!ok) {
-		pr_debug("%s: cqhci: disable / re-enable\n", mmc_hostname(mmc));
-		cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
-		cqcfg &= ~CQHCI_ENABLE;
-		cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
-		cqcfg |= CQHCI_ENABLE;
-		cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
-		/* Be sure that there are no tasks */
-		ok = cqhci_halt(mmc, CQHCI_FINISH_HALT_TIMEOUT);
-		if (!cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT))
-			ok = false;
-		WARN_ON(!ok);
-	}
+	if (!cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT))
+		ok = false;
+
+	/* Disable to make sure tasks really are cleared */
+	cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
+	cqcfg &= ~CQHCI_ENABLE;
+	cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+
+	cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
+	cqcfg |= CQHCI_ENABLE;
+	cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+
+	cqhci_halt(mmc, CQHCI_FINISH_HALT_TIMEOUT);
+
+	if (!ok)
+		cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT);
 
 	cqhci_recover_mrqs(cq_host);
 
diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
index d83261e857a5d6..77911a57b12cfc 100644
--- a/drivers/mmc/host/sdhci-pci-gli.c
+++ b/drivers/mmc/host/sdhci-pci-gli.c
@@ -28,6 +28,9 @@
 #define PCI_GLI_9750_PM_CTRL	0xFC
 #define   PCI_GLI_9750_PM_STATE	  GENMASK(1, 0)
 
+#define PCI_GLI_9750_CORRERR_MASK				0x214
+#define   PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT	  BIT(12)
+
 #define SDHCI_GLI_9750_CFG2          0x848
 #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
 #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F
@@ -152,6 +155,9 @@
 #define PCI_GLI_9755_PM_CTRL     0xFC
 #define   PCI_GLI_9755_PM_STATE    GENMASK(1, 0)
 
+#define PCI_GLI_9755_CORRERR_MASK				0x214
+#define   PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT	  BIT(12)
+
 #define SDHCI_GLI_9767_GM_BURST_SIZE			0x510
 #define   SDHCI_GLI_9767_GM_BURST_SIZE_AXI_ALWAYS_SET	  BIT(8)
 
@@ -561,6 +567,11 @@ static void gl9750_hw_setting(struct sdhci_host *host)
 	value &= ~PCI_GLI_9750_PM_STATE;
 	pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
 
+	/* mask the replay timer timeout of AER */
+	pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value);
+	value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
+	pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value);
+
 	gl9750_wt_off(host);
 }
 
@@ -770,6 +781,11 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
 	value &= ~PCI_GLI_9755_PM_STATE;
 	pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value);
 
+	/* mask the replay timer timeout of AER */
+	pci_read_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, &value);
+	value |= PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
+	pci_write_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, value);
+
 	gl9755_wt_off(pdev);
 }
 
@@ -1173,6 +1189,32 @@ static void gl9763e_hs400_enhanced_strobe(struct mmc_host *mmc,
 	sdhci_writel(host, val, SDHCI_GLI_9763E_HS400_ES_REG);
 }
 
+static void gl9763e_set_low_power_negotiation(struct sdhci_pci_slot *slot,
+					      bool enable)
+{
+	struct pci_dev *pdev = slot->chip->pdev;
+	u32 value;
+
+	pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value);
+	value &= ~GLI_9763E_VHS_REV;
+	value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_W);
+	pci_write_config_dword(pdev, PCIE_GLI_9763E_VHS, value);
+
+	pci_read_config_dword(pdev, PCIE_GLI_9763E_CFG, &value);
+
+	if (enable)
+		value &= ~GLI_9763E_CFG_LPSN_DIS;
+	else
+		value |= GLI_9763E_CFG_LPSN_DIS;
+
+	pci_write_config_dword(pdev, PCIE_GLI_9763E_CFG, value);
+
+	pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value);
+	value &= ~GLI_9763E_VHS_REV;
+	value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_R);
+	pci_write_config_dword(pdev, PCIE_GLI_9763E_VHS, value);
+}
+
 static void sdhci_set_gl9763e_signaling(struct sdhci_host *host,
 					unsigned int timing)
 {
@@ -1281,6 +1323,9 @@ static int gl9763e_add_host(struct sdhci_pci_slot *slot)
 	if (ret)
 		goto cleanup;
 
+	/* Disable LPM negotiation to avoid entering L1 state. */
+	gl9763e_set_low_power_negotiation(slot, false);
+
 	return 0;
 
 cleanup:
@@ -1324,31 +1369,6 @@ static void gli_set_gl9763e(struct sdhci_pci_slot *slot)
 }
 
 #ifdef CONFIG_PM
-static void gl9763e_set_low_power_negotiation(struct sdhci_pci_slot *slot, bool enable)
-{
-	struct pci_dev *pdev = slot->chip->pdev;
-	u32 value;
-
-	pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value);
-	value &= ~GLI_9763E_VHS_REV;
-	value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_W);
-	pci_write_config_dword(pdev, PCIE_GLI_9763E_VHS, value);
-
-	pci_read_config_dword(pdev, PCIE_GLI_9763E_CFG, &value);
-
-	if (enable)
-		value &= ~GLI_9763E_CFG_LPSN_DIS;
-	else
-		value |= GLI_9763E_CFG_LPSN_DIS;
-
-	pci_write_config_dword(pdev, PCIE_GLI_9763E_CFG, value);
-
-	pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value);
-	value &= ~GLI_9763E_VHS_REV;
-	value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_R);
-	pci_write_config_dword(pdev, PCIE_GLI_9763E_VHS, value);
-}
-
 static int gl9763e_runtime_suspend(struct sdhci_pci_chip *chip)
 {
 	struct sdhci_pci_slot *slot = chip->slots[0];
diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c
index 6b84ba27e6ab0d..6b8a57e2d20f0a 100644
--- a/drivers/mmc/host/sdhci-sprd.c
+++ b/drivers/mmc/host/sdhci-sprd.c
@@ -416,12 +416,33 @@ static void sdhci_sprd_request_done(struct sdhci_host *host,
 	mmc_request_done(host->mmc, mrq);
 }
 
+static void sdhci_sprd_set_power(struct sdhci_host *host, unsigned char mode,
+				 unsigned short vdd)
+{
+	struct mmc_host *mmc = host->mmc;
+
+	switch (mode) {
+	case MMC_POWER_OFF:
+		mmc_regulator_set_ocr(host->mmc, mmc->supply.vmmc, 0);
+
+		mmc_regulator_disable_vqmmc(mmc);
+		break;
+	case MMC_POWER_ON:
+		mmc_regulator_enable_vqmmc(mmc);
+		break;
+	case MMC_POWER_UP:
+		mmc_regulator_set_ocr(host->mmc, mmc->supply.vmmc, vdd);
+		break;
+	}
+}
+
 static struct sdhci_ops sdhci_sprd_ops = {
 	.read_l = sdhci_sprd_readl,
 	.write_l = sdhci_sprd_writel,
 	.write_w = sdhci_sprd_writew,
 	.write_b = sdhci_sprd_writeb,
 	.set_clock = sdhci_sprd_set_clock,
+	.set_power = sdhci_sprd_set_power,
 	.get_max_clock = sdhci_sprd_get_max_clock,
 	.get_min_clock = sdhci_sprd_get_min_clock,
 	.set_bus_width = sdhci_set_bus_width,
@@ -823,6 +844,10 @@ static int sdhci_sprd_probe(struct platform_device *pdev)
 	host->caps1 &= ~(SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_SDR104 |
 			 SDHCI_SUPPORT_DDR50);
 
+	ret = mmc_regulator_get_supply(host->mmc);
+	if (ret)
+		goto pm_runtime_disable;
+
 	ret = sdhci_setup_host(host);
 	if (ret)
 		goto pm_runtime_disable;
diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c
index c125485ba80e9c..967bd2dfcda1b2 100644
--- a/drivers/mmc/host/sdhci_am654.c
+++ b/drivers/mmc/host/sdhci_am654.c
@@ -598,7 +598,7 @@ static int sdhci_am654_get_otap_delay(struct sdhci_host *host,
 		return 0;
 	}
 
-	for (i = MMC_TIMING_MMC_HS; i <= MMC_TIMING_MMC_HS400; i++) {
+	for (i = MMC_TIMING_LEGACY; i <= MMC_TIMING_MMC_HS400; i++) {
 
 		ret = device_property_read_u32(dev, td[i].otap_binding,
 					       &sdhci_am654->otap_del_sel[i]);
diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c
index de3f443f5fdcc1..fd67c0682b38ae 100644
--- a/drivers/mmc/host/vub300.c
+++ b/drivers/mmc/host/vub300.c
@@ -2309,6 +2309,7 @@ static int vub300_probe(struct usb_interface *interface,
 		vub300->read_only =
 			(0x0010 & vub300->system_port_status.port_flags) ? 1 : 0;
 	} else {
+		retval = -EINVAL;
 		goto error5;
 	}
 	usb_set_intfdata(interface, vub300);
diff --git a/drivers/mtd/parsers/Kconfig b/drivers/mtd/parsers/Kconfig
index 60738edcd5d561..da03ab6efe04c6 100644
--- a/drivers/mtd/parsers/Kconfig
+++ b/drivers/mtd/parsers/Kconfig
@@ -1,9 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-config MTD_AR7_PARTS
-	tristate "TI AR7 partitioning parser"
-	help
-	  TI AR7 partitioning parser support
-
 config MTD_BCM47XX_PARTS
 	tristate "BCM47XX partitioning parser"
 	depends on BCM47XX || ARCH_BCM_5301X
diff --git a/drivers/mtd/parsers/Makefile b/drivers/mtd/parsers/Makefile
index 0e70b621a1d84e..9b00c62b837ae7 100644
--- a/drivers/mtd/parsers/Makefile
+++ b/drivers/mtd/parsers/Makefile
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_MTD_AR7_PARTS)		+= ar7part.o
 obj-$(CONFIG_MTD_BCM47XX_PARTS)		+= bcm47xxpart.o
 obj-$(CONFIG_MTD_BCM63XX_PARTS)		+= bcm63xxpart.o
 obj-$(CONFIG_MTD_BRCM_U_BOOT)		+= brcm_u-boot.o
diff --git a/drivers/mtd/parsers/ar7part.c b/drivers/mtd/parsers/ar7part.c
deleted file mode 100644
index 8cd683711ac609..00000000000000
--- a/drivers/mtd/parsers/ar7part.c
+++ /dev/null
@@ -1,129 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright © 2007 Eugene Konev <ejka@openwrt.org>
- *
- * TI AR7 flash partition table.
- * Based on ar7 map by Felix Fietkau <nbd@openwrt.org>
- */
-
-#include <linux/kernel.h>
-#include <linux/slab.h>
-
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/memblock.h>
-#include <linux/module.h>
-
-#include <uapi/linux/magic.h>
-
-#define AR7_PARTS	4
-#define ROOT_OFFSET	0xe0000
-
-#define LOADER_MAGIC1	le32_to_cpu(0xfeedfa42)
-#define LOADER_MAGIC2	le32_to_cpu(0xfeed1281)
-
-struct ar7_bin_rec {
-	unsigned int checksum;
-	unsigned int length;
-	unsigned int address;
-};
-
-static int create_mtd_partitions(struct mtd_info *master,
-				 const struct mtd_partition **pparts,
-				 struct mtd_part_parser_data *data)
-{
-	struct ar7_bin_rec header;
-	unsigned int offset;
-	size_t len;
-	unsigned int pre_size = master->erasesize, post_size = 0;
-	unsigned int root_offset = ROOT_OFFSET;
-
-	int retries = 10;
-	struct mtd_partition *ar7_parts;
-
-	ar7_parts = kcalloc(AR7_PARTS, sizeof(*ar7_parts), GFP_KERNEL);
-	if (!ar7_parts)
-		return -ENOMEM;
-	ar7_parts[0].name = "loader";
-	ar7_parts[0].offset = 0;
-	ar7_parts[0].size = master->erasesize;
-	ar7_parts[0].mask_flags = MTD_WRITEABLE;
-
-	ar7_parts[1].name = "config";
-	ar7_parts[1].offset = 0;
-	ar7_parts[1].size = master->erasesize;
-	ar7_parts[1].mask_flags = 0;
-
-	do { /* Try 10 blocks starting from master->erasesize */
-		offset = pre_size;
-		mtd_read(master, offset, sizeof(header), &len,
-			 (uint8_t *)&header);
-		if (!strncmp((char *)&header, "TIENV0.8", 8))
-			ar7_parts[1].offset = pre_size;
-		if (header.checksum == LOADER_MAGIC1)
-			break;
-		if (header.checksum == LOADER_MAGIC2)
-			break;
-		pre_size += master->erasesize;
-	} while (retries--);
-
-	pre_size = offset;
-
-	if (!ar7_parts[1].offset) {
-		ar7_parts[1].offset = master->size - master->erasesize;
-		post_size = master->erasesize;
-	}
-
-	switch (header.checksum) {
-	case LOADER_MAGIC1:
-		while (header.length) {
-			offset += sizeof(header) + header.length;
-			mtd_read(master, offset, sizeof(header), &len,
-				 (uint8_t *)&header);
-		}
-		root_offset = offset + sizeof(header) + 4;
-		break;
-	case LOADER_MAGIC2:
-		while (header.length) {
-			offset += sizeof(header) + header.length;
-			mtd_read(master, offset, sizeof(header), &len,
-				 (uint8_t *)&header);
-		}
-		root_offset = offset + sizeof(header) + 4 + 0xff;
-		root_offset &= ~(uint32_t)0xff;
-		break;
-	default:
-		printk(KERN_WARNING "Unknown magic: %08x\n", header.checksum);
-		break;
-	}
-
-	mtd_read(master, root_offset, sizeof(header), &len, (u8 *)&header);
-	if (header.checksum != SQUASHFS_MAGIC) {
-		root_offset += master->erasesize - 1;
-		root_offset &= ~(master->erasesize - 1);
-	}
-
-	ar7_parts[2].name = "linux";
-	ar7_parts[2].offset = pre_size;
-	ar7_parts[2].size = master->size - pre_size - post_size;
-	ar7_parts[2].mask_flags = 0;
-
-	ar7_parts[3].name = "rootfs";
-	ar7_parts[3].offset = root_offset;
-	ar7_parts[3].size = master->size - root_offset - post_size;
-	ar7_parts[3].mask_flags = 0;
-
-	*pparts = ar7_parts;
-	return AR7_PARTS;
-}
-
-static struct mtd_part_parser ar7_parser = {
-	.parse_fn = create_mtd_partitions,
-	.name = "ar7part",
-};
-module_mtd_part_parser(ar7_parser);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR(	"Felix Fietkau <nbd@openwrt.org>, "
-		"Eugene Konev <ejka@openwrt.org>");
-MODULE_DESCRIPTION("MTD partitioning for TI AR7");
diff --git a/drivers/net/arcnet/arcdevice.h b/drivers/net/arcnet/arcdevice.h
index 19e996a829c9db..b54275389f8acf 100644
--- a/drivers/net/arcnet/arcdevice.h
+++ b/drivers/net/arcnet/arcdevice.h
@@ -186,6 +186,8 @@ do {									\
 #define ARC_IS_5MBIT    1   /* card default speed is 5MBit */
 #define ARC_CAN_10MBIT  2   /* card uses COM20022, supporting 10MBit,
 				 but default is 2.5MBit. */
+#define ARC_HAS_LED     4   /* card has software controlled LEDs */
+#define ARC_HAS_ROTARY  8   /* card has rotary encoder */
 
 /* information needed to define an encapsulation driver */
 struct ArcProto {
diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c
index c580acb8b1d34e..7b5c8bb02f1194 100644
--- a/drivers/net/arcnet/com20020-pci.c
+++ b/drivers/net/arcnet/com20020-pci.c
@@ -213,12 +213,13 @@ static int com20020pci_probe(struct pci_dev *pdev,
 		if (!strncmp(ci->name, "EAE PLX-PCI FB2", 15))
 			lp->backplane = 1;
 
-		/* Get the dev_id from the PLX rotary coder */
-		if (!strncmp(ci->name, "EAE PLX-PCI MA1", 15))
-			dev_id_mask = 0x3;
-		dev->dev_id = (inb(priv->misc + ci->rotary) >> 4) & dev_id_mask;
-
-		snprintf(dev->name, sizeof(dev->name), "arc%d-%d", dev->dev_id, i);
+		if (ci->flags & ARC_HAS_ROTARY) {
+			/* Get the dev_id from the PLX rotary coder */
+			if (!strncmp(ci->name, "EAE PLX-PCI MA1", 15))
+				dev_id_mask = 0x3;
+			dev->dev_id = (inb(priv->misc + ci->rotary) >> 4) & dev_id_mask;
+			snprintf(dev->name, sizeof(dev->name), "arc%d-%d", dev->dev_id, i);
+		}
 
 		if (arcnet_inb(ioaddr, COM20020_REG_R_STATUS) == 0xFF) {
 			pr_err("IO address %Xh is empty!\n", ioaddr);
@@ -230,6 +231,10 @@ static int com20020pci_probe(struct pci_dev *pdev,
 			goto err_free_arcdev;
 		}
 
+		ret = com20020_found(dev, IRQF_SHARED);
+		if (ret)
+			goto err_free_arcdev;
+
 		card = devm_kzalloc(&pdev->dev, sizeof(struct com20020_dev),
 				    GFP_KERNEL);
 		if (!card) {
@@ -239,41 +244,39 @@ static int com20020pci_probe(struct pci_dev *pdev,
 
 		card->index = i;
 		card->pci_priv = priv;
-		card->tx_led.brightness_set = led_tx_set;
-		card->tx_led.default_trigger = devm_kasprintf(&pdev->dev,
-						GFP_KERNEL, "arc%d-%d-tx",
-						dev->dev_id, i);
-		card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
-						"pci:green:tx:%d-%d",
-						dev->dev_id, i);
-
-		card->tx_led.dev = &dev->dev;
-		card->recon_led.brightness_set = led_recon_set;
-		card->recon_led.default_trigger = devm_kasprintf(&pdev->dev,
-						GFP_KERNEL, "arc%d-%d-recon",
-						dev->dev_id, i);
-		card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
-						"pci:red:recon:%d-%d",
-						dev->dev_id, i);
-		card->recon_led.dev = &dev->dev;
-		card->dev = dev;
-
-		ret = devm_led_classdev_register(&pdev->dev, &card->tx_led);
-		if (ret)
-			goto err_free_arcdev;
 
-		ret = devm_led_classdev_register(&pdev->dev, &card->recon_led);
-		if (ret)
-			goto err_free_arcdev;
-
-		dev_set_drvdata(&dev->dev, card);
-
-		ret = com20020_found(dev, IRQF_SHARED);
-		if (ret)
-			goto err_free_arcdev;
-
-		devm_arcnet_led_init(dev, dev->dev_id, i);
+		if (ci->flags & ARC_HAS_LED) {
+			card->tx_led.brightness_set = led_tx_set;
+			card->tx_led.default_trigger = devm_kasprintf(&pdev->dev,
+							GFP_KERNEL, "arc%d-%d-tx",
+							dev->dev_id, i);
+			card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+							"pci:green:tx:%d-%d",
+							dev->dev_id, i);
+
+			card->tx_led.dev = &dev->dev;
+			card->recon_led.brightness_set = led_recon_set;
+			card->recon_led.default_trigger = devm_kasprintf(&pdev->dev,
+							GFP_KERNEL, "arc%d-%d-recon",
+							dev->dev_id, i);
+			card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+							"pci:red:recon:%d-%d",
+							dev->dev_id, i);
+			card->recon_led.dev = &dev->dev;
+
+			ret = devm_led_classdev_register(&pdev->dev, &card->tx_led);
+			if (ret)
+				goto err_free_arcdev;
+
+			ret = devm_led_classdev_register(&pdev->dev, &card->recon_led);
+			if (ret)
+				goto err_free_arcdev;
+
+			dev_set_drvdata(&dev->dev, card);
+			devm_arcnet_led_init(dev, dev->dev_id, i);
+		}
 
+		card->dev = dev;
 		list_add(&card->list, &priv->list_dev);
 		continue;
 
@@ -329,7 +332,7 @@ static struct com20020_pci_card_info card_info_5mbit = {
 };
 
 static struct com20020_pci_card_info card_info_sohard = {
-	.name = "PLX-PCI",
+	.name = "SOHARD SH ARC-PCI",
 	.devcount = 1,
 	/* SOHARD needs PCI base addr 4 */
 	.chan_map_tbl = {
@@ -364,7 +367,7 @@ static struct com20020_pci_card_info card_info_eae_arc1 = {
 		},
 	},
 	.rotary = 0x0,
-	.flags = ARC_CAN_10MBIT,
+	.flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT,
 };
 
 static struct com20020_pci_card_info card_info_eae_ma1 = {
@@ -396,7 +399,7 @@ static struct com20020_pci_card_info card_info_eae_ma1 = {
 		},
 	},
 	.rotary = 0x0,
-	.flags = ARC_CAN_10MBIT,
+	.flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT,
 };
 
 static struct com20020_pci_card_info card_info_eae_fb2 = {
@@ -421,7 +424,7 @@ static struct com20020_pci_card_info card_info_eae_fb2 = {
 		},
 	},
 	.rotary = 0x0,
-	.flags = ARC_CAN_10MBIT,
+	.flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT,
 };
 
 static const struct pci_device_id com20020pci_id_table[] = {
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 51d47eda1c873d..8e6cc0e133b7f1 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1500,6 +1500,10 @@ done:
 static void bond_setup_by_slave(struct net_device *bond_dev,
 				struct net_device *slave_dev)
 {
+	bool was_up = !!(bond_dev->flags & IFF_UP);
+
+	dev_close(bond_dev);
+
 	bond_dev->header_ops	    = slave_dev->header_ops;
 
 	bond_dev->type		    = slave_dev->type;
@@ -1514,6 +1518,8 @@ static void bond_setup_by_slave(struct net_device *bond_dev,
 		bond_dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST);
 		bond_dev->flags |= (IFF_POINTOPOINT | IFF_NOARP);
 	}
+	if (was_up)
+		dev_open(bond_dev, NULL);
 }
 
 /* On bonding slaves other than the currently active slave, suppress
diff --git a/drivers/net/dsa/lan9303_mdio.c b/drivers/net/dsa/lan9303_mdio.c
index d8ab2b77d201e0..167a86f39f2771 100644
--- a/drivers/net/dsa/lan9303_mdio.c
+++ b/drivers/net/dsa/lan9303_mdio.c
@@ -32,7 +32,7 @@ static int lan9303_mdio_write(void *ctx, uint32_t reg, uint32_t val)
 	struct lan9303_mdio *sw_dev = (struct lan9303_mdio *)ctx;
 
 	reg <<= 2; /* reg num to offset */
-	mutex_lock(&sw_dev->device->bus->mdio_lock);
+	mutex_lock_nested(&sw_dev->device->bus->mdio_lock, MDIO_MUTEX_NESTED);
 	lan9303_mdio_real_write(sw_dev->device, reg, val & 0xffff);
 	lan9303_mdio_real_write(sw_dev->device, reg + 2, (val >> 16) & 0xffff);
 	mutex_unlock(&sw_dev->device->bus->mdio_lock);
@@ -50,7 +50,7 @@ static int lan9303_mdio_read(void *ctx, uint32_t reg, uint32_t *val)
 	struct lan9303_mdio *sw_dev = (struct lan9303_mdio *)ctx;
 
 	reg <<= 2; /* reg num to offset */
-	mutex_lock(&sw_dev->device->bus->mdio_lock);
+	mutex_lock_nested(&sw_dev->device->bus->mdio_lock, MDIO_MUTEX_NESTED);
 	*val = lan9303_mdio_real_read(sw_dev->device, reg);
 	*val |= (lan9303_mdio_real_read(sw_dev->device, reg + 2) << 16);
 	mutex_unlock(&sw_dev->device->bus->mdio_lock);
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 3fed406fb46ae6..ff4b39601c937b 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -2713,10 +2713,18 @@ static int ksz_connect_tag_protocol(struct dsa_switch *ds,
 {
 	struct ksz_tagger_data *tagger_data;
 
-	tagger_data = ksz_tagger_data(ds);
-	tagger_data->xmit_work_fn = ksz_port_deferred_xmit;
-
-	return 0;
+	switch (proto) {
+	case DSA_TAG_PROTO_KSZ8795:
+		return 0;
+	case DSA_TAG_PROTO_KSZ9893:
+	case DSA_TAG_PROTO_KSZ9477:
+	case DSA_TAG_PROTO_LAN937X:
+		tagger_data = ksz_tagger_data(ds);
+		tagger_data->xmit_work_fn = ksz_port_deferred_xmit;
+		return 0;
+	default:
+		return -EPROTONOSUPPORT;
+	}
 }
 
 static int ksz_port_vlan_filtering(struct dsa_switch *ds, int port,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 42b1acaca33a96..07a22c74fe810a 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -577,6 +577,18 @@ static void mv88e6250_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
 	config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100;
 }
 
+static void mv88e6351_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
+				       struct phylink_config *config)
+{
+	unsigned long *supported = config->supported_interfaces;
+
+	/* Translate the default cmode */
+	mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported);
+
+	config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 |
+				   MAC_1000FD;
+}
+
 static int mv88e6352_get_port4_serdes_cmode(struct mv88e6xxx_chip *chip)
 {
 	u16 reg, val;
@@ -3880,7 +3892,8 @@ static int mv88e6xxx_port_setup(struct dsa_switch *ds, int port)
 	struct mv88e6xxx_chip *chip = ds->priv;
 	int err;
 
-	if (chip->info->ops->pcs_ops->pcs_init) {
+	if (chip->info->ops->pcs_ops &&
+	    chip->info->ops->pcs_ops->pcs_init) {
 		err = chip->info->ops->pcs_ops->pcs_init(chip, port);
 		if (err)
 			return err;
@@ -3895,7 +3908,8 @@ static void mv88e6xxx_port_teardown(struct dsa_switch *ds, int port)
 
 	mv88e6xxx_teardown_devlink_regions_port(ds, port);
 
-	if (chip->info->ops->pcs_ops->pcs_teardown)
+	if (chip->info->ops->pcs_ops &&
+	    chip->info->ops->pcs_ops->pcs_teardown)
 		chip->info->ops->pcs_ops->pcs_teardown(chip, port);
 }
 
@@ -4340,7 +4354,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6352_g1_stu_getnext,
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
-	.phylink_get_caps = mv88e6185_phylink_get_caps,
+	.phylink_get_caps = mv88e6351_phylink_get_caps,
 };
 
 static const struct mv88e6xxx_ops mv88e6172_ops = {
@@ -4440,7 +4454,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6352_g1_stu_getnext,
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
-	.phylink_get_caps = mv88e6185_phylink_get_caps,
+	.phylink_get_caps = mv88e6351_phylink_get_caps,
 };
 
 static const struct mv88e6xxx_ops mv88e6176_ops = {
@@ -5069,7 +5083,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.stu_getnext = mv88e6352_g1_stu_getnext,
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
-	.phylink_get_caps = mv88e6185_phylink_get_caps,
+	.phylink_get_caps = mv88e6351_phylink_get_caps,
 };
 
 static const struct mv88e6xxx_ops mv88e6351_ops = {
@@ -5117,7 +5131,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = {
 	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
-	.phylink_get_caps = mv88e6185_phylink_get_caps,
+	.phylink_get_caps = mv88e6351_phylink_get_caps,
 };
 
 static const struct mv88e6xxx_ops mv88e6352_ops = {
diff --git a/drivers/net/dsa/mv88e6xxx/pcs-639x.c b/drivers/net/dsa/mv88e6xxx/pcs-639x.c
index 9a8429f5d09cbf..d758a6c1b22638 100644
--- a/drivers/net/dsa/mv88e6xxx/pcs-639x.c
+++ b/drivers/net/dsa/mv88e6xxx/pcs-639x.c
@@ -465,6 +465,7 @@ mv88e639x_pcs_select(struct mv88e6xxx_chip *chip, int port,
 	case PHY_INTERFACE_MODE_10GBASER:
 	case PHY_INTERFACE_MODE_XAUI:
 	case PHY_INTERFACE_MODE_RXAUI:
+	case PHY_INTERFACE_MODE_USXGMII:
 		return &mpcs->xg_pcs;
 
 	default:
@@ -873,7 +874,8 @@ static int mv88e6393x_xg_pcs_post_config(struct phylink_pcs *pcs,
 	struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs);
 	int err;
 
-	if (interface == PHY_INTERFACE_MODE_10GBASER) {
+	if (interface == PHY_INTERFACE_MODE_10GBASER ||
+	    interface == PHY_INTERFACE_MODE_USXGMII) {
 		err = mv88e6393x_erratum_5_2(mpcs);
 		if (err)
 			return err;
@@ -886,12 +888,37 @@ static int mv88e6393x_xg_pcs_post_config(struct phylink_pcs *pcs,
 	return mv88e639x_xg_pcs_enable(mpcs);
 }
 
+static void mv88e6393x_xg_pcs_get_state(struct phylink_pcs *pcs,
+					struct phylink_link_state *state)
+{
+	struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs);
+	u16 status, lp_status;
+	int err;
+
+	if (state->interface != PHY_INTERFACE_MODE_USXGMII)
+		return mv88e639x_xg_pcs_get_state(pcs, state);
+
+	state->link = false;
+
+	err = mv88e639x_read(mpcs, MV88E6390_USXGMII_PHY_STATUS, &status);
+	err = err ? : mv88e639x_read(mpcs, MV88E6390_USXGMII_LP_STATUS, &lp_status);
+	if (err) {
+		dev_err(mpcs->mdio.dev.parent,
+			"can't read USXGMII status: %pe\n", ERR_PTR(err));
+		return;
+	}
+
+	state->link = !!(status & MDIO_USXGMII_LINK);
+	state->an_complete = state->link;
+	phylink_decode_usxgmii_word(state, lp_status);
+}
+
 static const struct phylink_pcs_ops mv88e6393x_xg_pcs_ops = {
 	.pcs_enable = mv88e6393x_xg_pcs_enable,
 	.pcs_disable = mv88e6393x_xg_pcs_disable,
 	.pcs_pre_config = mv88e6393x_xg_pcs_pre_config,
 	.pcs_post_config = mv88e6393x_xg_pcs_post_config,
-	.pcs_get_state = mv88e639x_xg_pcs_get_state,
+	.pcs_get_state = mv88e6393x_xg_pcs_get_state,
 	.pcs_config = mv88e639x_xg_pcs_config,
 };
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
index 3d6f0a466a9ed4..f9f886289b970a 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
@@ -328,9 +328,6 @@ static int ena_com_create_and_store_tx_meta_desc(struct ena_com_io_sq *io_sq,
 	 * compare it to the stored version, just create the meta
 	 */
 	if (io_sq->disable_meta_caching) {
-		if (unlikely(!ena_tx_ctx->meta_valid))
-			return -EINVAL;
-
 		*have_meta = true;
 		return ena_com_create_meta(io_sq, ena_meta);
 	}
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index b5bca481483099..c44c44e26ddfe7 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -74,6 +74,8 @@ static void ena_unmap_tx_buff(struct ena_ring *tx_ring,
 			      struct ena_tx_buffer *tx_info);
 static int ena_create_io_tx_queues_in_range(struct ena_adapter *adapter,
 					    int first_index, int count);
+static void ena_free_all_io_tx_resources_in_range(struct ena_adapter *adapter,
+						  int first_index, int count);
 
 /* Increase a stat by cnt while holding syncp seqlock on 32bit machines */
 static void ena_increase_stat(u64 *statp, u64 cnt,
@@ -457,23 +459,22 @@ static void ena_init_all_xdp_queues(struct ena_adapter *adapter)
 
 static int ena_setup_and_create_all_xdp_queues(struct ena_adapter *adapter)
 {
+	u32 xdp_first_ring = adapter->xdp_first_ring;
+	u32 xdp_num_queues = adapter->xdp_num_queues;
 	int rc = 0;
 
-	rc = ena_setup_tx_resources_in_range(adapter, adapter->xdp_first_ring,
-					     adapter->xdp_num_queues);
+	rc = ena_setup_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues);
 	if (rc)
 		goto setup_err;
 
-	rc = ena_create_io_tx_queues_in_range(adapter,
-					      adapter->xdp_first_ring,
-					      adapter->xdp_num_queues);
+	rc = ena_create_io_tx_queues_in_range(adapter, xdp_first_ring, xdp_num_queues);
 	if (rc)
 		goto create_err;
 
 	return 0;
 
 create_err:
-	ena_free_all_io_tx_resources(adapter);
+	ena_free_all_io_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues);
 setup_err:
 	return rc;
 }
@@ -1492,11 +1493,6 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 		if (unlikely(!skb))
 			return NULL;
 
-		/* sync this buffer for CPU use */
-		dma_sync_single_for_cpu(rx_ring->dev,
-					dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset,
-					len,
-					DMA_FROM_DEVICE);
 		skb_copy_to_linear_data(skb, buf_addr + buf_offset, len);
 		dma_sync_single_for_device(rx_ring->dev,
 					   dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset,
@@ -1515,17 +1511,10 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 
 	buf_len = SKB_DATA_ALIGN(len + buf_offset + tailroom);
 
-	pre_reuse_paddr = dma_unmap_addr(&rx_info->ena_buf, paddr);
-
 	/* If XDP isn't loaded try to reuse part of the RX buffer */
 	reuse_rx_buf_page = !is_xdp_loaded &&
 			    ena_try_rx_buf_page_reuse(rx_info, buf_len, len, pkt_offset);
 
-	dma_sync_single_for_cpu(rx_ring->dev,
-				pre_reuse_paddr + pkt_offset,
-				len,
-				DMA_FROM_DEVICE);
-
 	if (!reuse_rx_buf_page)
 		ena_unmap_rx_buff_attrs(rx_ring, rx_info, DMA_ATTR_SKIP_CPU_SYNC);
 
@@ -1671,20 +1660,23 @@ static void ena_set_rx_hash(struct ena_ring *rx_ring,
 	}
 }
 
-static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp)
+static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp, u16 num_descs)
 {
 	struct ena_rx_buffer *rx_info;
 	int ret;
 
+	/* XDP multi-buffer packets not supported */
+	if (unlikely(num_descs > 1)) {
+		netdev_err_once(rx_ring->adapter->netdev,
+				"xdp: dropped unsupported multi-buffer packets\n");
+		ena_increase_stat(&rx_ring->rx_stats.xdp_drop, 1, &rx_ring->syncp);
+		return ENA_XDP_DROP;
+	}
+
 	rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id];
 	xdp_prepare_buff(xdp, page_address(rx_info->page),
 			 rx_info->buf_offset,
 			 rx_ring->ena_bufs[0].len, false);
-	/* If for some reason we received a bigger packet than
-	 * we expect, then we simply drop it
-	 */
-	if (unlikely(rx_ring->ena_bufs[0].len > ENA_XDP_MAX_MTU))
-		return ENA_XDP_DROP;
 
 	ret = ena_xdp_execute(rx_ring, xdp);
 
@@ -1719,6 +1711,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 	int xdp_flags = 0;
 	int total_len = 0;
 	int xdp_verdict;
+	u8 pkt_offset;
 	int rc = 0;
 	int i;
 
@@ -1745,15 +1738,21 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 
 		/* First descriptor might have an offset set by the device */
 		rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id];
-		rx_info->buf_offset += ena_rx_ctx.pkt_offset;
+		pkt_offset = ena_rx_ctx.pkt_offset;
+		rx_info->buf_offset += pkt_offset;
 
 		netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev,
 			  "rx_poll: q %d got packet from ena. descs #: %d l3 proto %d l4 proto %d hash: %x\n",
 			  rx_ring->qid, ena_rx_ctx.descs, ena_rx_ctx.l3_proto,
 			  ena_rx_ctx.l4_proto, ena_rx_ctx.hash);
 
+		dma_sync_single_for_cpu(rx_ring->dev,
+					dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset,
+					rx_ring->ena_bufs[0].len,
+					DMA_FROM_DEVICE);
+
 		if (ena_xdp_present_ring(rx_ring))
-			xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp);
+			xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp, ena_rx_ctx.descs);
 
 		/* allocate skb and fill it */
 		if (xdp_verdict == ENA_XDP_PASS)
@@ -1777,7 +1776,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 				if (xdp_verdict & ENA_XDP_FORWARDED) {
 					ena_unmap_rx_buff_attrs(rx_ring,
 								&rx_ring->rx_buffer_info[req_id],
-								0);
+								DMA_ATTR_SKIP_CPU_SYNC);
 					rx_ring->rx_buffer_info[req_id].page = NULL;
 				}
 			}
diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index 045fe133f6ee99..5beadabc213618 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -146,7 +146,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
 	}
 
 	queue_work(pdsc->wq, &qcq->work);
-	pds_core_intr_mask(&pdsc->intr_ctrl[irq], PDS_CORE_INTR_MASK_CLEAR);
+	pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index f3a7deda997245..e35d3e7006bfc1 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -15,7 +15,7 @@
 #define PDSC_DRV_DESCRIPTION	"AMD/Pensando Core Driver"
 
 #define PDSC_WATCHDOG_SECS	5
-#define PDSC_QUEUE_NAME_MAX_SZ  32
+#define PDSC_QUEUE_NAME_MAX_SZ  16
 #define PDSC_ADMINQ_MIN_LENGTH	16	/* must be a power of two */
 #define PDSC_NOTIFYQ_LENGTH	64	/* must be a power of two */
 #define PDSC_TEARDOWN_RECOVERY	false
diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c
index 7c1b965d61a926..31940b857e0e50 100644
--- a/drivers/net/ethernet/amd/pds_core/dev.c
+++ b/drivers/net/ethernet/amd/pds_core/dev.c
@@ -261,10 +261,14 @@ static int pdsc_identify(struct pdsc *pdsc)
 	struct pds_core_drv_identity drv = {};
 	size_t sz;
 	int err;
+	int n;
 
 	drv.drv_type = cpu_to_le32(PDS_DRIVER_LINUX);
-	snprintf(drv.driver_ver_str, sizeof(drv.driver_ver_str),
-		 "%s %s", PDS_CORE_DRV_NAME, utsname()->release);
+	/* Catching the return quiets a Wformat-truncation complaint */
+	n = snprintf(drv.driver_ver_str, sizeof(drv.driver_ver_str),
+		     "%s %s", PDS_CORE_DRV_NAME, utsname()->release);
+	if (n > sizeof(drv.driver_ver_str))
+		dev_dbg(pdsc->dev, "release name truncated, don't care\n");
 
 	/* Next let's get some info about the device
 	 * We use the devcmd_lock at this level in order to
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index 57f88c8b37defe..e9948ea5bbcdba 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -104,7 +104,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 	struct pds_core_fw_list_info fw_list;
 	struct pdsc *pdsc = devlink_priv(dl);
 	union pds_core_dev_comp comp;
-	char buf[16];
+	char buf[32];
 	int listlen;
 	int err;
 	int i;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 614c0278419bcf..6b73648b377936 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -682,10 +682,24 @@ static void xgbe_service(struct work_struct *work)
 static void xgbe_service_timer(struct timer_list *t)
 {
 	struct xgbe_prv_data *pdata = from_timer(pdata, t, service_timer);
+	struct xgbe_channel *channel;
+	unsigned int i;
 
 	queue_work(pdata->dev_workqueue, &pdata->service_work);
 
 	mod_timer(&pdata->service_timer, jiffies + HZ);
+
+	if (!pdata->tx_usecs)
+		return;
+
+	for (i = 0; i < pdata->channel_count; i++) {
+		channel = pdata->channel[i];
+		if (!channel->tx_ring || channel->tx_timer_active)
+			break;
+		channel->tx_timer_active = 1;
+		mod_timer(&channel->tx_timer,
+			  jiffies + usecs_to_jiffies(pdata->tx_usecs));
+	}
 }
 
 static void xgbe_init_timers(struct xgbe_prv_data *pdata)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
index 6e83ff59172a36..32fab5e7724626 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
@@ -314,10 +314,15 @@ static int xgbe_get_link_ksettings(struct net_device *netdev,
 
 	cmd->base.phy_address = pdata->phy.address;
 
-	cmd->base.autoneg = pdata->phy.autoneg;
-	cmd->base.speed = pdata->phy.speed;
-	cmd->base.duplex = pdata->phy.duplex;
+	if (netif_carrier_ok(netdev)) {
+		cmd->base.speed = pdata->phy.speed;
+		cmd->base.duplex = pdata->phy.duplex;
+	} else {
+		cmd->base.speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
+	}
 
+	cmd->base.autoneg = pdata->phy.autoneg;
 	cmd->base.port = PORT_NONE;
 
 	XGBE_LM_COPY(cmd, supported, lks, supported);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 32d2c6fac65266..4a2dc705b52801 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -1193,7 +1193,19 @@ static int xgbe_phy_config_fixed(struct xgbe_prv_data *pdata)
 	if (pdata->phy.duplex != DUPLEX_FULL)
 		return -EINVAL;
 
-	xgbe_set_mode(pdata, mode);
+	/* Force the mode change for SFI in Fixed PHY config.
+	 * Fixed PHY configs needs PLL to be enabled while doing mode set.
+	 * When the SFP module isn't connected during boot, driver assumes
+	 * AN is ON and attempts autonegotiation. However, if the connected
+	 * SFP comes up in Fixed PHY config, the link will not come up as
+	 * PLL isn't enabled while the initial mode set command is issued.
+	 * So, force the mode change for SFI in Fixed PHY configuration to
+	 * fix link issues.
+	 */
+	if (mode == XGBE_MODE_SFI)
+		xgbe_change_mode(pdata, mode);
+	else
+		xgbe_set_mode(pdata, mode);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
index 80b44043e6c53f..28c9b6f1a54f14 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
@@ -553,17 +553,17 @@ void aq_ptp_tx_hwtstamp(struct aq_nic_s *aq_nic, u64 timestamp)
 
 /* aq_ptp_rx_hwtstamp - utility function which checks for RX time stamp
  * @adapter: pointer to adapter struct
- * @skb: particular skb to send timestamp with
+ * @shhwtstamps: particular skb_shared_hwtstamps to save timestamp
  *
  * if the timestamp is valid, we convert it into the timecounter ns
  * value, then store that result into the hwtstamps structure which
  * is passed up the network stack
  */
-static void aq_ptp_rx_hwtstamp(struct aq_ptp_s *aq_ptp, struct sk_buff *skb,
+static void aq_ptp_rx_hwtstamp(struct aq_ptp_s *aq_ptp, struct skb_shared_hwtstamps *shhwtstamps,
 			       u64 timestamp)
 {
 	timestamp -= atomic_read(&aq_ptp->offset_ingress);
-	aq_ptp_convert_to_hwtstamp(aq_ptp, skb_hwtstamps(skb), timestamp);
+	aq_ptp_convert_to_hwtstamp(aq_ptp, shhwtstamps, timestamp);
 }
 
 void aq_ptp_hwtstamp_config_get(struct aq_ptp_s *aq_ptp,
@@ -639,7 +639,7 @@ bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring)
 	       &aq_ptp->ptp_rx == ring || &aq_ptp->hwts_rx == ring;
 }
 
-u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct sk_buff *skb, u8 *p,
+u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct skb_shared_hwtstamps *shhwtstamps, u8 *p,
 		      unsigned int len)
 {
 	struct aq_ptp_s *aq_ptp = aq_nic->aq_ptp;
@@ -648,7 +648,7 @@ u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct sk_buff *skb, u8 *p,
 						   p, len, &timestamp);
 
 	if (ret > 0)
-		aq_ptp_rx_hwtstamp(aq_ptp, skb, timestamp);
+		aq_ptp_rx_hwtstamp(aq_ptp, shhwtstamps, timestamp);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h
index 28ccb7ca2df9e7..210b723f22072c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h
@@ -67,7 +67,7 @@ int aq_ptp_hwtstamp_config_set(struct aq_ptp_s *aq_ptp,
 /* Return either ring is belong to PTP or not*/
 bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring);
 
-u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct sk_buff *skb, u8 *p,
+u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct skb_shared_hwtstamps *shhwtstamps, u8 *p,
 		      unsigned int len);
 
 struct ptp_clock *aq_ptp_get_ptp_clock(struct aq_ptp_s *aq_ptp);
@@ -143,7 +143,7 @@ static inline bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring)
 }
 
 static inline u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic,
-				    struct sk_buff *skb, u8 *p,
+				    struct skb_shared_hwtstamps *shhwtstamps, u8 *p,
 				    unsigned int len)
 {
 	return 0;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 4de22eed099a84..e1885c1eb100a1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -647,7 +647,7 @@ static int __aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi,
 		}
 		if (is_ptp_ring)
 			buff->len -=
-				aq_ptp_extract_ts(self->aq_nic, skb,
+				aq_ptp_extract_ts(self->aq_nic, skb_hwtstamps(skb),
 						  aq_buf_vaddr(&buff->rxdata),
 						  buff->len);
 
@@ -742,6 +742,8 @@ static int __aq_ring_xdp_clean(struct aq_ring_s *rx_ring,
 		struct aq_ring_buff_s *buff = &rx_ring->buff_ring[rx_ring->sw_head];
 		bool is_ptp_ring = aq_ptp_ring(rx_ring->aq_nic, rx_ring);
 		struct aq_ring_buff_s *buff_ = NULL;
+		u16 ptp_hwtstamp_len = 0;
+		struct skb_shared_hwtstamps shhwtstamps;
 		struct sk_buff *skb = NULL;
 		unsigned int next_ = 0U;
 		struct xdp_buff xdp;
@@ -810,11 +812,12 @@ static int __aq_ring_xdp_clean(struct aq_ring_s *rx_ring,
 		hard_start = page_address(buff->rxdata.page) +
 			     buff->rxdata.pg_off - rx_ring->page_offset;
 
-		if (is_ptp_ring)
-			buff->len -=
-				aq_ptp_extract_ts(rx_ring->aq_nic, skb,
-						  aq_buf_vaddr(&buff->rxdata),
-						  buff->len);
+		if (is_ptp_ring) {
+			ptp_hwtstamp_len = aq_ptp_extract_ts(rx_ring->aq_nic, &shhwtstamps,
+							     aq_buf_vaddr(&buff->rxdata),
+							     buff->len);
+			buff->len -= ptp_hwtstamp_len;
+		}
 
 		xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq);
 		xdp_prepare_buff(&xdp, hard_start, rx_ring->page_offset,
@@ -834,6 +837,9 @@ static int __aq_ring_xdp_clean(struct aq_ring_s *rx_ring,
 		if (IS_ERR(skb) || !skb)
 			continue;
 
+		if (ptp_hwtstamp_len > 0)
+			*skb_hwtstamps(skb) = shhwtstamps;
+
 		if (buff->is_vlan)
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
 					       buff->vlan_rx_tag);
@@ -932,11 +938,14 @@ void aq_ring_free(struct aq_ring_s *self)
 		return;
 
 	kfree(self->buff_ring);
+	self->buff_ring = NULL;
 
-	if (self->dx_ring)
+	if (self->dx_ring) {
 		dma_free_coherent(aq_nic_get_dev(self->aq_nic),
 				  self->size * self->dx_size, self->dx_ring,
 				  self->dx_ring_pa);
+		self->dx_ring = NULL;
+	}
 }
 
 unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data)
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 5935be190b9e22..5f2a6fcba96708 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -866,10 +866,13 @@ static int atl1e_setup_ring_resources(struct atl1e_adapter *adapter)
 		netdev_err(adapter->netdev, "offset(%d) > ring size(%d) !!\n",
 			   offset, adapter->ring_size);
 		err = -1;
-		goto failed;
+		goto free_buffer;
 	}
 
 	return 0;
+free_buffer:
+	kfree(tx_ring->tx_buffer);
+	tx_ring->tx_buffer = NULL;
 failed:
 	if (adapter->ring_vir_addr != NULL) {
 		dma_free_coherent(&pdev->dev, adapter->ring_size,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d0359b569afeb1..579eebb6fc5663 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1748,16 +1748,32 @@ static void bnxt_tpa_agg(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi,
 			     struct sk_buff *skb)
 {
+	skb_mark_for_recycle(skb);
+
 	if (skb->dev != bp->dev) {
 		/* this packet belongs to a vf-rep */
 		bnxt_vf_rep_rx(bp, skb);
 		return;
 	}
 	skb_record_rx_queue(skb, bnapi->index);
-	skb_mark_for_recycle(skb);
 	napi_gro_receive(&bnapi->napi, skb);
 }
 
+static bool bnxt_rx_ts_valid(struct bnxt *bp, u32 flags,
+			     struct rx_cmp_ext *rxcmp1, u32 *cmpl_ts)
+{
+	u32 ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp);
+
+	if (BNXT_PTP_RX_TS_VALID(flags))
+		goto ts_valid;
+	if (!bp->ptp_all_rx_tstamp || !ts || !BNXT_ALL_RX_TS_VALID(flags))
+		return false;
+
+ts_valid:
+	*cmpl_ts = ts;
+	return true;
+}
+
 /* returns the following:
  * 1       - 1 packet successfully received
  * 0       - successful TPA_START, packet not completed yet
@@ -1783,6 +1799,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	struct sk_buff *skb;
 	struct xdp_buff xdp;
 	u32 flags, misc;
+	u32 cmpl_ts;
 	void *data;
 	int rc = 0;
 
@@ -2005,10 +2022,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		}
 	}
 
-	if (unlikely((flags & RX_CMP_FLAGS_ITYPES_MASK) ==
-		     RX_CMP_FLAGS_ITYPE_PTP_W_TS) || bp->ptp_all_rx_tstamp) {
+	if (bnxt_rx_ts_valid(bp, flags, rxcmp1, &cmpl_ts)) {
 		if (bp->flags & BNXT_FLAG_CHIP_P5) {
-			u32 cmpl_ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp);
 			u64 ns, ts;
 
 			if (!bnxt_get_rx_ts_p5(bp, &ts, cmpl_ts)) {
@@ -10731,10 +10746,8 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	bnxt_free_mem(bp, irq_re_init);
 }
 
-int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
+void bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
-	int rc = 0;
-
 	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		/* If we get here, it means firmware reset is in progress
 		 * while we are trying to close.  We can safely proceed with
@@ -10749,15 +10762,18 @@ int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 
 #ifdef CONFIG_BNXT_SRIOV
 	if (bp->sriov_cfg) {
+		int rc;
+
 		rc = wait_event_interruptible_timeout(bp->sriov_cfg_wait,
 						      !bp->sriov_cfg,
 						      BNXT_SRIOV_CFG_WAIT_TMO);
-		if (rc)
-			netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete!\n");
+		if (!rc)
+			netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete, proceeding to close!\n");
+		else if (rc < 0)
+			netdev_warn(bp->dev, "SRIOV config operation interrupted, proceeding to close!\n");
 	}
 #endif
 	__bnxt_close_nic(bp, irq_re_init, link_re_init);
-	return rc;
 }
 
 static int bnxt_close(struct net_device *dev)
@@ -13940,6 +13956,8 @@ static int bnxt_resume(struct device *device)
 	if (rc)
 		goto resume_exit;
 
+	bnxt_clear_reservations(bp, true);
+
 	if (bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, false)) {
 		rc = -ENODEV;
 		goto resume_exit;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index e702dbc3e6b131..a7d7b09ea16202 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -161,7 +161,7 @@ struct rx_cmp {
 	#define RX_CMP_FLAGS_ERROR				(1 << 6)
 	#define RX_CMP_FLAGS_PLACEMENT				(7 << 7)
 	#define RX_CMP_FLAGS_RSS_VALID				(1 << 10)
-	#define RX_CMP_FLAGS_UNUSED				(1 << 11)
+	#define RX_CMP_FLAGS_PKT_METADATA_PRESENT		(1 << 11)
 	 #define RX_CMP_FLAGS_ITYPES_SHIFT			 12
 	 #define RX_CMP_FLAGS_ITYPES_MASK			 0xf000
 	 #define RX_CMP_FLAGS_ITYPE_UNKNOWN			 (0 << 12)
@@ -188,6 +188,12 @@ struct rx_cmp {
 	__le32 rx_cmp_rss_hash;
 };
 
+#define BNXT_PTP_RX_TS_VALID(flags)				\
+	(((flags) & RX_CMP_FLAGS_ITYPES_MASK) == RX_CMP_FLAGS_ITYPE_PTP_W_TS)
+
+#define BNXT_ALL_RX_TS_VALID(flags)				\
+	!((flags) & RX_CMP_FLAGS_PKT_METADATA_PRESENT)
+
 #define RX_CMP_HASH_VALID(rxcmp)				\
 	((rxcmp)->rx_cmp_len_flags_type & cpu_to_le32(RX_CMP_FLAGS_RSS_VALID))
 
@@ -2375,7 +2381,7 @@ int bnxt_open_nic(struct bnxt *, bool, bool);
 int bnxt_half_open_nic(struct bnxt *bp);
 void bnxt_half_close_nic(struct bnxt *bp);
 void bnxt_reenable_sriov(struct bnxt *bp);
-int bnxt_close_nic(struct bnxt *, bool, bool);
+void bnxt_close_nic(struct bnxt *, bool, bool);
 void bnxt_get_ring_err_stats(struct bnxt *bp,
 			     struct bnxt_total_ring_err_stats *stats);
 int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index f302dac565996d..89809f1b129c0e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -449,15 +449,8 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 			return -ENODEV;
 		}
 		bnxt_ulp_stop(bp);
-		if (netif_running(bp->dev)) {
-			rc = bnxt_close_nic(bp, true, true);
-			if (rc) {
-				NL_SET_ERR_MSG_MOD(extack, "Failed to close");
-				dev_close(bp->dev);
-				rtnl_unlock();
-				break;
-			}
-		}
+		if (netif_running(bp->dev))
+			bnxt_close_nic(bp, true, true);
 		bnxt_vf_reps_free(bp);
 		rc = bnxt_hwrm_func_drv_unrgtr(bp);
 		if (rc) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index f3f384773ac038..5f67a7f94e7d1f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -165,9 +165,8 @@ static int bnxt_set_coalesce(struct net_device *dev,
 reset_coalesce:
 	if (test_bit(BNXT_STATE_OPEN, &bp->state)) {
 		if (update_stats) {
-			rc = bnxt_close_nic(bp, true, false);
-			if (!rc)
-				rc = bnxt_open_nic(bp, true, false);
+			bnxt_close_nic(bp, true, false);
+			rc = bnxt_open_nic(bp, true, false);
 		} else {
 			rc = bnxt_hwrm_set_coal(bp);
 		}
@@ -972,12 +971,7 @@ static int bnxt_set_channels(struct net_device *dev,
 			 * before PF unload
 			 */
 		}
-		rc = bnxt_close_nic(bp, true, false);
-		if (rc) {
-			netdev_err(bp->dev, "Set channel failure rc :%x\n",
-				   rc);
-			return rc;
-		}
+		bnxt_close_nic(bp, true, false);
 	}
 
 	if (sh) {
@@ -4042,12 +4036,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 		bnxt_run_fw_tests(bp, test_mask, &test_results);
 	} else {
 		bnxt_ulp_stop(bp);
-		rc = bnxt_close_nic(bp, true, false);
-		if (rc) {
-			etest->flags |= ETH_TEST_FL_FAILED;
-			bnxt_ulp_start(bp, rc);
-			return;
-		}
+		bnxt_close_nic(bp, true, false);
 		bnxt_run_fw_tests(bp, test_mask, &test_results);
 
 		buf[BNXT_MACLPBK_TEST_IDX] = 1;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index f3886710e77873..6e3da3362bd617 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -521,9 +521,8 @@ static int bnxt_hwrm_ptp_cfg(struct bnxt *bp)
 
 	if (netif_running(bp->dev)) {
 		if (ptp->rx_filter == HWTSTAMP_FILTER_ALL) {
-			rc = bnxt_close_nic(bp, false, false);
-			if (!rc)
-				rc = bnxt_open_nic(bp, false, false);
+			bnxt_close_nic(bp, false, false);
+			rc = bnxt_open_nic(bp, false, false);
 		} else {
 			bnxt_ptp_cfg_tstamp_filters(bp);
 		}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 38d89d80b4a9c7..273c9ba48f09a1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -2075,6 +2075,7 @@ destroy_flow_table:
 	rhashtable_destroy(&tc_info->flow_table);
 free_tc_info:
 	kfree(tc_info);
+	bp->tc_info = NULL;
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 96f5ca778c67d6..8cb9a99154aad9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -59,7 +59,6 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
 	for (i = 0; i < num_frags ; i++) {
 		skb_frag_t *frag = &sinfo->frags[i];
 		struct bnxt_sw_tx_bd *frag_tx_buf;
-		struct pci_dev *pdev = bp->pdev;
 		dma_addr_t frag_mapping;
 		int frag_len;
 
@@ -73,16 +72,10 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
 		txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
 
 		frag_len = skb_frag_size(frag);
-		frag_mapping = skb_frag_dma_map(&pdev->dev, frag, 0,
-						frag_len, DMA_TO_DEVICE);
-
-		if (unlikely(dma_mapping_error(&pdev->dev, frag_mapping)))
-			return NULL;
-
-		dma_unmap_addr_set(frag_tx_buf, mapping, frag_mapping);
-
 		flags = frag_len << TX_BD_LEN_SHIFT;
 		txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
+		frag_mapping = page_pool_get_dma_addr(skb_frag_page(frag)) +
+			       skb_frag_off(frag);
 		txbd->tx_bd_haddr = cpu_to_le64(frag_mapping);
 
 		len = frag_len;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 5665d0c3668fb1..f52830dfb26a1e 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6474,6 +6474,14 @@ static void tg3_dump_state(struct tg3 *tp)
 	int i;
 	u32 *regs;
 
+	/* If it is a PCI error, all registers will be 0xffff,
+	 * we don't dump them out, just report the error and return
+	 */
+	if (tp->pdev->error_state != pci_channel_io_normal) {
+		netdev_err(tp->dev, "PCI channel ERROR!\n");
+		return;
+	}
+
 	regs = kzalloc(TG3_REG_BLK_SIZE, GFP_ATOMIC);
 	if (!regs)
 		return;
@@ -6647,9 +6655,9 @@ static void tg3_tx(struct tg3_napi *tnapi)
 
 	tnapi->tx_cons = sw_idx;
 
-	/* Need to make the tx_cons update visible to tg3_start_xmit()
+	/* Need to make the tx_cons update visible to __tg3_start_xmit()
 	 * before checking for netif_queue_stopped().  Without the
-	 * memory barrier, there is a small possibility that tg3_start_xmit()
+	 * memory barrier, there is a small possibility that __tg3_start_xmit()
 	 * will miss it and cause the queue to be stopped forever.
 	 */
 	smp_mb();
@@ -6889,7 +6897,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 				       desc_idx, *post_ptr);
 		drop_it_no_recycle:
 			/* Other statistics kept track of by card. */
-			tp->rx_dropped++;
+			tnapi->rx_dropped++;
 			goto next_pkt;
 		}
 
@@ -7889,7 +7897,7 @@ static bool tg3_tso_bug_gso_check(struct tg3_napi *tnapi, struct sk_buff *skb)
 	return skb_shinfo(skb)->gso_segs < tnapi->tx_pending / 3;
 }
 
-static netdev_tx_t tg3_start_xmit(struct sk_buff *, struct net_device *);
+static netdev_tx_t __tg3_start_xmit(struct sk_buff *, struct net_device *);
 
 /* Use GSO to workaround all TSO packets that meet HW bug conditions
  * indicated in tg3_tx_frag_set()
@@ -7918,12 +7926,14 @@ static int tg3_tso_bug(struct tg3 *tp, struct tg3_napi *tnapi,
 
 	segs = skb_gso_segment(skb, tp->dev->features &
 				    ~(NETIF_F_TSO | NETIF_F_TSO6));
-	if (IS_ERR(segs) || !segs)
+	if (IS_ERR(segs) || !segs) {
+		tnapi->tx_dropped++;
 		goto tg3_tso_bug_end;
+	}
 
 	skb_list_walk_safe(segs, seg, next) {
 		skb_mark_not_on_list(seg);
-		tg3_start_xmit(seg, tp->dev);
+		__tg3_start_xmit(seg, tp->dev);
 	}
 
 tg3_tso_bug_end:
@@ -7933,7 +7943,7 @@ tg3_tso_bug_end:
 }
 
 /* hard_start_xmit for all devices */
-static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t __tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct tg3 *tp = netdev_priv(dev);
 	u32 len, entry, base_flags, mss, vlan = 0;
@@ -8182,11 +8192,6 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			netif_tx_wake_queue(txq);
 	}
 
-	if (!netdev_xmit_more() || netif_xmit_stopped(txq)) {
-		/* Packets are ready, update Tx producer idx on card. */
-		tw32_tx_mbox(tnapi->prodmbox, entry);
-	}
-
 	return NETDEV_TX_OK;
 
 dma_error:
@@ -8195,10 +8200,46 @@ dma_error:
 drop:
 	dev_kfree_skb_any(skb);
 drop_nofree:
-	tp->tx_dropped++;
+	tnapi->tx_dropped++;
 	return NETDEV_TX_OK;
 }
 
+static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct netdev_queue *txq;
+	u16 skb_queue_mapping;
+	netdev_tx_t ret;
+
+	skb_queue_mapping = skb_get_queue_mapping(skb);
+	txq = netdev_get_tx_queue(dev, skb_queue_mapping);
+
+	ret = __tg3_start_xmit(skb, dev);
+
+	/* Notify the hardware that packets are ready by updating the TX ring
+	 * tail pointer. We respect netdev_xmit_more() thus avoiding poking
+	 * the hardware for every packet. To guarantee forward progress the TX
+	 * ring must be drained when it is full as indicated by
+	 * netif_xmit_stopped(). This needs to happen even when the current
+	 * skb was dropped or rejected with NETDEV_TX_BUSY. Otherwise packets
+	 * queued by previous __tg3_start_xmit() calls might get stuck in
+	 * the queue forever.
+	 */
+	if (!netdev_xmit_more() || netif_xmit_stopped(txq)) {
+		struct tg3_napi *tnapi;
+		struct tg3 *tp;
+
+		tp = netdev_priv(dev);
+		tnapi = &tp->napi[skb_queue_mapping];
+
+		if (tg3_flag(tp, ENABLE_TSS))
+			tnapi++;
+
+		tw32_tx_mbox(tnapi->prodmbox, tnapi->tx_prod);
+	}
+
+	return ret;
+}
+
 static void tg3_mac_loopback(struct tg3 *tp, bool enable)
 {
 	if (enable) {
@@ -9374,7 +9415,7 @@ static void __tg3_set_rx_mode(struct net_device *);
 /* tp->lock is held. */
 static int tg3_halt(struct tg3 *tp, int kind, bool silent)
 {
-	int err;
+	int err, i;
 
 	tg3_stop_fw(tp);
 
@@ -9395,6 +9436,13 @@ static int tg3_halt(struct tg3 *tp, int kind, bool silent)
 
 		/* And make sure the next sample is new data */
 		memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats));
+
+		for (i = 0; i < TG3_IRQ_MAX_VECS; ++i) {
+			struct tg3_napi *tnapi = &tp->napi[i];
+
+			tnapi->rx_dropped = 0;
+			tnapi->tx_dropped = 0;
+		}
 	}
 
 	return err;
@@ -11219,7 +11267,8 @@ static void tg3_reset_task(struct work_struct *work)
 	rtnl_lock();
 	tg3_full_lock(tp, 0);
 
-	if (tp->pcierr_recovery || !netif_running(tp->dev)) {
+	if (tp->pcierr_recovery || !netif_running(tp->dev) ||
+	    tp->pdev->error_state != pci_channel_io_normal) {
 		tg3_flag_clear(tp, RESET_TASK_PENDING);
 		tg3_full_unlock(tp);
 		rtnl_unlock();
@@ -11944,6 +11993,9 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats)
 {
 	struct rtnl_link_stats64 *old_stats = &tp->net_stats_prev;
 	struct tg3_hw_stats *hw_stats = tp->hw_stats;
+	unsigned long rx_dropped;
+	unsigned long tx_dropped;
+	int i;
 
 	stats->rx_packets = old_stats->rx_packets +
 		get_stat64(&hw_stats->rx_ucast_packets) +
@@ -11990,8 +12042,26 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats)
 	stats->rx_missed_errors = old_stats->rx_missed_errors +
 		get_stat64(&hw_stats->rx_discards);
 
-	stats->rx_dropped = tp->rx_dropped;
-	stats->tx_dropped = tp->tx_dropped;
+	/* Aggregate per-queue counters. The per-queue counters are updated
+	 * by a single writer, race-free. The result computed by this loop
+	 * might not be 100% accurate (counters can be updated in the middle of
+	 * the loop) but the next tg3_get_nstats() will recompute the current
+	 * value so it is acceptable.
+	 *
+	 * Note that these counters wrap around at 4G on 32bit machines.
+	 */
+	rx_dropped = (unsigned long)(old_stats->rx_dropped);
+	tx_dropped = (unsigned long)(old_stats->tx_dropped);
+
+	for (i = 0; i < tp->irq_cnt; i++) {
+		struct tg3_napi *tnapi = &tp->napi[i];
+
+		rx_dropped += tnapi->rx_dropped;
+		tx_dropped += tnapi->tx_dropped;
+	}
+
+	stats->rx_dropped = rx_dropped;
+	stats->tx_dropped = tx_dropped;
 }
 
 static int tg3_get_regs_len(struct net_device *dev)
@@ -17729,7 +17799,7 @@ static int tg3_init_one(struct pci_dev *pdev,
 	 * device behind the EPB cannot support DMA addresses > 40-bit.
 	 * On 64-bit systems with IOMMU, use 40-bit dma_mask.
 	 * On 64-bit systems without IOMMU, use 64-bit dma_mask and
-	 * do DMA address check in tg3_start_xmit().
+	 * do DMA address check in __tg3_start_xmit().
 	 */
 	if (tg3_flag(tp, IS_5788))
 		persist_dma_mask = dma_mask = DMA_BIT_MASK(32);
@@ -18127,7 +18197,8 @@ static void tg3_shutdown(struct pci_dev *pdev)
 	if (netif_running(dev))
 		dev_close(dev);
 
-	tg3_power_down(tp);
+	if (system_state == SYSTEM_POWER_OFF)
+		tg3_power_down(tp);
 
 	rtnl_unlock();
 
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index ae5c01bd111043..5016475e50054d 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -3018,6 +3018,7 @@ struct tg3_napi {
 	u16				*rx_rcb_prod_idx;
 	struct tg3_rx_prodring_set	prodring;
 	struct tg3_rx_buffer_desc	*rx_rcb;
+	unsigned long			rx_dropped;
 
 	u32				tx_prod	____cacheline_aligned;
 	u32				tx_cons;
@@ -3026,6 +3027,7 @@ struct tg3_napi {
 	u32				prodmbox;
 	struct tg3_tx_buffer_desc	*tx_ring;
 	struct tg3_tx_ring_info		*tx_buffers;
+	unsigned long			tx_dropped;
 
 	dma_addr_t			status_mapping;
 	dma_addr_t			rx_rcb_mapping;
@@ -3220,8 +3222,6 @@ struct tg3 {
 
 
 	/* begin "everything else" cacheline(s) section */
-	unsigned long			rx_dropped;
-	unsigned long			tx_dropped;
 	struct rtnl_link_stats64	net_stats_prev;
 	struct tg3_ethtool_stats	estats_prev;
 
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 5423fe26b4ef02..78287cfcbf6388 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -432,8 +432,8 @@ static const struct gmac_max_framelen gmac_maxlens[] = {
 		.val = CONFIG0_MAXLEN_1536,
 	},
 	{
-		.max_l3_len = 1542,
-		.val = CONFIG0_MAXLEN_1542,
+		.max_l3_len = 1548,
+		.val = CONFIG0_MAXLEN_1548,
 	},
 	{
 		.max_l3_len = 9212,
@@ -1145,6 +1145,7 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 	dma_addr_t mapping;
 	unsigned short mtu;
 	void *buffer;
+	int ret;
 
 	mtu  = ETH_HLEN;
 	mtu += netdev->mtu;
@@ -1159,9 +1160,30 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 		word3 |= mtu;
 	}
 
-	if (skb->ip_summed != CHECKSUM_NONE) {
+	if (skb->len >= ETH_FRAME_LEN) {
+		/* Hardware offloaded checksumming isn't working on frames
+		 * bigger than 1514 bytes. A hypothesis about this is that the
+		 * checksum buffer is only 1518 bytes, so when the frames get
+		 * bigger they get truncated, or the last few bytes get
+		 * overwritten by the FCS.
+		 *
+		 * Just use software checksumming and bypass on bigger frames.
+		 */
+		if (skb->ip_summed == CHECKSUM_PARTIAL) {
+			ret = skb_checksum_help(skb);
+			if (ret)
+				return ret;
+		}
+		word1 |= TSS_BYPASS_BIT;
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		int tcp = 0;
 
+		/* We do not switch off the checksumming on non TCP/UDP
+		 * frames: as is shown from tests, the checksumming engine
+		 * is smart enough to see that a frame is not actually TCP
+		 * or UDP and then just pass it through without any changes
+		 * to the frame.
+		 */
 		if (skb->protocol == htons(ETH_P_IP)) {
 			word1 |= TSS_IP_CHKSUM_BIT;
 			tcp = ip_hdr(skb)->protocol == IPPROTO_TCP;
@@ -1978,15 +2000,6 @@ static int gmac_change_mtu(struct net_device *netdev, int new_mtu)
 	return 0;
 }
 
-static netdev_features_t gmac_fix_features(struct net_device *netdev,
-					   netdev_features_t features)
-{
-	if (netdev->mtu + ETH_HLEN + VLAN_HLEN > MTU_SIZE_BIT_MASK)
-		features &= ~GMAC_OFFLOAD_FEATURES;
-
-	return features;
-}
-
 static int gmac_set_features(struct net_device *netdev,
 			     netdev_features_t features)
 {
@@ -2212,7 +2225,6 @@ static const struct net_device_ops gmac_351x_ops = {
 	.ndo_set_mac_address	= gmac_set_mac_address,
 	.ndo_get_stats64	= gmac_get_stats64,
 	.ndo_change_mtu		= gmac_change_mtu,
-	.ndo_fix_features	= gmac_fix_features,
 	.ndo_set_features	= gmac_set_features,
 };
 
@@ -2464,11 +2476,12 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 
 	netdev->hw_features = GMAC_OFFLOAD_FEATURES;
 	netdev->features |= GMAC_OFFLOAD_FEATURES | NETIF_F_GRO;
-	/* We can handle jumbo frames up to 10236 bytes so, let's accept
-	 * payloads of 10236 bytes minus VLAN and ethernet header
+	/* We can receive jumbo frames up to 10236 bytes but only
+	 * transmit 2047 bytes so, let's accept payloads of 2047
+	 * bytes minus VLAN and ethernet header
 	 */
 	netdev->min_mtu = ETH_MIN_MTU;
-	netdev->max_mtu = 10236 - VLAN_ETH_HLEN;
+	netdev->max_mtu = MTU_SIZE_BIT_MASK - VLAN_ETH_HLEN;
 
 	port->freeq_refill = 0;
 	netif_napi_add(netdev, &port->napi, gmac_napi_poll);
diff --git a/drivers/net/ethernet/cortina/gemini.h b/drivers/net/ethernet/cortina/gemini.h
index 9fdf77d5eb3740..24bb989981f233 100644
--- a/drivers/net/ethernet/cortina/gemini.h
+++ b/drivers/net/ethernet/cortina/gemini.h
@@ -502,7 +502,7 @@ union gmac_txdesc_3 {
 #define SOF_BIT			0x80000000
 #define EOF_BIT			0x40000000
 #define EOFIE_BIT		BIT(29)
-#define MTU_SIZE_BIT_MASK	0x1fff
+#define MTU_SIZE_BIT_MASK	0x7ff /* Max MTU 2047 bytes */
 
 /* GMAC Tx Descriptor */
 struct gmac_txdesc {
@@ -787,7 +787,7 @@ union gmac_config0 {
 #define  CONFIG0_MAXLEN_1536	0
 #define  CONFIG0_MAXLEN_1518	1
 #define  CONFIG0_MAXLEN_1522	2
-#define  CONFIG0_MAXLEN_1542	3
+#define  CONFIG0_MAXLEN_1548	3
 #define  CONFIG0_MAXLEN_9k	4	/* 9212 */
 #define  CONFIG0_MAXLEN_10k	5	/* 10236 */
 #define  CONFIG0_MAXLEN_1518__6	6
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 15bab41cee48df..888509cf1f210e 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -516,8 +516,6 @@ struct sk_buff *dpaa2_eth_alloc_skb(struct dpaa2_eth_priv *priv,
 
 	memcpy(skb->data, fd_vaddr + fd_offset, fd_length);
 
-	dpaa2_eth_recycle_buf(priv, ch, dpaa2_fd_get_addr(fd));
-
 	return skb;
 }
 
@@ -589,6 +587,7 @@ void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	struct rtnl_link_stats64 *percpu_stats;
 	struct dpaa2_eth_drv_stats *percpu_extras;
 	struct device *dev = priv->net_dev->dev.parent;
+	bool recycle_rx_buf = false;
 	void *buf_data;
 	u32 xdp_act;
 
@@ -618,6 +617,8 @@ void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 			dma_unmap_page(dev, addr, priv->rx_buf_size,
 				       DMA_BIDIRECTIONAL);
 			skb = dpaa2_eth_build_linear_skb(ch, fd, vaddr);
+		} else {
+			recycle_rx_buf = true;
 		}
 	} else if (fd_format == dpaa2_fd_sg) {
 		WARN_ON(priv->xdp_prog);
@@ -637,6 +638,9 @@ void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 		goto err_build_skb;
 
 	dpaa2_eth_receive_skb(priv, ch, fd, vaddr, fq, percpu_stats, skb);
+
+	if (recycle_rx_buf)
+		dpaa2_eth_recycle_buf(priv, ch, dpaa2_fd_get_addr(fd));
 	return;
 
 err_build_skb:
@@ -1073,14 +1077,12 @@ static int dpaa2_eth_build_single_fd(struct dpaa2_eth_priv *priv,
 	dma_addr_t addr;
 
 	buffer_start = skb->data - dpaa2_eth_needed_headroom(skb);
-
-	/* If there's enough room to align the FD address, do it.
-	 * It will help hardware optimize accesses.
-	 */
 	aligned_start = PTR_ALIGN(buffer_start - DPAA2_ETH_TX_BUF_ALIGN,
 				  DPAA2_ETH_TX_BUF_ALIGN);
 	if (aligned_start >= skb->head)
 		buffer_start = aligned_start;
+	else
+		return -ENOMEM;
 
 	/* Store a backpointer to the skb at the beginning of the buffer
 	 * (in the private data area) such that we can release it
@@ -4967,6 +4969,8 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 	if (err)
 		goto err_dl_port_add;
 
+	net_dev->needed_headroom = DPAA2_ETH_SWA_SIZE + DPAA2_ETH_TX_BUF_ALIGN;
+
 	err = register_netdev(net_dev);
 	if (err < 0) {
 		dev_err(dev, "register_netdev() failed\n");
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index bfb6c96c3b2f08..834cba8c3a4163 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -740,7 +740,7 @@ static inline bool dpaa2_eth_rx_pause_enabled(u64 link_options)
 
 static inline unsigned int dpaa2_eth_needed_headroom(struct sk_buff *skb)
 {
-	unsigned int headroom = DPAA2_ETH_SWA_SIZE;
+	unsigned int headroom = DPAA2_ETH_SWA_SIZE + DPAA2_ETH_TX_BUF_ALIGN;
 
 	/* If we don't have an skb (e.g. XDP buffer), we only need space for
 	 * the software annotation area
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
index 4798fb7fe35d14..b6a534a3e0b123 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
@@ -139,7 +139,8 @@ int dpaa2_switch_acl_entry_add(struct dpaa2_switch_filter_block *filter_block,
 	err = dpsw_acl_add_entry(ethsw->mc_io, 0, ethsw->dpsw_handle,
 				 filter_block->acl_id, acl_entry_cfg);
 
-	dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff),
+	dma_unmap_single(dev, acl_entry_cfg->key_iova,
+			 DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE,
 			 DMA_TO_DEVICE);
 	if (err) {
 		dev_err(dev, "dpsw_acl_add_entry() failed %d\n", err);
@@ -181,8 +182,8 @@ dpaa2_switch_acl_entry_remove(struct dpaa2_switch_filter_block *block,
 	err = dpsw_acl_remove_entry(ethsw->mc_io, 0, ethsw->dpsw_handle,
 				    block->acl_id, acl_entry_cfg);
 
-	dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff),
-			 DMA_TO_DEVICE);
+	dma_unmap_single(dev, acl_entry_cfg->key_iova,
+			 DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE, DMA_TO_DEVICE);
 	if (err) {
 		dev_err(dev, "dpsw_acl_remove_entry() failed %d\n", err);
 		kfree(cmd_buff);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index 97d3151076d534..e01a246124ac69 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -1998,9 +1998,6 @@ static int dpaa2_switch_port_attr_set_event(struct net_device *netdev,
 	return notifier_from_errno(err);
 }
 
-static struct notifier_block dpaa2_switch_port_switchdev_nb;
-static struct notifier_block dpaa2_switch_port_switchdev_blocking_nb;
-
 static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 					 struct net_device *upper_dev,
 					 struct netlink_ext_ack *extack)
@@ -2043,9 +2040,7 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 		goto err_egress_flood;
 
 	err = switchdev_bridge_port_offload(netdev, netdev, NULL,
-					    &dpaa2_switch_port_switchdev_nb,
-					    &dpaa2_switch_port_switchdev_blocking_nb,
-					    false, extack);
+					    NULL, NULL, false, extack);
 	if (err)
 		goto err_switchdev_offload;
 
@@ -2079,9 +2074,7 @@ static int dpaa2_switch_port_restore_rxvlan(struct net_device *vdev, int vid, vo
 
 static void dpaa2_switch_port_pre_bridge_leave(struct net_device *netdev)
 {
-	switchdev_bridge_port_unoffload(netdev, NULL,
-					&dpaa2_switch_port_switchdev_nb,
-					&dpaa2_switch_port_switchdev_blocking_nb);
+	switchdev_bridge_port_unoffload(netdev, NULL, NULL, NULL);
 }
 
 static int dpaa2_switch_port_bridge_leave(struct net_device *netdev)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 30bec47bc665bf..cffbf27c4656b2 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -2769,7 +2769,7 @@ static int enetc_setup_xdp_prog(struct net_device *ndev, struct bpf_prog *prog,
 	if (priv->min_num_stack_tx_queues + num_xdp_tx_queues >
 	    priv->num_tx_rings) {
 		NL_SET_ERR_MSG_FMT_MOD(extack,
-				       "Reserving %d XDP TXQs does not leave a minimum of %d TXQs for network stack (total %d available)",
+				       "Reserving %d XDP TXQs does not leave a minimum of %d for stack (total %d)",
 				       num_xdp_tx_queues,
 				       priv->min_num_stack_tx_queues,
 				       priv->num_tx_rings);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index c3b7694a74851c..e08c7b572497d3 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3731,31 +3731,26 @@ static int fec_set_features(struct net_device *netdev,
 	return 0;
 }
 
-static u16 fec_enet_get_raw_vlan_tci(struct sk_buff *skb)
-{
-	struct vlan_ethhdr *vhdr;
-	unsigned short vlan_TCI = 0;
-
-	if (skb->protocol == htons(ETH_P_ALL)) {
-		vhdr = (struct vlan_ethhdr *)(skb->data);
-		vlan_TCI = ntohs(vhdr->h_vlan_TCI);
-	}
-
-	return vlan_TCI;
-}
-
 static u16 fec_enet_select_queue(struct net_device *ndev, struct sk_buff *skb,
 				 struct net_device *sb_dev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	u16 vlan_tag;
+	u16 vlan_tag = 0;
 
 	if (!(fep->quirks & FEC_QUIRK_HAS_AVB))
 		return netdev_pick_tx(ndev, skb, NULL);
 
-	vlan_tag = fec_enet_get_raw_vlan_tci(skb);
-	if (!vlan_tag)
+	/* VLAN is present in the payload.*/
+	if (eth_type_vlan(skb->protocol)) {
+		struct vlan_ethhdr *vhdr = skb_vlan_eth_hdr(skb);
+
+		vlan_tag = ntohs(vhdr->h_vlan_TCI);
+	/*  VLAN is present in the skb but not yet pushed in the payload.*/
+	} else if (skb_vlan_tag_present(skb)) {
+		vlan_tag = skb->vlan_tci;
+	} else {
 		return vlan_tag;
+	}
 
 	return fec_enet_vlan_pri_to_queue[vlan_tag >> 13];
 }
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 276f996f95dcc8..2d42e733837b0d 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -254,10 +254,13 @@ static int gve_napi_poll(struct napi_struct *napi, int budget)
 	if (block->tx) {
 		if (block->tx->q_num < priv->tx_cfg.num_queues)
 			reschedule |= gve_tx_poll(block, budget);
-		else
+		else if (budget)
 			reschedule |= gve_xdp_poll(block, budget);
 	}
 
+	if (!budget)
+		return 0;
+
 	if (block->rx) {
 		work_done = gve_rx_poll(block, budget);
 		reschedule |= work_done == budget;
@@ -298,6 +301,9 @@ static int gve_napi_poll_dqo(struct napi_struct *napi, int budget)
 	if (block->tx)
 		reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true);
 
+	if (!budget)
+		return 0;
+
 	if (block->rx) {
 		work_done = gve_rx_poll_dqo(block, budget);
 		reschedule |= work_done == budget;
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index e84a066aa1a40a..73655347902d2d 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -1007,10 +1007,6 @@ int gve_rx_poll(struct gve_notify_block *block, int budget)
 
 	feat = block->napi.dev->features;
 
-	/* If budget is 0, do all the work */
-	if (budget == 0)
-		budget = INT_MAX;
-
 	if (budget > 0)
 		work_done = gve_clean_rx_done(rx, budget, feat);
 
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index 6957a865cff37c..9f6ffc4a54f0bb 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -925,10 +925,6 @@ bool gve_xdp_poll(struct gve_notify_block *block, int budget)
 	bool repoll;
 	u32 to_do;
 
-	/* If budget is 0, do all the work */
-	if (budget == 0)
-		budget = INT_MAX;
-
 	/* Find out how much work there is to be done */
 	nic_done = gve_tx_load_event_counter(priv, tx);
 	to_do = min_t(u32, (nic_done - tx->done), budget);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index 928d934cb21a5a..f75668c4793519 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -66,6 +66,27 @@ static enum mac_mode hns_get_enet_interface(const struct hns_mac_cb *mac_cb)
 	}
 }
 
+static u32 hns_mac_link_anti_shake(struct mac_driver *mac_ctrl_drv)
+{
+#define HNS_MAC_LINK_WAIT_TIME 5
+#define HNS_MAC_LINK_WAIT_CNT 40
+
+	u32 link_status = 0;
+	int i;
+
+	if (!mac_ctrl_drv->get_link_status)
+		return link_status;
+
+	for (i = 0; i < HNS_MAC_LINK_WAIT_CNT; i++) {
+		msleep(HNS_MAC_LINK_WAIT_TIME);
+		mac_ctrl_drv->get_link_status(mac_ctrl_drv, &link_status);
+		if (!link_status)
+			break;
+	}
+
+	return link_status;
+}
+
 void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status)
 {
 	struct mac_driver *mac_ctrl_drv;
@@ -83,6 +104,14 @@ void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status)
 							       &sfp_prsnt);
 		if (!ret)
 			*link_status = *link_status && sfp_prsnt;
+
+		/* for FIBER port, it may have a fake link up.
+		 * when the link status changes from down to up, we need to do
+		 * anti-shake. the anti-shake time is base on tests.
+		 * only FIBER port need to do this.
+		 */
+		if (*link_status && !mac_cb->link)
+			*link_status = hns_mac_link_anti_shake(mac_ctrl_drv);
 	}
 
 	mac_cb->link = *link_status;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 0900abf5c5086b..8a713eed446582 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -142,7 +142,8 @@ MODULE_DEVICE_TABLE(acpi, hns_enet_acpi_match);
 
 static void fill_desc(struct hnae_ring *ring, void *priv,
 		      int size, dma_addr_t dma, int frag_end,
-		      int buf_num, enum hns_desc_type type, int mtu)
+		      int buf_num, enum hns_desc_type type, int mtu,
+		      bool is_gso)
 {
 	struct hnae_desc *desc = &ring->desc[ring->next_to_use];
 	struct hnae_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
@@ -275,6 +276,15 @@ static int hns_nic_maybe_stop_tso(
 	return 0;
 }
 
+static int hns_nic_maybe_stop_tx_v2(struct sk_buff **out_skb, int *bnum,
+				    struct hnae_ring *ring)
+{
+	if (skb_is_gso(*out_skb))
+		return hns_nic_maybe_stop_tso(out_skb, bnum, ring);
+	else
+		return hns_nic_maybe_stop_tx(out_skb, bnum, ring);
+}
+
 static void fill_tso_desc(struct hnae_ring *ring, void *priv,
 			  int size, dma_addr_t dma, int frag_end,
 			  int buf_num, enum hns_desc_type type, int mtu)
@@ -300,6 +310,19 @@ static void fill_tso_desc(struct hnae_ring *ring, void *priv,
 				mtu);
 }
 
+static void fill_desc_v2(struct hnae_ring *ring, void *priv,
+			 int size, dma_addr_t dma, int frag_end,
+			 int buf_num, enum hns_desc_type type, int mtu,
+			 bool is_gso)
+{
+	if (is_gso)
+		fill_tso_desc(ring, priv, size, dma, frag_end, buf_num, type,
+			      mtu);
+	else
+		fill_v2_desc(ring, priv, size, dma, frag_end, buf_num, type,
+			     mtu);
+}
+
 netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev,
 				struct sk_buff *skb,
 				struct hns_nic_ring_data *ring_data)
@@ -313,6 +336,7 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev,
 	int seg_num;
 	dma_addr_t dma;
 	int size, next_to_use;
+	bool is_gso;
 	int i;
 
 	switch (priv->ops.maybe_stop_tx(&skb, &buf_num, ring)) {
@@ -339,8 +363,9 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev,
 		ring->stats.sw_err_cnt++;
 		goto out_err_tx_ok;
 	}
+	is_gso = skb_is_gso(skb);
 	priv->ops.fill_desc(ring, skb, size, dma, seg_num == 1 ? 1 : 0,
-			    buf_num, DESC_TYPE_SKB, ndev->mtu);
+			    buf_num, DESC_TYPE_SKB, ndev->mtu, is_gso);
 
 	/* fill the fragments */
 	for (i = 1; i < seg_num; i++) {
@@ -354,7 +379,7 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev,
 		}
 		priv->ops.fill_desc(ring, skb_frag_page(frag), size, dma,
 				    seg_num - 1 == i ? 1 : 0, buf_num,
-				    DESC_TYPE_PAGE, ndev->mtu);
+				    DESC_TYPE_PAGE, ndev->mtu, is_gso);
 	}
 
 	/*complete translate all packets*/
@@ -1776,15 +1801,6 @@ static int hns_nic_set_features(struct net_device *netdev,
 			netdev_info(netdev, "enet v1 do not support tso!\n");
 		break;
 	default:
-		if (features & (NETIF_F_TSO | NETIF_F_TSO6)) {
-			priv->ops.fill_desc = fill_tso_desc;
-			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tso;
-			/* The chip only support 7*4096 */
-			netif_set_tso_max_size(netdev, 7 * 4096);
-		} else {
-			priv->ops.fill_desc = fill_v2_desc;
-			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx;
-		}
 		break;
 	}
 	netdev->features = features;
@@ -2159,16 +2175,9 @@ static void hns_nic_set_priv_ops(struct net_device *netdev)
 		priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx;
 	} else {
 		priv->ops.get_rxd_bnum = get_v2rx_desc_bnum;
-		if ((netdev->features & NETIF_F_TSO) ||
-		    (netdev->features & NETIF_F_TSO6)) {
-			priv->ops.fill_desc = fill_tso_desc;
-			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tso;
-			/* This chip only support 7*4096 */
-			netif_set_tso_max_size(netdev, 7 * 4096);
-		} else {
-			priv->ops.fill_desc = fill_v2_desc;
-			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx;
-		}
+		priv->ops.fill_desc = fill_desc_v2;
+		priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx_v2;
+		netif_set_tso_max_size(netdev, 7 * 4096);
 		/* enable tso when init
 		 * control tso on/off through TSE bit in bd
 		 */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
index ffa9d6573f54bc..3f3ee032f631c4 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
@@ -44,7 +44,8 @@ struct hns_nic_ring_data {
 struct hns_nic_ops {
 	void (*fill_desc)(struct hnae_ring *ring, void *priv,
 			  int size, dma_addr_t dma, int frag_end,
-			  int buf_num, enum hns_desc_type type, int mtu);
+			  int buf_num, enum hns_desc_type type, int mtu,
+			  bool is_gso);
 	int (*maybe_stop_tx)(struct sk_buff **out_skb,
 			     int *bnum, struct hnae_ring *ring);
 	void (*get_rxd_bnum)(u32 bnum_flag, int *out_bnum);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 0b138635bafa9d..c083d1d10767bb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -503,11 +503,14 @@ static void hns3_get_coal_info(struct hns3_enet_tqp_vector *tqp_vector,
 	}
 
 	sprintf(result[j++], "%d", i);
-	sprintf(result[j++], "%s", dim_state_str[dim->state]);
+	sprintf(result[j++], "%s", dim->state < ARRAY_SIZE(dim_state_str) ?
+		dim_state_str[dim->state] : "unknown");
 	sprintf(result[j++], "%u", dim->profile_ix);
-	sprintf(result[j++], "%s", dim_cqe_mode_str[dim->mode]);
+	sprintf(result[j++], "%s", dim->mode < ARRAY_SIZE(dim_cqe_mode_str) ?
+		dim_cqe_mode_str[dim->mode] : "unknown");
 	sprintf(result[j++], "%s",
-		dim_tune_stat_str[dim->tune_state]);
+		dim->tune_state < ARRAY_SIZE(dim_tune_stat_str) ?
+		dim_tune_stat_str[dim->tune_state] : "unknown");
 	sprintf(result[j++], "%u", dim->steps_left);
 	sprintf(result[j++], "%u", dim->steps_right);
 	sprintf(result[j++], "%u", dim->tired);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 06117502001f92..b618797a7e8de2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -5139,7 +5139,7 @@ static int hns3_init_mac_addr(struct net_device *netdev)
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	char format_mac_addr[HNAE3_FORMAT_MAC_ADDR_LEN];
 	struct hnae3_handle *h = priv->ae_handle;
-	u8 mac_addr_temp[ETH_ALEN];
+	u8 mac_addr_temp[ETH_ALEN] = {0};
 	int ret = 0;
 
 	if (h->ae_algo->ops->get_mac_addr)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 66e5807903a02a..5ea9e59569effb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -61,6 +61,7 @@ static void hclge_sync_fd_table(struct hclge_dev *hdev);
 static void hclge_update_fec_stats(struct hclge_dev *hdev);
 static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret,
 				      int wait_cnt);
+static int hclge_update_port_info(struct hclge_dev *hdev);
 
 static struct hnae3_ae_algo ae_algo;
 
@@ -3041,6 +3042,9 @@ static void hclge_update_link_status(struct hclge_dev *hdev)
 
 	if (state != hdev->hw.mac.link) {
 		hdev->hw.mac.link = state;
+		if (state == HCLGE_LINK_STATUS_UP)
+			hclge_update_port_info(hdev);
+
 		client->ops->link_status_change(handle, state);
 		hclge_config_mac_tnl_int(hdev, state);
 		if (rclient && rclient->ops->link_status_change)
@@ -10025,8 +10029,6 @@ static void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id,
 	struct hclge_vport_vlan_cfg *vlan, *tmp;
 	struct hclge_dev *hdev = vport->back;
 
-	mutex_lock(&hdev->vport_lock);
-
 	list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) {
 		if (vlan->vlan_id == vlan_id) {
 			if (is_write_tbl && vlan->hd_tbl_status)
@@ -10041,8 +10043,6 @@ static void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id,
 			break;
 		}
 	}
-
-	mutex_unlock(&hdev->vport_lock);
 }
 
 void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list)
@@ -10451,11 +10451,16 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
 	 * handle mailbox. Just record the vlan id, and remove it after
 	 * reset finished.
 	 */
+	mutex_lock(&hdev->vport_lock);
 	if ((test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
 	     test_bit(HCLGE_STATE_RST_FAIL, &hdev->state)) && is_kill) {
 		set_bit(vlan_id, vport->vlan_del_fail_bmap);
+		mutex_unlock(&hdev->vport_lock);
 		return -EBUSY;
+	} else if (!is_kill && test_bit(vlan_id, vport->vlan_del_fail_bmap)) {
+		clear_bit(vlan_id, vport->vlan_del_fail_bmap);
 	}
+	mutex_unlock(&hdev->vport_lock);
 
 	/* when port base vlan enabled, we use port base vlan as the vlan
 	 * filter entry. In this case, we don't update vlan filter table
@@ -10470,17 +10475,22 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
 	}
 
 	if (!ret) {
-		if (!is_kill)
+		if (!is_kill) {
 			hclge_add_vport_vlan_table(vport, vlan_id,
 						   writen_to_tbl);
-		else if (is_kill && vlan_id != 0)
+		} else if (is_kill && vlan_id != 0) {
+			mutex_lock(&hdev->vport_lock);
 			hclge_rm_vport_vlan_table(vport, vlan_id, false);
+			mutex_unlock(&hdev->vport_lock);
+		}
 	} else if (is_kill) {
 		/* when remove hw vlan filter failed, record the vlan id,
 		 * and try to remove it from hw later, to be consistence
 		 * with stack
 		 */
+		mutex_lock(&hdev->vport_lock);
 		set_bit(vlan_id, vport->vlan_del_fail_bmap);
+		mutex_unlock(&hdev->vport_lock);
 	}
 
 	hclge_set_vport_vlan_fltr_change(vport);
@@ -10520,6 +10530,7 @@ static void hclge_sync_vlan_filter(struct hclge_dev *hdev)
 	int i, ret, sync_cnt = 0;
 	u16 vlan_id;
 
+	mutex_lock(&hdev->vport_lock);
 	/* start from vport 1 for PF is always alive */
 	for (i = 0; i < hdev->num_alloc_vport; i++) {
 		struct hclge_vport *vport = &hdev->vport[i];
@@ -10530,21 +10541,26 @@ static void hclge_sync_vlan_filter(struct hclge_dev *hdev)
 			ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q),
 						       vport->vport_id, vlan_id,
 						       true);
-			if (ret && ret != -EINVAL)
+			if (ret && ret != -EINVAL) {
+				mutex_unlock(&hdev->vport_lock);
 				return;
+			}
 
 			clear_bit(vlan_id, vport->vlan_del_fail_bmap);
 			hclge_rm_vport_vlan_table(vport, vlan_id, false);
 			hclge_set_vport_vlan_fltr_change(vport);
 
 			sync_cnt++;
-			if (sync_cnt >= HCLGE_MAX_SYNC_COUNT)
+			if (sync_cnt >= HCLGE_MAX_SYNC_COUNT) {
+				mutex_unlock(&hdev->vport_lock);
 				return;
+			}
 
 			vlan_id = find_first_bit(vport->vlan_del_fail_bmap,
 						 VLAN_N_VID);
 		}
 	}
+	mutex_unlock(&hdev->vport_lock);
 
 	hclge_sync_vlan_fltr_state(hdev);
 }
@@ -11651,6 +11667,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		goto err_msi_irq_uninit;
 
 	if (hdev->hw.mac.media_type == HNAE3_MEDIA_TYPE_COPPER) {
+		clear_bit(HNAE3_DEV_SUPPORT_FEC_B, ae_dev->caps);
 		if (hnae3_dev_phy_imp_supported(hdev))
 			ret = hclge_update_tp_port_info(hdev);
 		else
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index a4d68fb216fb92..0aa9beefd1c7ee 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1206,6 +1206,8 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle,
 	     test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state)) && is_kill) {
 		set_bit(vlan_id, hdev->vlan_del_fail_bmap);
 		return -EBUSY;
+	} else if (!is_kill && test_bit(vlan_id, hdev->vlan_del_fail_bmap)) {
+		clear_bit(vlan_id, hdev->vlan_del_fail_bmap);
 	}
 
 	hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN,
@@ -1233,20 +1235,25 @@ static void hclgevf_sync_vlan_filter(struct hclgevf_dev *hdev)
 	int ret, sync_cnt = 0;
 	u16 vlan_id;
 
+	if (bitmap_empty(hdev->vlan_del_fail_bmap, VLAN_N_VID))
+		return;
+
+	rtnl_lock();
 	vlan_id = find_first_bit(hdev->vlan_del_fail_bmap, VLAN_N_VID);
 	while (vlan_id != VLAN_N_VID) {
 		ret = hclgevf_set_vlan_filter(handle, htons(ETH_P_8021Q),
 					      vlan_id, true);
 		if (ret)
-			return;
+			break;
 
 		clear_bit(vlan_id, hdev->vlan_del_fail_bmap);
 		sync_cnt++;
 		if (sync_cnt >= HCLGEVF_MAX_SYNC_COUNT)
-			return;
+			break;
 
 		vlan_id = find_first_bit(hdev->vlan_del_fail_bmap, VLAN_N_VID);
 	}
+	rtnl_unlock();
 }
 
 static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
@@ -1974,8 +1981,18 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 	return HCLGEVF_VECTOR0_EVENT_OTHER;
 }
 
+static void hclgevf_reset_timer(struct timer_list *t)
+{
+	struct hclgevf_dev *hdev = from_timer(hdev, t, reset_timer);
+
+	hclgevf_clear_event_cause(hdev, HCLGEVF_VECTOR0_EVENT_RST);
+	hclgevf_reset_task_schedule(hdev);
+}
+
 static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data)
 {
+#define HCLGEVF_RESET_DELAY	5
+
 	enum hclgevf_evt_cause event_cause;
 	struct hclgevf_dev *hdev = data;
 	u32 clearval;
@@ -1987,7 +2004,8 @@ static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data)
 
 	switch (event_cause) {
 	case HCLGEVF_VECTOR0_EVENT_RST:
-		hclgevf_reset_task_schedule(hdev);
+		mod_timer(&hdev->reset_timer,
+			  jiffies + msecs_to_jiffies(HCLGEVF_RESET_DELAY));
 		break;
 	case HCLGEVF_VECTOR0_EVENT_MBX:
 		hclgevf_mbx_handler(hdev);
@@ -2930,6 +2948,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		 HCLGEVF_DRIVER_NAME);
 
 	hclgevf_task_schedule(hdev, round_jiffies_relative(HZ));
+	timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 81c16b8c8da296..a73f2bf3a56a64 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -219,6 +219,7 @@ struct hclgevf_dev {
 	enum hnae3_reset_type reset_level;
 	unsigned long reset_pending;
 	enum hnae3_reset_type reset_type;
+	struct timer_list reset_timer;
 
 #define HCLGEVF_RESET_REQUESTED		0
 #define HCLGEVF_RESET_PENDING		1
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index bbf7b14079de3c..85c2a634c8f96a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -63,6 +63,9 @@ static int hclgevf_get_mbx_resp(struct hclgevf_dev *hdev, u16 code0, u16 code1,
 		i++;
 	}
 
+	/* ensure additional_info will be seen after received_resp */
+	smp_rmb();
+
 	if (i >= HCLGEVF_MAX_TRY_TIMES) {
 		dev_err(&hdev->pdev->dev,
 			"VF could not get mbx(%u,%u) resp(=%d) from PF in %d tries\n",
@@ -178,6 +181,10 @@ static void hclgevf_handle_mbx_response(struct hclgevf_dev *hdev,
 	resp->resp_status = hclgevf_resp_to_errno(resp_status);
 	memcpy(resp->additional_info, req->msg.resp_data,
 	       HCLGE_MBX_MAX_RESP_DATA_SIZE * sizeof(u8));
+
+	/* ensure additional_info will be seen before setting received_resp */
+	smp_wmb();
+
 	if (match_id) {
 		/* If match_id is not zero, it means PF support match_id.
 		 * if the match_id is right, VF get the right response, or
diff --git a/drivers/net/ethernet/intel/i40e/i40e_devlink.c b/drivers/net/ethernet/intel/i40e/i40e_devlink.c
index 74bc111b484941..cc4e9e2addb75f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_devlink.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_devlink.c
@@ -231,6 +231,5 @@ int i40e_devlink_create_port(struct i40e_pf *pf)
  **/
 void i40e_devlink_destroy_port(struct i40e_pf *pf)
 {
-	devlink_port_type_clear(&pf->devlink_port);
 	devlink_port_unregister(&pf->devlink_port);
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 3157d14d9b1213..1ab8dbe2d8800d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -14213,8 +14213,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi)
 	}
 	set_bit(__I40E_VSI_RELEASING, vsi->state);
 	uplink_seid = vsi->uplink_seid;
-	if (vsi->type == I40E_VSI_MAIN)
-		i40e_devlink_destroy_port(pf);
+
 	if (vsi->type != I40E_VSI_SRIOV) {
 		if (vsi->netdev_registered) {
 			vsi->netdev_registered = false;
@@ -14228,6 +14227,9 @@ int i40e_vsi_release(struct i40e_vsi *vsi)
 		i40e_vsi_disable_irq(vsi);
 	}
 
+	if (vsi->type == I40E_VSI_MAIN)
+		i40e_devlink_destroy_port(pf);
+
 	spin_lock_bh(&vsi->mac_filter_hash_lock);
 
 	/* clear the sync flag on all filters */
@@ -14402,14 +14404,14 @@ static struct i40e_vsi *i40e_vsi_reinit_setup(struct i40e_vsi *vsi)
 
 err_rings:
 	i40e_vsi_free_q_vectors(vsi);
-	if (vsi->type == I40E_VSI_MAIN)
-		i40e_devlink_destroy_port(pf);
 	if (vsi->netdev_registered) {
 		vsi->netdev_registered = false;
 		unregister_netdev(vsi->netdev);
 		free_netdev(vsi->netdev);
 		vsi->netdev = NULL;
 	}
+	if (vsi->type == I40E_VSI_MAIN)
+		i40e_devlink_destroy_port(pf);
 	i40e_aq_delete_element(&pf->hw, vsi->seid, NULL);
 err_vsi:
 	i40e_vsi_clear(vsi);
@@ -16222,7 +16224,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	       I40E_PRTGL_SAH_MFS_MASK) >> I40E_PRTGL_SAH_MFS_SHIFT;
 	if (val < MAX_FRAME_SIZE_DEFAULT)
 		dev_warn(&pdev->dev, "MFS for port %x has been set below the default: %x\n",
-			 i, val);
+			 pf->hw.port, val);
 
 	/* Add a filter to drop all Flow control frames from any VSI from being
 	 * transmitted. By doing so we stop a malicious VF from sending out
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index f408fcf23ce86d..f6671ac797353a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -207,7 +207,7 @@
 #define I40E_GLGEN_MSCA_OPCODE_SHIFT 26
 #define I40E_GLGEN_MSCA_OPCODE_MASK(_i) I40E_MASK(_i, I40E_GLGEN_MSCA_OPCODE_SHIFT)
 #define I40E_GLGEN_MSCA_STCODE_SHIFT 28
-#define I40E_GLGEN_MSCA_STCODE_MASK I40E_MASK(0x1, I40E_GLGEN_MSCA_STCODE_SHIFT)
+#define I40E_GLGEN_MSCA_STCODE_MASK(_i) I40E_MASK(_i, I40E_GLGEN_MSCA_STCODE_SHIFT)
 #define I40E_GLGEN_MSCA_MDICMD_SHIFT 30
 #define I40E_GLGEN_MSCA_MDICMD_MASK I40E_MASK(0x1, I40E_GLGEN_MSCA_MDICMD_SHIFT)
 #define I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT 31
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index aff6dc6afbe21b..f95bc2a4a83883 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -37,11 +37,11 @@ typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct i40e_aq_desc *);
 #define I40E_QTX_CTL_VM_QUEUE	0x1
 #define I40E_QTX_CTL_PF_QUEUE	0x2
 
-#define I40E_MDIO_CLAUSE22_STCODE_MASK		I40E_GLGEN_MSCA_STCODE_MASK
+#define I40E_MDIO_CLAUSE22_STCODE_MASK		I40E_GLGEN_MSCA_STCODE_MASK(1)
 #define I40E_MDIO_CLAUSE22_OPCODE_WRITE_MASK	I40E_GLGEN_MSCA_OPCODE_MASK(1)
 #define I40E_MDIO_CLAUSE22_OPCODE_READ_MASK	I40E_GLGEN_MSCA_OPCODE_MASK(2)
 
-#define I40E_MDIO_CLAUSE45_STCODE_MASK		I40E_GLGEN_MSCA_STCODE_MASK
+#define I40E_MDIO_CLAUSE45_STCODE_MASK		I40E_GLGEN_MSCA_STCODE_MASK(0)
 #define I40E_MDIO_CLAUSE45_OPCODE_ADDRESS_MASK	I40E_GLGEN_MSCA_OPCODE_MASK(0)
 #define I40E_MDIO_CLAUSE45_OPCODE_WRITE_MASK	I40E_GLGEN_MSCA_OPCODE_MASK(1)
 #define I40E_MDIO_CLAUSE45_OPCODE_READ_MASK	I40E_GLGEN_MSCA_OPCODE_MASK(3)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 08d7edccfb8ddb..3f99eb19824527 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -3844,7 +3844,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = NULL;
 	int aq_ret = 0;
-	int i, ret;
+	int i;
 
 	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = -EINVAL;
@@ -3868,8 +3868,10 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 	}
 
 	cfilter = kzalloc(sizeof(*cfilter), GFP_KERNEL);
-	if (!cfilter)
-		return -ENOMEM;
+	if (!cfilter) {
+		aq_ret = -ENOMEM;
+		goto err_out;
+	}
 
 	/* parse destination mac address */
 	for (i = 0; i < ETH_ALEN; i++)
@@ -3917,13 +3919,13 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 
 	/* Adding cloud filter programmed as TC filter */
 	if (tcf.dst_port)
-		ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, true);
+		aq_ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, true);
 	else
-		ret = i40e_add_del_cloud_filter(vsi, cfilter, true);
-	if (ret) {
+		aq_ret = i40e_add_del_cloud_filter(vsi, cfilter, true);
+	if (aq_ret) {
 		dev_err(&pf->pdev->dev,
 			"VF %d: Failed to add cloud filter, err %pe aq_err %s\n",
-			vf->vf_id, ERR_PTR(ret),
+			vf->vf_id, ERR_PTR(aq_ret),
 			i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
 		goto err_free;
 	}
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index e7ab89dc883aa6..63b45c61cc4aa3 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -292,6 +292,7 @@ struct iavf_adapter {
 #define IAVF_FLAG_QUEUES_DISABLED		BIT(17)
 #define IAVF_FLAG_SETUP_NETDEV_FEATURES		BIT(18)
 #define IAVF_FLAG_REINIT_MSIX_NEEDED		BIT(20)
+#define IAVF_FLAG_FDIR_ENABLED			BIT(21)
 /* duplicates for common code */
 #define IAVF_FLAG_DCB_ENABLED			0
 	/* flags for admin queue service task */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 6f236d1a6444e8..dc499fe7734ec9 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -827,18 +827,10 @@ static int __iavf_set_coalesce(struct net_device *netdev,
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	int i;
 
-	if (ec->rx_coalesce_usecs == 0) {
-		if (ec->use_adaptive_rx_coalesce)
-			netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n");
-	} else if ((ec->rx_coalesce_usecs < IAVF_MIN_ITR) ||
-		   (ec->rx_coalesce_usecs > IAVF_MAX_ITR)) {
+	if (ec->rx_coalesce_usecs > IAVF_MAX_ITR) {
 		netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n");
 		return -EINVAL;
-	} else if (ec->tx_coalesce_usecs == 0) {
-		if (ec->use_adaptive_tx_coalesce)
-			netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n");
-	} else if ((ec->tx_coalesce_usecs < IAVF_MIN_ITR) ||
-		   (ec->tx_coalesce_usecs > IAVF_MAX_ITR)) {
+	} else if (ec->tx_coalesce_usecs > IAVF_MAX_ITR) {
 		netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n");
 		return -EINVAL;
 	}
@@ -1069,7 +1061,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter,
 	struct iavf_fdir_fltr *rule = NULL;
 	int ret = 0;
 
-	if (!FDIR_FLTR_SUPPORT(adapter))
+	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
 	spin_lock_bh(&adapter->fdir_fltr_lock);
@@ -1211,7 +1203,7 @@ iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd,
 	unsigned int cnt = 0;
 	int val = 0;
 
-	if (!FDIR_FLTR_SUPPORT(adapter))
+	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
 	cmd->data = IAVF_MAX_FDIR_FILTERS;
@@ -1403,7 +1395,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	int count = 50;
 	int err;
 
-	if (!FDIR_FLTR_SUPPORT(adapter))
+	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
 	if (fsp->flow_type & FLOW_MAC_EXT)
@@ -1444,12 +1436,16 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	spin_lock_bh(&adapter->fdir_fltr_lock);
 	iavf_fdir_list_add_fltr(adapter, fltr);
 	adapter->fdir_active_fltr++;
-	fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST;
-	adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+	if (adapter->link_up) {
+		fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST;
+		adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+	} else {
+		fltr->state = IAVF_FDIR_FLTR_INACTIVE;
+	}
 	spin_unlock_bh(&adapter->fdir_fltr_lock);
 
-	mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
-
+	if (adapter->link_up)
+		mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
 ret:
 	if (err && fltr)
 		kfree(fltr);
@@ -1471,7 +1467,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	struct iavf_fdir_fltr *fltr = NULL;
 	int err = 0;
 
-	if (!FDIR_FLTR_SUPPORT(adapter))
+	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
 	spin_lock_bh(&adapter->fdir_fltr_lock);
@@ -1480,6 +1476,11 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 		if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) {
 			fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST;
 			adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER;
+		} else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) {
+			list_del(&fltr->list);
+			kfree(fltr);
+			adapter->fdir_active_fltr--;
+			fltr = NULL;
 		} else {
 			err = -EBUSY;
 		}
@@ -1788,7 +1789,7 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 		ret = 0;
 		break;
 	case ETHTOOL_GRXCLSRLCNT:
-		if (!FDIR_FLTR_SUPPORT(adapter))
+		if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 			break;
 		spin_lock_bh(&adapter->fdir_fltr_lock);
 		cmd->rule_cnt = adapter->fdir_active_fltr;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h
index 9eb9f73f6adf3a..d31bd923ba8cbf 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h
@@ -6,12 +6,25 @@
 
 struct iavf_adapter;
 
-/* State of Flow Director filter */
+/* State of Flow Director filter
+ *
+ * *_REQUEST states are used to mark filter to be sent to PF driver to perform
+ * an action (either add or delete filter). *_PENDING states are an indication
+ * that request was sent to PF and the driver is waiting for response.
+ *
+ * Both DELETE and DISABLE states are being used to delete a filter in PF.
+ * The difference is that after a successful response filter in DEL_PENDING
+ * state is being deleted from VF driver as well and filter in DIS_PENDING state
+ * is being changed to INACTIVE state.
+ */
 enum iavf_fdir_fltr_state_t {
 	IAVF_FDIR_FLTR_ADD_REQUEST,	/* User requests to add filter */
 	IAVF_FDIR_FLTR_ADD_PENDING,	/* Filter pending add by the PF */
 	IAVF_FDIR_FLTR_DEL_REQUEST,	/* User requests to delete filter */
 	IAVF_FDIR_FLTR_DEL_PENDING,	/* Filter pending delete by the PF */
+	IAVF_FDIR_FLTR_DIS_REQUEST,	/* Filter scheduled to be disabled */
+	IAVF_FDIR_FLTR_DIS_PENDING,	/* Filter pending disable by the PF */
+	IAVF_FDIR_FLTR_INACTIVE,	/* Filter inactive on link down */
 	IAVF_FDIR_FLTR_ACTIVE,		/* Filter is active */
 };
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index c862ebcd2e392e..e8d5b889addcb4 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -277,27 +277,6 @@ void iavf_free_virt_mem(struct iavf_hw *hw, struct iavf_virt_mem *mem)
 }
 
 /**
- * iavf_lock_timeout - try to lock mutex but give up after timeout
- * @lock: mutex that should be locked
- * @msecs: timeout in msecs
- *
- * Returns 0 on success, negative on failure
- **/
-static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs)
-{
-	unsigned int wait, delay = 10;
-
-	for (wait = 0; wait < msecs; wait += delay) {
-		if (mutex_trylock(lock))
-			return 0;
-
-		msleep(delay);
-	}
-
-	return -1;
-}
-
-/**
  * iavf_schedule_reset - Set the flags and schedule a reset event
  * @adapter: board private structure
  * @flags: IAVF_FLAG_RESET_PENDING or IAVF_FLAG_RESET_NEEDED
@@ -1353,18 +1332,20 @@ static void iavf_clear_cloud_filters(struct iavf_adapter *adapter)
  **/
 static void iavf_clear_fdir_filters(struct iavf_adapter *adapter)
 {
-	struct iavf_fdir_fltr *fdir, *fdirtmp;
+	struct iavf_fdir_fltr *fdir;
 
 	/* remove all Flow Director filters */
 	spin_lock_bh(&adapter->fdir_fltr_lock);
-	list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head,
-				 list) {
+	list_for_each_entry(fdir, &adapter->fdir_list_head, list) {
 		if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST) {
-			list_del(&fdir->list);
-			kfree(fdir);
-			adapter->fdir_active_fltr--;
-		} else {
-			fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST;
+			/* Cancel a request, keep filter as inactive */
+			fdir->state = IAVF_FDIR_FLTR_INACTIVE;
+		} else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING ||
+			 fdir->state == IAVF_FDIR_FLTR_ACTIVE) {
+			/* Disable filters which are active or have a pending
+			 * request to PF to be added
+			 */
+			fdir->state = IAVF_FDIR_FLTR_DIS_REQUEST;
 		}
 	}
 	spin_unlock_bh(&adapter->fdir_fltr_lock);
@@ -4113,6 +4094,33 @@ static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 }
 
 /**
+ * iavf_restore_fdir_filters
+ * @adapter: board private structure
+ *
+ * Restore existing FDIR filters when VF netdev comes back up.
+ **/
+static void iavf_restore_fdir_filters(struct iavf_adapter *adapter)
+{
+	struct iavf_fdir_fltr *f;
+
+	spin_lock_bh(&adapter->fdir_fltr_lock);
+	list_for_each_entry(f, &adapter->fdir_list_head, list) {
+		if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST) {
+			/* Cancel a request, keep filter as active */
+			f->state = IAVF_FDIR_FLTR_ACTIVE;
+		} else if (f->state == IAVF_FDIR_FLTR_DIS_PENDING ||
+			   f->state == IAVF_FDIR_FLTR_INACTIVE) {
+			/* Add filters which are inactive or have a pending
+			 * request to PF to be deleted
+			 */
+			f->state = IAVF_FDIR_FLTR_ADD_REQUEST;
+			adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+		}
+	}
+	spin_unlock_bh(&adapter->fdir_fltr_lock);
+}
+
+/**
  * iavf_open - Called when a network interface is made active
  * @netdev: network interface device structure
  *
@@ -4179,8 +4187,9 @@ static int iavf_open(struct net_device *netdev)
 
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
-	/* Restore VLAN filters that were removed with IFF_DOWN */
+	/* Restore filters that were removed with IFF_DOWN */
 	iavf_restore_filters(adapter);
+	iavf_restore_fdir_filters(adapter);
 
 	iavf_configure(adapter);
 
@@ -4311,6 +4320,49 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu)
 	return ret;
 }
 
+/**
+ * iavf_disable_fdir - disable Flow Director and clear existing filters
+ * @adapter: board private structure
+ **/
+static void iavf_disable_fdir(struct iavf_adapter *adapter)
+{
+	struct iavf_fdir_fltr *fdir, *fdirtmp;
+	bool del_filters = false;
+
+	adapter->flags &= ~IAVF_FLAG_FDIR_ENABLED;
+
+	/* remove all Flow Director filters */
+	spin_lock_bh(&adapter->fdir_fltr_lock);
+	list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head,
+				 list) {
+		if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST ||
+		    fdir->state == IAVF_FDIR_FLTR_INACTIVE) {
+			/* Delete filters not registered in PF */
+			list_del(&fdir->list);
+			kfree(fdir);
+			adapter->fdir_active_fltr--;
+		} else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING ||
+			   fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST ||
+			   fdir->state == IAVF_FDIR_FLTR_ACTIVE) {
+			/* Filters registered in PF, schedule their deletion */
+			fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST;
+			del_filters = true;
+		} else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) {
+			/* Request to delete filter already sent to PF, change
+			 * state to DEL_PENDING to delete filter after PF's
+			 * response, not set as INACTIVE
+			 */
+			fdir->state = IAVF_FDIR_FLTR_DEL_PENDING;
+		}
+	}
+	spin_unlock_bh(&adapter->fdir_fltr_lock);
+
+	if (del_filters) {
+		adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER;
+		mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+	}
+}
+
 #define NETIF_VLAN_OFFLOAD_FEATURES	(NETIF_F_HW_VLAN_CTAG_RX | \
 					 NETIF_F_HW_VLAN_CTAG_TX | \
 					 NETIF_F_HW_VLAN_STAG_RX | \
@@ -4336,6 +4388,13 @@ static int iavf_set_features(struct net_device *netdev,
 	    ((netdev->features & NETIF_F_RXFCS) ^ (features & NETIF_F_RXFCS)))
 		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
 
+	if ((netdev->features & NETIF_F_NTUPLE) ^ (features & NETIF_F_NTUPLE)) {
+		if (features & NETIF_F_NTUPLE)
+			adapter->flags |= IAVF_FLAG_FDIR_ENABLED;
+		else
+			iavf_disable_fdir(adapter);
+	}
+
 	return 0;
 }
 
@@ -4685,6 +4744,9 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev,
 
 	features = iavf_fix_netdev_vlan_features(adapter, features);
 
+	if (!FDIR_FLTR_SUPPORT(adapter))
+		features &= ~NETIF_F_NTUPLE;
+
 	return iavf_fix_strip_features(adapter, features);
 }
 
@@ -4802,6 +4864,12 @@ int iavf_process_config(struct iavf_adapter *adapter)
 	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
 		netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 
+	if (FDIR_FLTR_SUPPORT(adapter)) {
+		netdev->hw_features |= NETIF_F_NTUPLE;
+		netdev->features |= NETIF_F_NTUPLE;
+		adapter->flags |= IAVF_FLAG_FDIR_ENABLED;
+	}
+
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
 	/* Do not turn on offloads when they are requested to be turned off.
@@ -4826,34 +4894,6 @@ int iavf_process_config(struct iavf_adapter *adapter)
 }
 
 /**
- * iavf_shutdown - Shutdown the device in preparation for a reboot
- * @pdev: pci device structure
- **/
-static void iavf_shutdown(struct pci_dev *pdev)
-{
-	struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev);
-	struct net_device *netdev = adapter->netdev;
-
-	netif_device_detach(netdev);
-
-	if (netif_running(netdev))
-		iavf_close(netdev);
-
-	if (iavf_lock_timeout(&adapter->crit_lock, 5000))
-		dev_warn(&adapter->pdev->dev, "%s: failed to acquire crit_lock\n", __func__);
-	/* Prevent the watchdog from running. */
-	iavf_change_state(adapter, __IAVF_REMOVE);
-	adapter->aq_required = 0;
-	mutex_unlock(&adapter->crit_lock);
-
-#ifdef CONFIG_PM
-	pci_save_state(pdev);
-
-#endif
-	pci_disable_device(pdev);
-}
-
-/**
  * iavf_probe - Device Initialization Routine
  * @pdev: PCI device information struct
  * @ent: entry in iavf_pci_tbl
@@ -5063,16 +5103,21 @@ static int __maybe_unused iavf_resume(struct device *dev_d)
  **/
 static void iavf_remove(struct pci_dev *pdev)
 {
-	struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev);
 	struct iavf_fdir_fltr *fdir, *fdirtmp;
 	struct iavf_vlan_filter *vlf, *vlftmp;
 	struct iavf_cloud_filter *cf, *cftmp;
 	struct iavf_adv_rss *rss, *rsstmp;
 	struct iavf_mac_filter *f, *ftmp;
+	struct iavf_adapter *adapter;
 	struct net_device *netdev;
 	struct iavf_hw *hw;
 
-	netdev = adapter->netdev;
+	/* Don't proceed with remove if netdev is already freed */
+	netdev = pci_get_drvdata(pdev);
+	if (!netdev)
+		return;
+
+	adapter = iavf_pdev_to_adapter(pdev);
 	hw = &adapter->hw;
 
 	if (test_and_set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
@@ -5184,11 +5229,25 @@ static void iavf_remove(struct pci_dev *pdev)
 
 	destroy_workqueue(adapter->wq);
 
+	pci_set_drvdata(pdev, NULL);
+
 	free_netdev(netdev);
 
 	pci_disable_device(pdev);
 }
 
+/**
+ * iavf_shutdown - Shutdown the device in preparation for a reboot
+ * @pdev: pci device structure
+ **/
+static void iavf_shutdown(struct pci_dev *pdev)
+{
+	iavf_remove(pdev);
+
+	if (system_state == SYSTEM_POWER_OFF)
+		pci_set_power_state(pdev, PCI_D3hot);
+}
+
 static SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume);
 
 static struct pci_driver iavf_driver = {
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index 7e6ee32d19b696..10ba36602c0c14 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -15,7 +15,6 @@
  */
 #define IAVF_ITR_DYNAMIC	0x8000	/* use top bit as a flag */
 #define IAVF_ITR_MASK		0x1FFE	/* mask for ITR register value */
-#define IAVF_MIN_ITR		     2	/* reg uses 2 usec resolution */
 #define IAVF_ITR_100K		    10	/* all values below must be even */
 #define IAVF_ITR_50K		    20
 #define IAVF_ITR_20K		    50
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 64c4443dbef9ca..2d9366be0ec506 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -1735,8 +1735,8 @@ void iavf_add_fdir_filter(struct iavf_adapter *adapter)
  **/
 void iavf_del_fdir_filter(struct iavf_adapter *adapter)
 {
+	struct virtchnl_fdir_del f = {};
 	struct iavf_fdir_fltr *fdir;
-	struct virtchnl_fdir_del f;
 	bool process_fltr = false;
 	int len;
 
@@ -1753,11 +1753,16 @@ void iavf_del_fdir_filter(struct iavf_adapter *adapter)
 	list_for_each_entry(fdir, &adapter->fdir_list_head, list) {
 		if (fdir->state == IAVF_FDIR_FLTR_DEL_REQUEST) {
 			process_fltr = true;
-			memset(&f, 0, len);
 			f.vsi_id = fdir->vc_add_msg.vsi_id;
 			f.flow_id = fdir->flow_id;
 			fdir->state = IAVF_FDIR_FLTR_DEL_PENDING;
 			break;
+		} else if (fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST) {
+			process_fltr = true;
+			f.vsi_id = fdir->vc_add_msg.vsi_id;
+			f.flow_id = fdir->flow_id;
+			fdir->state = IAVF_FDIR_FLTR_DIS_PENDING;
+			break;
 		}
 	}
 	spin_unlock_bh(&adapter->fdir_fltr_lock);
@@ -1902,6 +1907,48 @@ static void iavf_netdev_features_vlan_strip_set(struct net_device *netdev,
 }
 
 /**
+ * iavf_activate_fdir_filters - Reactivate all FDIR filters after a reset
+ * @adapter: private adapter structure
+ *
+ * Called after a reset to re-add all FDIR filters and delete some of them
+ * if they were pending to be deleted.
+ */
+static void iavf_activate_fdir_filters(struct iavf_adapter *adapter)
+{
+	struct iavf_fdir_fltr *f, *ftmp;
+	bool add_filters = false;
+
+	spin_lock_bh(&adapter->fdir_fltr_lock);
+	list_for_each_entry_safe(f, ftmp, &adapter->fdir_list_head, list) {
+		if (f->state == IAVF_FDIR_FLTR_ADD_REQUEST ||
+		    f->state == IAVF_FDIR_FLTR_ADD_PENDING ||
+		    f->state == IAVF_FDIR_FLTR_ACTIVE) {
+			/* All filters and requests have been removed in PF,
+			 * restore them
+			 */
+			f->state = IAVF_FDIR_FLTR_ADD_REQUEST;
+			add_filters = true;
+		} else if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST ||
+			   f->state == IAVF_FDIR_FLTR_DIS_PENDING) {
+			/* Link down state, leave filters as inactive */
+			f->state = IAVF_FDIR_FLTR_INACTIVE;
+		} else if (f->state == IAVF_FDIR_FLTR_DEL_REQUEST ||
+			   f->state == IAVF_FDIR_FLTR_DEL_PENDING) {
+			/* Delete filters that were pending to be deleted, the
+			 * list on PF is already cleared after a reset
+			 */
+			list_del(&f->list);
+			kfree(f);
+			adapter->fdir_active_fltr--;
+		}
+	}
+	spin_unlock_bh(&adapter->fdir_fltr_lock);
+
+	if (add_filters)
+		adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+}
+
+/**
  * iavf_virtchnl_completion
  * @adapter: adapter structure
  * @v_opcode: opcode sent by PF
@@ -2078,7 +2125,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 			spin_lock_bh(&adapter->fdir_fltr_lock);
 			list_for_each_entry(fdir, &adapter->fdir_list_head,
 					    list) {
-				if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) {
+				if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING ||
+				    fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) {
 					fdir->state = IAVF_FDIR_FLTR_ACTIVE;
 					dev_info(&adapter->pdev->dev, "Failed to del Flow Director filter, error %s\n",
 						 iavf_stat_str(&adapter->hw,
@@ -2214,6 +2262,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 
 		spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
+		iavf_activate_fdir_filters(adapter);
+
 		iavf_parse_vf_resource_msg(adapter);
 
 		/* negotiated VIRTCHNL_VF_OFFLOAD_VLAN_V2, so wait for the
@@ -2390,7 +2440,9 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		list_for_each_entry_safe(fdir, fdir_tmp, &adapter->fdir_list_head,
 					 list) {
 			if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) {
-				if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS) {
+				if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS ||
+				    del_fltr->status ==
+				    VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) {
 					dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n",
 						 fdir->loc);
 					list_del(&fdir->list);
@@ -2402,6 +2454,17 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 						 del_fltr->status);
 					iavf_print_fdir_fltr(adapter, fdir);
 				}
+			} else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) {
+				if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS ||
+				    del_fltr->status ==
+				    VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) {
+					fdir->state = IAVF_FDIR_FLTR_INACTIVE;
+				} else {
+					fdir->state = IAVF_FDIR_FLTR_ACTIVE;
+					dev_info(&adapter->pdev->dev, "Failed to disable Flow Director filter with status: %d\n",
+						 del_fltr->status);
+					iavf_print_fdir_fltr(adapter, fdir);
+				}
 			}
 		}
 		spin_unlock_bh(&adapter->fdir_fltr_lock);
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index cfb1580f5850b5..8b7504a9df316c 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -1479,14 +1479,14 @@ ice_post_dwnld_pkg_actions(struct ice_hw *hw)
 }
 
 /**
- * ice_download_pkg
+ * ice_download_pkg_with_sig_seg
  * @hw: pointer to the hardware structure
  * @pkg_hdr: pointer to package header
  *
  * Handles the download of a complete package.
  */
 static enum ice_ddp_state
-ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
+ice_download_pkg_with_sig_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
 {
 	enum ice_aq_err aq_err = hw->adminq.sq_last_status;
 	enum ice_ddp_state state = ICE_DDP_PKG_ERR;
@@ -1519,6 +1519,103 @@ ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
 		state = ice_post_dwnld_pkg_actions(hw);
 
 	ice_release_global_cfg_lock(hw);
+
+	return state;
+}
+
+/**
+ * ice_dwnld_cfg_bufs
+ * @hw: pointer to the hardware structure
+ * @bufs: pointer to an array of buffers
+ * @count: the number of buffers in the array
+ *
+ * Obtains global config lock and downloads the package configuration buffers
+ * to the firmware.
+ */
+static enum ice_ddp_state
+ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count)
+{
+	enum ice_ddp_state state;
+	struct ice_buf_hdr *bh;
+	int status;
+
+	if (!bufs || !count)
+		return ICE_DDP_PKG_ERR;
+
+	/* If the first buffer's first section has its metadata bit set
+	 * then there are no buffers to be downloaded, and the operation is
+	 * considered a success.
+	 */
+	bh = (struct ice_buf_hdr *)bufs;
+	if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF)
+		return ICE_DDP_PKG_SUCCESS;
+
+	status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE);
+	if (status) {
+		if (status == -EALREADY)
+			return ICE_DDP_PKG_ALREADY_LOADED;
+		return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status);
+	}
+
+	state = ice_dwnld_cfg_bufs_no_lock(hw, bufs, 0, count, true);
+	if (!state)
+		state = ice_post_dwnld_pkg_actions(hw);
+
+	ice_release_global_cfg_lock(hw);
+
+	return state;
+}
+
+/**
+ * ice_download_pkg_without_sig_seg
+ * @hw: pointer to the hardware structure
+ * @ice_seg: pointer to the segment of the package to be downloaded
+ *
+ * Handles the download of a complete package without signature segment.
+ */
+static enum ice_ddp_state
+ice_download_pkg_without_sig_seg(struct ice_hw *hw, struct ice_seg *ice_seg)
+{
+	struct ice_buf_table *ice_buf_tbl;
+
+	ice_debug(hw, ICE_DBG_PKG, "Segment format version: %d.%d.%d.%d\n",
+		  ice_seg->hdr.seg_format_ver.major,
+		  ice_seg->hdr.seg_format_ver.minor,
+		  ice_seg->hdr.seg_format_ver.update,
+		  ice_seg->hdr.seg_format_ver.draft);
+
+	ice_debug(hw, ICE_DBG_PKG, "Seg: type 0x%X, size %d, name %s\n",
+		  le32_to_cpu(ice_seg->hdr.seg_type),
+		  le32_to_cpu(ice_seg->hdr.seg_size), ice_seg->hdr.seg_id);
+
+	ice_buf_tbl = ice_find_buf_table(ice_seg);
+
+	ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n",
+		  le32_to_cpu(ice_buf_tbl->buf_count));
+
+	return ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array,
+				  le32_to_cpu(ice_buf_tbl->buf_count));
+}
+
+/**
+ * ice_download_pkg
+ * @hw: pointer to the hardware structure
+ * @pkg_hdr: pointer to package header
+ * @ice_seg: pointer to the segment of the package to be downloaded
+ *
+ * Handles the download of a complete package.
+ */
+static enum ice_ddp_state
+ice_download_pkg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr,
+		 struct ice_seg *ice_seg)
+{
+	enum ice_ddp_state state;
+
+	if (hw->pkg_has_signing_seg)
+		state = ice_download_pkg_with_sig_seg(hw, pkg_hdr);
+	else
+		state = ice_download_pkg_without_sig_seg(hw, ice_seg);
+
 	ice_post_pkg_dwnld_vlan_mode_cfg(hw);
 
 	return state;
@@ -2083,7 +2180,7 @@ enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len)
 
 	/* initialize package hints and then download package */
 	ice_init_pkg_hints(hw, seg);
-	state = ice_download_pkg(hw, pkg);
+	state = ice_download_pkg(hw, pkg, seg);
 	if (state == ICE_DDP_PKG_ALREADY_LOADED) {
 		ice_debug(hw, ICE_DBG_INIT,
 			  "package previously loaded - no work.\n");
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c
index 835c419ccc7437..86b180cb32a027 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.c
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.c
@@ -815,12 +815,6 @@ ice_dpll_input_prio_set(const struct dpll_pin *pin, void *pin_priv,
 	struct ice_pf *pf = d->pf;
 	int ret;
 
-	if (prio > ICE_DPLL_PRIO_MAX) {
-		NL_SET_ERR_MSG_FMT(extack, "prio out of supported range 0-%d",
-				   ICE_DPLL_PRIO_MAX);
-		return -EINVAL;
-	}
-
 	mutex_lock(&pf->dplls.lock);
 	ret = ice_dpll_hw_input_prio_set(pf, d, p, prio, extack);
 	mutex_unlock(&pf->dplls.lock);
@@ -1756,6 +1750,7 @@ ice_dpll_init_dpll(struct ice_pf *pf, struct ice_dpll *d, bool cgu,
 	}
 	d->pf = pf;
 	if (cgu) {
+		ice_dpll_update_state(pf, d, true);
 		ret = dpll_device_register(d->dpll, type, &ice_dpll_ops, d);
 		if (ret) {
 			dpll_device_put(d->dpll);
@@ -1796,8 +1791,6 @@ static int ice_dpll_init_worker(struct ice_pf *pf)
 	struct ice_dplls *d = &pf->dplls;
 	struct kthread_worker *kworker;
 
-	ice_dpll_update_state(pf, &d->eec, true);
-	ice_dpll_update_state(pf, &d->pps, true);
 	kthread_init_delayed_work(&d->work, ice_dpll_periodic_work);
 	kworker = kthread_create_worker(0, "ice-dplls-%s",
 					dev_name(ice_pf_to_dev(pf)));
@@ -1830,6 +1823,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 	int num_pins, i, ret = -EINVAL;
 	struct ice_hw *hw = &pf->hw;
 	struct ice_dpll_pin *pins;
+	unsigned long caps;
 	u8 freq_supp_num;
 	bool input;
 
@@ -1849,6 +1843,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 	}
 
 	for (i = 0; i < num_pins; i++) {
+		caps = 0;
 		pins[i].idx = i;
 		pins[i].prop.board_label = ice_cgu_get_pin_name(hw, i, input);
 		pins[i].prop.type = ice_cgu_get_pin_type(hw, i, input);
@@ -1861,8 +1856,8 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 						      &dp->input_prio[i]);
 			if (ret)
 				return ret;
-			pins[i].prop.capabilities |=
-				DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE;
+			caps |= (DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE |
+				 DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE);
 			pins[i].prop.phase_range.min =
 				pf->dplls.input_phase_adj_max;
 			pins[i].prop.phase_range.max =
@@ -1872,9 +1867,11 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf,
 				pf->dplls.output_phase_adj_max;
 			pins[i].prop.phase_range.max =
 				-pf->dplls.output_phase_adj_max;
+			ret = ice_cgu_get_output_pin_state_caps(hw, i, &caps);
+			if (ret)
+				return ret;
 		}
-		pins[i].prop.capabilities |=
-			DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE;
+		pins[i].prop.capabilities = caps;
 		ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL);
 		if (ret)
 			return ret;
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h
index bb32b6d88373e2..93172e93995b94 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.h
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.h
@@ -6,7 +6,6 @@
 
 #include "ice.h"
 
-#define ICE_DPLL_PRIO_MAX	0xF
 #define ICE_DPLL_RCLK_NUM_MAX	4
 
 /** ice_dpll_pin - store info about pins
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index a34083567e6ff5..bde9bc74f92878 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -1850,14 +1850,14 @@ ice_phy_type_to_ethtool(struct net_device *netdev,
 	linkmode_zero(ks->link_modes.supported);
 	linkmode_zero(ks->link_modes.advertising);
 
-	for (i = 0; i < BITS_PER_TYPE(u64); i++) {
+	for (i = 0; i < ARRAY_SIZE(phy_type_low_lkup); i++) {
 		if (phy_types_low & BIT_ULL(i))
 			ice_linkmode_set_bit(&phy_type_low_lkup[i], ks,
 					     req_speeds, advert_phy_type_lo,
 					     i);
 	}
 
-	for (i = 0; i < BITS_PER_TYPE(u64); i++) {
+	for (i = 0; i < ARRAY_SIZE(phy_type_high_lkup); i++) {
 		if (phy_types_high & BIT_ULL(i))
 			ice_linkmode_set_bit(&phy_type_high_lkup[i], ks,
 					     req_speeds, advert_phy_type_hi,
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index b980f89dc892df..b47cd43ae87108 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -570,6 +570,50 @@ resume_traffic:
 }
 
 /**
+ * ice_lag_build_netdev_list - populate the lag struct's netdev list
+ * @lag: local lag struct
+ * @ndlist: pointer to netdev list to populate
+ */
+static void ice_lag_build_netdev_list(struct ice_lag *lag,
+				      struct ice_lag_netdev_list *ndlist)
+{
+	struct ice_lag_netdev_list *nl;
+	struct net_device *tmp_nd;
+
+	INIT_LIST_HEAD(&ndlist->node);
+	rcu_read_lock();
+	for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) {
+		nl = kzalloc(sizeof(*nl), GFP_ATOMIC);
+		if (!nl)
+			break;
+
+		nl->netdev = tmp_nd;
+		list_add(&nl->node, &ndlist->node);
+	}
+	rcu_read_unlock();
+	lag->netdev_head = &ndlist->node;
+}
+
+/**
+ * ice_lag_destroy_netdev_list - free lag struct's netdev list
+ * @lag: pointer to local lag struct
+ * @ndlist: pointer to lag struct netdev list
+ */
+static void ice_lag_destroy_netdev_list(struct ice_lag *lag,
+					struct ice_lag_netdev_list *ndlist)
+{
+	struct ice_lag_netdev_list *entry, *n;
+
+	rcu_read_lock();
+	list_for_each_entry_safe(entry, n, &ndlist->node, node) {
+		list_del(&entry->node);
+		kfree(entry);
+	}
+	rcu_read_unlock();
+	lag->netdev_head = NULL;
+}
+
+/**
  * ice_lag_move_single_vf_nodes - Move Tx scheduling nodes for single VF
  * @lag: primary interface LAG struct
  * @oldport: lport of previous interface
@@ -597,7 +641,6 @@ ice_lag_move_single_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport,
 void ice_lag_move_new_vf_nodes(struct ice_vf *vf)
 {
 	struct ice_lag_netdev_list ndlist;
-	struct list_head *tmp, *n;
 	u8 pri_port, act_port;
 	struct ice_lag *lag;
 	struct ice_vsi *vsi;
@@ -621,38 +664,15 @@ void ice_lag_move_new_vf_nodes(struct ice_vf *vf)
 	pri_port = pf->hw.port_info->lport;
 	act_port = lag->active_port;
 
-	if (lag->upper_netdev) {
-		struct ice_lag_netdev_list *nl;
-		struct net_device *tmp_nd;
-
-		INIT_LIST_HEAD(&ndlist.node);
-		rcu_read_lock();
-		for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) {
-			nl = kzalloc(sizeof(*nl), GFP_KERNEL);
-			if (!nl)
-				break;
-
-			nl->netdev = tmp_nd;
-			list_add(&nl->node, &ndlist.node);
-		}
-		rcu_read_unlock();
-	}
-
-	lag->netdev_head = &ndlist.node;
+	if (lag->upper_netdev)
+		ice_lag_build_netdev_list(lag, &ndlist);
 
 	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) &&
 	    lag->bonded && lag->primary && pri_port != act_port &&
 	    !list_empty(lag->netdev_head))
 		ice_lag_move_single_vf_nodes(lag, pri_port, act_port, vsi->idx);
 
-	list_for_each_safe(tmp, n, &ndlist.node) {
-		struct ice_lag_netdev_list *entry;
-
-		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
-		list_del(&entry->node);
-		kfree(entry);
-	}
-	lag->netdev_head = NULL;
+	ice_lag_destroy_netdev_list(lag, &ndlist);
 
 new_vf_unlock:
 	mutex_unlock(&pf->lag_mutex);
@@ -679,6 +699,29 @@ static void ice_lag_move_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport)
 			ice_lag_move_single_vf_nodes(lag, oldport, newport, i);
 }
 
+/**
+ * ice_lag_move_vf_nodes_cfg - move vf nodes outside LAG netdev event context
+ * @lag: local lag struct
+ * @src_prt: lport value for source port
+ * @dst_prt: lport value for destination port
+ *
+ * This function is used to move nodes during an out-of-netdev-event situation,
+ * primarily when the driver needs to reconfigure or recreate resources.
+ *
+ * Must be called while holding the lag_mutex to avoid lag events from
+ * processing while out-of-sync moves are happening.  Also, paired moves,
+ * such as used in a reset flow, should both be called under the same mutex
+ * lock to avoid changes between start of reset and end of reset.
+ */
+void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt)
+{
+	struct ice_lag_netdev_list ndlist;
+
+	ice_lag_build_netdev_list(lag, &ndlist);
+	ice_lag_move_vf_nodes(lag, src_prt, dst_prt);
+	ice_lag_destroy_netdev_list(lag, &ndlist);
+}
+
 #define ICE_LAG_SRIOV_CP_RECIPE		10
 #define ICE_LAG_SRIOV_TRAIN_PKT_LEN	16
 
@@ -1555,18 +1598,12 @@ static void ice_lag_chk_disabled_bond(struct ice_lag *lag, void *ptr)
  */
 static void ice_lag_disable_sriov_bond(struct ice_lag *lag)
 {
-	struct ice_lag_netdev_list *entry;
 	struct ice_netdev_priv *np;
-	struct net_device *netdev;
 	struct ice_pf *pf;
 
-	list_for_each_entry(entry, lag->netdev_head, node) {
-		netdev = entry->netdev;
-		np = netdev_priv(netdev);
-		pf = np->vsi->back;
-
-		ice_clear_feature_support(pf, ICE_F_SRIOV_LAG);
-	}
+	np = netdev_priv(lag->netdev);
+	pf = np->vsi->back;
+	ice_clear_feature_support(pf, ICE_F_SRIOV_LAG);
 }
 
 /**
@@ -1698,7 +1735,7 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event,
 
 		rcu_read_lock();
 		for_each_netdev_in_bond_rcu(upper_netdev, tmp_nd) {
-			nd_list = kzalloc(sizeof(*nd_list), GFP_KERNEL);
+			nd_list = kzalloc(sizeof(*nd_list), GFP_ATOMIC);
 			if (!nd_list)
 				break;
 
@@ -1944,6 +1981,8 @@ int ice_init_lag(struct ice_pf *pf)
 	int n, err;
 
 	ice_lag_init_feature_support_flag(pf);
+	if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
+		return 0;
 
 	pf->lag = kzalloc(sizeof(*lag), GFP_KERNEL);
 	if (!pf->lag)
@@ -2057,7 +2096,6 @@ void ice_lag_rebuild(struct ice_pf *pf)
 {
 	struct ice_lag_netdev_list ndlist;
 	struct ice_lag *lag, *prim_lag;
-	struct list_head *tmp, *n;
 	u8 act_port, loc_port;
 
 	if (!pf->lag || !pf->lag->bonded)
@@ -2069,21 +2107,7 @@ void ice_lag_rebuild(struct ice_pf *pf)
 	if (lag->primary) {
 		prim_lag = lag;
 	} else {
-		struct ice_lag_netdev_list *nl;
-		struct net_device *tmp_nd;
-
-		INIT_LIST_HEAD(&ndlist.node);
-		rcu_read_lock();
-		for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) {
-			nl = kzalloc(sizeof(*nl), GFP_KERNEL);
-			if (!nl)
-				break;
-
-			nl->netdev = tmp_nd;
-			list_add(&nl->node, &ndlist.node);
-		}
-		rcu_read_unlock();
-		lag->netdev_head = &ndlist.node;
+		ice_lag_build_netdev_list(lag, &ndlist);
 		prim_lag = ice_lag_find_primary(lag);
 	}
 
@@ -2113,13 +2137,7 @@ void ice_lag_rebuild(struct ice_pf *pf)
 
 	ice_clear_rdma_cap(pf);
 lag_rebuild_out:
-	list_for_each_safe(tmp, n, &ndlist.node) {
-		struct ice_lag_netdev_list *entry;
-
-		entry = list_entry(tmp, struct ice_lag_netdev_list, node);
-		list_del(&entry->node);
-		kfree(entry);
-	}
+	ice_lag_destroy_netdev_list(lag, &ndlist);
 	mutex_unlock(&pf->lag_mutex);
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h
index 9557e8605a07bf..ede833dfa65866 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.h
+++ b/drivers/net/ethernet/intel/ice/ice_lag.h
@@ -65,4 +65,5 @@ int ice_init_lag(struct ice_pf *pf);
 void ice_deinit_lag(struct ice_pf *pf);
 void ice_lag_rebuild(struct ice_pf *pf);
 bool ice_lag_is_switchdev_running(struct ice_pf *pf);
+void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt);
 #endif /* _ICE_LAG_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 4b1e56396293a4..1bad6e17f9befd 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2371,6 +2371,9 @@ static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi)
 		} else {
 			max_txqs[i] = vsi->alloc_txq;
 		}
+
+		if (vsi->type == ICE_VSI_PF)
+			max_txqs[i] += vsi->num_xdp_txq;
 	}
 
 	dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc);
@@ -2620,10 +2623,6 @@ void ice_vsi_decfg(struct ice_vsi *vsi)
 	if (vsi->type == ICE_VSI_VF &&
 	    vsi->agg_node && vsi->agg_node->valid)
 		vsi->agg_node->num_vsis--;
-	if (vsi->agg_node) {
-		vsi->agg_node->valid = false;
-		vsi->agg_node->agg_id = 0;
-	}
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 6607fa6fe55626..fb9c93f37e84f7 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -7401,15 +7401,6 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 		goto err_vsi_rebuild;
 	}
 
-	/* configure PTP timestamping after VSI rebuild */
-	if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) {
-		if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_SELF)
-			ice_ptp_cfg_timestamp(pf, false);
-		else if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_ALL)
-			/* for E82x PHC owner always need to have interrupts */
-			ice_ptp_cfg_timestamp(pf, true);
-	}
-
 	err = ice_vsi_rebuild_by_type(pf, ICE_VSI_SWITCHDEV_CTRL);
 	if (err) {
 		dev_err(dev, "Switchdev CTRL VSI rebuild failed: %d\n", err);
@@ -7461,6 +7452,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 	ice_plug_aux_dev(pf);
 	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
 		ice_lag_rebuild(pf);
+
+	/* Restore timestamp mode settings after VSI rebuild */
+	ice_ptp_restore_timestamp_mode(pf);
 	return;
 
 err_vsi_rebuild:
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 1eddcbe89b0c47..71f405f8a6fee6 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -256,48 +256,42 @@ ice_verify_pin_e810t(struct ptp_clock_info *info, unsigned int pin,
 }
 
 /**
- * ice_ptp_configure_tx_tstamp - Enable or disable Tx timestamp interrupt
- * @pf: The PF pointer to search in
- * @on: bool value for whether timestamp interrupt is enabled or disabled
+ * ice_ptp_cfg_tx_interrupt - Configure Tx timestamp interrupt for the device
+ * @pf: Board private structure
+ *
+ * Program the device to respond appropriately to the Tx timestamp interrupt
+ * cause.
  */
-static void ice_ptp_configure_tx_tstamp(struct ice_pf *pf, bool on)
+static void ice_ptp_cfg_tx_interrupt(struct ice_pf *pf)
 {
+	struct ice_hw *hw = &pf->hw;
+	bool enable;
 	u32 val;
 
+	switch (pf->ptp.tx_interrupt_mode) {
+	case ICE_PTP_TX_INTERRUPT_ALL:
+		/* React to interrupts across all quads. */
+		wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x1f);
+		enable = true;
+		break;
+	case ICE_PTP_TX_INTERRUPT_NONE:
+		/* Do not react to interrupts on any quad. */
+		wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x0);
+		enable = false;
+		break;
+	case ICE_PTP_TX_INTERRUPT_SELF:
+	default:
+		enable = pf->ptp.tstamp_config.tx_type == HWTSTAMP_TX_ON;
+		break;
+	}
+
 	/* Configure the Tx timestamp interrupt */
-	val = rd32(&pf->hw, PFINT_OICR_ENA);
-	if (on)
+	val = rd32(hw, PFINT_OICR_ENA);
+	if (enable)
 		val |= PFINT_OICR_TSYN_TX_M;
 	else
 		val &= ~PFINT_OICR_TSYN_TX_M;
-	wr32(&pf->hw, PFINT_OICR_ENA, val);
-}
-
-/**
- * ice_set_tx_tstamp - Enable or disable Tx timestamping
- * @pf: The PF pointer to search in
- * @on: bool value for whether timestamps are enabled or disabled
- */
-static void ice_set_tx_tstamp(struct ice_pf *pf, bool on)
-{
-	struct ice_vsi *vsi;
-	u16 i;
-
-	vsi = ice_get_main_vsi(pf);
-	if (!vsi)
-		return;
-
-	/* Set the timestamp enable flag for all the Tx rings */
-	ice_for_each_txq(vsi, i) {
-		if (!vsi->tx_rings[i])
-			continue;
-		vsi->tx_rings[i]->ptp_tx = on;
-	}
-
-	if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_SELF)
-		ice_ptp_configure_tx_tstamp(pf, on);
-
-	pf->ptp.tstamp_config.tx_type = on ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	wr32(hw, PFINT_OICR_ENA, val);
 }
 
 /**
@@ -311,7 +305,7 @@ static void ice_set_rx_tstamp(struct ice_pf *pf, bool on)
 	u16 i;
 
 	vsi = ice_get_main_vsi(pf);
-	if (!vsi)
+	if (!vsi || !vsi->rx_rings)
 		return;
 
 	/* Set the timestamp flag for all the Rx rings */
@@ -320,23 +314,50 @@ static void ice_set_rx_tstamp(struct ice_pf *pf, bool on)
 			continue;
 		vsi->rx_rings[i]->ptp_rx = on;
 	}
+}
+
+/**
+ * ice_ptp_disable_timestamp_mode - Disable current timestamp mode
+ * @pf: Board private structure
+ *
+ * Called during preparation for reset to temporarily disable timestamping on
+ * the device. Called during remove to disable timestamping while cleaning up
+ * driver resources.
+ */
+static void ice_ptp_disable_timestamp_mode(struct ice_pf *pf)
+{
+	struct ice_hw *hw = &pf->hw;
+	u32 val;
+
+	val = rd32(hw, PFINT_OICR_ENA);
+	val &= ~PFINT_OICR_TSYN_TX_M;
+	wr32(hw, PFINT_OICR_ENA, val);
 
-	pf->ptp.tstamp_config.rx_filter = on ? HWTSTAMP_FILTER_ALL :
-					       HWTSTAMP_FILTER_NONE;
+	ice_set_rx_tstamp(pf, false);
 }
 
 /**
- * ice_ptp_cfg_timestamp - Configure timestamp for init/deinit
+ * ice_ptp_restore_timestamp_mode - Restore timestamp configuration
  * @pf: Board private structure
- * @ena: bool value to enable or disable time stamp
  *
- * This function will configure timestamping during PTP initialization
- * and deinitialization
+ * Called at the end of rebuild to restore timestamp configuration after
+ * a device reset.
  */
-void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena)
+void ice_ptp_restore_timestamp_mode(struct ice_pf *pf)
 {
-	ice_set_tx_tstamp(pf, ena);
-	ice_set_rx_tstamp(pf, ena);
+	struct ice_hw *hw = &pf->hw;
+	bool enable_rx;
+
+	ice_ptp_cfg_tx_interrupt(pf);
+
+	enable_rx = pf->ptp.tstamp_config.rx_filter == HWTSTAMP_FILTER_ALL;
+	ice_set_rx_tstamp(pf, enable_rx);
+
+	/* Trigger an immediate software interrupt to ensure that timestamps
+	 * which occurred during reset are handled now.
+	 */
+	wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M);
+	ice_flush(hw);
 }
 
 /**
@@ -2037,10 +2058,10 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config)
 {
 	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
-		ice_set_tx_tstamp(pf, false);
+		pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_OFF;
 		break;
 	case HWTSTAMP_TX_ON:
-		ice_set_tx_tstamp(pf, true);
+		pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_ON;
 		break;
 	default:
 		return -ERANGE;
@@ -2048,7 +2069,7 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config)
 
 	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
-		ice_set_rx_tstamp(pf, false);
+		pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
@@ -2064,12 +2085,15 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config)
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
 	case HWTSTAMP_FILTER_NTP_ALL:
 	case HWTSTAMP_FILTER_ALL:
-		ice_set_rx_tstamp(pf, true);
+		pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:
 		return -ERANGE;
 	}
 
+	/* Immediately update the device timestamping mode */
+	ice_ptp_restore_timestamp_mode(pf);
+
 	return 0;
 }
 
@@ -2737,7 +2761,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf)
 	clear_bit(ICE_FLAG_PTP, pf->flags);
 
 	/* Disable timestamping for both Tx and Rx */
-	ice_ptp_cfg_timestamp(pf, false);
+	ice_ptp_disable_timestamp_mode(pf);
 
 	kthread_cancel_delayed_work_sync(&ptp->work);
 
@@ -2803,15 +2827,7 @@ static int ice_ptp_init_owner(struct ice_pf *pf)
 	/* Release the global hardware lock */
 	ice_ptp_unlock(hw);
 
-	if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_ALL) {
-		/* The clock owner for this device type handles the timestamp
-		 * interrupt for all ports.
-		 */
-		ice_ptp_configure_tx_tstamp(pf, true);
-
-		/* React on all quads interrupts for E82x */
-		wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x1f);
-
+	if (!ice_is_e810(hw)) {
 		/* Enable quad interrupts */
 		err = ice_ptp_tx_ena_intr(pf, true, itr);
 		if (err)
@@ -2881,13 +2897,6 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
 	case ICE_PHY_E810:
 		return ice_ptp_init_tx_e810(pf, &ptp_port->tx);
 	case ICE_PHY_E822:
-		/* Non-owner PFs don't react to any interrupts on E82x,
-		 * neither on own quad nor on others
-		 */
-		if (!ice_ptp_pf_handles_tx_interrupt(pf)) {
-			ice_ptp_configure_tx_tstamp(pf, false);
-			wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x0);
-		}
 		kthread_init_delayed_work(&ptp_port->ov_work,
 					  ice_ptp_wait_for_offsets);
 
@@ -3032,6 +3041,9 @@ void ice_ptp_init(struct ice_pf *pf)
 	/* Start the PHY timestamping block */
 	ice_ptp_reset_phy_timestamping(pf);
 
+	/* Configure initial Tx interrupt settings */
+	ice_ptp_cfg_tx_interrupt(pf);
+
 	set_bit(ICE_FLAG_PTP, pf->flags);
 	err = ice_ptp_init_work(pf, ptp);
 	if (err)
@@ -3067,7 +3079,7 @@ void ice_ptp_release(struct ice_pf *pf)
 		return;
 
 	/* Disable timestamping for both Tx and Rx */
-	ice_ptp_cfg_timestamp(pf, false);
+	ice_ptp_disable_timestamp_mode(pf);
 
 	ice_ptp_remove_auxbus_device(pf);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
index 8f6f9439275643..06a330867fc9be 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -292,7 +292,7 @@ int ice_ptp_clock_index(struct ice_pf *pf);
 struct ice_pf;
 int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr);
 int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr);
-void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena);
+void ice_ptp_restore_timestamp_mode(struct ice_pf *pf);
 
 void ice_ptp_extts_event(struct ice_pf *pf);
 s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb);
@@ -317,8 +317,7 @@ static inline int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr)
 	return -EOPNOTSUPP;
 }
 
-static inline void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena) { }
-
+static inline void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) { }
 static inline void ice_ptp_extts_event(struct ice_pf *pf) { }
 static inline s8
 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb)
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 6d573908de7a0b..a00b55e14aac4e 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -3961,3 +3961,57 @@ int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num)
 
 	return ret;
 }
+
+/**
+ * ice_cgu_get_output_pin_state_caps - get output pin state capabilities
+ * @hw: pointer to the hw struct
+ * @pin_id: id of a pin
+ * @caps: capabilities to modify
+ *
+ * Return:
+ * * 0 - success, state capabilities were modified
+ * * negative - failure, capabilities were not modified
+ */
+int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id,
+				      unsigned long *caps)
+{
+	bool can_change = true;
+
+	switch (hw->device_id) {
+	case ICE_DEV_ID_E810C_SFP:
+		if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3)
+			can_change = false;
+		break;
+	case ICE_DEV_ID_E810C_QSFP:
+		if (pin_id == ZL_OUT2 || pin_id == ZL_OUT3 || pin_id == ZL_OUT4)
+			can_change = false;
+		break;
+	case ICE_DEV_ID_E823L_10G_BASE_T:
+	case ICE_DEV_ID_E823L_1GBE:
+	case ICE_DEV_ID_E823L_BACKPLANE:
+	case ICE_DEV_ID_E823L_QSFP:
+	case ICE_DEV_ID_E823L_SFP:
+	case ICE_DEV_ID_E823C_10G_BASE_T:
+	case ICE_DEV_ID_E823C_BACKPLANE:
+	case ICE_DEV_ID_E823C_QSFP:
+	case ICE_DEV_ID_E823C_SFP:
+	case ICE_DEV_ID_E823C_SGMII:
+		if (hw->cgu_part_number ==
+		    ICE_AQC_GET_LINK_TOPO_NODE_NR_ZL30632_80032 &&
+		    pin_id == ZL_OUT2)
+			can_change = false;
+		else if (hw->cgu_part_number ==
+			 ICE_AQC_GET_LINK_TOPO_NODE_NR_SI5383_5384 &&
+			 pin_id == SI_OUT1)
+			can_change = false;
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (can_change)
+		*caps |= DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE;
+	else
+		*caps &= ~DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE;
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 36aeeef99ec07e..cf76701566c724 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -282,6 +282,8 @@ int ice_get_cgu_state(struct ice_hw *hw, u8 dpll_idx,
 int ice_get_cgu_rclk_pin_info(struct ice_hw *hw, u8 *base_idx, u8 *pin_num);
 
 void ice_ptp_init_phy_model(struct ice_hw *hw);
+int ice_cgu_get_output_pin_state_caps(struct ice_hw *hw, u8 pin_id,
+				      unsigned long *caps);
 
 #define PFTSYN_SEM_BYTES	4
 
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index 2a5e6616cc0a79..e1494f24f661d3 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -374,16 +374,11 @@ static void ice_ena_vf_mappings(struct ice_vf *vf)
  */
 int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector)
 {
-	struct ice_pf *pf;
-
 	if (!vf || !q_vector)
 		return -EINVAL;
 
-	pf = vf->pf;
-
 	/* always add one to account for the OICR being the first MSIX */
-	return pf->sriov_base_vector + pf->vfs.num_msix_per * vf->vf_id +
-		q_vector->v_idx + 1;
+	return vf->first_vector_idx + q_vector->v_idx + 1;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index 37b54db91df275..dd03cb69ad26b4 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -630,32 +630,83 @@ bool ice_is_tunnel_supported(struct net_device *dev)
 	return ice_tc_tun_get_type(dev) != TNL_LAST;
 }
 
-static int
-ice_eswitch_tc_parse_action(struct ice_tc_flower_fltr *fltr,
-			    struct flow_action_entry *act)
+static bool ice_tc_is_dev_uplink(struct net_device *dev)
+{
+	return netif_is_ice(dev) || ice_is_tunnel_supported(dev);
+}
+
+static int ice_tc_setup_redirect_action(struct net_device *filter_dev,
+					struct ice_tc_flower_fltr *fltr,
+					struct net_device *target_dev)
 {
 	struct ice_repr *repr;
 
+	fltr->action.fltr_act = ICE_FWD_TO_VSI;
+
+	if (ice_is_port_repr_netdev(filter_dev) &&
+	    ice_is_port_repr_netdev(target_dev)) {
+		repr = ice_netdev_to_repr(target_dev);
+
+		fltr->dest_vsi = repr->src_vsi;
+		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
+	} else if (ice_is_port_repr_netdev(filter_dev) &&
+		   ice_tc_is_dev_uplink(target_dev)) {
+		repr = ice_netdev_to_repr(filter_dev);
+
+		fltr->dest_vsi = repr->src_vsi->back->switchdev.uplink_vsi;
+		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
+	} else if (ice_tc_is_dev_uplink(filter_dev) &&
+		   ice_is_port_repr_netdev(target_dev)) {
+		repr = ice_netdev_to_repr(target_dev);
+
+		fltr->dest_vsi = repr->src_vsi;
+		fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
+	} else {
+		NL_SET_ERR_MSG_MOD(fltr->extack,
+				   "Unsupported netdevice in switchdev mode");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+ice_tc_setup_drop_action(struct net_device *filter_dev,
+			 struct ice_tc_flower_fltr *fltr)
+{
+	fltr->action.fltr_act = ICE_DROP_PACKET;
+
+	if (ice_is_port_repr_netdev(filter_dev)) {
+		fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
+	} else if (ice_tc_is_dev_uplink(filter_dev)) {
+		fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
+	} else {
+		NL_SET_ERR_MSG_MOD(fltr->extack,
+				   "Unsupported netdevice in switchdev mode");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ice_eswitch_tc_parse_action(struct net_device *filter_dev,
+				       struct ice_tc_flower_fltr *fltr,
+				       struct flow_action_entry *act)
+{
+	int err;
+
 	switch (act->id) {
 	case FLOW_ACTION_DROP:
-		fltr->action.fltr_act = ICE_DROP_PACKET;
+		err = ice_tc_setup_drop_action(filter_dev, fltr);
+		if (err)
+			return err;
+
 		break;
 
 	case FLOW_ACTION_REDIRECT:
-		fltr->action.fltr_act = ICE_FWD_TO_VSI;
-
-		if (ice_is_port_repr_netdev(act->dev)) {
-			repr = ice_netdev_to_repr(act->dev);
-
-			fltr->dest_vsi = repr->src_vsi;
-			fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
-		} else if (netif_is_ice(act->dev) ||
-			   ice_is_tunnel_supported(act->dev)) {
-			fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
-		} else {
-			NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported netdevice in switchdev mode");
-			return -EINVAL;
-		}
+		err = ice_tc_setup_redirect_action(filter_dev, fltr, act->dev);
+		if (err)
+			return err;
 
 		break;
 
@@ -696,10 +747,6 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 		goto exit;
 	}
 
-	/* egress traffic is always redirect to uplink */
-	if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS)
-		fltr->dest_vsi = vsi->back->switchdev.uplink_vsi;
-
 	rule_info.sw_act.fltr_act = fltr->action.fltr_act;
 	if (fltr->action.fltr_act != ICE_DROP_PACKET)
 		rule_info.sw_act.vsi_handle = fltr->dest_vsi->idx;
@@ -713,13 +760,21 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr)
 	rule_info.flags_info.act_valid = true;
 
 	if (fltr->direction == ICE_ESWITCH_FLTR_INGRESS) {
+		/* Uplink to VF */
 		rule_info.sw_act.flag |= ICE_FLTR_RX;
 		rule_info.sw_act.src = hw->pf_id;
 		rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE;
-	} else {
+	} else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
+		   fltr->dest_vsi == vsi->back->switchdev.uplink_vsi) {
+		/* VF to Uplink */
 		rule_info.sw_act.flag |= ICE_FLTR_TX;
 		rule_info.sw_act.src = vsi->idx;
 		rule_info.flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE;
+	} else {
+		/* VF to VF */
+		rule_info.sw_act.flag |= ICE_FLTR_TX;
+		rule_info.sw_act.src = vsi->idx;
+		rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE;
 	}
 
 	/* specify the cookie as filter_rule_id */
@@ -1745,16 +1800,17 @@ ice_tc_parse_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr,
 
 /**
  * ice_parse_tc_flower_actions - Parse the actions for a TC filter
+ * @filter_dev: Pointer to device on which filter is being added
  * @vsi: Pointer to VSI
  * @cls_flower: Pointer to TC flower offload structure
  * @fltr: Pointer to TC flower filter structure
  *
  * Parse the actions for a TC filter
  */
-static int
-ice_parse_tc_flower_actions(struct ice_vsi *vsi,
-			    struct flow_cls_offload *cls_flower,
-			    struct ice_tc_flower_fltr *fltr)
+static int ice_parse_tc_flower_actions(struct net_device *filter_dev,
+				       struct ice_vsi *vsi,
+				       struct flow_cls_offload *cls_flower,
+				       struct ice_tc_flower_fltr *fltr)
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(cls_flower);
 	struct flow_action *flow_action = &rule->action;
@@ -1769,7 +1825,7 @@ ice_parse_tc_flower_actions(struct ice_vsi *vsi,
 
 	flow_action_for_each(i, act, flow_action) {
 		if (ice_is_eswitch_mode_switchdev(vsi->back))
-			err = ice_eswitch_tc_parse_action(fltr, act);
+			err = ice_eswitch_tc_parse_action(filter_dev, fltr, act);
 		else
 			err = ice_tc_parse_action(vsi, fltr, act);
 		if (err)
@@ -1856,7 +1912,7 @@ ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi,
 	if (err < 0)
 		goto err;
 
-	err = ice_parse_tc_flower_actions(vsi, f, fltr);
+	err = ice_parse_tc_flower_actions(netdev, vsi, f, fltr);
 	if (err < 0)
 		goto err;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 52d0a126eb6161..9e97ea86306867 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -2306,9 +2306,6 @@ ice_tstamp(struct ice_tx_ring *tx_ring, struct sk_buff *skb,
 	if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
 		return;
 
-	if (!tx_ring->ptp_tx)
-		return;
-
 	/* Tx timestamps cannot be sampled when doing TSO */
 	if (first->tx_flags & ICE_TX_FLAGS_TSO)
 		return;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 166413fc33f48f..daf7b9dbb1435a 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -380,7 +380,6 @@ struct ice_tx_ring {
 #define ICE_TX_FLAGS_RING_VLAN_L2TAG2	BIT(2)
 	u8 flags;
 	u8 dcb_tc;			/* Traffic class of ring */
-	u8 ptp_tx;
 } ____cacheline_internodealigned_in_smp;
 
 static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring)
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index aca1f2ea50340f..b7ae099521566f 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -829,12 +829,16 @@ static void ice_notify_vf_reset(struct ice_vf *vf)
 int ice_reset_vf(struct ice_vf *vf, u32 flags)
 {
 	struct ice_pf *pf = vf->pf;
+	struct ice_lag *lag;
 	struct ice_vsi *vsi;
+	u8 act_prt, pri_prt;
 	struct device *dev;
 	int err = 0;
 	bool rsd;
 
 	dev = ice_pf_to_dev(pf);
+	act_prt = ICE_LAG_INVALID_PORT;
+	pri_prt = pf->hw.port_info->lport;
 
 	if (flags & ICE_VF_RESET_NOTIFY)
 		ice_notify_vf_reset(vf);
@@ -845,6 +849,17 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)
 		return 0;
 	}
 
+	lag = pf->lag;
+	mutex_lock(&pf->lag_mutex);
+	if (lag && lag->bonded && lag->primary) {
+		act_prt = lag->active_port;
+		if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT &&
+		    lag->upper_netdev)
+			ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt);
+		else
+			act_prt = ICE_LAG_INVALID_PORT;
+	}
+
 	if (flags & ICE_VF_RESET_LOCK)
 		mutex_lock(&vf->cfg_lock);
 	else
@@ -937,6 +952,11 @@ out_unlock:
 	if (flags & ICE_VF_RESET_LOCK)
 		mutex_unlock(&vf->cfg_lock);
 
+	if (lag && lag->bonded && lag->primary &&
+	    act_prt != ICE_LAG_INVALID_PORT)
+		ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt);
+	mutex_unlock(&pf->lag_mutex);
+
 	return err;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c
index d7b10dc67f0352..80dc4bcdd3a41c 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c
@@ -32,7 +32,6 @@ static void ice_port_vlan_on(struct ice_vsi *vsi)
 		/* setup outer VLAN ops */
 		vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan;
 		vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan;
-		vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan;
 
 		/* setup inner VLAN ops */
 		vlan_ops = &vsi->inner_vlan_ops;
@@ -47,8 +46,13 @@ static void ice_port_vlan_on(struct ice_vsi *vsi)
 
 		vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan;
 		vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan;
-		vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan;
 	}
+
+	/* all Rx traffic should be in the domain of the assigned port VLAN,
+	 * so prevent disabling Rx VLAN filtering
+	 */
+	vlan_ops->dis_rx_filtering = noop_vlan;
+
 	vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering;
 }
 
@@ -77,6 +81,8 @@ static void ice_port_vlan_off(struct ice_vsi *vsi)
 		vlan_ops->del_vlan = ice_vsi_del_vlan;
 	}
 
+	vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering;
+
 	if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags))
 		vlan_ops->ena_rx_filtering = noop_vlan;
 	else
@@ -141,7 +147,6 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi)
 		&vsi->outer_vlan_ops : &vsi->inner_vlan_ops;
 
 	vlan_ops->add_vlan = ice_vsi_add_vlan;
-	vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering;
 	vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering;
 	vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index cdf17b1e2f252b..1c7b4ded948b63 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -1523,7 +1523,6 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg)
 	u16 num_q_vectors_mapped, vsi_id, vector_id;
 	struct virtchnl_irq_map_info *irqmap_info;
 	struct virtchnl_vector_map *map;
-	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
 	int i;
 
@@ -1535,7 +1534,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg)
 	 * there is actually at least a single VF queue vector mapped
 	 */
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) ||
-	    pf->vfs.num_msix_per < num_q_vectors_mapped ||
+	    vf->num_msix < num_q_vectors_mapped ||
 	    !num_q_vectors_mapped) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
@@ -1557,7 +1556,7 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg)
 		/* vector_id is always 0-based for each VF, and can never be
 		 * larger than or equal to the max allowed interrupts per VF
 		 */
-		if (!(vector_id < pf->vfs.num_msix_per) ||
+		if (!(vector_id < vf->num_msix) ||
 		    !ice_vc_isvalid_vsi_id(vf, vsi_id) ||
 		    (!vector_id && (map->rxq_map || map->txq_map))) {
 			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
@@ -1603,9 +1602,24 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 	    (struct virtchnl_vsi_queue_config_info *)msg;
 	struct virtchnl_queue_pair_info *qpi;
 	struct ice_pf *pf = vf->pf;
+	struct ice_lag *lag;
 	struct ice_vsi *vsi;
+	u8 act_prt, pri_prt;
 	int i = -1, q_idx;
 
+	lag = pf->lag;
+	mutex_lock(&pf->lag_mutex);
+	act_prt = ICE_LAG_INVALID_PORT;
+	pri_prt = pf->hw.port_info->lport;
+	if (lag && lag->bonded && lag->primary) {
+		act_prt = lag->active_port;
+		if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT &&
+		    lag->upper_netdev)
+			ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt);
+		else
+			act_prt = ICE_LAG_INVALID_PORT;
+	}
+
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
 		goto error_param;
 
@@ -1729,6 +1743,11 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 		}
 	}
 
+	if (lag && lag->bonded && lag->primary &&
+	    act_prt != ICE_LAG_INVALID_PORT)
+		ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt);
+	mutex_unlock(&pf->lag_mutex);
+
 	/* send the response to the VF */
 	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES,
 				     VIRTCHNL_STATUS_SUCCESS, NULL, 0);
@@ -1743,6 +1762,11 @@ error_param:
 				vf->vf_id, i);
 	}
 
+	if (lag && lag->bonded && lag->primary &&
+	    act_prt != ICE_LAG_INVALID_PORT)
+		ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt);
+	mutex_unlock(&pf->lag_mutex);
+
 	ice_lag_move_new_vf_nodes(vf);
 
 	/* send the response to the VF */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 5e1ef70d54fe41..1f728a9004d9e4 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -2365,7 +2365,7 @@ static void idpf_tx_splitq_map(struct idpf_queue *tx_q,
  */
 int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off)
 {
-	const struct skb_shared_info *shinfo = skb_shinfo(skb);
+	const struct skb_shared_info *shinfo;
 	union {
 		struct iphdr *v4;
 		struct ipv6hdr *v6;
@@ -2379,13 +2379,15 @@ int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off)
 	u32 paylen, l4_start;
 	int err;
 
-	if (!shinfo->gso_size)
+	if (!skb_is_gso(skb))
 		return 0;
 
 	err = skb_cow_head(skb, 0);
 	if (err < 0)
 		return err;
 
+	shinfo = skb_shinfo(skb);
+
 	ip.hdr = skb_network_header(skb);
 	l4.hdr = skb_transport_header(skb);
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 90817136808d46..29aac327574d64 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4790,14 +4790,17 @@ static void mvneta_ethtool_get_strings(struct net_device *netdev, u32 sset,
 				       u8 *data)
 {
 	if (sset == ETH_SS_STATS) {
+		struct mvneta_port *pp = netdev_priv(netdev);
 		int i;
 
 		for (i = 0; i < ARRAY_SIZE(mvneta_statistics); i++)
 			memcpy(data + i * ETH_GSTRING_LEN,
 			       mvneta_statistics[i].name, ETH_GSTRING_LEN);
 
-		data += ETH_GSTRING_LEN * ARRAY_SIZE(mvneta_statistics);
-		page_pool_ethtool_stats_get_strings(data);
+		if (!pp->bm_priv) {
+			data += ETH_GSTRING_LEN * ARRAY_SIZE(mvneta_statistics);
+			page_pool_ethtool_stats_get_strings(data);
+		}
 	}
 }
 
@@ -4915,8 +4918,10 @@ static void mvneta_ethtool_pp_stats(struct mvneta_port *pp, u64 *data)
 	struct page_pool_stats stats = {};
 	int i;
 
-	for (i = 0; i < rxq_number; i++)
-		page_pool_get_stats(pp->rxqs[i].page_pool, &stats);
+	for (i = 0; i < rxq_number; i++) {
+		if (pp->rxqs[i].page_pool)
+			page_pool_get_stats(pp->rxqs[i].page_pool, &stats);
+	}
 
 	page_pool_ethtool_stats_get(data, &stats);
 }
@@ -4932,14 +4937,21 @@ static void mvneta_ethtool_get_stats(struct net_device *dev,
 	for (i = 0; i < ARRAY_SIZE(mvneta_statistics); i++)
 		*data++ = pp->ethtool_stats[i];
 
-	mvneta_ethtool_pp_stats(pp, data);
+	if (!pp->bm_priv)
+		mvneta_ethtool_pp_stats(pp, data);
 }
 
 static int mvneta_ethtool_get_sset_count(struct net_device *dev, int sset)
 {
-	if (sset == ETH_SS_STATS)
-		return ARRAY_SIZE(mvneta_statistics) +
-		       page_pool_ethtool_stats_get_count();
+	if (sset == ETH_SS_STATS) {
+		int count = ARRAY_SIZE(mvneta_statistics);
+		struct mvneta_port *pp = netdev_priv(dev);
+
+		if (!pp->bm_priv)
+			count += page_pool_ethtool_stats_get_count();
+
+		return count;
+	}
 
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index 552970c7dec097..a9bdf3283a852f 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -1193,6 +1193,13 @@ int octep_device_setup(struct octep_device *oct)
 	if (ret)
 		return ret;
 
+	INIT_WORK(&oct->tx_timeout_task, octep_tx_timeout_task);
+	INIT_WORK(&oct->ctrl_mbox_task, octep_ctrl_mbox_task);
+	INIT_DELAYED_WORK(&oct->intr_poll_task, octep_intr_poll_task);
+	oct->poll_non_ioq_intr = true;
+	queue_delayed_work(octep_wq, &oct->intr_poll_task,
+			   msecs_to_jiffies(OCTEP_INTR_POLL_TIME_MSECS));
+
 	atomic_set(&oct->hb_miss_cnt, 0);
 	INIT_DELAYED_WORK(&oct->hb_task, octep_hb_timeout_task);
 
@@ -1258,7 +1265,8 @@ static bool get_fw_ready_status(struct pci_dev *pdev)
 
 		pci_read_config_byte(pdev, (pos + 8), &status);
 		dev_info(&pdev->dev, "Firmware ready status = %u\n", status);
-		return status;
+#define FW_STATUS_READY 1ULL
+		return status == FW_STATUS_READY;
 	}
 	return false;
 }
@@ -1325,21 +1333,18 @@ static int octep_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_octep_config;
 	}
 
-	octep_ctrl_net_get_info(octep_dev, OCTEP_CTRL_NET_INVALID_VFID,
-				&octep_dev->conf->fw_info);
+	err = octep_ctrl_net_get_info(octep_dev, OCTEP_CTRL_NET_INVALID_VFID,
+				      &octep_dev->conf->fw_info);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to get firmware info\n");
+		goto register_dev_err;
+	}
 	dev_info(&octep_dev->pdev->dev, "Heartbeat interval %u msecs Heartbeat miss count %u\n",
 		 octep_dev->conf->fw_info.hb_interval,
 		 octep_dev->conf->fw_info.hb_miss_count);
 	queue_delayed_work(octep_wq, &octep_dev->hb_task,
 			   msecs_to_jiffies(octep_dev->conf->fw_info.hb_interval));
 
-	INIT_WORK(&octep_dev->tx_timeout_task, octep_tx_timeout_task);
-	INIT_WORK(&octep_dev->ctrl_mbox_task, octep_ctrl_mbox_task);
-	INIT_DELAYED_WORK(&octep_dev->intr_poll_task, octep_intr_poll_task);
-	octep_dev->poll_non_ioq_intr = true;
-	queue_delayed_work(octep_wq, &octep_dev->intr_poll_task,
-			   msecs_to_jiffies(OCTEP_INTR_POLL_TIME_MSECS));
-
 	netdev->netdev_ops = &octep_netdev_ops;
 	octep_set_ethtool_ops(netdev);
 	netif_carrier_off(netdev);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 6845556581c3fa..5df42634ceb84c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -1945,7 +1945,7 @@ struct mcs_hw_info {
 	u8 tcam_entries;	/* RX/TX Tcam entries per mcs block */
 	u8 secy_entries;	/* RX/TX SECY entries per mcs block */
 	u8 sc_entries;		/* RX/TX SC CAM entries per mcs block */
-	u8 sa_entries;		/* PN table entries = SA entries */
+	u16 sa_entries;		/* PN table entries = SA entries */
 	u64 rsvd[16];
 };
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c
index c43f19dfbd7440..c1775bd01c2b48 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c
@@ -117,7 +117,7 @@ void mcs_get_rx_secy_stats(struct mcs *mcs, struct mcs_secy_stats *stats, int id
 	reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYTAGGEDCTLX(id);
 	stats->pkt_tagged_ctl_cnt = mcs_reg_read(mcs, reg);
 
-	reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDORNOTAGX(id);
+	reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDX(id);
 	stats->pkt_untaged_cnt = mcs_reg_read(mcs, reg);
 
 	reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYCTLX(id);
@@ -215,7 +215,7 @@ void mcs_get_sc_stats(struct mcs *mcs, struct mcs_sc_stats *stats,
 		reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSCNOTVALIDX(id);
 		stats->pkt_notvalid_cnt = mcs_reg_read(mcs, reg);
 
-		reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDOROKX(id);
+		reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDX(id);
 		stats->pkt_unchecked_cnt = mcs_reg_read(mcs, reg);
 
 		if (mcs->hw->mcs_blks > 1) {
@@ -1219,6 +1219,17 @@ struct mcs *mcs_get_pdata(int mcs_id)
 	return NULL;
 }
 
+bool is_mcs_bypass(int mcs_id)
+{
+	struct mcs *mcs_dev;
+
+	list_for_each_entry(mcs_dev, &mcs_list, mcs_list) {
+		if (mcs_dev->mcs_id == mcs_id)
+			return mcs_dev->bypass;
+	}
+	return true;
+}
+
 void mcs_set_port_cfg(struct mcs *mcs, struct mcs_port_cfg_set_req *req)
 {
 	u64 val = 0;
@@ -1436,7 +1447,7 @@ static int mcs_x2p_calibration(struct mcs *mcs)
 	return err;
 }
 
-static void mcs_set_external_bypass(struct mcs *mcs, u8 bypass)
+static void mcs_set_external_bypass(struct mcs *mcs, bool bypass)
 {
 	u64 val;
 
@@ -1447,6 +1458,7 @@ static void mcs_set_external_bypass(struct mcs *mcs, u8 bypass)
 	else
 		val &= ~BIT_ULL(6);
 	mcs_reg_write(mcs, MCSX_MIL_GLOBAL, val);
+	mcs->bypass = bypass;
 }
 
 static void mcs_global_cfg(struct mcs *mcs)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.h b/drivers/net/ethernet/marvell/octeontx2/af/mcs.h
index 0f89dcb764654b..f927cc61dfd21f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.h
@@ -149,6 +149,7 @@ struct mcs {
 	u16			num_vec;
 	void			*rvu;
 	u16			*tx_sa_active;
+	bool                      bypass;
 };
 
 struct mcs_ops {
@@ -206,6 +207,7 @@ void mcs_get_custom_tag_cfg(struct mcs *mcs, struct mcs_custom_tag_cfg_get_req *
 int mcs_alloc_ctrlpktrule(struct rsrc_bmap *rsrc, u16 *pf_map, u16 offset, u16 pcifunc);
 int mcs_free_ctrlpktrule(struct mcs *mcs, struct mcs_free_ctrl_pkt_rule_req *req);
 int mcs_ctrlpktrule_write(struct mcs *mcs, struct mcs_ctrl_pkt_rule_write_req *req);
+bool is_mcs_bypass(int mcs_id);
 
 /* CN10K-B APIs */
 void cn10kb_mcs_set_hw_capabilities(struct mcs *mcs);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h
index f3ab01fc363c8d..f4c6de89002c1d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h
@@ -810,14 +810,37 @@
 		offset = 0x9d8ull;			\
 	offset; })
 
+#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDX(a) ({	\
+	u64 offset;					\
+							\
+	offset = 0xee80ull;				\
+	if (mcs->hw->mcs_blks > 1)			\
+		offset = 0xe818ull;			\
+	offset += (a) * 0x8ull;				\
+	offset; })
+
+#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDX(a) ({	\
+	u64 offset;					\
+							\
+	offset = 0xa680ull;				\
+	if (mcs->hw->mcs_blks > 1)			\
+		offset = 0xd018ull;			\
+	offset += (a) * 0x8ull;				\
+	offset; })
+
+#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCLATEORDELAYEDX(a)	({	\
+	u64 offset;						\
+								\
+	offset = 0xf680ull;					\
+	if (mcs->hw->mcs_blks > 1)				\
+		offset = 0xe018ull;				\
+	offset += (a) * 0x8ull;					\
+	offset; })
+
 #define MCSX_CSE_RX_MEM_SLAVE_INOCTETSSCDECRYPTEDX(a)	(0xe680ull + (a) * 0x8ull)
 #define MCSX_CSE_RX_MEM_SLAVE_INOCTETSSCVALIDATEX(a)	(0xde80ull + (a) * 0x8ull)
-#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDORNOTAGX(a)	(0xa680ull + (a) * 0x8ull)
 #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYNOTAGX(a)	(0xd218 + (a) * 0x8ull)
-#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDX(a)	(0xd018ull + (a) * 0x8ull)
-#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDOROKX(a)	(0xee80ull + (a) * 0x8ull)
 #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYCTLX(a)		(0xb680ull + (a) * 0x8ull)
-#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCLATEORDELAYEDX(a) (0xf680ull + (a) * 0x8ull)
 #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSAINVALIDX(a)	(0x12680ull + (a) * 0x8ull)
 #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSANOTUSINGSAERRORX(a) (0x15680ull + (a) * 0x8ull)
 #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSANOTVALIDX(a)	(0x13680ull + (a) * 0x8ull)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index af21e2030cff28..4728ba34b0e34c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -373,6 +373,11 @@ void rpm_lmac_pause_frm_config(void *rpmd, int lmac_id, bool enable)
 	cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE;
 	rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg);
 
+	/* Disable forward pause to driver */
+	cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG);
+	cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD;
+	rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg);
+
 	/* Enable channel mask for all LMACS */
 	if (is_dev_rpm2(rpm))
 		rpm_write(rpm, lmac_id, RPM2_CMR_CHAN_MSK_OR, 0xffff);
@@ -616,12 +621,10 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 p
 
 	if (rx_pause) {
 		cfg &= ~(RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE |
-				RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE |
-				RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD);
+			 RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE);
 	} else {
 		cfg |= (RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE |
-				RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE |
-				RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD);
+			RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE);
 	}
 
 	if (tx_pause) {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 22c395c7d040b4..731bb82b577c20 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -2631,6 +2631,9 @@ static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc)
 	rvu_npc_free_mcam_entries(rvu, pcifunc, -1);
 	rvu_mac_reset(rvu, pcifunc);
 
+	if (rvu->mcs_blk_cnt)
+		rvu_mcs_flr_handler(rvu, pcifunc);
+
 	mutex_unlock(&rvu->flr_lock);
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index c4d999ef5ab4b2..cce2806aaa50cc 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -345,6 +345,7 @@ struct nix_hw {
 	struct nix_txvlan txvlan;
 	struct nix_ipolicer *ipolicer;
 	u64    *tx_credits;
+	u8	cc_mcs_cnt;
 };
 
 /* RVU block's capabilities or functionality,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index c70932625d0da0..21b5d71c1e3758 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -538,7 +538,7 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl)
 
 	rvu_dl->devlink_wq = create_workqueue("rvu_devlink_wq");
 	if (!rvu_dl->devlink_wq)
-		goto err;
+		return -ENOMEM;
 
 	INIT_WORK(&rvu_reporters->intr_work, rvu_nix_intr_work);
 	INIT_WORK(&rvu_reporters->gen_work, rvu_nix_gen_work);
@@ -546,9 +546,6 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl)
 	INIT_WORK(&rvu_reporters->ras_work, rvu_nix_ras_work);
 
 	return 0;
-err:
-	rvu_nix_health_reporters_destroy(rvu_dl);
-	return -ENOMEM;
 }
 
 static int rvu_nix_health_reporters_create(struct rvu_devlink *rvu_dl)
@@ -1087,7 +1084,7 @@ static int rvu_npa_register_reporters(struct rvu_devlink *rvu_dl)
 
 	rvu_dl->devlink_wq = create_workqueue("rvu_devlink_wq");
 	if (!rvu_dl->devlink_wq)
-		goto err;
+		return -ENOMEM;
 
 	INIT_WORK(&rvu_reporters->intr_work, rvu_npa_intr_work);
 	INIT_WORK(&rvu_reporters->err_work, rvu_npa_err_work);
@@ -1095,9 +1092,6 @@ static int rvu_npa_register_reporters(struct rvu_devlink *rvu_dl)
 	INIT_WORK(&rvu_reporters->ras_work, rvu_npa_ras_work);
 
 	return 0;
-err:
-	rvu_npa_health_reporters_destroy(rvu_dl);
-	return -ENOMEM;
 }
 
 static int rvu_npa_health_reporters_create(struct rvu_devlink *rvu_dl)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 23c2f2ed2fb832..4227ebb4a758db 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -12,6 +12,7 @@
 #include "rvu_reg.h"
 #include "rvu.h"
 #include "npc.h"
+#include "mcs.h"
 #include "cgx.h"
 #include "lmac_common.h"
 #include "rvu_npc_hash.h"
@@ -4389,6 +4390,12 @@ static void nix_link_config(struct rvu *rvu, int blkaddr,
 			    SDP_HW_MAX_FRS << 16 | NIC_HW_MIN_FRS);
 	}
 
+	/* Get MCS external bypass status for CN10K-B */
+	if (mcs_get_blkcnt() == 1) {
+		/* Adjust for 2 credits when external bypass is disabled */
+		nix_hw->cc_mcs_cnt = is_mcs_bypass(0) ? 0 : 2;
+	}
+
 	/* Set credits for Tx links assuming max packet length allowed.
 	 * This will be reconfigured based on MTU set for PF/VF.
 	 */
@@ -4412,6 +4419,7 @@ static void nix_link_config(struct rvu *rvu, int blkaddr,
 			tx_credits = (lmac_fifo_len - lmac_max_frs) / 16;
 			/* Enable credits and set credit pkt count to max allowed */
 			cfg =  (tx_credits << 12) | (0x1FF << 2) | BIT_ULL(1);
+			cfg |= FIELD_PREP(NIX_AF_LINKX_MCS_CNT_MASK, nix_hw->cc_mcs_cnt);
 
 			link = iter + slink;
 			nix_hw->tx_credits[link] = tx_credits;
@@ -5505,6 +5513,8 @@ int rvu_mbox_handler_nix_bandprof_free(struct rvu *rvu,
 
 		ipolicer = &nix_hw->ipolicer[layer];
 		for (idx = 0; idx < req->prof_count[layer]; idx++) {
+			if (idx == MAX_BANDPROF_PER_PFFUNC)
+				break;
 			prof_idx = req->prof_idx[layer][idx];
 			if (prof_idx >= ipolicer->band_prof.max ||
 			    ipolicer->pfvf_map[prof_idx] != pcifunc)
@@ -5518,8 +5528,6 @@ int rvu_mbox_handler_nix_bandprof_free(struct rvu *rvu,
 			ipolicer->pfvf_map[prof_idx] = 0x00;
 			ipolicer->match_id[prof_idx] = 0;
 			rvu_free_rsrc(&ipolicer->band_prof, prof_idx);
-			if (idx == MAX_BANDPROF_PER_PFFUNC)
-				break;
 		}
 	}
 	mutex_unlock(&rvu->rsrc_lock);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 16cfc802e348d9..0bcf3e55928065 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -389,7 +389,13 @@ static u64 npc_get_default_entry_action(struct rvu *rvu, struct npc_mcam *mcam,
 	int bank, nixlf, index;
 
 	/* get ucast entry rule entry index */
-	nix_get_nixlf(rvu, pf_func, &nixlf, NULL);
+	if (nix_get_nixlf(rvu, pf_func, &nixlf, NULL)) {
+		dev_err(rvu->dev, "%s: nixlf not attached to pcifunc:0x%x\n",
+			__func__, pf_func);
+		/* Action 0 is drop */
+		return 0;
+	}
+
 	index = npc_get_nixlf_mcam_index(mcam, pf_func, nixlf,
 					 NIXLF_UCAST_ENTRY);
 	bank = npc_get_bank(mcam, index);
@@ -665,6 +671,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 	int blkaddr, ucast_idx, index;
 	struct nix_rx_action action = { 0 };
 	u64 relaxed_mask;
+	u8 flow_key_alg;
 
 	if (!hw->cap.nix_rx_multicast && is_cgx_vf(rvu, pcifunc))
 		return;
@@ -695,6 +702,8 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 		action.op = NIX_RX_ACTIONOP_UCAST;
 	}
 
+	flow_key_alg = action.flow_key_alg;
+
 	/* RX_ACTION set to MCAST for CGX PF's */
 	if (hw->cap.nix_rx_multicast && pfvf->use_mce_list &&
 	    is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) {
@@ -734,7 +743,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 	req.vf = pcifunc;
 	req.index = action.index;
 	req.match_id = action.match_id;
-	req.flow_key_alg = action.flow_key_alg;
+	req.flow_key_alg = flow_key_alg;
 
 	rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
 }
@@ -848,6 +857,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 	u8 mac_addr[ETH_ALEN] = { 0 };
 	struct nix_rx_action action = { 0 };
 	struct rvu_pfvf *pfvf;
+	u8 flow_key_alg;
 	u16 vf_func;
 
 	/* Only CGX PF/VF can add allmulticast entry */
@@ -882,6 +892,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 		*(u64 *)&action = npc_get_mcam_action(rvu, mcam,
 							blkaddr, ucast_idx);
 
+	flow_key_alg = action.flow_key_alg;
 	if (action.op != NIX_RX_ACTIONOP_RSS) {
 		*(u64 *)&action = 0;
 		action.op = NIX_RX_ACTIONOP_UCAST;
@@ -918,7 +929,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 	req.vf = pcifunc | vf_func;
 	req.index = action.index;
 	req.match_id = action.match_id;
-	req.flow_key_alg = action.flow_key_alg;
+	req.flow_key_alg = flow_key_alg;
 
 	rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
 }
@@ -984,11 +995,38 @@ static void npc_update_vf_flow_entry(struct rvu *rvu, struct npc_mcam *mcam,
 	mutex_unlock(&mcam->lock);
 }
 
+static void npc_update_rx_action_with_alg_idx(struct rvu *rvu, struct nix_rx_action action,
+					      struct rvu_pfvf *pfvf, int mcam_index, int blkaddr,
+					      int alg_idx)
+
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	struct rvu_hwinfo *hw = rvu->hw;
+	int bank, op_rss;
+
+	if (!is_mcam_entry_enabled(rvu, mcam, blkaddr, mcam_index))
+		return;
+
+	op_rss = (!hw->cap.nix_rx_multicast || !pfvf->use_mce_list);
+
+	bank = npc_get_bank(mcam, mcam_index);
+	mcam_index &= (mcam->banksize - 1);
+
+	/* If Rx action is MCAST update only RSS algorithm index */
+	if (!op_rss) {
+		*(u64 *)&action = rvu_read64(rvu, blkaddr,
+				NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank));
+
+		action.flow_key_alg = alg_idx;
+	}
+	rvu_write64(rvu, blkaddr,
+		    NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank), *(u64 *)&action);
+}
+
 void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    int group, int alg_idx, int mcam_index)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
-	struct rvu_hwinfo *hw = rvu->hw;
 	struct nix_rx_action action;
 	int blkaddr, index, bank;
 	struct rvu_pfvf *pfvf;
@@ -1044,15 +1082,16 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 	/* If PF's promiscuous entry is enabled,
 	 * Set RSS action for that entry as well
 	 */
-	if ((!hw->cap.nix_rx_multicast || !pfvf->use_mce_list) &&
-	    is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) {
-		bank = npc_get_bank(mcam, index);
-		index &= (mcam->banksize - 1);
+	npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr,
+					  alg_idx);
 
-		rvu_write64(rvu, blkaddr,
-			    NPC_AF_MCAMEX_BANKX_ACTION(index, bank),
-			    *(u64 *)&action);
-	}
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					 nixlf, NIXLF_ALLMULTI_ENTRY);
+	/* If PF's allmulti  entry is enabled,
+	 * Set RSS action for that entry as well
+	 */
+	npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr,
+					  alg_idx);
 }
 
 void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c
index b3150f05329196..d46ac29adb966d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c
@@ -31,8 +31,8 @@ static struct hw_reg_map txsch_reg_map[NIX_TXSCH_LVL_CNT] = {
 	{NIX_TXSCH_LVL_TL4, 3, 0xFFFF, {{0x0B00, 0x0B08}, {0x0B10, 0x0B18},
 			      {0x1200, 0x12E0} } },
 	{NIX_TXSCH_LVL_TL3, 4, 0xFFFF, {{0x1000, 0x10E0}, {0x1600, 0x1608},
-			      {0x1610, 0x1618}, {0x1700, 0x17B0} } },
-	{NIX_TXSCH_LVL_TL2, 2, 0xFFFF, {{0x0E00, 0x0EE0}, {0x1700, 0x17B0} } },
+			      {0x1610, 0x1618}, {0x1700, 0x17C8} } },
+	{NIX_TXSCH_LVL_TL2, 2, 0xFFFF, {{0x0E00, 0x0EE0}, {0x1700, 0x17C8} } },
 	{NIX_TXSCH_LVL_TL1, 1, 0xFFFF, {{0x0C00, 0x0D98} } },
 };
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index b42e631e52d0fd..18c1c9f361cc62 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -437,6 +437,7 @@
 
 #define NIX_AF_LINKX_BASE_MASK		GENMASK_ULL(11, 0)
 #define NIX_AF_LINKX_RANGE_MASK		GENMASK_ULL(19, 16)
+#define NIX_AF_LINKX_MCS_CNT_MASK	GENMASK_ULL(33, 32)
 
 /* SSO */
 #define SSO_AF_CONST			(0x1000)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
index a4a258da8dd59a..c1c99d7054f87f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
@@ -450,6 +450,9 @@ int cn10k_set_ipolicer_rate(struct otx2_nic *pfvf, u16 profile,
 	aq->prof.pebs_mantissa = 0;
 	aq->prof_mask.pebs_mantissa = 0xFF;
 
+	aq->prof.hl_en = 0;
+	aq->prof_mask.hl_en = 1;
+
 	/* Fill AQ info */
 	aq->qidx = profile;
 	aq->ctype = NIX_AQ_CTYPE_BANDPROF;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 1a42bfded8722a..7ca6941ea0b9b4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -818,7 +818,6 @@ void otx2_sqb_flush(struct otx2_nic *pfvf)
 	int qidx, sqe_tail, sqe_head;
 	struct otx2_snd_queue *sq;
 	u64 incr, *ptr, val;
-	int timeout = 1000;
 
 	ptr = (u64 *)otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_STATUS);
 	for (qidx = 0; qidx < otx2_get_total_tx_queues(pfvf); qidx++) {
@@ -827,15 +826,11 @@ void otx2_sqb_flush(struct otx2_nic *pfvf)
 			continue;
 
 		incr = (u64)qidx << 32;
-		while (timeout) {
-			val = otx2_atomic64_add(incr, ptr);
-			sqe_head = (val >> 20) & 0x3F;
-			sqe_tail = (val >> 28) & 0x3F;
-			if (sqe_head == sqe_tail)
-				break;
-			usleep_range(1, 3);
-			timeout--;
-		}
+		val = otx2_atomic64_add(incr, ptr);
+		sqe_head = (val >> 20) & 0x3F;
+		sqe_tail = (val >> 28) & 0x3F;
+		if (sqe_head != sqe_tail)
+			usleep_range(50, 60);
 	}
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index c04a8ee53a82f1..06910307085efa 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -977,6 +977,7 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool pfc_en);
 int otx2_txsch_alloc(struct otx2_nic *pfvf);
 void otx2_txschq_stop(struct otx2_nic *pfvf);
 void otx2_txschq_free_one(struct otx2_nic *pfvf, u16 lvl, u16 schq);
+void otx2_free_pending_sqe(struct otx2_nic *pfvf);
 void otx2_sqb_flush(struct otx2_nic *pfvf);
 int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 		    dma_addr_t *dma);
@@ -1069,6 +1070,8 @@ int otx2_init_tc(struct otx2_nic *nic);
 void otx2_shutdown_tc(struct otx2_nic *nic);
 int otx2_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 		  void *type_data);
+void otx2_tc_apply_ingress_police_rules(struct otx2_nic *nic);
+
 /* CGX/RPM DMAC filters support */
 int otx2_dmacflt_get_max_cnt(struct otx2_nic *pf);
 int otx2_dmacflt_add(struct otx2_nic *pf, const u8 *mac, u32 bit_pos);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
index bfddbff7bcdfbf..28fb643d2917f7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c
@@ -399,9 +399,10 @@ static int otx2_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc)
 static int otx2_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc)
 {
 	struct otx2_nic *pfvf = netdev_priv(dev);
+	u8 old_pfc_en;
 	int err;
 
-	/* Save PFC configuration to interface */
+	old_pfc_en = pfvf->pfc_en;
 	pfvf->pfc_en = pfc->pfc_en;
 
 	if (pfvf->hw.tx_queues >= NIX_PF_PFC_PRIO_MAX)
@@ -411,13 +412,17 @@ static int otx2_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc)
 	 * supported by the tx queue configuration
 	 */
 	err = otx2_check_pfc_config(pfvf);
-	if (err)
+	if (err) {
+		pfvf->pfc_en = old_pfc_en;
 		return err;
+	}
 
 process_pfc:
 	err = otx2_config_priority_flow_ctrl(pfvf);
-	if (err)
+	if (err) {
+		pfvf->pfc_en = old_pfc_en;
 		return err;
+	}
 
 	/* Request Per channel Bpids */
 	if (pfc->pfc_en)
@@ -425,6 +430,12 @@ process_pfc:
 
 	err = otx2_pfc_txschq_update(pfvf);
 	if (err) {
+		if (pfc->pfc_en)
+			otx2_nix_config_bp(pfvf, false);
+
+		otx2_pfc_txschq_stop(pfvf);
+		pfvf->pfc_en = old_pfc_en;
+		otx2_config_priority_flow_ctrl(pfvf);
 		dev_err(pfvf->dev, "%s failed to update TX schedulers\n", __func__);
 		return err;
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 9efcec549834e8..53f6258a973c28 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -334,9 +334,12 @@ static void otx2_get_pauseparam(struct net_device *netdev,
 	if (is_otx2_lbkvf(pfvf->pdev))
 		return;
 
+	mutex_lock(&pfvf->mbox.lock);
 	req = otx2_mbox_alloc_msg_cgx_cfg_pause_frm(&pfvf->mbox);
-	if (!req)
+	if (!req) {
+		mutex_unlock(&pfvf->mbox.lock);
 		return;
+	}
 
 	if (!otx2_sync_mbox_msg(&pfvf->mbox)) {
 		rsp = (struct cgx_pause_frm_cfg *)
@@ -344,6 +347,7 @@ static void otx2_get_pauseparam(struct net_device *netdev,
 		pause->rx_pause = rsp->rx_pause;
 		pause->tx_pause = rsp->tx_pause;
 	}
+	mutex_unlock(&pfvf->mbox.lock);
 }
 
 static int otx2_set_pauseparam(struct net_device *netdev,
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 4762dbea64a12b..97a71e9b856372 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -1088,6 +1088,7 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc)
 	struct ethhdr *eth_hdr;
 	bool new = false;
 	int err = 0;
+	u64 vf_num;
 	u32 ring;
 
 	if (!flow_cfg->max_flows) {
@@ -1100,7 +1101,21 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc)
 	if (!(pfvf->flags & OTX2_FLAG_NTUPLE_SUPPORT))
 		return -ENOMEM;
 
-	if (ring >= pfvf->hw.rx_queues && fsp->ring_cookie != RX_CLS_FLOW_DISC)
+	/* Number of queues on a VF can be greater or less than
+	 * the PF's queue. Hence no need to check for the
+	 * queue count. Hence no need to check queue count if PF
+	 * is installing for its VF. Below is the expected vf_num value
+	 * based on the ethtool commands.
+	 *
+	 * e.g.
+	 * 1. ethtool -U <netdev> ... action -1  ==> vf_num:255
+	 * 2. ethtool -U <netdev> ... action <queue_num>  ==> vf_num:0
+	 * 3. ethtool -U <netdev> ... vf <vf_idx> queue <queue_num>  ==>
+	 *    vf_num:vf_idx+1
+	 */
+	vf_num = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie);
+	if (!is_otx2_vf(pfvf->pcifunc) && !vf_num &&
+	    ring >= pfvf->hw.rx_queues && fsp->ring_cookie != RX_CLS_FLOW_DISC)
 		return -EINVAL;
 
 	if (fsp->location >= otx2_get_maxflows(flow_cfg))
@@ -1182,6 +1197,9 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc)
 		flow_cfg->nr_flows++;
 	}
 
+	if (flow->is_vf)
+		netdev_info(pfvf->netdev,
+			    "Make sure that VF's queue number is within its queue limit\n");
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 6daf4d58c25d63..a57455aebff6fc 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -566,7 +566,9 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
 		otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(1), intr);
 		otx2_queue_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr,
 				TYPE_PFVF);
-		vfs -= 64;
+		if (intr)
+			trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr);
+		vfs = 64;
 	}
 
 	intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(0));
@@ -574,7 +576,8 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
 
 	otx2_queue_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr, TYPE_PFVF);
 
-	trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr);
+	if (intr)
+		trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr);
 
 	return IRQ_HANDLED;
 }
@@ -1193,31 +1196,32 @@ static char *nix_mnqerr_e_str[NIX_MNQERR_MAX] = {
 };
 
 static char *nix_snd_status_e_str[NIX_SND_STATUS_MAX] =  {
-	"NIX_SND_STATUS_GOOD",
-	"NIX_SND_STATUS_SQ_CTX_FAULT",
-	"NIX_SND_STATUS_SQ_CTX_POISON",
-	"NIX_SND_STATUS_SQB_FAULT",
-	"NIX_SND_STATUS_SQB_POISON",
-	"NIX_SND_STATUS_HDR_ERR",
-	"NIX_SND_STATUS_EXT_ERR",
-	"NIX_SND_STATUS_JUMP_FAULT",
-	"NIX_SND_STATUS_JUMP_POISON",
-	"NIX_SND_STATUS_CRC_ERR",
-	"NIX_SND_STATUS_IMM_ERR",
-	"NIX_SND_STATUS_SG_ERR",
-	"NIX_SND_STATUS_MEM_ERR",
-	"NIX_SND_STATUS_INVALID_SUBDC",
-	"NIX_SND_STATUS_SUBDC_ORDER_ERR",
-	"NIX_SND_STATUS_DATA_FAULT",
-	"NIX_SND_STATUS_DATA_POISON",
-	"NIX_SND_STATUS_NPC_DROP_ACTION",
-	"NIX_SND_STATUS_LOCK_VIOL",
-	"NIX_SND_STATUS_NPC_UCAST_CHAN_ERR",
-	"NIX_SND_STATUS_NPC_MCAST_CHAN_ERR",
-	"NIX_SND_STATUS_NPC_MCAST_ABORT",
-	"NIX_SND_STATUS_NPC_VTAG_PTR_ERR",
-	"NIX_SND_STATUS_NPC_VTAG_SIZE_ERR",
-	"NIX_SND_STATUS_SEND_STATS_ERR",
+	[NIX_SND_STATUS_GOOD] = "NIX_SND_STATUS_GOOD",
+	[NIX_SND_STATUS_SQ_CTX_FAULT] = "NIX_SND_STATUS_SQ_CTX_FAULT",
+	[NIX_SND_STATUS_SQ_CTX_POISON] = "NIX_SND_STATUS_SQ_CTX_POISON",
+	[NIX_SND_STATUS_SQB_FAULT] = "NIX_SND_STATUS_SQB_FAULT",
+	[NIX_SND_STATUS_SQB_POISON] = "NIX_SND_STATUS_SQB_POISON",
+	[NIX_SND_STATUS_HDR_ERR] = "NIX_SND_STATUS_HDR_ERR",
+	[NIX_SND_STATUS_EXT_ERR] = "NIX_SND_STATUS_EXT_ERR",
+	[NIX_SND_STATUS_JUMP_FAULT] = "NIX_SND_STATUS_JUMP_FAULT",
+	[NIX_SND_STATUS_JUMP_POISON] = "NIX_SND_STATUS_JUMP_POISON",
+	[NIX_SND_STATUS_CRC_ERR] = "NIX_SND_STATUS_CRC_ERR",
+	[NIX_SND_STATUS_IMM_ERR] = "NIX_SND_STATUS_IMM_ERR",
+	[NIX_SND_STATUS_SG_ERR] = "NIX_SND_STATUS_SG_ERR",
+	[NIX_SND_STATUS_MEM_ERR] = "NIX_SND_STATUS_MEM_ERR",
+	[NIX_SND_STATUS_INVALID_SUBDC] = "NIX_SND_STATUS_INVALID_SUBDC",
+	[NIX_SND_STATUS_SUBDC_ORDER_ERR] = "NIX_SND_STATUS_SUBDC_ORDER_ERR",
+	[NIX_SND_STATUS_DATA_FAULT] = "NIX_SND_STATUS_DATA_FAULT",
+	[NIX_SND_STATUS_DATA_POISON] = "NIX_SND_STATUS_DATA_POISON",
+	[NIX_SND_STATUS_NPC_DROP_ACTION] = "NIX_SND_STATUS_NPC_DROP_ACTION",
+	[NIX_SND_STATUS_LOCK_VIOL] = "NIX_SND_STATUS_LOCK_VIOL",
+	[NIX_SND_STATUS_NPC_UCAST_CHAN_ERR] = "NIX_SND_STAT_NPC_UCAST_CHAN_ERR",
+	[NIX_SND_STATUS_NPC_MCAST_CHAN_ERR] = "NIX_SND_STAT_NPC_MCAST_CHAN_ERR",
+	[NIX_SND_STATUS_NPC_MCAST_ABORT] = "NIX_SND_STATUS_NPC_MCAST_ABORT",
+	[NIX_SND_STATUS_NPC_VTAG_PTR_ERR] = "NIX_SND_STATUS_NPC_VTAG_PTR_ERR",
+	[NIX_SND_STATUS_NPC_VTAG_SIZE_ERR] = "NIX_SND_STATUS_NPC_VTAG_SIZE_ERR",
+	[NIX_SND_STATUS_SEND_MEM_FAULT] = "NIX_SND_STATUS_SEND_MEM_FAULT",
+	[NIX_SND_STATUS_SEND_STATS_ERR] = "NIX_SND_STATUS_SEND_STATS_ERR",
 };
 
 static irqreturn_t otx2_q_intr_handler(int irq, void *data)
@@ -1238,14 +1242,16 @@ static irqreturn_t otx2_q_intr_handler(int irq, void *data)
 			continue;
 
 		if (val & BIT_ULL(42)) {
-			netdev_err(pf->netdev, "CQ%lld: error reading NIX_LF_CQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
+			netdev_err(pf->netdev,
+				   "CQ%lld: error reading NIX_LF_CQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
 				   qidx, otx2_read64(pf, NIX_LF_ERR_INT));
 		} else {
 			if (val & BIT_ULL(NIX_CQERRINT_DOOR_ERR))
 				netdev_err(pf->netdev, "CQ%lld: Doorbell error",
 					   qidx);
 			if (val & BIT_ULL(NIX_CQERRINT_CQE_FAULT))
-				netdev_err(pf->netdev, "CQ%lld: Memory fault on CQE write to LLC/DRAM",
+				netdev_err(pf->netdev,
+					   "CQ%lld: Memory fault on CQE write to LLC/DRAM",
 					   qidx);
 		}
 
@@ -1272,7 +1278,8 @@ static irqreturn_t otx2_q_intr_handler(int irq, void *data)
 			     (val & NIX_SQINT_BITS));
 
 		if (val & BIT_ULL(42)) {
-			netdev_err(pf->netdev, "SQ%lld: error reading NIX_LF_SQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
+			netdev_err(pf->netdev,
+				   "SQ%lld: error reading NIX_LF_SQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
 				   qidx, otx2_read64(pf, NIX_LF_ERR_INT));
 			goto done;
 		}
@@ -1282,8 +1289,11 @@ static irqreturn_t otx2_q_intr_handler(int irq, void *data)
 			goto chk_mnq_err_dbg;
 
 		sq_op_err_code = FIELD_GET(GENMASK(7, 0), sq_op_err_dbg);
-		netdev_err(pf->netdev, "SQ%lld: NIX_LF_SQ_OP_ERR_DBG(%llx)  err=%s\n",
-			   qidx, sq_op_err_dbg, nix_sqoperr_e_str[sq_op_err_code]);
+		netdev_err(pf->netdev,
+			   "SQ%lld: NIX_LF_SQ_OP_ERR_DBG(0x%llx)  err=%s(%#x)\n",
+			   qidx, sq_op_err_dbg,
+			   nix_sqoperr_e_str[sq_op_err_code],
+			   sq_op_err_code);
 
 		otx2_write64(pf, NIX_LF_SQ_OP_ERR_DBG, BIT_ULL(44));
 
@@ -1300,16 +1310,21 @@ chk_mnq_err_dbg:
 			goto chk_snd_err_dbg;
 
 		mnq_err_code = FIELD_GET(GENMASK(7, 0), mnq_err_dbg);
-		netdev_err(pf->netdev, "SQ%lld: NIX_LF_MNQ_ERR_DBG(%llx)  err=%s\n",
-			   qidx, mnq_err_dbg,  nix_mnqerr_e_str[mnq_err_code]);
+		netdev_err(pf->netdev,
+			   "SQ%lld: NIX_LF_MNQ_ERR_DBG(0x%llx)  err=%s(%#x)\n",
+			   qidx, mnq_err_dbg,  nix_mnqerr_e_str[mnq_err_code],
+			   mnq_err_code);
 		otx2_write64(pf, NIX_LF_MNQ_ERR_DBG, BIT_ULL(44));
 
 chk_snd_err_dbg:
 		snd_err_dbg = otx2_read64(pf, NIX_LF_SEND_ERR_DBG);
 		if (snd_err_dbg & BIT(44)) {
 			snd_err_code = FIELD_GET(GENMASK(7, 0), snd_err_dbg);
-			netdev_err(pf->netdev, "SQ%lld: NIX_LF_SND_ERR_DBG:0x%llx err=%s\n",
-				   qidx, snd_err_dbg, nix_snd_status_e_str[snd_err_code]);
+			netdev_err(pf->netdev,
+				   "SQ%lld: NIX_LF_SND_ERR_DBG:0x%llx err=%s(%#x)\n",
+				   qidx, snd_err_dbg,
+				   nix_snd_status_e_str[snd_err_code],
+				   snd_err_code);
 			otx2_write64(pf, NIX_LF_SEND_ERR_DBG, BIT_ULL(44));
 		}
 
@@ -1589,6 +1604,7 @@ static void otx2_free_hw_resources(struct otx2_nic *pf)
 		else
 			otx2_cleanup_tx_cqes(pf, cq);
 	}
+	otx2_free_pending_sqe(pf);
 
 	otx2_free_sq_res(pf);
 
@@ -1634,6 +1650,21 @@ static void otx2_free_hw_resources(struct otx2_nic *pf)
 	mutex_unlock(&mbox->lock);
 }
 
+static bool otx2_promisc_use_mce_list(struct otx2_nic *pfvf)
+{
+	int vf;
+
+	/* The AF driver will determine whether to allow the VF netdev or not */
+	if (is_otx2_vf(pfvf->pcifunc))
+		return true;
+
+	/* check if there are any trusted VFs associated with the PF netdev */
+	for (vf = 0; vf < pci_num_vf(pfvf->pdev); vf++)
+		if (pfvf->vf_configs[vf].trusted)
+			return true;
+	return false;
+}
+
 static void otx2_do_set_rx_mode(struct otx2_nic *pf)
 {
 	struct net_device *netdev = pf->netdev;
@@ -1666,12 +1697,21 @@ static void otx2_do_set_rx_mode(struct otx2_nic *pf)
 	if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST))
 		req->mode |= NIX_RX_MODE_ALLMULTI;
 
-	req->mode |= NIX_RX_MODE_USE_MCE;
+	if (otx2_promisc_use_mce_list(pf))
+		req->mode |= NIX_RX_MODE_USE_MCE;
 
 	otx2_sync_mbox_msg(&pf->mbox);
 	mutex_unlock(&pf->mbox.lock);
 }
 
+static void otx2_set_irq_coalesce(struct otx2_nic *pfvf)
+{
+	int cint;
+
+	for (cint = 0; cint < pfvf->hw.cint_cnt; cint++)
+		otx2_config_irq_coalescing(pfvf, cint);
+}
+
 static void otx2_dim_work(struct work_struct *w)
 {
 	struct dim_cq_moder cur_moder;
@@ -1687,6 +1727,7 @@ static void otx2_dim_work(struct work_struct *w)
 		CQ_TIMER_THRESH_MAX : cur_moder.usec;
 	pfvf->hw.cq_ecount_wait = (cur_moder.pkts > NAPI_POLL_WEIGHT) ?
 		NAPI_POLL_WEIGHT : cur_moder.pkts;
+	otx2_set_irq_coalesce(pfvf);
 	dim->state = DIM_START_MEASURE;
 }
 
@@ -1857,6 +1898,8 @@ int otx2_open(struct net_device *netdev)
 	if (pf->flags & OTX2_FLAG_DMACFLTR_SUPPORT)
 		otx2_dmacflt_reinstall_flows(pf);
 
+	otx2_tc_apply_ingress_police_rules(pf);
+
 	err = otx2_rxtx_enable(pf, true);
 	/* If a mbox communication error happens at this point then interface
 	 * will end up in a state such that it is in down state but hardware
@@ -1921,6 +1964,8 @@ int otx2_stop(struct net_device *netdev)
 	/* Clear RSS enable flag */
 	rss = &pf->hw.rss_info;
 	rss->enable = false;
+	if (!netif_is_rxfh_configured(netdev))
+		kfree(rss->rss_ctx[DEFAULT_RSS_CONTEXT_GROUP]);
 
 	/* Cleanup Queue IRQ */
 	vec = pci_irq_vector(pf->pdev,
@@ -2662,11 +2707,14 @@ static int otx2_ndo_set_vf_trust(struct net_device *netdev, int vf,
 	pf->vf_configs[vf].trusted = enable;
 	rc = otx2_set_vf_permissions(pf, vf, OTX2_TRUSTED_VF);
 
-	if (rc)
+	if (rc) {
 		pf->vf_configs[vf].trusted = !enable;
-	else
+	} else {
 		netdev_info(pf->netdev, "VF %d is %strusted\n",
 			    vf, enable ? "" : "not ");
+		otx2_set_rx_mode(netdev);
+	}
+
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_struct.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_struct.h
index fa37b9f312cae4..4e5899d8fa2e6e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_struct.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_struct.h
@@ -318,23 +318,23 @@ enum nix_snd_status_e {
 	NIX_SND_STATUS_EXT_ERR = 0x6,
 	NIX_SND_STATUS_JUMP_FAULT = 0x7,
 	NIX_SND_STATUS_JUMP_POISON = 0x8,
-	NIX_SND_STATUS_CRC_ERR = 0x9,
-	NIX_SND_STATUS_IMM_ERR = 0x10,
-	NIX_SND_STATUS_SG_ERR = 0x11,
-	NIX_SND_STATUS_MEM_ERR = 0x12,
-	NIX_SND_STATUS_INVALID_SUBDC = 0x13,
-	NIX_SND_STATUS_SUBDC_ORDER_ERR = 0x14,
-	NIX_SND_STATUS_DATA_FAULT = 0x15,
-	NIX_SND_STATUS_DATA_POISON = 0x16,
-	NIX_SND_STATUS_NPC_DROP_ACTION = 0x17,
-	NIX_SND_STATUS_LOCK_VIOL = 0x18,
-	NIX_SND_STATUS_NPC_UCAST_CHAN_ERR = 0x19,
-	NIX_SND_STATUS_NPC_MCAST_CHAN_ERR = 0x20,
-	NIX_SND_STATUS_NPC_MCAST_ABORT = 0x21,
-	NIX_SND_STATUS_NPC_VTAG_PTR_ERR = 0x22,
-	NIX_SND_STATUS_NPC_VTAG_SIZE_ERR = 0x23,
-	NIX_SND_STATUS_SEND_MEM_FAULT = 0x24,
-	NIX_SND_STATUS_SEND_STATS_ERR = 0x25,
+	NIX_SND_STATUS_CRC_ERR = 0x10,
+	NIX_SND_STATUS_IMM_ERR = 0x11,
+	NIX_SND_STATUS_SG_ERR = 0x12,
+	NIX_SND_STATUS_MEM_ERR = 0x13,
+	NIX_SND_STATUS_INVALID_SUBDC = 0x14,
+	NIX_SND_STATUS_SUBDC_ORDER_ERR = 0x15,
+	NIX_SND_STATUS_DATA_FAULT = 0x16,
+	NIX_SND_STATUS_DATA_POISON = 0x17,
+	NIX_SND_STATUS_NPC_DROP_ACTION = 0x20,
+	NIX_SND_STATUS_LOCK_VIOL = 0x21,
+	NIX_SND_STATUS_NPC_UCAST_CHAN_ERR = 0x22,
+	NIX_SND_STATUS_NPC_MCAST_CHAN_ERR = 0x23,
+	NIX_SND_STATUS_NPC_MCAST_ABORT = 0x24,
+	NIX_SND_STATUS_NPC_VTAG_PTR_ERR = 0x25,
+	NIX_SND_STATUS_NPC_VTAG_SIZE_ERR = 0x26,
+	NIX_SND_STATUS_SEND_MEM_FAULT = 0x27,
+	NIX_SND_STATUS_SEND_STATS_ERR = 0x28,
 	NIX_SND_STATUS_MAX,
 };
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 8a5e3987a482c2..db1e0e0e812d3d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -47,6 +47,9 @@ struct otx2_tc_flow {
 	bool				is_act_police;
 	u32				prio;
 	struct npc_install_flow_req	req;
+	u64				rate;
+	u32				burst;
+	bool				is_pps;
 };
 
 static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst,
@@ -284,21 +287,10 @@ static int otx2_tc_egress_matchall_delete(struct otx2_nic *nic,
 	return err;
 }
 
-static int otx2_tc_act_set_police(struct otx2_nic *nic,
-				  struct otx2_tc_flow *node,
-				  struct flow_cls_offload *f,
-				  u64 rate, u32 burst, u32 mark,
-				  struct npc_install_flow_req *req, bool pps)
+static int otx2_tc_act_set_hw_police(struct otx2_nic *nic,
+				     struct otx2_tc_flow *node)
 {
-	struct netlink_ext_ack *extack = f->common.extack;
-	struct otx2_hw *hw = &nic->hw;
-	int rq_idx, rc;
-
-	rq_idx = find_first_zero_bit(&nic->rq_bmap, hw->rx_queues);
-	if (rq_idx >= hw->rx_queues) {
-		NL_SET_ERR_MSG_MOD(extack, "Police action rules exceeded");
-		return -EINVAL;
-	}
+	int rc;
 
 	mutex_lock(&nic->mbox.lock);
 
@@ -308,23 +300,17 @@ static int otx2_tc_act_set_police(struct otx2_nic *nic,
 		return rc;
 	}
 
-	rc = cn10k_set_ipolicer_rate(nic, node->leaf_profile, burst, rate, pps);
+	rc = cn10k_set_ipolicer_rate(nic, node->leaf_profile,
+				     node->burst, node->rate, node->is_pps);
 	if (rc)
 		goto free_leaf;
 
-	rc = cn10k_map_unmap_rq_policer(nic, rq_idx, node->leaf_profile, true);
+	rc = cn10k_map_unmap_rq_policer(nic, node->rq, node->leaf_profile, true);
 	if (rc)
 		goto free_leaf;
 
 	mutex_unlock(&nic->mbox.lock);
 
-	req->match_id = mark & 0xFFFFULL;
-	req->index = rq_idx;
-	req->op = NIX_RX_ACTIONOP_UCAST;
-	set_bit(rq_idx, &nic->rq_bmap);
-	node->is_act_police = true;
-	node->rq = rq_idx;
-
 	return 0;
 
 free_leaf:
@@ -336,6 +322,39 @@ free_leaf:
 	return rc;
 }
 
+static int otx2_tc_act_set_police(struct otx2_nic *nic,
+				  struct otx2_tc_flow *node,
+				  struct flow_cls_offload *f,
+				  u64 rate, u32 burst, u32 mark,
+				  struct npc_install_flow_req *req, bool pps)
+{
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct otx2_hw *hw = &nic->hw;
+	int rq_idx, rc;
+
+	rq_idx = find_first_zero_bit(&nic->rq_bmap, hw->rx_queues);
+	if (rq_idx >= hw->rx_queues) {
+		NL_SET_ERR_MSG_MOD(extack, "Police action rules exceeded");
+		return -EINVAL;
+	}
+
+	req->match_id = mark & 0xFFFFULL;
+	req->index = rq_idx;
+	req->op = NIX_RX_ACTIONOP_UCAST;
+
+	node->is_act_police = true;
+	node->rq = rq_idx;
+	node->burst = burst;
+	node->rate = rate;
+	node->is_pps = pps;
+
+	rc = otx2_tc_act_set_hw_police(nic, node);
+	if (!rc)
+		set_bit(rq_idx, &nic->rq_bmap);
+
+	return rc;
+}
+
 static int otx2_tc_parse_actions(struct otx2_nic *nic,
 				 struct flow_action *flow_action,
 				 struct npc_install_flow_req *req,
@@ -1044,6 +1063,11 @@ static int otx2_tc_del_flow(struct otx2_nic *nic,
 	}
 
 	if (flow_node->is_act_police) {
+		__clear_bit(flow_node->rq, &nic->rq_bmap);
+
+		if (nic->flags & OTX2_FLAG_INTF_DOWN)
+			goto free_mcam_flow;
+
 		mutex_lock(&nic->mbox.lock);
 
 		err = cn10k_map_unmap_rq_policer(nic, flow_node->rq,
@@ -1059,11 +1083,10 @@ static int otx2_tc_del_flow(struct otx2_nic *nic,
 				   "Unable to free leaf bandwidth profile(%d)\n",
 				   flow_node->leaf_profile);
 
-		__clear_bit(flow_node->rq, &nic->rq_bmap);
-
 		mutex_unlock(&nic->mbox.lock);
 	}
 
+free_mcam_flow:
 	otx2_del_mcam_flow_entry(nic, flow_node->entry, NULL);
 	otx2_tc_update_mcam_table(nic, flow_cfg, flow_node, false);
 	kfree_rcu(flow_node, rcu);
@@ -1083,6 +1106,11 @@ static int otx2_tc_add_flow(struct otx2_nic *nic,
 	if (!(nic->flags & OTX2_FLAG_TC_FLOWER_SUPPORT))
 		return -ENOMEM;
 
+	if (nic->flags & OTX2_FLAG_INTF_DOWN) {
+		NL_SET_ERR_MSG_MOD(extack, "Interface not initialized");
+		return -EINVAL;
+	}
+
 	if (flow_cfg->nr_flows == flow_cfg->max_flows) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Free MCAM entry not available to add the flow");
@@ -1442,3 +1470,45 @@ void otx2_shutdown_tc(struct otx2_nic *nic)
 	otx2_destroy_tc_flow_list(nic);
 }
 EXPORT_SYMBOL(otx2_shutdown_tc);
+
+static void otx2_tc_config_ingress_rule(struct otx2_nic *nic,
+					struct otx2_tc_flow *node)
+{
+	struct npc_install_flow_req *req;
+
+	if (otx2_tc_act_set_hw_police(nic, node))
+		return;
+
+	mutex_lock(&nic->mbox.lock);
+
+	req = otx2_mbox_alloc_msg_npc_install_flow(&nic->mbox);
+	if (!req)
+		goto err;
+
+	memcpy(req, &node->req, sizeof(struct npc_install_flow_req));
+
+	if (otx2_sync_mbox_msg(&nic->mbox))
+		netdev_err(nic->netdev,
+			   "Failed to install MCAM flow entry for ingress rule");
+err:
+	mutex_unlock(&nic->mbox.lock);
+}
+
+void otx2_tc_apply_ingress_police_rules(struct otx2_nic *nic)
+{
+	struct otx2_flow_config *flow_cfg = nic->flow_cfg;
+	struct otx2_tc_flow *node;
+
+	/* If any ingress policer rules exist for the interface then
+	 * apply those rules. Ingress policer rules depend on bandwidth
+	 * profiles linked to the receive queues. Since no receive queues
+	 * exist when interface is down, ingress policer rules are stored
+	 * and configured in hardware after all receive queues are allocated
+	 * in otx2_open.
+	 */
+	list_for_each_entry(node, &flow_cfg->flow_list_tc, list) {
+		if (node->is_act_police)
+			otx2_tc_config_ingress_rule(nic, node);
+	}
+}
+EXPORT_SYMBOL(otx2_tc_apply_ingress_police_rules);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 53b2a4ef529852..4d519ea833b2c7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -512,11 +512,18 @@ static void otx2_adjust_adaptive_coalese(struct otx2_nic *pfvf, struct otx2_cq_p
 {
 	struct dim_sample dim_sample;
 	u64 rx_frames, rx_bytes;
+	u64 tx_frames, tx_bytes;
 
 	rx_frames = OTX2_GET_RX_STATS(RX_BCAST) + OTX2_GET_RX_STATS(RX_MCAST) +
 		OTX2_GET_RX_STATS(RX_UCAST);
 	rx_bytes = OTX2_GET_RX_STATS(RX_OCTS);
-	dim_update_sample(pfvf->napi_events, rx_frames, rx_bytes, &dim_sample);
+	tx_bytes = OTX2_GET_TX_STATS(TX_OCTS);
+	tx_frames = OTX2_GET_TX_STATS(TX_UCAST);
+
+	dim_update_sample(pfvf->napi_events,
+			  rx_frames + tx_frames,
+			  rx_bytes + tx_bytes,
+			  &dim_sample);
 	net_dim(&cq_poll->dim, dim_sample);
 }
 
@@ -558,16 +565,9 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 		if (pfvf->flags & OTX2_FLAG_INTF_DOWN)
 			return workdone;
 
-		/* Check for adaptive interrupt coalesce */
-		if (workdone != 0 &&
-		    ((pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED) ==
-		     OTX2_FLAG_ADPTV_INT_COAL_ENABLED)) {
-			/* Adjust irq coalese using net_dim */
+		/* Adjust irq coalese using net_dim */
+		if (pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED)
 			otx2_adjust_adaptive_coalese(pfvf, cq_poll);
-			/* Update irq coalescing */
-			for (i = 0; i < pfvf->hw.cint_cnt; i++)
-				otx2_config_irq_coalescing(pfvf, i);
-		}
 
 		if (unlikely(!filled_cnt)) {
 			struct refill_work *work;
@@ -1247,9 +1247,11 @@ void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int q
 
 void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq)
 {
+	int tx_pkts = 0, tx_bytes = 0;
 	struct sk_buff *skb = NULL;
 	struct otx2_snd_queue *sq;
 	struct nix_cqe_tx_s *cqe;
+	struct netdev_queue *txq;
 	int processed_cqe = 0;
 	struct sg_list *sg;
 	int qidx;
@@ -1270,12 +1272,20 @@ void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq)
 		sg = &sq->sg[cqe->comp.sqe_id];
 		skb = (struct sk_buff *)sg->skb;
 		if (skb) {
+			tx_bytes += skb->len;
+			tx_pkts++;
 			otx2_dma_unmap_skb_frags(pfvf, sg);
 			dev_kfree_skb_any(skb);
 			sg->skb = (u64)NULL;
 		}
 	}
 
+	if (likely(tx_pkts)) {
+		if (qidx >= pfvf->hw.tx_queues)
+			qidx -= pfvf->hw.xdp_queues;
+		txq = netdev_get_tx_queue(pfvf->netdev, qidx);
+		netdev_tx_completed_queue(txq, tx_pkts, tx_bytes);
+	}
 	/* Free CQEs to HW */
 	otx2_write64(pfvf, NIX_LF_CQ_OP_DOOR,
 		     ((u64)cq->cq_idx << 32) | processed_cqe);
@@ -1302,6 +1312,38 @@ int otx2_rxtx_enable(struct otx2_nic *pfvf, bool enable)
 	return err;
 }
 
+void otx2_free_pending_sqe(struct otx2_nic *pfvf)
+{
+	int tx_pkts = 0, tx_bytes = 0;
+	struct sk_buff *skb = NULL;
+	struct otx2_snd_queue *sq;
+	struct netdev_queue *txq;
+	struct sg_list *sg;
+	int sq_idx, sqe;
+
+	for (sq_idx = 0; sq_idx < pfvf->hw.tx_queues; sq_idx++) {
+		sq = &pfvf->qset.sq[sq_idx];
+		for (sqe = 0; sqe < sq->sqe_cnt; sqe++) {
+			sg = &sq->sg[sqe];
+			skb = (struct sk_buff *)sg->skb;
+			if (skb) {
+				tx_bytes += skb->len;
+				tx_pkts++;
+				otx2_dma_unmap_skb_frags(pfvf, sg);
+				dev_kfree_skb_any(skb);
+				sg->skb = (u64)NULL;
+			}
+		}
+
+		if (!tx_pkts)
+			continue;
+		txq = netdev_get_tx_queue(pfvf->netdev, sq_idx);
+		netdev_tx_completed_queue(txq, tx_pkts, tx_bytes);
+		tx_pkts = 0;
+		tx_bytes = 0;
+	}
+}
+
 static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, u64 dma_addr,
 				int len, int *offset)
 {
diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c
index 3bd51a3d665001..ae44ad5f8ce8a1 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed_wo.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c
@@ -291,6 +291,9 @@ mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q)
 	for (i = 0; i < q->n_desc; i++) {
 		struct mtk_wed_wo_queue_entry *entry = &q->entry[i];
 
+		if (!entry->buf)
+			continue;
+
 		dma_unmap_single(wo->hw->dev, entry->addr, entry->len,
 				 DMA_TO_DEVICE);
 		skb_free_frag(entry->buf);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index f8f0a712c943f2..a7b1f9686c09a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -156,15 +156,18 @@ static u8 alloc_token(struct mlx5_cmd *cmd)
 	return token;
 }
 
-static int cmd_alloc_index(struct mlx5_cmd *cmd)
+static int cmd_alloc_index(struct mlx5_cmd *cmd, struct mlx5_cmd_work_ent *ent)
 {
 	unsigned long flags;
 	int ret;
 
 	spin_lock_irqsave(&cmd->alloc_lock, flags);
 	ret = find_first_bit(&cmd->vars.bitmask, cmd->vars.max_reg_cmds);
-	if (ret < cmd->vars.max_reg_cmds)
+	if (ret < cmd->vars.max_reg_cmds) {
 		clear_bit(ret, &cmd->vars.bitmask);
+		ent->idx = ret;
+		cmd->ent_arr[ent->idx] = ent;
+	}
 	spin_unlock_irqrestore(&cmd->alloc_lock, flags);
 
 	return ret < cmd->vars.max_reg_cmds ? ret : -ENOMEM;
@@ -979,7 +982,7 @@ static void cmd_work_handler(struct work_struct *work)
 	sem = ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem;
 	down(sem);
 	if (!ent->page_queue) {
-		alloc_ret = cmd_alloc_index(cmd);
+		alloc_ret = cmd_alloc_index(cmd, ent);
 		if (alloc_ret < 0) {
 			mlx5_core_err_rl(dev, "failed to allocate command entry\n");
 			if (ent->callback) {
@@ -994,15 +997,14 @@ static void cmd_work_handler(struct work_struct *work)
 			up(sem);
 			return;
 		}
-		ent->idx = alloc_ret;
 	} else {
 		ent->idx = cmd->vars.max_reg_cmds;
 		spin_lock_irqsave(&cmd->alloc_lock, flags);
 		clear_bit(ent->idx, &cmd->vars.bitmask);
+		cmd->ent_arr[ent->idx] = ent;
 		spin_unlock_irqrestore(&cmd->alloc_lock, flags);
 	}
 
-	cmd->ent_arr[ent->idx] = ent;
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index 76d27d2ee40cbb..080e7eab52c7e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -718,7 +718,7 @@ static void mlx5_fw_tracer_handle_traces(struct work_struct *work)
 
 	while (block_timestamp > tracer->last_timestamp) {
 		/* Check block override if it's not the first block */
-		if (!tracer->last_timestamp) {
+		if (tracer->last_timestamp) {
 			u64 *ts_event;
 			/* To avoid block override be the HW in case of buffer
 			 * wraparound, the time stamp of the previous block
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index b2a5da9739d2b4..729a11b5fb2524 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -826,6 +826,7 @@ enum {
 	MLX5E_STATE_DESTROYING,
 	MLX5E_STATE_XDP_TX_ENABLED,
 	MLX5E_STATE_XDP_ACTIVE,
+	MLX5E_STATE_CHANNELS_ACTIVE,
 };
 
 struct mlx5e_modify_sq_param {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
index be83ad9db82a47..e1283531e0b810 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
@@ -154,6 +154,7 @@ static int fs_udp_create_groups(struct mlx5e_flow_table *ft, enum fs_udp_type ty
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if  (!in || !ft->g) {
 		kfree(ft->g);
+		ft->g = NULL;
 		kvfree(in);
 		return -ENOMEM;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index bb11e644d24f7b..af3928eddafd11 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -177,6 +177,8 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq,
 
 static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq,
 				    struct mlx5_cqe64 *cqe,
+				    u8 *md_buff,
+				    u8 *md_buff_sz,
 				    int budget)
 {
 	struct mlx5e_ptp_port_ts_cqe_list *pending_cqe_list = ptpsq->ts_cqe_pending_list;
@@ -211,19 +213,24 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq,
 	mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp);
 out:
 	napi_consume_skb(skb, budget);
-	mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist, metadata_id);
+	md_buff[*md_buff_sz++] = metadata_id;
 	if (unlikely(mlx5e_ptp_metadata_map_unhealthy(&ptpsq->metadata_map)) &&
 	    !test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
 		queue_work(ptpsq->txqsq.priv->wq, &ptpsq->report_unhealthy_work);
 }
 
-static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget)
+static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int napi_budget)
 {
 	struct mlx5e_ptpsq *ptpsq = container_of(cq, struct mlx5e_ptpsq, ts_cq);
-	struct mlx5_cqwq *cqwq = &cq->wq;
+	int budget = min(napi_budget, MLX5E_TX_CQ_POLL_BUDGET);
+	u8 metadata_buff[MLX5E_TX_CQ_POLL_BUDGET];
+	u8 metadata_buff_sz = 0;
+	struct mlx5_cqwq *cqwq;
 	struct mlx5_cqe64 *cqe;
 	int work_done = 0;
 
+	cqwq = &cq->wq;
+
 	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &ptpsq->txqsq.state)))
 		return false;
 
@@ -234,7 +241,8 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget)
 	do {
 		mlx5_cqwq_pop(cqwq);
 
-		mlx5e_ptp_handle_ts_cqe(ptpsq, cqe, budget);
+		mlx5e_ptp_handle_ts_cqe(ptpsq, cqe,
+					metadata_buff, &metadata_buff_sz, napi_budget);
 	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq)));
 
 	mlx5_cqwq_update_db_record(cqwq);
@@ -242,6 +250,10 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget)
 	/* ensure cq space is freed before enabling more cqes */
 	wmb();
 
+	while (metadata_buff_sz > 0)
+		mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist,
+					     metadata_buff[--metadata_buff_sz]);
+
 	mlx5e_txqsq_wake(&ptpsq->txqsq);
 
 	return work_done == budget;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index fea8c0a5fe893b..4358798d6ce14a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -492,11 +492,11 @@ static int mlx5e_rx_reporter_dump(struct devlink_health_reporter *reporter,
 
 void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq)
 {
-	char icosq_str[MLX5E_REPORTER_PER_Q_MAX_LEN] = {};
 	char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN];
 	struct mlx5e_icosq *icosq = rq->icosq;
 	struct mlx5e_priv *priv = rq->priv;
 	struct mlx5e_err_ctx err_ctx = {};
+	char icosq_str[32] = {};
 
 	err_ctx.ctx = rq;
 	err_ctx.recover = mlx5e_rx_reporter_timeout_recover;
@@ -505,7 +505,7 @@ void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq)
 	if (icosq)
 		snprintf(icosq_str, sizeof(icosq_str), "ICOSQ: 0x%x, ", icosq->sqn);
 	snprintf(err_str, sizeof(err_str),
-		 "RX timeout on channel: %d, %sRQ: 0x%x, CQ: 0x%x",
+		 "RX timeout on channel: %d, %s RQ: 0x%x, CQ: 0x%x",
 		 rq->ix, icosq_str, rq->rqn, rq->cq.mcq.cqn);
 
 	mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
index f63402c480280c..1b418095b79a39 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
@@ -197,7 +197,7 @@ parse_mirred_encap(struct mlx5e_tc_act_parse_state *parse_state,
 	}
 	esw_attr->dests[esw_attr->out_count].flags |= MLX5_ESW_DEST_ENCAP;
 	esw_attr->out_count++;
-	/* attr->dests[].rep is resolved when we handle encap */
+	/* attr->dests[].vport is resolved when we handle encap */
 
 	return 0;
 }
@@ -270,7 +270,8 @@ parse_mirred(struct mlx5e_tc_act_parse_state *parse_state,
 
 	out_priv = netdev_priv(out_dev);
 	rpriv = out_priv->ppriv;
-	esw_attr->dests[esw_attr->out_count].rep = rpriv->rep;
+	esw_attr->dests[esw_attr->out_count].vport_valid = true;
+	esw_attr->dests[esw_attr->out_count].vport = rpriv->rep->vport;
 	esw_attr->dests[esw_attr->out_count].mdev = out_priv->mdev;
 
 	esw_attr->out_count++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
index 4e923a2874aefe..86bf007fd05b73 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
@@ -83,6 +83,9 @@ mlx5e_tc_post_act_offload(struct mlx5e_post_act *post_act,
 	struct mlx5_flow_spec *spec;
 	int err;
 
+	if (IS_ERR(post_act))
+		return PTR_ERR(post_act);
+
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec)
 		return -ENOMEM;
@@ -111,6 +114,9 @@ mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *po
 	struct mlx5e_post_act_handle *handle;
 	int err;
 
+	if (IS_ERR(post_act))
+		return ERR_CAST(post_act);
+
 	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
 	if (!handle)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 00a04fdd756f57..8dfb57f712b0dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -302,6 +302,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 
 	e->encap_size = ipv4_encap_size;
 	e->encap_header = encap_header;
+	encap_header = NULL;
 
 	if (!(nud_state & NUD_VALID)) {
 		neigh_event_send(attr.n, NULL);
@@ -313,8 +314,8 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 
 	memset(&reformat_params, 0, sizeof(reformat_params));
 	reformat_params.type = e->reformat_type;
-	reformat_params.size = ipv4_encap_size;
-	reformat_params.data = encap_header;
+	reformat_params.size = e->encap_size;
+	reformat_params.data = e->encap_header;
 	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
@@ -407,6 +408,7 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv,
 	e->encap_size = ipv4_encap_size;
 	kfree(e->encap_header);
 	e->encap_header = encap_header;
+	encap_header = NULL;
 
 	if (!(nud_state & NUD_VALID)) {
 		neigh_event_send(attr.n, NULL);
@@ -418,8 +420,8 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv,
 
 	memset(&reformat_params, 0, sizeof(reformat_params));
 	reformat_params.type = e->reformat_type;
-	reformat_params.size = ipv4_encap_size;
-	reformat_params.data = encap_header;
+	reformat_params.size = e->encap_size;
+	reformat_params.data = e->encap_header;
 	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
@@ -570,6 +572,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 
 	e->encap_size = ipv6_encap_size;
 	e->encap_header = encap_header;
+	encap_header = NULL;
 
 	if (!(nud_state & NUD_VALID)) {
 		neigh_event_send(attr.n, NULL);
@@ -581,8 +584,8 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 
 	memset(&reformat_params, 0, sizeof(reformat_params));
 	reformat_params.type = e->reformat_type;
-	reformat_params.size = ipv6_encap_size;
-	reformat_params.data = encap_header;
+	reformat_params.size = e->encap_size;
+	reformat_params.data = e->encap_header;
 	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
@@ -674,6 +677,7 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv,
 	e->encap_size = ipv6_encap_size;
 	kfree(e->encap_header);
 	e->encap_header = encap_header;
+	encap_header = NULL;
 
 	if (!(nud_state & NUD_VALID)) {
 		neigh_event_send(attr.n, NULL);
@@ -685,8 +689,8 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv,
 
 	memset(&reformat_params, 0, sizeof(reformat_params));
 	reformat_params.type = e->reformat_type;
-	reformat_params.size = ipv6_encap_size;
-	reformat_params.data = encap_header;
+	reformat_params.size = e->encap_size;
+	reformat_params.data = e->encap_header;
 	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params,
 						     MLX5_FLOW_NAMESPACE_FDB);
 	if (IS_ERR(e->pkt_reformat)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index b10e40e1a9c141..f1d1e1542e81b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -1064,7 +1064,8 @@ int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv,
 
 		out_priv = netdev_priv(encap_dev);
 		rpriv = out_priv->ppriv;
-		esw_attr->dests[out_index].rep = rpriv->rep;
+		esw_attr->dests[out_index].vport_valid = true;
+		esw_attr->dests[out_index].vport = rpriv->rep->vport;
 		esw_attr->dests[out_index].mdev = out_priv->mdev;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 7decc81ed33a9e..13c7ed1bb37e93 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -493,6 +493,7 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 	dma_addr_t dma_addr = xdptxd->dma_addr;
 	u32 dma_len = xdptxd->len;
 	u16 ds_cnt, inline_hdr_sz;
+	unsigned int frags_size;
 	u8 num_wqebbs = 1;
 	int num_frags = 0;
 	bool inline_ok;
@@ -503,8 +504,9 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 
 	inline_ok = sq->min_inline_mode == MLX5_INLINE_MODE_NONE ||
 		dma_len >= MLX5E_XDP_MIN_INLINE;
+	frags_size = xdptxd->has_frags ? xdptxdf->sinfo->xdp_frags_size : 0;
 
-	if (unlikely(!inline_ok || sq->hw_mtu < dma_len)) {
+	if (unlikely(!inline_ok || sq->hw_mtu < dma_len + frags_size)) {
 		stats->err++;
 		return false;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 655496598c6884..161c5190c236a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -121,7 +121,14 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry)
 	if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO)
 		esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom));
 
-	sa_entry->esn_state.esn = esn;
+	if (sa_entry->esn_state.esn_msb)
+		sa_entry->esn_state.esn = esn;
+	else
+		/* According to RFC4303, section "3.3.3. Sequence Number Generation",
+		 * the first packet sent using a given SA will contain a sequence
+		 * number of 1.
+		 */
+		sa_entry->esn_state.esn = max_t(u32, esn, 1);
 	sa_entry->esn_state.esn_msb = esn_msb;
 
 	if (unlikely(overlap && seq_bottom < MLX5E_IPSEC_ESN_SCOPE_MID)) {
@@ -335,6 +342,27 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 		attrs->replay_esn.esn = sa_entry->esn_state.esn;
 		attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb;
 		attrs->replay_esn.overlap = sa_entry->esn_state.overlap;
+		switch (x->replay_esn->replay_window) {
+		case 32:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_32BIT;
+			break;
+		case 64:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_64BIT;
+			break;
+		case 128:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_128BIT;
+			break;
+		case 256:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_256BIT;
+			break;
+		default:
+			WARN_ON(true);
+			return;
+		}
 	}
 
 	attrs->dir = x->xso.dir;
@@ -907,9 +935,11 @@ void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv)
 		return;
 
 	mlx5e_accel_ipsec_fs_cleanup(ipsec);
-	if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_TUNNEL)
+	if (ipsec->netevent_nb.notifier_call) {
 		unregister_netevent_notifier(&ipsec->netevent_nb);
-	if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)
+		ipsec->netevent_nb.notifier_call = NULL;
+	}
+	if (ipsec->aso)
 		mlx5e_ipsec_aso_cleanup(ipsec);
 	destroy_workqueue(ipsec->wq);
 	kfree(ipsec);
@@ -1018,6 +1048,12 @@ static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev,
 		}
 	}
 
+	if (x->xdo.type == XFRM_DEV_OFFLOAD_PACKET &&
+	    !(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)) {
+		NL_SET_ERR_MSG_MOD(extack, "Packet offload is not supported");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -1113,14 +1149,6 @@ static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = {
 	.xdo_dev_state_free	= mlx5e_xfrm_free_state,
 	.xdo_dev_offload_ok	= mlx5e_ipsec_offload_ok,
 	.xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state,
-};
-
-static const struct xfrmdev_ops mlx5e_ipsec_packet_xfrmdev_ops = {
-	.xdo_dev_state_add	= mlx5e_xfrm_add_state,
-	.xdo_dev_state_delete	= mlx5e_xfrm_del_state,
-	.xdo_dev_state_free	= mlx5e_xfrm_free_state,
-	.xdo_dev_offload_ok	= mlx5e_ipsec_offload_ok,
-	.xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state,
 
 	.xdo_dev_state_update_curlft = mlx5e_xfrm_update_curlft,
 	.xdo_dev_policy_add = mlx5e_xfrm_add_policy,
@@ -1138,11 +1166,7 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv)
 
 	mlx5_core_info(mdev, "mlx5e: IPSec ESP acceleration enabled\n");
 
-	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)
-		netdev->xfrmdev_ops = &mlx5e_ipsec_packet_xfrmdev_ops;
-	else
-		netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops;
-
+	netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops;
 	netdev->features |= NETIF_F_HW_ESP;
 	netdev->hw_enc_features |= NETIF_F_HW_ESP;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 8f4a37bceaf455..adaea3493193ef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -189,11 +189,19 @@ struct mlx5e_ipsec_ft {
 	u32 refcnt;
 };
 
+struct mlx5e_ipsec_drop {
+	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *fc;
+};
+
 struct mlx5e_ipsec_rule {
 	struct mlx5_flow_handle *rule;
 	struct mlx5_modify_hdr *modify_hdr;
 	struct mlx5_pkt_reformat *pkt_reformat;
 	struct mlx5_fc *fc;
+	struct mlx5e_ipsec_drop replay;
+	struct mlx5e_ipsec_drop auth;
+	struct mlx5e_ipsec_drop trailer;
 };
 
 struct mlx5e_ipsec_miss {
@@ -201,19 +209,6 @@ struct mlx5e_ipsec_miss {
 	struct mlx5_flow_handle *rule;
 };
 
-struct mlx5e_ipsec_rx {
-	struct mlx5e_ipsec_ft ft;
-	struct mlx5e_ipsec_miss pol;
-	struct mlx5e_ipsec_miss sa;
-	struct mlx5e_ipsec_rule status;
-	struct mlx5e_ipsec_miss status_drop;
-	struct mlx5_fc *status_drop_cnt;
-	struct mlx5e_ipsec_fc *fc;
-	struct mlx5_fs_chains *chains;
-	u8 allow_tunnel_mode : 1;
-	struct xarray ipsec_obj_id_map;
-};
-
 struct mlx5e_ipsec_tx_create_attr {
 	int prio;
 	int pol_level;
@@ -248,6 +243,7 @@ struct mlx5e_ipsec {
 	struct mlx5_ipsec_fs *roce;
 	u8 is_uplink_rep: 1;
 	struct mlx5e_ipsec_mpv_work mpv_work;
+	struct xarray ipsec_obj_id_map;
 };
 
 struct mlx5e_ipsec_esn_state {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index f41c976dc33f93..41a2543a52cda0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -32,6 +32,22 @@ struct mlx5e_ipsec_tx {
 	u8 allow_tunnel_mode : 1;
 };
 
+struct mlx5e_ipsec_status_checks {
+	struct mlx5_flow_group *drop_all_group;
+	struct mlx5e_ipsec_drop all;
+};
+
+struct mlx5e_ipsec_rx {
+	struct mlx5e_ipsec_ft ft;
+	struct mlx5e_ipsec_miss pol;
+	struct mlx5e_ipsec_miss sa;
+	struct mlx5e_ipsec_rule status;
+	struct mlx5e_ipsec_status_checks status_drops;
+	struct mlx5e_ipsec_fc *fc;
+	struct mlx5_fs_chains *chains;
+	u8 allow_tunnel_mode : 1;
+};
+
 /* IPsec RX flow steering */
 static enum mlx5_traffic_types family2tt(u32 family)
 {
@@ -128,14 +144,37 @@ static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns,
 	return mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
 }
 
-static int ipsec_status_rule(struct mlx5_core_dev *mdev,
-			     struct mlx5e_ipsec_rx *rx,
-			     struct mlx5_flow_destination *dest)
+static void ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
+					 struct mlx5e_ipsec_rx *rx)
+{
+	mlx5_del_flow_rules(rx->status_drops.all.rule);
+	mlx5_fc_destroy(ipsec->mdev, rx->status_drops.all.fc);
+	mlx5_destroy_flow_group(rx->status_drops.drop_all_group);
+}
+
+static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
+					 struct mlx5e_ipsec_rx *rx)
 {
-	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	mlx5_del_flow_rules(rx->status.rule);
+
+	if (rx != ipsec->rx_esw)
+		return;
+
+#ifdef CONFIG_MLX5_ESWITCH
+	mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0);
+#endif
+}
+
+static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry,
+					 struct mlx5e_ipsec_rx *rx)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct mlx5_flow_table *ft = rx->ft.status;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_act flow_act = {};
-	struct mlx5_modify_hdr *modify_hdr;
-	struct mlx5_flow_handle *fte;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *flow_counter;
 	struct mlx5_flow_spec *spec;
 	int err;
 
@@ -143,48 +182,273 @@ static int ipsec_status_rule(struct mlx5_core_dev *mdev,
 	if (!spec)
 		return -ENOMEM;
 
-	/* Action to copy 7 bit ipsec_syndrome to regB[24:30] */
-	MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY);
-	MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME);
-	MLX5_SET(copy_action_in, action, src_offset, 0);
-	MLX5_SET(copy_action_in, action, length, 7);
-	MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
-	MLX5_SET(copy_action_in, action, dst_offset, 24);
+	flow_counter = mlx5_fc_create(mdev, true);
+	if (IS_ERR(flow_counter)) {
+		err = PTR_ERR(flow_counter);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+		goto err_cnt;
+	}
+	sa_entry->ipsec_rule.auth.fc = flow_counter;
 
-	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL,
-					      1, action);
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	flow_act.flags = FLOW_ACT_NO_APPEND;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter_id = mlx5_fc_id(flow_counter);
+	if (rx == ipsec->rx_esw)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
 
-	if (IS_ERR(modify_hdr)) {
-		err = PTR_ERR(modify_hdr);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.ipsec_syndrome);
+	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 1);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.metadata_reg_c_2,
+		 sa_entry->ipsec_obj_id | BIT(31));
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
 		mlx5_core_err(mdev,
-			      "fail to alloc ipsec copy modify_header_id err=%d\n", err);
-		goto out_spec;
+			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
+		goto err_rule;
 	}
+	sa_entry->ipsec_rule.auth.rule = rule;
 
-	/* create fte */
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
-			  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+	flow_counter = mlx5_fc_create(mdev, true);
+	if (IS_ERR(flow_counter)) {
+		err = PTR_ERR(flow_counter);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+		goto err_cnt_2;
+	}
+	sa_entry->ipsec_rule.trailer.fc = flow_counter;
+
+	dest.counter_id = mlx5_fc_id(flow_counter);
+	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 2);
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
+		goto err_rule_2;
+	}
+	sa_entry->ipsec_rule.trailer.rule = rule;
+
+	kvfree(spec);
+	return 0;
+
+err_rule_2:
+	mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.trailer.fc);
+err_cnt_2:
+	mlx5_del_flow_rules(sa_entry->ipsec_rule.auth.rule);
+err_rule:
+	mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.auth.fc);
+err_cnt:
+	kvfree(spec);
+	return err;
+}
+
+static int rx_add_rule_drop_replay(struct mlx5e_ipsec_sa_entry *sa_entry, struct mlx5e_ipsec_rx *rx)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct mlx5_flow_table *ft = rx->ft.status;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *flow_counter;
+	struct mlx5_flow_spec *spec;
+	int err;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	flow_counter = mlx5_fc_create(mdev, true);
+	if (IS_ERR(flow_counter)) {
+		err = PTR_ERR(flow_counter);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+		goto err_cnt;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	flow_act.flags = FLOW_ACT_NO_APPEND;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter_id = mlx5_fc_id(flow_counter);
+	if (rx == ipsec->rx_esw)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_4);
+	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_4, 1);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
+	MLX5_SET(fte_match_param, spec->match_value,  misc_parameters_2.metadata_reg_c_2,
+		 sa_entry->ipsec_obj_id | BIT(31));
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
+		goto err_rule;
+	}
+
+	sa_entry->ipsec_rule.replay.rule = rule;
+	sa_entry->ipsec_rule.replay.fc = flow_counter;
+
+	kvfree(spec);
+	return 0;
+
+err_rule:
+	mlx5_fc_destroy(mdev, flow_counter);
+err_cnt:
+	kvfree(spec);
+	return err;
+}
+
+static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec,
+					   struct mlx5e_ipsec_rx *rx)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_table *ft = rx->ft.status;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *flow_counter;
+	struct mlx5_flow_spec *spec;
+	struct mlx5_flow_group *g;
+	u32 *flow_group_in;
+	int err = 0;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!flow_group_in || !spec) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1);
+	g = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop flow group, err=%d\n", err);
+		goto err_out;
+	}
+
+	flow_counter = mlx5_fc_create(mdev, false);
+	if (IS_ERR(flow_counter)) {
+		err = PTR_ERR(flow_counter);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+		goto err_cnt;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter_id = mlx5_fc_id(flow_counter);
+	if (rx == ipsec->rx_esw)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
+		goto err_rule;
+	}
+
+	rx->status_drops.drop_all_group = g;
+	rx->status_drops.all.rule = rule;
+	rx->status_drops.all.fc = flow_counter;
+
+	kvfree(flow_group_in);
+	kvfree(spec);
+	return 0;
+
+err_rule:
+	mlx5_fc_destroy(mdev, flow_counter);
+err_cnt:
+	mlx5_destroy_flow_group(g);
+err_out:
+	kvfree(flow_group_in);
+	kvfree(spec);
+	return err;
+}
+
+static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx *rx,
+				       struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.ipsec_syndrome);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.metadata_reg_c_4);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.ipsec_syndrome, 0);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.metadata_reg_c_4, 0);
+	if (rx == ipsec->rx_esw)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	flow_act.flags = FLOW_ACT_NO_APPEND;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	flow_act.modify_hdr = modify_hdr;
-	fte = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
-	if (IS_ERR(fte)) {
-		err = PTR_ERR(fte);
-		mlx5_core_err(mdev, "fail to add ipsec rx err copy rule err=%d\n", err);
-		goto out;
+	rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_warn(ipsec->mdev,
+			       "Failed to add ipsec rx status pass rule, err=%d\n", err);
+		goto err_rule;
 	}
 
+	rx->status.rule = rule;
 	kvfree(spec);
-	rx->status.rule = fte;
-	rx->status.modify_hdr = modify_hdr;
 	return 0;
 
-out:
-	mlx5_modify_header_dealloc(mdev, modify_hdr);
-out_spec:
+err_rule:
 	kvfree(spec);
 	return err;
 }
 
+static void mlx5_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
+					 struct mlx5e_ipsec_rx *rx)
+{
+	ipsec_rx_status_pass_destroy(ipsec, rx);
+	ipsec_rx_status_drop_destroy(ipsec, rx);
+}
+
+static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx *rx,
+				       struct mlx5_flow_destination *dest)
+{
+	int err;
+
+	err = ipsec_rx_status_drop_all_create(ipsec, rx);
+	if (err)
+		return err;
+
+	err = ipsec_rx_status_pass_create(ipsec, rx, dest);
+	if (err)
+		goto err_pass_create;
+
+	return 0;
+
+err_pass_create:
+	ipsec_rx_status_drop_destroy(ipsec, rx);
+	return err;
+}
+
 static int ipsec_miss_create(struct mlx5_core_dev *mdev,
 			     struct mlx5_flow_table *ft,
 			     struct mlx5e_ipsec_miss *miss,
@@ -333,12 +597,7 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_destroy_flow_table(rx->ft.sa);
 	if (rx->allow_tunnel_mode)
 		mlx5_eswitch_unblock_encap(mdev);
-	if (rx == ipsec->rx_esw) {
-		mlx5_esw_ipsec_rx_status_destroy(ipsec, rx);
-	} else {
-		mlx5_del_flow_rules(rx->status.rule);
-		mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
-	}
+	mlx5_ipsec_rx_status_destroy(ipsec, rx);
 	mlx5_destroy_flow_table(rx->ft.status);
 
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev);
@@ -419,7 +678,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (err)
 		return err;
 
-	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 1, 0);
+	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_fs_ft_status;
@@ -428,10 +687,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 
 	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
 	dest[1].counter_id = mlx5_fc_id(rx->fc->cnt);
-	if (rx == ipsec->rx_esw)
-		err = mlx5_esw_ipsec_rx_status_create(ipsec, rx, dest);
-	else
-		err = ipsec_status_rule(mdev, rx, dest);
+	err = mlx5_ipsec_rx_status_create(ipsec, rx, dest);
 	if (err)
 		goto err_add;
 
@@ -956,13 +1212,22 @@ static void setup_fte_esp(struct mlx5_flow_spec *spec)
 	MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, IPPROTO_ESP);
 }
 
-static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi)
+static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi, bool encap)
 {
 	/* SPI number */
 	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
 
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters.outer_esp_spi);
-	MLX5_SET(fte_match_param, spec->match_value, misc_parameters.outer_esp_spi, spi);
+	if (encap) {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 misc_parameters.inner_esp_spi);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 misc_parameters.inner_esp_spi, spi);
+	} else {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 misc_parameters.outer_esp_spi);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 misc_parameters.outer_esp_spi, spi);
+	}
 }
 
 static void setup_fte_no_frags(struct mlx5_flow_spec *spec)
@@ -1052,29 +1317,48 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8
 			       struct mlx5_flow_act *flow_act)
 {
 	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, type, dir);
-	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	u8 action[3][MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
 	struct mlx5_core_dev *mdev = ipsec->mdev;
 	struct mlx5_modify_hdr *modify_hdr;
+	u8 num_of_actions = 1;
 
-	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, action[0], action_type, MLX5_ACTION_TYPE_SET);
 	switch (dir) {
 	case XFRM_DEV_OFFLOAD_IN:
-		MLX5_SET(set_action_in, action, field,
+		MLX5_SET(set_action_in, action[0], field,
 			 MLX5_ACTION_IN_FIELD_METADATA_REG_B);
+
+		num_of_actions++;
+		MLX5_SET(set_action_in, action[1], action_type, MLX5_ACTION_TYPE_SET);
+		MLX5_SET(set_action_in, action[1], field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_2);
+		MLX5_SET(set_action_in, action[1], data, val);
+		MLX5_SET(set_action_in, action[1], offset, 0);
+		MLX5_SET(set_action_in, action[1], length, 32);
+
+		if (type == XFRM_DEV_OFFLOAD_CRYPTO) {
+			num_of_actions++;
+			MLX5_SET(set_action_in, action[2], action_type,
+				 MLX5_ACTION_TYPE_SET);
+			MLX5_SET(set_action_in, action[2], field,
+				 MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
+			MLX5_SET(set_action_in, action[2], data, 0);
+			MLX5_SET(set_action_in, action[2], offset, 0);
+			MLX5_SET(set_action_in, action[2], length, 32);
+		}
 		break;
 	case XFRM_DEV_OFFLOAD_OUT:
-		MLX5_SET(set_action_in, action, field,
+		MLX5_SET(set_action_in, action[0], field,
 			 MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	MLX5_SET(set_action_in, action, data, val);
-	MLX5_SET(set_action_in, action, offset, 0);
-	MLX5_SET(set_action_in, action, length, 32);
+	MLX5_SET(set_action_in, action[0], data, val);
+	MLX5_SET(set_action_in, action[0], offset, 0);
+	MLX5_SET(set_action_in, action[0], length, 32);
 
-	modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, 1, action);
+	modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, num_of_actions, action);
 	if (IS_ERR(modify_hdr)) {
 		mlx5_core_err(mdev, "Failed to allocate modify_header %ld\n",
 			      PTR_ERR(modify_hdr));
@@ -1321,8 +1605,9 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	else
 		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
 
-	setup_fte_spi(spec, attrs->spi);
-	setup_fte_esp(spec);
+	setup_fte_spi(spec, attrs->spi, attrs->encap);
+	if (!attrs->encap)
+		setup_fte_esp(spec);
 	setup_fte_no_frags(spec);
 	setup_fte_upper_proto_match(spec, &attrs->upspec);
 
@@ -1372,6 +1657,15 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		mlx5_core_err(mdev, "fail to add RX ipsec rule err=%d\n", err);
 		goto err_add_flow;
 	}
+	if (attrs->type == XFRM_DEV_OFFLOAD_PACKET)
+		err = rx_add_rule_drop_replay(sa_entry, rx);
+	if (err)
+		goto err_add_replay;
+
+	err = rx_add_rule_drop_auth_trailer(sa_entry, rx);
+	if (err)
+		goto err_drop_reason;
+
 	kvfree(spec);
 
 	sa_entry->ipsec_rule.rule = rule;
@@ -1380,6 +1674,13 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	sa_entry->ipsec_rule.pkt_reformat = flow_act.pkt_reformat;
 	return 0;
 
+err_drop_reason:
+	if (sa_entry->ipsec_rule.replay.rule) {
+		mlx5_del_flow_rules(sa_entry->ipsec_rule.replay.rule);
+		mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.replay.fc);
+	}
+err_add_replay:
+	mlx5_del_flow_rules(rule);
 err_add_flow:
 	mlx5_fc_destroy(mdev, counter);
 err_add_cnt:
@@ -1428,7 +1729,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 	switch (attrs->type) {
 	case XFRM_DEV_OFFLOAD_CRYPTO:
-		setup_fte_spi(spec, attrs->spi);
+		setup_fte_spi(spec, attrs->spi, false);
 		setup_fte_esp(spec);
 		setup_fte_reg_a(spec);
 		break;
@@ -1809,8 +2110,11 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev)
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
 	int err = 0;
 
-	if (esw)
-		down_write(&esw->mode_lock);
+	if (esw) {
+		err = mlx5_esw_lock(esw);
+		if (err)
+			return err;
+	}
 
 	if (mdev->num_block_ipsec) {
 		err = -EBUSY;
@@ -1821,7 +2125,7 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev)
 
 unlock:
 	if (esw)
-		up_write(&esw->mode_lock);
+		mlx5_esw_unlock(esw);
 
 	return err;
 }
@@ -1838,7 +2142,7 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev)
 
 static void mlx5e_ipsec_unblock_tc_offload(struct mlx5_core_dev *mdev)
 {
-	mdev->num_block_tc++;
+	mdev->num_block_tc--;
 }
 
 int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
@@ -1887,6 +2191,17 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 	if (ipsec_rule->modify_hdr)
 		mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr);
+
+	mlx5_del_flow_rules(ipsec_rule->trailer.rule);
+	mlx5_fc_destroy(mdev, ipsec_rule->trailer.fc);
+
+	mlx5_del_flow_rules(ipsec_rule->auth.rule);
+	mlx5_fc_destroy(mdev, ipsec_rule->auth.fc);
+
+	if (ipsec_rule->replay.rule) {
+		mlx5_del_flow_rules(ipsec_rule->replay.rule);
+		mlx5_fc_destroy(mdev, ipsec_rule->replay.fc);
+	}
 	mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry);
 	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type);
 }
@@ -1957,7 +2272,7 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec)
 	kfree(ipsec->rx_ipv6);
 
 	if (ipsec->is_uplink_rep) {
-		xa_destroy(&ipsec->rx_esw->ipsec_obj_id_map);
+		xa_destroy(&ipsec->ipsec_obj_id_map);
 
 		mutex_destroy(&ipsec->tx_esw->ft.mutex);
 		WARN_ON(ipsec->tx_esw->ft.refcnt);
@@ -2020,7 +2335,7 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec,
 		mutex_init(&ipsec->tx_esw->ft.mutex);
 		mutex_init(&ipsec->rx_esw->ft.mutex);
 		ipsec->tx_esw->ns = ns_esw;
-		xa_init_flags(&ipsec->rx_esw->ipsec_obj_id_map, XA_FLAGS_ALLOC1);
+		xa_init_flags(&ipsec->ipsec_obj_id_map, XA_FLAGS_ALLOC1);
 	} else if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE) {
 		ipsec->roce = mlx5_ipsec_fs_roce_init(mdev, devcom);
 	} else {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index a91f772dc981a1..6e00afe4671b78 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -6,6 +6,8 @@
 #include "ipsec.h"
 #include "lib/crypto.h"
 #include "lib/ipsec_fs_roce.h"
+#include "fs_core.h"
+#include "eswitch.h"
 
 enum {
 	MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET,
@@ -38,7 +40,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 	    MLX5_CAP_ETH(mdev, insert_trailer) && MLX5_CAP_ETH(mdev, swp))
 		caps |= MLX5_IPSEC_CAP_CRYPTO;
 
-	if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload)) {
+	if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload) &&
+	    (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS ||
+	     (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS &&
+	     is_mdev_legacy_mode(mdev)))) {
 		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,
 					      reformat_add_esp_trasport) &&
 		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
@@ -95,7 +100,7 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn,
 
 		if (attrs->dir == XFRM_DEV_OFFLOAD_IN) {
 			MLX5_SET(ipsec_aso, aso_ctx, window_sz,
-				 attrs->replay_esn.replay_window / 64);
+				 attrs->replay_esn.replay_window);
 			MLX5_SET(ipsec_aso, aso_ctx, mode,
 				 MLX5_IPSEC_ASO_REPLAY_PROTECTION);
 		}
@@ -559,6 +564,7 @@ void mlx5e_ipsec_aso_cleanup(struct mlx5e_ipsec *ipsec)
 	dma_unmap_single(pdev, aso->dma_addr, sizeof(aso->ctx),
 			 DMA_BIDIRECTIONAL);
 	kfree(aso);
+	ipsec->aso = NULL;
 }
 
 static void mlx5e_ipsec_aso_copy(struct mlx5_wqe_aso_ctrl_seg *ctrl,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 215261a6925507..c7c1b667b105a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -43,12 +43,17 @@ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
+	int count;
 
 	strscpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver));
-	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
-		 "%d.%d.%04d (%.16s)",
-		 fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev),
-		 mdev->board_id);
+	count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+			 "%d.%d.%04d (%.16s)", fw_rev_maj(mdev),
+			 fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id);
+	if (count >= sizeof(drvinfo->fw_version))
+		snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+			 "%d.%d.%04d", fw_rev_maj(mdev),
+			 fw_rev_min(mdev), fw_rev_sub(mdev));
+
 	strscpy(drvinfo->bus_info, dev_name(mdev->device),
 		sizeof(drvinfo->bus_info));
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index ea58c691743302..0c87ddb8a7a218 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2731,6 +2731,7 @@ void mlx5e_close_channels(struct mlx5e_channels *chs)
 {
 	int i;
 
+	ASSERT_RTNL();
 	if (chs->ptp) {
 		mlx5e_ptp_close(chs->ptp);
 		chs->ptp = NULL;
@@ -3012,17 +3013,29 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 	if (mlx5e_is_vport_rep(priv))
 		mlx5e_rep_activate_channels(priv);
 
+	set_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state);
+
 	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
 
 	if (priv->rx_res)
 		mlx5e_rx_res_channels_activate(priv->rx_res, &priv->channels);
 }
 
+static void mlx5e_cancel_tx_timeout_work(struct mlx5e_priv *priv)
+{
+	WARN_ON_ONCE(test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state));
+	if (current_work() != &priv->tx_timeout_work)
+		cancel_work_sync(&priv->tx_timeout_work);
+}
+
 void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 {
 	if (priv->rx_res)
 		mlx5e_rx_res_channels_deactivate(priv->rx_res);
 
+	clear_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state);
+	mlx5e_cancel_tx_timeout_work(priv);
+
 	if (mlx5e_is_vport_rep(priv))
 		mlx5e_rep_deactivate_channels(priv);
 
@@ -4801,8 +4814,17 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 	struct net_device *netdev = priv->netdev;
 	int i;
 
-	rtnl_lock();
-	mutex_lock(&priv->state_lock);
+	/* Take rtnl_lock to ensure no change in netdev->real_num_tx_queues
+	 * through this flow. However, channel closing flows have to wait for
+	 * this work to finish while holding rtnl lock too. So either get the
+	 * lock or find that channels are being closed for other reason and
+	 * this work is not relevant anymore.
+	 */
+	while (!rtnl_trylock()) {
+		if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state))
+			return;
+		msleep(20);
+	}
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
 		goto unlock;
@@ -4821,7 +4843,6 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 	}
 
 unlock:
-	mutex_unlock(&priv->state_lock);
 	rtnl_unlock();
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 693e55b010d9e8..e92d4f83592ed9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -71,13 +71,17 @@ static void mlx5e_rep_get_drvinfo(struct net_device *dev,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
+	int count;
 
 	strscpy(drvinfo->driver, mlx5e_rep_driver_name,
 		sizeof(drvinfo->driver));
-	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
-		 "%d.%d.%04d (%.16s)",
-		 fw_rev_maj(mdev), fw_rev_min(mdev),
-		 fw_rev_sub(mdev), mdev->board_id);
+	count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+			 "%d.%d.%04d (%.16s)", fw_rev_maj(mdev),
+			 fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id);
+	if (count >= sizeof(drvinfo->fw_version))
+		snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+			 "%d.%d.%04d", fw_rev_maj(mdev),
+			 fw_rev_min(mdev), fw_rev_sub(mdev));
 }
 
 static const struct counter_desc sw_rep_stats_desc[] = {
@@ -1493,7 +1497,7 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 
 	dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch,
 						 rpriv->rep->vport);
-	if (dl_port) {
+	if (!IS_ERR(dl_port)) {
 		SET_NETDEV_DEVLINK_PORT(netdev, dl_port);
 		mlx5e_rep_vnic_reporter_create(priv, dl_port);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9a5a5c2c7da9e1..96af9e2ab1d87d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -444,6 +444,9 @@ mlx5e_tc_add_flow_meter(struct mlx5e_priv *priv,
 	struct mlx5e_flow_meter_handle *meter;
 	enum mlx5e_post_meter_type type;
 
+	if (IS_ERR(post_act))
+		return PTR_ERR(post_act);
+
 	meter = mlx5e_tc_meter_replace(priv->mdev, &attr->meter_attr.params);
 	if (IS_ERR(meter)) {
 		mlx5_core_err(priv->mdev, "Failed to get flow meter\n");
@@ -3147,7 +3150,7 @@ static struct mlx5_fields fields[] = {
 	OFFLOAD(DIPV6_31_0,   32, U32_MAX, ip6.daddr.s6_addr32[3], 0,
 		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[12]),
 	OFFLOAD(IPV6_HOPLIMIT, 8,  U8_MAX, ip6.hop_limit, 0, ttl_hoplimit),
-	OFFLOAD(IP_DSCP, 16,  0xc00f, ip6, 0, ip_dscp),
+	OFFLOAD(IP_DSCP, 16,  0x0fc0, ip6, 0, ip_dscp),
 
 	OFFLOAD(TCP_SPORT, 16, U16_MAX, tcp.source,  0, tcp_sport),
 	OFFLOAD(TCP_DPORT, 16, U16_MAX, tcp.dest,    0, tcp_dport),
@@ -3158,21 +3161,31 @@ static struct mlx5_fields fields[] = {
 	OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest,   0, udp_dport),
 };
 
-static unsigned long mask_to_le(unsigned long mask, int size)
+static u32 mask_field_get(void *mask, struct mlx5_fields *f)
 {
-	__be32 mask_be32;
-	__be16 mask_be16;
-
-	if (size == 32) {
-		mask_be32 = (__force __be32)(mask);
-		mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32));
-	} else if (size == 16) {
-		mask_be32 = (__force __be32)(mask);
-		mask_be16 = *(__be16 *)&mask_be32;
-		mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16));
+	switch (f->field_bsize) {
+	case 32:
+		return be32_to_cpu(*(__be32 *)mask) & f->field_mask;
+	case 16:
+		return be16_to_cpu(*(__be16 *)mask) & (u16)f->field_mask;
+	default:
+		return *(u8 *)mask & (u8)f->field_mask;
 	}
+}
 
-	return mask;
+static void mask_field_clear(void *mask, struct mlx5_fields *f)
+{
+	switch (f->field_bsize) {
+	case 32:
+		*(__be32 *)mask &= ~cpu_to_be32(f->field_mask);
+		break;
+	case 16:
+		*(__be16 *)mask &= ~cpu_to_be16((u16)f->field_mask);
+		break;
+	default:
+		*(u8 *)mask &= ~(u8)f->field_mask;
+		break;
+	}
 }
 
 static int offload_pedit_fields(struct mlx5e_priv *priv,
@@ -3184,11 +3197,12 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 	struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
 	struct pedit_headers_action *hdrs = parse_attr->hdrs;
 	void *headers_c, *headers_v, *action, *vals_p;
-	u32 *s_masks_p, *a_masks_p, s_mask, a_mask;
 	struct mlx5e_tc_mod_hdr_acts *mod_acts;
-	unsigned long mask, field_mask;
+	void *s_masks_p, *a_masks_p;
 	int i, first, last, next_z;
 	struct mlx5_fields *f;
+	unsigned long mask;
+	u32 s_mask, a_mask;
 	u8 cmd;
 
 	mod_acts = &parse_attr->mod_hdr_acts;
@@ -3204,15 +3218,11 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 		bool skip;
 
 		f = &fields[i];
-		/* avoid seeing bits set from previous iterations */
-		s_mask = 0;
-		a_mask = 0;
-
 		s_masks_p = (void *)set_masks + f->offset;
 		a_masks_p = (void *)add_masks + f->offset;
 
-		s_mask = *s_masks_p & f->field_mask;
-		a_mask = *a_masks_p & f->field_mask;
+		s_mask = mask_field_get(s_masks_p, f);
+		a_mask = mask_field_get(a_masks_p, f);
 
 		if (!s_mask && !a_mask) /* nothing to offload here */
 			continue;
@@ -3239,22 +3249,20 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 					 match_mask, f->field_bsize))
 				skip = true;
 			/* clear to denote we consumed this field */
-			*s_masks_p &= ~f->field_mask;
+			mask_field_clear(s_masks_p, f);
 		} else {
 			cmd  = MLX5_ACTION_TYPE_ADD;
 			mask = a_mask;
 			vals_p = (void *)add_vals + f->offset;
 			/* add 0 is no change */
-			if ((*(u32 *)vals_p & f->field_mask) == 0)
+			if (!mask_field_get(vals_p, f))
 				skip = true;
 			/* clear to denote we consumed this field */
-			*a_masks_p &= ~f->field_mask;
+			mask_field_clear(a_masks_p, f);
 		}
 		if (skip)
 			continue;
 
-		mask = mask_to_le(mask, f->field_bsize);
-
 		first = find_first_bit(&mask, f->field_bsize);
 		next_z = find_next_zero_bit(&mask, f->field_bsize, first);
 		last  = find_last_bit(&mask, f->field_bsize);
@@ -3281,10 +3289,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 		MLX5_SET(set_action_in, action, field, f->field);
 
 		if (cmd == MLX5_ACTION_TYPE_SET) {
+			unsigned long field_mask = f->field_mask;
 			int start;
 
-			field_mask = mask_to_le(f->field_mask, f->field_bsize);
-
 			/* if field is bit sized it can start not from first bit */
 			start = find_first_bit(&field_mask, f->field_bsize);
 
@@ -3735,6 +3742,20 @@ out_free:
 }
 
 static int
+set_branch_dest_ft(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr)
+{
+	struct mlx5e_post_act *post_act = get_post_action(priv);
+
+	if (IS_ERR(post_act))
+		return PTR_ERR(post_act);
+
+	attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	attr->dest_ft = mlx5e_tc_post_act_get_ft(post_act);
+
+	return 0;
+}
+
+static int
 alloc_branch_attr(struct mlx5e_tc_flow *flow,
 		  struct mlx5e_tc_act_branch_ctrl *cond,
 		  struct mlx5_flow_attr **cond_attr,
@@ -3757,8 +3778,9 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow,
 		break;
 	case FLOW_ACTION_ACCEPT:
 	case FLOW_ACTION_PIPE:
-		attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-		attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv));
+		err = set_branch_dest_ft(flow->priv, attr);
+		if (err)
+			goto out_err;
 		break;
 	case FLOW_ACTION_JUMP:
 		if (*jump_count) {
@@ -3767,8 +3789,9 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow,
 			goto out_err;
 		}
 		*jump_count = cond->extval;
-		attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-		attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv));
+		err = set_branch_dest_ft(flow->priv, attr);
+		if (err)
+			goto out_err;
 		break;
 	default:
 		err = -EOPNOTSUPP;
@@ -5715,8 +5738,10 @@ int mlx5e_tc_action_miss_mapping_get(struct mlx5e_priv *priv, struct mlx5_flow_a
 
 	esw = priv->mdev->priv.eswitch;
 	attr->act_id_restore_rule = esw_add_restore_rule(esw, *act_miss_mapping);
-	if (IS_ERR(attr->act_id_restore_rule))
+	if (IS_ERR(attr->act_id_restore_rule)) {
+		err = PTR_ERR(attr->act_id_restore_rule);
 		goto err_rule;
+	}
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index d41435c22ce56f..f0b506e562df31 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -399,9 +399,9 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		u8 metadata_index = be32_to_cpu(eseg->flow_table_metadata);
 
 		mlx5e_skb_cb_hwtstamp_init(skb);
-		mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index);
 		mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb,
 					   metadata_index);
+		mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index);
 		if (!netif_tx_queue_stopped(sq->txq) &&
 		    mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq)) {
 			netif_tx_stop_queue(sq->txq);
@@ -494,10 +494,10 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 
 err_drop:
 	stats->dropped++;
-	dev_kfree_skb_any(skb);
 	if (unlikely(sq->ptpsq && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
 		mlx5e_ptp_metadata_fifo_push(&sq->ptpsq->metadata_freelist,
 					     be32_to_cpu(eseg->flow_table_metadata));
+	dev_kfree_skb_any(skb);
 	mlx5e_tx_flush(sq);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index ea0405e0a43fac..40a6cb052a2da3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -885,11 +885,14 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_irq *irq;
+	int cpu;
 
 	irq = xa_load(&table->comp_irqs, vecidx);
 	if (!irq)
 		return;
 
+	cpu = cpumask_first(mlx5_irq_get_affinity_mask(irq));
+	cpumask_clear_cpu(cpu, &table->used_cpus);
 	xa_erase(&table->comp_irqs, vecidx);
 	mlx5_irq_affinity_irq_release(dev, irq);
 }
@@ -897,16 +900,26 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx)
 static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
+	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
+	struct irq_affinity_desc af_desc = {};
 	struct mlx5_irq *irq;
 
-	irq = mlx5_irq_affinity_irq_request_auto(dev, &table->used_cpus, vecidx);
-	if (IS_ERR(irq)) {
-		/* In case SF irq pool does not exist, fallback to the PF irqs*/
-		if (PTR_ERR(irq) == -ENOENT)
-			return comp_irq_request_pci(dev, vecidx);
+	/* In case SF irq pool does not exist, fallback to the PF irqs*/
+	if (!mlx5_irq_pool_is_sf_pool(pool))
+		return comp_irq_request_pci(dev, vecidx);
 
+	af_desc.is_managed = 1;
+	cpumask_copy(&af_desc.mask, cpu_online_mask);
+	cpumask_andnot(&af_desc.mask, &af_desc.mask, &table->used_cpus);
+	irq = mlx5_irq_affinity_request(pool, &af_desc);
+	if (IS_ERR(irq))
 		return PTR_ERR(irq);
-	}
+
+	cpumask_or(&table->used_cpus, &table->used_cpus, mlx5_irq_get_affinity_mask(irq));
+	mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n",
+		      pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)),
+		      cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)),
+		      mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ);
 
 	return xa_err(xa_store(&table->comp_irqs, vecidx, irq, GFP_KERNEL));
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 095f31f380fa3a..190f10aba17028 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -21,158 +21,6 @@ enum {
 	MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL,
 };
 
-static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
-					     struct mlx5e_ipsec_rx *rx)
-{
-	mlx5_del_flow_rules(rx->status_drop.rule);
-	mlx5_destroy_flow_group(rx->status_drop.group);
-	mlx5_fc_destroy(ipsec->mdev, rx->status_drop_cnt);
-}
-
-static void esw_ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
-					     struct mlx5e_ipsec_rx *rx)
-{
-	mlx5_del_flow_rules(rx->status.rule);
-	mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0);
-}
-
-static int esw_ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec,
-					   struct mlx5e_ipsec_rx *rx)
-{
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct mlx5_flow_table *ft = rx->ft.status;
-	struct mlx5_core_dev *mdev = ipsec->mdev;
-	struct mlx5_flow_destination dest = {};
-	struct mlx5_flow_act flow_act = {};
-	struct mlx5_flow_handle *rule;
-	struct mlx5_fc *flow_counter;
-	struct mlx5_flow_spec *spec;
-	struct mlx5_flow_group *g;
-	u32 *flow_group_in;
-	int err = 0;
-
-	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!flow_group_in || !spec) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1);
-	g = mlx5_create_flow_group(ft, flow_group_in);
-	if (IS_ERR(g)) {
-		err = PTR_ERR(g);
-		mlx5_core_err(mdev,
-			      "Failed to add ipsec rx status drop flow group, err=%d\n", err);
-		goto err_out;
-	}
-
-	flow_counter = mlx5_fc_create(mdev, false);
-	if (IS_ERR(flow_counter)) {
-		err = PTR_ERR(flow_counter);
-		mlx5_core_err(mdev,
-			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
-		goto err_cnt;
-	}
-
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest.counter_id = mlx5_fc_id(flow_counter);
-	spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
-	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
-	if (IS_ERR(rule)) {
-		err = PTR_ERR(rule);
-		mlx5_core_err(mdev,
-			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
-		goto err_rule;
-	}
-
-	rx->status_drop.group = g;
-	rx->status_drop.rule = rule;
-	rx->status_drop_cnt = flow_counter;
-
-	kvfree(flow_group_in);
-	kvfree(spec);
-	return 0;
-
-err_rule:
-	mlx5_fc_destroy(mdev, flow_counter);
-err_cnt:
-	mlx5_destroy_flow_group(g);
-err_out:
-	kvfree(flow_group_in);
-	kvfree(spec);
-	return err;
-}
-
-static int esw_ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
-					   struct mlx5e_ipsec_rx *rx,
-					   struct mlx5_flow_destination *dest)
-{
-	struct mlx5_flow_act flow_act = {};
-	struct mlx5_flow_handle *rule;
-	struct mlx5_flow_spec *spec;
-	int err;
-
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!spec)
-		return -ENOMEM;
-
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
-			 misc_parameters_2.ipsec_syndrome);
-	MLX5_SET(fte_match_param, spec->match_value,
-		 misc_parameters_2.ipsec_syndrome, 0);
-	spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
-	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
-	flow_act.flags = FLOW_ACT_NO_APPEND;
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
-			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
-	if (IS_ERR(rule)) {
-		err = PTR_ERR(rule);
-		mlx5_core_warn(ipsec->mdev,
-			       "Failed to add ipsec rx status pass rule, err=%d\n", err);
-		goto err_rule;
-	}
-
-	rx->status.rule = rule;
-	kvfree(spec);
-	return 0;
-
-err_rule:
-	kvfree(spec);
-	return err;
-}
-
-void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
-				      struct mlx5e_ipsec_rx *rx)
-{
-	esw_ipsec_rx_status_pass_destroy(ipsec, rx);
-	esw_ipsec_rx_status_drop_destroy(ipsec, rx);
-}
-
-int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
-				    struct mlx5e_ipsec_rx *rx,
-				    struct mlx5_flow_destination *dest)
-{
-	int err;
-
-	err = esw_ipsec_rx_status_drop_create(ipsec, rx);
-	if (err)
-		return err;
-
-	err = esw_ipsec_rx_status_pass_create(ipsec, rx, dest);
-	if (err)
-		goto err_pass_create;
-
-	return 0;
-
-err_pass_create:
-	esw_ipsec_rx_status_drop_destroy(ipsec, rx);
-	return err;
-}
-
 void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_rx_create_attr *attr)
 {
@@ -202,7 +50,7 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
 	u32 mapped_id;
 	int err;
 
-	err = xa_alloc_bh(&ipsec->rx_esw->ipsec_obj_id_map, &mapped_id,
+	err = xa_alloc_bh(&ipsec->ipsec_obj_id_map, &mapped_id,
 			  xa_mk_value(sa_entry->ipsec_obj_id),
 			  XA_LIMIT(1, ESW_IPSEC_RX_MAPPED_ID_MASK), 0);
 	if (err)
@@ -233,7 +81,7 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
 	return 0;
 
 err_header_alloc:
-	xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, mapped_id);
+	xa_erase_bh(&ipsec->ipsec_obj_id_map, mapped_id);
 	return err;
 }
 
@@ -242,7 +90,7 @@ void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry)
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
 
 	if (sa_entry->rx_mapped_id)
-		xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map,
+		xa_erase_bh(&ipsec->ipsec_obj_id_map,
 			    sa_entry->rx_mapped_id);
 }
 
@@ -252,7 +100,7 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 	struct mlx5e_ipsec *ipsec = priv->ipsec;
 	void *val;
 
-	val = xa_load(&ipsec->rx_esw->ipsec_obj_id_map, id);
+	val = xa_load(&ipsec->ipsec_obj_id_map, id);
 	if (!val)
 		return -ENOENT;
 
@@ -304,7 +152,7 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev)
 
 	xa_for_each(&esw->offloads.vport_reps, i, rep) {
 		rpriv = rep->rep_data[REP_ETH].priv;
-		if (!rpriv || !rpriv->netdev)
+		if (!rpriv || !rpriv->netdev || !atomic_read(&rpriv->tc_ht.nelems))
 			continue;
 
 		rhashtable_walk_enter(&rpriv->tc_ht, &iter);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
index 0c90f7a8b0d32c..ac9c65b89166e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
@@ -8,11 +8,6 @@ struct mlx5e_ipsec;
 struct mlx5e_ipsec_sa_entry;
 
 #ifdef CONFIG_MLX5_ESWITCH
-void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
-				      struct mlx5e_ipsec_rx *rx);
-int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
-				    struct mlx5e_ipsec_rx *rx,
-				    struct mlx5_flow_destination *dest);
 void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_rx_create_attr *attr);
 int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
@@ -26,16 +21,6 @@ void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_tx_create_attr *attr);
 void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev);
 #else
-static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
-						    struct mlx5e_ipsec_rx *rx) {}
-
-static inline int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
-						  struct mlx5e_ipsec_rx *rx,
-						  struct mlx5_flow_destination *dest)
-{
-	return  -EINVAL;
-}
-
 static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 						     struct mlx5e_ipsec_rx_create_attr *attr) {}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 8d0b915a31214e..3047d7015c5256 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1463,7 +1463,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs)
 {
 	int err;
 
-	lockdep_assert_held(&esw->mode_lock);
+	devl_assert_locked(priv_to_devlink(esw->dev));
 
 	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
 		esw_warn(esw->dev, "FDB is not supported, aborting ...\n");
@@ -1531,7 +1531,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 	if (toggle_lag)
 		mlx5_lag_disable_change(esw->dev);
 
-	down_write(&esw->mode_lock);
 	if (!mlx5_esw_is_fdb_created(esw)) {
 		ret = mlx5_eswitch_enable_locked(esw, num_vfs);
 	} else {
@@ -1554,8 +1553,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 		}
 	}
 
-	up_write(&esw->mode_lock);
-
 	if (toggle_lag)
 		mlx5_lag_enable_change(esw->dev);
 
@@ -1569,12 +1566,11 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf)
 		return;
 
 	devl_assert_locked(priv_to_devlink(esw->dev));
-	down_write(&esw->mode_lock);
 	/* If driver is unloaded, this function is called twice by remove_one()
 	 * and mlx5_unload(). Prevent the second call.
 	 */
 	if (!esw->esw_funcs.num_vfs && !esw->esw_funcs.num_ec_vfs && !clear_vf)
-		goto unlock;
+		return;
 
 	esw_info(esw->dev, "Unload vfs: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n",
 		 esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
@@ -1603,9 +1599,6 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf)
 		esw->esw_funcs.num_vfs = 0;
 	else
 		esw->esw_funcs.num_ec_vfs = 0;
-
-unlock:
-	up_write(&esw->mode_lock);
 }
 
 /* Free resources for corresponding eswitch mode. It is called by devlink
@@ -1647,10 +1640,8 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
 
 	devl_assert_locked(priv_to_devlink(esw->dev));
 	mlx5_lag_disable_change(esw->dev);
-	down_write(&esw->mode_lock);
 	mlx5_eswitch_disable_locked(esw);
 	esw->mode = MLX5_ESWITCH_LEGACY;
-	up_write(&esw->mode_lock);
 	mlx5_lag_enable_change(esw->dev);
 }
 
@@ -2254,8 +2245,13 @@ bool mlx5_esw_hold(struct mlx5_core_dev *mdev)
 	if (!mlx5_esw_allowed(esw))
 		return true;
 
-	if (down_read_trylock(&esw->mode_lock) != 0)
+	if (down_read_trylock(&esw->mode_lock) != 0) {
+		if (esw->eswitch_operation_in_progress) {
+			up_read(&esw->mode_lock);
+			return false;
+		}
 		return true;
+	}
 
 	return false;
 }
@@ -2312,7 +2308,8 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw)
 	if (down_write_trylock(&esw->mode_lock) == 0)
 		return -EINVAL;
 
-	if (atomic64_read(&esw->user_count) > 0) {
+	if (esw->eswitch_operation_in_progress ||
+	    atomic64_read(&esw->user_count) > 0) {
 		up_write(&esw->mode_lock);
 		return -EBUSY;
 	}
@@ -2320,6 +2317,18 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw)
 	return esw->mode;
 }
 
+int mlx5_esw_lock(struct mlx5_eswitch *esw)
+{
+	down_write(&esw->mode_lock);
+
+	if (esw->eswitch_operation_in_progress) {
+		up_write(&esw->mode_lock);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
 /**
  * mlx5_esw_unlock() - Release write lock on esw mode lock
  * @esw: eswitch device.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 37ab66e7b403f1..b4eb17141edf3e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -383,6 +383,7 @@ struct mlx5_eswitch {
 	struct xarray paired;
 	struct mlx5_devcom_comp_dev *devcom;
 	u16 enabled_ipsec_vf_count;
+	bool eswitch_operation_in_progress;
 };
 
 void esw_offloads_disable(struct mlx5_eswitch *esw);
@@ -525,7 +526,8 @@ struct mlx5_esw_flow_attr {
 	u8	total_vlan;
 	struct {
 		u32 flags;
-		struct mlx5_eswitch_rep *rep;
+		bool vport_valid;
+		u16 vport;
 		struct mlx5_pkt_reformat *pkt_reformat;
 		struct mlx5_core_dev *mdev;
 		struct mlx5_termtbl_handle *termtbl;
@@ -827,6 +829,7 @@ void mlx5_esw_release(struct mlx5_core_dev *dev);
 void mlx5_esw_get(struct mlx5_core_dev *dev);
 void mlx5_esw_put(struct mlx5_core_dev *dev);
 int mlx5_esw_try_lock(struct mlx5_eswitch *esw);
+int mlx5_esw_lock(struct mlx5_eswitch *esw);
 void mlx5_esw_unlock(struct mlx5_eswitch *esw);
 
 void esw_vport_change_handle_locked(struct mlx5_vport *vport);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index b296ac52a43974..b0455134c98eff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -287,10 +287,9 @@ static void esw_put_dest_tables_loop(struct mlx5_eswitch *esw, struct mlx5_flow_
 	for (i = from; i < to; i++)
 		if (esw_attr->dests[i].flags & MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE)
 			mlx5_chains_put_table(chains, 0, 1, 0);
-		else if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport,
+		else if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].vport,
 						     esw_attr->dests[i].mdev))
-			mlx5_esw_indir_table_put(esw, esw_attr->dests[i].rep->vport,
-						 false);
+			mlx5_esw_indir_table_put(esw, esw_attr->dests[i].vport, false);
 }
 
 static bool
@@ -358,8 +357,8 @@ esw_is_indir_table(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr)
 	 * this criteria.
 	 */
 	for (i = esw_attr->split_count; i < esw_attr->out_count; i++) {
-		if (esw_attr->dests[i].rep &&
-		    mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport,
+		if (esw_attr->dests[i].vport_valid &&
+		    mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].vport,
 						esw_attr->dests[i].mdev)) {
 			result = true;
 		} else {
@@ -388,7 +387,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest,
 		dest[*i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 
 		dest[*i].ft = mlx5_esw_indir_table_get(esw, attr,
-						       esw_attr->dests[j].rep->vport, false);
+						       esw_attr->dests[j].vport, false);
 		if (IS_ERR(dest[*i].ft)) {
 			err = PTR_ERR(dest[*i].ft);
 			goto err_indir_tbl_get;
@@ -432,11 +431,11 @@ static bool esw_setup_uplink_fwd_ipsec_needed(struct mlx5_eswitch *esw,
 					      int attr_idx)
 {
 	if (esw->offloads.ft_ipsec_tx_pol &&
-	    esw_attr->dests[attr_idx].rep &&
-	    esw_attr->dests[attr_idx].rep->vport == MLX5_VPORT_UPLINK &&
+	    esw_attr->dests[attr_idx].vport_valid &&
+	    esw_attr->dests[attr_idx].vport == MLX5_VPORT_UPLINK &&
 	    /* To be aligned with software, encryption is needed only for tunnel device */
 	    (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP_VALID) &&
-	    esw_attr->dests[attr_idx].rep != esw_attr->in_rep &&
+	    esw_attr->dests[attr_idx].vport != esw_attr->in_rep->vport &&
 	    esw_same_vhca_id(esw_attr->dests[attr_idx].mdev, esw->dev))
 		return true;
 
@@ -469,7 +468,7 @@ esw_setup_dest_fwd_vport(struct mlx5_flow_destination *dest, struct mlx5_flow_ac
 			 int attr_idx, int dest_idx, bool pkt_reformat)
 {
 	dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-	dest[dest_idx].vport.num = esw_attr->dests[attr_idx].rep->vport;
+	dest[dest_idx].vport.num = esw_attr->dests[attr_idx].vport;
 	if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) {
 		dest[dest_idx].vport.vhca_id =
 			MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id);
@@ -984,7 +983,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw,
 	dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
-	if (rep->vport == MLX5_VPORT_UPLINK && on_esw->offloads.ft_ipsec_tx_pol) {
+	if (rep->vport == MLX5_VPORT_UPLINK &&
+	    on_esw == from_esw && on_esw->offloads.ft_ipsec_tx_pol) {
 		dest.ft = on_esw->offloads.ft_ipsec_tx_pol;
 		flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL;
 		dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
@@ -1176,9 +1176,9 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	struct mlx5_flow_handle *flow;
 	struct mlx5_flow_spec *spec;
 	struct mlx5_vport *vport;
+	int err, pfindex;
 	unsigned long i;
 	void *misc;
-	int err;
 
 	if (!MLX5_VPORT_MANAGER(esw->dev) && !mlx5_core_is_ecpf_esw_manager(esw->dev))
 		return 0;
@@ -1254,7 +1254,15 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 			flows[vport->index] = flow;
 		}
 	}
-	esw->fdb_table.offloads.peer_miss_rules[mlx5_get_dev_index(peer_dev)] = flows;
+
+	pfindex = mlx5_get_dev_index(peer_dev);
+	if (pfindex >= MLX5_MAX_PORTS) {
+		esw_warn(esw->dev, "Peer dev index(%d) is over the max num defined(%d)\n",
+			 pfindex, MLX5_MAX_PORTS);
+		err = -EINVAL;
+		goto add_ec_vf_flow_err;
+	}
+	esw->fdb_table.offloads.peer_miss_rules[pfindex] = flows;
 
 	kvfree(spec);
 	return 0;
@@ -3652,14 +3660,18 @@ static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode)
 
 static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink)
 {
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	struct net *devl_net, *netdev_net;
-	struct mlx5_eswitch *esw;
-
-	esw = mlx5_devlink_eswitch_nocheck_get(devlink);
-	netdev_net = dev_net(esw->dev->mlx5e_res.uplink_netdev);
-	devl_net = devlink_net(devlink);
+	bool ret = false;
 
-	return net_eq(devl_net, netdev_net);
+	mutex_lock(&dev->mlx5e_res.uplink_netdev_lock);
+	if (dev->mlx5e_res.uplink_netdev) {
+		netdev_net = dev_net(dev->mlx5e_res.uplink_netdev);
+		devl_net = devlink_net(devlink);
+		ret = net_eq(devl_net, netdev_net);
+	}
+	mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock);
+	return ret;
 }
 
 int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev)
@@ -3732,13 +3744,16 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 		goto unlock;
 	}
 
+	esw->eswitch_operation_in_progress = true;
+	up_write(&esw->mode_lock);
+
 	mlx5_eswitch_disable_locked(esw);
 	if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) {
 		if (mlx5_devlink_trap_get_num_active(esw->dev)) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Can't change mode while devlink traps are active");
 			err = -EOPNOTSUPP;
-			goto unlock;
+			goto skip;
 		}
 		err = esw_offloads_start(esw, extack);
 	} else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) {
@@ -3748,6 +3763,9 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 		err = -EINVAL;
 	}
 
+skip:
+	down_write(&esw->mode_lock);
+	esw->eswitch_operation_in_progress = false;
 unlock:
 	mlx5_esw_unlock(esw);
 enable_lag:
@@ -3758,16 +3776,12 @@ enable_lag:
 int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
 {
 	struct mlx5_eswitch *esw;
-	int err;
 
 	esw = mlx5_devlink_eswitch_get(devlink);
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_read(&esw->mode_lock);
-	err = esw_mode_to_devlink(esw->mode, mode);
-	up_read(&esw->mode_lock);
-	return err;
+	return esw_mode_to_devlink(esw->mode, mode);
 }
 
 static int mlx5_esw_vports_inline_set(struct mlx5_eswitch *esw, u8 mlx5_mode,
@@ -3861,11 +3875,15 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 	if (err)
 		goto out;
 
+	esw->eswitch_operation_in_progress = true;
+	up_write(&esw->mode_lock);
+
 	err = mlx5_esw_vports_inline_set(esw, mlx5_mode, extack);
-	if (err)
-		goto out;
+	if (!err)
+		esw->offloads.inline_mode = mlx5_mode;
 
-	esw->offloads.inline_mode = mlx5_mode;
+	down_write(&esw->mode_lock);
+	esw->eswitch_operation_in_progress = false;
 	up_write(&esw->mode_lock);
 	return 0;
 
@@ -3877,16 +3895,12 @@ out:
 int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
 {
 	struct mlx5_eswitch *esw;
-	int err;
 
 	esw = mlx5_devlink_eswitch_get(devlink);
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_read(&esw->mode_lock);
-	err = esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
-	up_read(&esw->mode_lock);
-	return err;
+	return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
 }
 
 bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev)
@@ -3968,6 +3982,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
 		goto unlock;
 	}
 
+	esw->eswitch_operation_in_progress = true;
+	up_write(&esw->mode_lock);
+
 	esw_destroy_offloads_fdb_tables(esw);
 
 	esw->offloads.encap = encap;
@@ -3981,6 +3998,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
 		(void)esw_create_offloads_fdb_tables(esw);
 	}
 
+	down_write(&esw->mode_lock);
+	esw->eswitch_operation_in_progress = false;
+
 unlock:
 	up_write(&esw->mode_lock);
 	return err;
@@ -3995,9 +4015,7 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink,
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_read(&esw->mode_lock);
 	*encap = esw->offloads.encap;
-	up_read(&esw->mode_lock);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
index edd91025831441..40bdc677f051dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
@@ -233,8 +233,8 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw,
 
 	/* hairpin */
 	for (i = esw_attr->split_count; i < esw_attr->out_count; i++)
-		if (!esw_attr->dest_int_port && esw_attr->dests[i].rep &&
-		    esw_attr->dests[i].rep->vport == MLX5_VPORT_UPLINK)
+		if (!esw_attr->dest_int_port && esw_attr->dests[i].vport_valid &&
+		    esw_attr->dests[i].vport == MLX5_VPORT_UPLINK)
 			return true;
 
 	return false;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index b568988e92e3e9..c4e19d627da214 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -325,6 +325,29 @@ static void mlx5_fw_live_patch_event(struct work_struct *work)
 		mlx5_core_err(dev, "Failed to reload FW tracer\n");
 }
 
+#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
+static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev)
+{
+	struct pci_dev *bridge = dev->pdev->bus->self;
+	u16 reg16;
+	int err;
+
+	if (!bridge)
+		return -EOPNOTSUPP;
+
+	err = pcie_capability_read_word(bridge, PCI_EXP_SLTCTL, &reg16);
+	if (err)
+		return err;
+
+	if ((reg16 & PCI_EXP_SLTCTL_HPIE) && (reg16 & PCI_EXP_SLTCTL_DLLSCE)) {
+		mlx5_core_warn(dev, "FW reset is not supported as HotPlug is enabled\n");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+#endif
+
 static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id)
 {
 	struct pci_bus *bridge_bus = dev->pdev->bus;
@@ -357,6 +380,12 @@ static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev)
 		return false;
 	}
 
+#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
+	err = mlx5_check_hotplug_interrupt(dev);
+	if (err)
+		return false;
+#endif
+
 	err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id);
 	if (err)
 		return false;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
index 047d5fed5f89e6..612e666ec26356 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
@@ -168,45 +168,3 @@ void mlx5_irq_affinity_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *i
 		if (pool->irqs_per_cpu)
 			cpu_put(pool, cpu);
 }
-
-/**
- * mlx5_irq_affinity_irq_request_auto - request one IRQ for mlx5 device.
- * @dev: mlx5 device that is requesting the IRQ.
- * @used_cpus: cpumask of bounded cpus by the device
- * @vecidx: vector index to request an IRQ for.
- *
- * Each IRQ is bounded to at most 1 CPU.
- * This function is requesting an IRQ according to the default assignment.
- * The default assignment policy is:
- * - request the least loaded IRQ which is not bound to any
- *   CPU of the previous IRQs requested.
- *
- * On success, this function updates used_cpus mask and returns an irq pointer.
- * In case of an error, an appropriate error pointer is returned.
- */
-struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev,
-						    struct cpumask *used_cpus, u16 vecidx)
-{
-	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
-	struct irq_affinity_desc af_desc = {};
-	struct mlx5_irq *irq;
-
-	if (!mlx5_irq_pool_is_sf_pool(pool))
-		return ERR_PTR(-ENOENT);
-
-	af_desc.is_managed = 1;
-	cpumask_copy(&af_desc.mask, cpu_online_mask);
-	cpumask_andnot(&af_desc.mask, &af_desc.mask, used_cpus);
-	irq = mlx5_irq_affinity_request(pool, &af_desc);
-
-	if (IS_ERR(irq))
-		return irq;
-
-	cpumask_or(used_cpus, used_cpus, mlx5_irq_get_affinity_mask(irq));
-	mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n",
-		      pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)),
-		      cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)),
-		      mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ);
-
-	return irq;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index aa29f09e835642..0c83ef174275a7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -384,7 +384,12 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 
 static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta)
 {
-	return mlx5_ptp_adjtime(ptp, delta);
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev;
+
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
+
+	return mlx5_ptp_adjtime_real_time(mdev, delta);
 }
 
 static int mlx5_ptp_freq_adj_real_time(struct mlx5_core_dev *mdev, long scaled_ppm)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 653648216730ac..4dcf995cb1a204 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -28,7 +28,7 @@
 struct mlx5_irq {
 	struct atomic_notifier_head nh;
 	cpumask_var_t mask;
-	char name[MLX5_MAX_IRQ_NAME];
+	char name[MLX5_MAX_IRQ_FORMATTED_NAME];
 	struct mlx5_irq_pool *pool;
 	int refcount;
 	struct msi_map map;
@@ -292,8 +292,8 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i,
 	else
 		irq_sf_set_name(pool, name, i);
 	ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh);
-	snprintf(irq->name, MLX5_MAX_IRQ_NAME,
-		 "%s@pci:%s", name, pci_name(dev->pdev));
+	snprintf(irq->name, MLX5_MAX_IRQ_FORMATTED_NAME,
+		 MLX5_IRQ_NAME_FORMAT_STR, name, pci_name(dev->pdev));
 	err = request_irq(irq->map.virq, irq_int_handler, 0, irq->name,
 			  &irq->nh);
 	if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
index d3a77a0ab8488b..c4d377f8df3089 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
@@ -7,6 +7,9 @@
 #include <linux/mlx5/driver.h>
 
 #define MLX5_MAX_IRQ_NAME (32)
+#define MLX5_IRQ_NAME_FORMAT_STR ("%s@pci:%s")
+#define MLX5_MAX_IRQ_FORMATTED_NAME \
+	(MLX5_MAX_IRQ_NAME + sizeof(MLX5_IRQ_NAME_FORMAT_STR))
 /* max irq_index is 2047, so four chars */
 #define MLX5_MAX_IRQ_IDX_CHARS (4)
 #define MLX5_EQ_REFS_PER_IRQ (2)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index 6ea88a58180472..e3ec559369fa07 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -57,7 +57,8 @@ static const char *dr_action_id_to_str(enum mlx5dr_action_type action_id)
 
 static bool mlx5dr_action_supp_fwd_fdb_multi_ft(struct mlx5_core_dev *dev)
 {
-	return (MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table_limit_regc) ||
+	return (MLX5_CAP_GEN(dev, steering_format_version) < MLX5_STEERING_FORMAT_CONNECTX_6DX ||
+		MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table_limit_regc) ||
 		MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_any_table));
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 4e8527a724f504..6fa06ba2d34653 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -52,7 +52,6 @@ struct dr_qp_init_attr {
 	u32 cqn;
 	u32 pdn;
 	u32 max_send_wr;
-	u32 max_send_sge;
 	struct mlx5_uars_page *uar;
 	u8 isolate_vl_tc:1;
 };
@@ -247,37 +246,6 @@ static int dr_poll_cq(struct mlx5dr_cq *dr_cq, int ne)
 	return err == CQ_POLL_ERR ? err : npolled;
 }
 
-static int dr_qp_get_args_update_send_wqe_size(struct dr_qp_init_attr *attr)
-{
-	return roundup_pow_of_two(sizeof(struct mlx5_wqe_ctrl_seg) +
-				  sizeof(struct mlx5_wqe_flow_update_ctrl_seg) +
-				  sizeof(struct mlx5_wqe_header_modify_argument_update_seg));
-}
-
-/* We calculate for specific RC QP with the required functionality */
-static int dr_qp_calc_rc_send_wqe(struct dr_qp_init_attr *attr)
-{
-	int update_arg_size;
-	int inl_size = 0;
-	int tot_size;
-	int size;
-
-	update_arg_size = dr_qp_get_args_update_send_wqe_size(attr);
-
-	size = sizeof(struct mlx5_wqe_ctrl_seg) +
-	       sizeof(struct mlx5_wqe_raddr_seg);
-	inl_size = size + ALIGN(sizeof(struct mlx5_wqe_inline_seg) +
-				DR_STE_SIZE, 16);
-
-	size += attr->max_send_sge * sizeof(struct mlx5_wqe_data_seg);
-
-	size = max(size, update_arg_size);
-
-	tot_size = max(size, inl_size);
-
-	return ALIGN(tot_size, MLX5_SEND_WQE_BB);
-}
-
 static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 					 struct dr_qp_init_attr *attr)
 {
@@ -285,7 +253,6 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 	u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {};
 	struct mlx5_wq_param wqp;
 	struct mlx5dr_qp *dr_qp;
-	int wqe_size;
 	int inlen;
 	void *qpc;
 	void *in;
@@ -365,15 +332,6 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 	if (err)
 		goto err_in;
 	dr_qp->uar = attr->uar;
-	wqe_size = dr_qp_calc_rc_send_wqe(attr);
-	dr_qp->max_inline_data = min(wqe_size -
-				     (sizeof(struct mlx5_wqe_ctrl_seg) +
-				      sizeof(struct mlx5_wqe_raddr_seg) +
-				      sizeof(struct mlx5_wqe_inline_seg)),
-				     (2 * MLX5_SEND_WQE_BB -
-				      (sizeof(struct mlx5_wqe_ctrl_seg) +
-				       sizeof(struct mlx5_wqe_raddr_seg) +
-				       sizeof(struct mlx5_wqe_inline_seg))));
 
 	return dr_qp;
 
@@ -437,48 +395,8 @@ dr_rdma_handle_flow_access_arg_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl,
 		MLX5_SEND_WQE_DS;
 }
 
-static int dr_set_data_inl_seg(struct mlx5dr_qp *dr_qp,
-			       struct dr_data_seg *data_seg, void *wqe)
-{
-	int inline_header_size = sizeof(struct mlx5_wqe_ctrl_seg) +
-				sizeof(struct mlx5_wqe_raddr_seg) +
-				sizeof(struct mlx5_wqe_inline_seg);
-	struct mlx5_wqe_inline_seg *seg;
-	int left_space;
-	int inl = 0;
-	void *addr;
-	int len;
-	int idx;
-
-	seg = wqe;
-	wqe += sizeof(*seg);
-	addr = (void *)(unsigned long)(data_seg->addr);
-	len  = data_seg->length;
-	inl += len;
-	left_space = MLX5_SEND_WQE_BB - inline_header_size;
-
-	if (likely(len > left_space)) {
-		memcpy(wqe, addr, left_space);
-		len -= left_space;
-		addr += left_space;
-		idx = (dr_qp->sq.pc + 1) & (dr_qp->sq.wqe_cnt - 1);
-		wqe = mlx5_wq_cyc_get_wqe(&dr_qp->wq.sq, idx);
-	}
-
-	memcpy(wqe, addr, len);
-
-	if (likely(inl)) {
-		seg->byte_count = cpu_to_be32(inl | MLX5_INLINE_SEG);
-		return DIV_ROUND_UP(inl + sizeof(seg->byte_count),
-				    MLX5_SEND_WQE_DS);
-	} else {
-		return 0;
-	}
-}
-
 static void
-dr_rdma_handle_icm_write_segments(struct mlx5dr_qp *dr_qp,
-				  struct mlx5_wqe_ctrl_seg *wq_ctrl,
+dr_rdma_handle_icm_write_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl,
 				  u64 remote_addr,
 				  u32 rkey,
 				  struct dr_data_seg *data_seg,
@@ -494,17 +412,15 @@ dr_rdma_handle_icm_write_segments(struct mlx5dr_qp *dr_qp,
 	wq_raddr->reserved = 0;
 
 	wq_dseg = (void *)(wq_raddr + 1);
-	/* WQE ctrl segment + WQE remote addr segment */
-	*size = (sizeof(*wq_ctrl) + sizeof(*wq_raddr)) / MLX5_SEND_WQE_DS;
 
-	if (data_seg->send_flags & IB_SEND_INLINE) {
-		*size += dr_set_data_inl_seg(dr_qp, data_seg, wq_dseg);
-	} else {
-		wq_dseg->byte_count = cpu_to_be32(data_seg->length);
-		wq_dseg->lkey = cpu_to_be32(data_seg->lkey);
-		wq_dseg->addr = cpu_to_be64(data_seg->addr);
-		*size += sizeof(*wq_dseg) / MLX5_SEND_WQE_DS;  /* WQE data segment */
-	}
+	wq_dseg->byte_count = cpu_to_be32(data_seg->length);
+	wq_dseg->lkey = cpu_to_be32(data_seg->lkey);
+	wq_dseg->addr = cpu_to_be64(data_seg->addr);
+
+	*size = (sizeof(*wq_ctrl) +    /* WQE ctrl segment */
+		 sizeof(*wq_dseg) +    /* WQE data segment */
+		 sizeof(*wq_raddr)) /  /* WQE remote addr segment */
+		MLX5_SEND_WQE_DS;
 }
 
 static void dr_set_ctrl_seg(struct mlx5_wqe_ctrl_seg *wq_ctrl,
@@ -535,7 +451,7 @@ static void dr_rdma_segments(struct mlx5dr_qp *dr_qp, u64 remote_addr,
 	switch (opcode) {
 	case MLX5_OPCODE_RDMA_READ:
 	case MLX5_OPCODE_RDMA_WRITE:
-		dr_rdma_handle_icm_write_segments(dr_qp, wq_ctrl, remote_addr,
+		dr_rdma_handle_icm_write_segments(wq_ctrl, remote_addr,
 						  rkey, data_seg, &size);
 		break;
 	case MLX5_OPCODE_FLOW_TBL_ACCESS:
@@ -656,7 +572,7 @@ static void dr_fill_write_args_segs(struct mlx5dr_send_ring *send_ring,
 	if (send_ring->pending_wqe % send_ring->signal_th == 0)
 		send_info->write.send_flags |= IB_SEND_SIGNALED;
 	else
-		send_info->write.send_flags &= ~IB_SEND_SIGNALED;
+		send_info->write.send_flags = 0;
 }
 
 static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn,
@@ -680,13 +596,9 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn,
 	}
 
 	send_ring->pending_wqe++;
-	if (!send_info->write.lkey)
-		send_info->write.send_flags |= IB_SEND_INLINE;
 
 	if (send_ring->pending_wqe % send_ring->signal_th == 0)
 		send_info->write.send_flags |= IB_SEND_SIGNALED;
-	else
-		send_info->write.send_flags &= ~IB_SEND_SIGNALED;
 
 	send_ring->pending_wqe++;
 	send_info->read.length = send_info->write.length;
@@ -696,9 +608,9 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn,
 	send_info->read.lkey = send_ring->sync_mr->mkey;
 
 	if (send_ring->pending_wqe % send_ring->signal_th == 0)
-		send_info->read.send_flags |= IB_SEND_SIGNALED;
+		send_info->read.send_flags = IB_SEND_SIGNALED;
 	else
-		send_info->read.send_flags &= ~IB_SEND_SIGNALED;
+		send_info->read.send_flags = 0;
 }
 
 static void dr_fill_data_segs(struct mlx5dr_domain *dmn,
@@ -1345,7 +1257,6 @@ int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn)
 	dmn->send_ring->cq->qp = dmn->send_ring->qp;
 
 	dmn->info.max_send_wr = QUEUE_SIZE;
-	init_attr.max_send_sge = 1;
 	dmn->info.max_inline_size = min(dmn->send_ring->qp->max_inline_data,
 					DR_STE_SIZE);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 5a31fb47ffa58b..21753f32786850 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -277,7 +277,7 @@ int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev,
 		req_list_size = max_list_size;
 	}
 
-	out_sz = MLX5_ST_SZ_BYTES(query_nic_vport_context_in) +
+	out_sz = MLX5_ST_SZ_BYTES(query_nic_vport_context_out) +
 			req_list_size * MLX5_ST_SZ_BYTES(mac_address_layout);
 
 	out = kvzalloc(out_sz, GFP_KERNEL);
diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h
index fecd43754cead1..e5ec0a363aff84 100644
--- a/drivers/net/ethernet/micrel/ks8851.h
+++ b/drivers/net/ethernet/micrel/ks8851.h
@@ -350,6 +350,8 @@ union ks8851_tx_hdr {
  * @rxd: Space for receiving SPI data, in DMA-able space.
  * @txd: Space for transmitting SPI data, in DMA-able space.
  * @msg_enable: The message flags controlling driver output (see ethtool).
+ * @tx_space: Free space in the hardware TX buffer (cached copy of KS_TXMIR).
+ * @queued_len: Space required in hardware TX buffer for queued packets in txq.
  * @fid: Incrementing frame id tag.
  * @rc_ier: Cached copy of KS_IER.
  * @rc_ccr: Cached copy of KS_CCR.
@@ -399,6 +401,7 @@ struct ks8851_net {
 	struct work_struct	rxctrl_work;
 
 	struct sk_buff_head	txq;
+	unsigned int		queued_len;
 
 	struct eeprom_93cx6	eeprom;
 	struct regulator	*vdd_reg;
diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c
index cfbc900d4aeb9e..0bf13b38b8f5b9 100644
--- a/drivers/net/ethernet/micrel/ks8851_common.c
+++ b/drivers/net/ethernet/micrel/ks8851_common.c
@@ -362,16 +362,18 @@ static irqreturn_t ks8851_irq(int irq, void *_ks)
 		handled |= IRQ_RXPSI;
 
 	if (status & IRQ_TXI) {
-		handled |= IRQ_TXI;
+		unsigned short tx_space = ks8851_rdreg16(ks, KS_TXMIR);
 
-		/* no lock here, tx queue should have been stopped */
+		netif_dbg(ks, intr, ks->netdev,
+			  "%s: txspace %d\n", __func__, tx_space);
 
-		/* update our idea of how much tx space is available to the
-		 * system */
-		ks->tx_space = ks8851_rdreg16(ks, KS_TXMIR);
+		spin_lock(&ks->statelock);
+		ks->tx_space = tx_space;
+		if (netif_queue_stopped(ks->netdev))
+			netif_wake_queue(ks->netdev);
+		spin_unlock(&ks->statelock);
 
-		netif_dbg(ks, intr, ks->netdev,
-			  "%s: txspace %d\n", __func__, ks->tx_space);
+		handled |= IRQ_TXI;
 	}
 
 	if (status & IRQ_RXI)
@@ -414,9 +416,6 @@ static irqreturn_t ks8851_irq(int irq, void *_ks)
 	if (status & IRQ_LCI)
 		mii_check_link(&ks->mii);
 
-	if (status & IRQ_TXI)
-		netif_wake_queue(ks->netdev);
-
 	return IRQ_HANDLED;
 }
 
@@ -500,6 +499,7 @@ static int ks8851_net_open(struct net_device *dev)
 	ks8851_wrreg16(ks, KS_ISR, ks->rc_ier);
 	ks8851_wrreg16(ks, KS_IER, ks->rc_ier);
 
+	ks->queued_len = 0;
 	netif_start_queue(ks->netdev);
 
 	netif_dbg(ks, ifup, ks->netdev, "network device up\n");
diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c
index 70bc7253454f6b..88e26c120b4836 100644
--- a/drivers/net/ethernet/micrel/ks8851_spi.c
+++ b/drivers/net/ethernet/micrel/ks8851_spi.c
@@ -287,6 +287,18 @@ static void ks8851_wrfifo_spi(struct ks8851_net *ks, struct sk_buff *txp,
 }
 
 /**
+ * calc_txlen - calculate size of message to send packet
+ * @len: Length of data
+ *
+ * Returns the size of the TXFIFO message needed to send
+ * this packet.
+ */
+static unsigned int calc_txlen(unsigned int len)
+{
+	return ALIGN(len + 4, 4);
+}
+
+/**
  * ks8851_rx_skb_spi - receive skbuff
  * @ks: The device state
  * @skb: The skbuff
@@ -305,7 +317,9 @@ static void ks8851_rx_skb_spi(struct ks8851_net *ks, struct sk_buff *skb)
  */
 static void ks8851_tx_work(struct work_struct *work)
 {
+	unsigned int dequeued_len = 0;
 	struct ks8851_net_spi *kss;
+	unsigned short tx_space;
 	struct ks8851_net *ks;
 	unsigned long flags;
 	struct sk_buff *txb;
@@ -322,6 +336,8 @@ static void ks8851_tx_work(struct work_struct *work)
 		last = skb_queue_empty(&ks->txq);
 
 		if (txb) {
+			dequeued_len += calc_txlen(txb->len);
+
 			ks8851_wrreg16_spi(ks, KS_RXQCR,
 					   ks->rc_rxqcr | RXQCR_SDA);
 			ks8851_wrfifo_spi(ks, txb, last);
@@ -332,6 +348,13 @@ static void ks8851_tx_work(struct work_struct *work)
 		}
 	}
 
+	tx_space = ks8851_rdreg16_spi(ks, KS_TXMIR);
+
+	spin_lock(&ks->statelock);
+	ks->queued_len -= dequeued_len;
+	ks->tx_space = tx_space;
+	spin_unlock(&ks->statelock);
+
 	ks8851_unlock_spi(ks, &flags);
 }
 
@@ -347,18 +370,6 @@ static void ks8851_flush_tx_work_spi(struct ks8851_net *ks)
 }
 
 /**
- * calc_txlen - calculate size of message to send packet
- * @len: Length of data
- *
- * Returns the size of the TXFIFO message needed to send
- * this packet.
- */
-static unsigned int calc_txlen(unsigned int len)
-{
-	return ALIGN(len + 4, 4);
-}
-
-/**
  * ks8851_start_xmit_spi - transmit packet using SPI
  * @skb: The buffer to transmit
  * @dev: The device used to transmit the packet.
@@ -386,16 +397,17 @@ static netdev_tx_t ks8851_start_xmit_spi(struct sk_buff *skb,
 
 	spin_lock(&ks->statelock);
 
-	if (needed > ks->tx_space) {
+	if (ks->queued_len + needed > ks->tx_space) {
 		netif_stop_queue(dev);
 		ret = NETDEV_TX_BUSY;
 	} else {
-		ks->tx_space -= needed;
+		ks->queued_len += needed;
 		skb_queue_tail(&ks->txq, skb);
 	}
 
 	spin_unlock(&ks->statelock);
-	schedule_work(&kss->tx_work);
+	if (ret == NETDEV_TX_OK)
+		schedule_work(&kss->tx_work);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/microsoft/Kconfig b/drivers/net/ethernet/microsoft/Kconfig
index 090e6b9832431c..01eb7445ead951 100644
--- a/drivers/net/ethernet/microsoft/Kconfig
+++ b/drivers/net/ethernet/microsoft/Kconfig
@@ -20,6 +20,7 @@ config MICROSOFT_MANA
 	depends on PCI_MSI && X86_64
 	depends on PCI_HYPERV
 	select AUXILIARY_BUS
+	select PAGE_POOL
 	help
 	  This driver supports Microsoft Azure Network Adapter (MANA).
 	  So far, the driver is only supported on X86_64.
diff --git a/drivers/net/ethernet/mscc/ocelot_stats.c b/drivers/net/ethernet/mscc/ocelot_stats.c
index 5c55197c7327df..c018783757fb2f 100644
--- a/drivers/net/ethernet/mscc/ocelot_stats.c
+++ b/drivers/net/ethernet/mscc/ocelot_stats.c
@@ -582,10 +582,10 @@ static void ocelot_port_rmon_stats_cb(struct ocelot *ocelot, int port, void *pri
 	rmon_stats->hist_tx[0] = s[OCELOT_STAT_TX_64];
 	rmon_stats->hist_tx[1] = s[OCELOT_STAT_TX_65_127];
 	rmon_stats->hist_tx[2] = s[OCELOT_STAT_TX_128_255];
-	rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_128_255];
-	rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_256_511];
-	rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_512_1023];
-	rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_1024_1526];
+	rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_256_511];
+	rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_512_1023];
+	rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_1024_1526];
+	rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_1527_MAX];
 }
 
 static void ocelot_port_pmac_rmon_stats_cb(struct ocelot *ocelot, int port,
@@ -610,10 +610,10 @@ static void ocelot_port_pmac_rmon_stats_cb(struct ocelot *ocelot, int port,
 	rmon_stats->hist_tx[0] = s[OCELOT_STAT_TX_PMAC_64];
 	rmon_stats->hist_tx[1] = s[OCELOT_STAT_TX_PMAC_65_127];
 	rmon_stats->hist_tx[2] = s[OCELOT_STAT_TX_PMAC_128_255];
-	rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_PMAC_128_255];
-	rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_PMAC_256_511];
-	rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_PMAC_512_1023];
-	rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_PMAC_1024_1526];
+	rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_PMAC_256_511];
+	rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_PMAC_512_1023];
+	rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_PMAC_1024_1526];
+	rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_PMAC_1527_MAX];
 }
 
 void ocelot_port_get_rmon_stats(struct ocelot *ocelot, int port,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index 060a77f2265d9a..e522845c7c2116 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -160,6 +160,18 @@ struct nfp_tun_mac_addr_offload {
 	u8 addr[ETH_ALEN];
 };
 
+/**
+ * struct nfp_neigh_update_work - update neighbour information to nfp
+ * @work:	Work queue for writing neigh to the nfp
+ * @n:		neighbour entry
+ * @app:	Back pointer to app
+ */
+struct nfp_neigh_update_work {
+	struct work_struct work;
+	struct neighbour *n;
+	struct nfp_app *app;
+};
+
 enum nfp_flower_mac_offload_cmd {
 	NFP_TUNNEL_MAC_OFFLOAD_ADD =		0,
 	NFP_TUNNEL_MAC_OFFLOAD_DEL =		1,
@@ -607,38 +619,30 @@ err:
 	nfp_flower_cmsg_warn(app, "Neighbour configuration failed.\n");
 }
 
-static int
-nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event,
-			    void *ptr)
+static void
+nfp_tun_release_neigh_update_work(struct nfp_neigh_update_work *update_work)
 {
-	struct nfp_flower_priv *app_priv;
-	struct netevent_redirect *redir;
-	struct neighbour *n;
+	neigh_release(update_work->n);
+	kfree(update_work);
+}
+
+static void nfp_tun_neigh_update(struct work_struct *work)
+{
+	struct nfp_neigh_update_work *update_work;
 	struct nfp_app *app;
+	struct neighbour *n;
 	bool neigh_invalid;
 	int err;
 
-	switch (event) {
-	case NETEVENT_REDIRECT:
-		redir = (struct netevent_redirect *)ptr;
-		n = redir->neigh;
-		break;
-	case NETEVENT_NEIGH_UPDATE:
-		n = (struct neighbour *)ptr;
-		break;
-	default:
-		return NOTIFY_DONE;
-	}
-
-	neigh_invalid = !(n->nud_state & NUD_VALID) || n->dead;
-
-	app_priv = container_of(nb, struct nfp_flower_priv, tun.neigh_nb);
-	app = app_priv->app;
+	update_work = container_of(work, struct nfp_neigh_update_work, work);
+	app = update_work->app;
+	n = update_work->n;
 
 	if (!nfp_flower_get_port_id_from_netdev(app, n->dev))
-		return NOTIFY_DONE;
+		goto out;
 
 #if IS_ENABLED(CONFIG_INET)
+	neigh_invalid = !(n->nud_state & NUD_VALID) || n->dead;
 	if (n->tbl->family == AF_INET6) {
 #if IS_ENABLED(CONFIG_IPV6)
 		struct flowi6 flow6 = {};
@@ -655,13 +659,11 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event,
 			dst = ip6_dst_lookup_flow(dev_net(n->dev), NULL,
 						  &flow6, NULL);
 			if (IS_ERR(dst))
-				return NOTIFY_DONE;
+				goto out;
 
 			dst_release(dst);
 		}
 		nfp_tun_write_neigh(n->dev, app, &flow6, n, true, false);
-#else
-		return NOTIFY_DONE;
 #endif /* CONFIG_IPV6 */
 	} else {
 		struct flowi4 flow4 = {};
@@ -678,17 +680,71 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event,
 			rt = ip_route_output_key(dev_net(n->dev), &flow4);
 			err = PTR_ERR_OR_ZERO(rt);
 			if (err)
-				return NOTIFY_DONE;
+				goto out;
 
 			ip_rt_put(rt);
 		}
 		nfp_tun_write_neigh(n->dev, app, &flow4, n, false, false);
 	}
-#else
-	return NOTIFY_DONE;
 #endif /* CONFIG_INET */
+out:
+	nfp_tun_release_neigh_update_work(update_work);
+}
 
-	return NOTIFY_OK;
+static struct nfp_neigh_update_work *
+nfp_tun_alloc_neigh_update_work(struct nfp_app *app, struct neighbour *n)
+{
+	struct nfp_neigh_update_work *update_work;
+
+	update_work = kzalloc(sizeof(*update_work), GFP_ATOMIC);
+	if (!update_work)
+		return NULL;
+
+	INIT_WORK(&update_work->work, nfp_tun_neigh_update);
+	neigh_hold(n);
+	update_work->n = n;
+	update_work->app = app;
+
+	return update_work;
+}
+
+static int
+nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event,
+			    void *ptr)
+{
+	struct nfp_neigh_update_work *update_work;
+	struct nfp_flower_priv *app_priv;
+	struct netevent_redirect *redir;
+	struct neighbour *n;
+	struct nfp_app *app;
+
+	switch (event) {
+	case NETEVENT_REDIRECT:
+		redir = (struct netevent_redirect *)ptr;
+		n = redir->neigh;
+		break;
+	case NETEVENT_NEIGH_UPDATE:
+		n = (struct neighbour *)ptr;
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+#if IS_ENABLED(CONFIG_IPV6)
+	if (n->tbl != ipv6_stub->nd_tbl && n->tbl != &arp_tbl)
+#else
+	if (n->tbl != &arp_tbl)
+#endif
+		return NOTIFY_DONE;
+
+	app_priv = container_of(nb, struct nfp_flower_priv, tun.neigh_nb);
+	app = app_priv->app;
+	update_work = nfp_tun_alloc_neigh_update_work(app, n);
+	if (!update_work)
+		return NOTIFY_DONE;
+
+	queue_work(system_highpri_wq, &update_work->work);
+
+	return NOTIFY_DONE;
 }
 
 void nfp_tunnel_request_route_v4(struct nfp_app *app, struct sk_buff *skb)
@@ -706,6 +762,7 @@ void nfp_tunnel_request_route_v4(struct nfp_app *app, struct sk_buff *skb)
 	netdev = nfp_app_dev_get(app, be32_to_cpu(payload->ingress_port), NULL);
 	if (!netdev)
 		goto fail_rcu_unlock;
+	dev_hold(netdev);
 
 	flow.daddr = payload->ipv4_addr;
 	flow.flowi4_proto = IPPROTO_UDP;
@@ -725,13 +782,16 @@ void nfp_tunnel_request_route_v4(struct nfp_app *app, struct sk_buff *skb)
 	ip_rt_put(rt);
 	if (!n)
 		goto fail_rcu_unlock;
+	rcu_read_unlock();
+
 	nfp_tun_write_neigh(n->dev, app, &flow, n, false, true);
 	neigh_release(n);
-	rcu_read_unlock();
+	dev_put(netdev);
 	return;
 
 fail_rcu_unlock:
 	rcu_read_unlock();
+	dev_put(netdev);
 	nfp_flower_cmsg_warn(app, "Requested route not found.\n");
 }
 
@@ -749,6 +809,7 @@ void nfp_tunnel_request_route_v6(struct nfp_app *app, struct sk_buff *skb)
 	netdev = nfp_app_dev_get(app, be32_to_cpu(payload->ingress_port), NULL);
 	if (!netdev)
 		goto fail_rcu_unlock;
+	dev_hold(netdev);
 
 	flow.daddr = payload->ipv6_addr;
 	flow.flowi6_proto = IPPROTO_UDP;
@@ -766,14 +827,16 @@ void nfp_tunnel_request_route_v6(struct nfp_app *app, struct sk_buff *skb)
 	dst_release(dst);
 	if (!n)
 		goto fail_rcu_unlock;
+	rcu_read_unlock();
 
 	nfp_tun_write_neigh(n->dev, app, &flow, n, true, true);
 	neigh_release(n);
-	rcu_read_unlock();
+	dev_put(netdev);
 	return;
 
 fail_rcu_unlock:
 	rcu_read_unlock();
+	dev_put(netdev);
 	nfp_flower_cmsg_warn(app, "Requested IPv6 route not found.\n");
 }
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
index 1dbc3cb50b1d90..9b546304007529 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@@ -223,7 +223,7 @@ struct ionic_desc_info {
 	void *cb_arg;
 };
 
-#define IONIC_QUEUE_NAME_MAX_SZ		32
+#define IONIC_QUEUE_NAME_MAX_SZ		16
 
 struct ionic_queue {
 	struct device *dev;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index edc14730ce88b5..bad919343180e9 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -49,24 +49,24 @@ static void ionic_lif_queue_identify(struct ionic_lif *lif);
 static void ionic_dim_work(struct work_struct *work)
 {
 	struct dim *dim = container_of(work, struct dim, work);
+	struct ionic_intr_info *intr;
 	struct dim_cq_moder cur_moder;
 	struct ionic_qcq *qcq;
+	struct ionic_lif *lif;
 	u32 new_coal;
 
 	cur_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
 	qcq = container_of(dim, struct ionic_qcq, dim);
-	new_coal = ionic_coal_usec_to_hw(qcq->q.lif->ionic, cur_moder.usec);
+	lif = qcq->q.lif;
+	new_coal = ionic_coal_usec_to_hw(lif->ionic, cur_moder.usec);
 	new_coal = new_coal ? new_coal : 1;
 
-	if (qcq->intr.dim_coal_hw != new_coal) {
-		unsigned int qi = qcq->cq.bound_q->index;
-		struct ionic_lif *lif = qcq->q.lif;
-
-		qcq->intr.dim_coal_hw = new_coal;
+	intr = &qcq->intr;
+	if (intr->dim_coal_hw != new_coal) {
+		intr->dim_coal_hw = new_coal;
 
 		ionic_intr_coal_init(lif->ionic->idev.intr_ctrl,
-				     lif->rxqcqs[qi]->intr.index,
-				     qcq->intr.dim_coal_hw);
+				     intr->index, intr->dim_coal_hw);
 	}
 
 	dim->state = DIM_START_MEASURE;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 65e20693c549e1..33f4f58ee51c68 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -933,6 +933,7 @@ static void qed_ilt_shadow_free(struct qed_hwfn *p_hwfn)
 		p_dma->virt_addr = NULL;
 	}
 	kfree(p_mngr->ilt_shadow);
+	p_mngr->ilt_shadow = NULL;
 }
 
 static int qed_ilt_blk_alloc(struct qed_hwfn *p_hwfn,
diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c
index 6f2fa2a42770aa..1822f2ad8f0ddf 100644
--- a/drivers/net/ethernet/qualcomm/qca_debug.c
+++ b/drivers/net/ethernet/qualcomm/qca_debug.c
@@ -30,6 +30,8 @@
 
 #define QCASPI_MAX_REGS 0x20
 
+#define QCASPI_RX_MAX_FRAMES 4
+
 static const u16 qcaspi_spi_regs[] = {
 	SPI_REG_BFR_SIZE,
 	SPI_REG_WRBUF_SPC_AVA,
@@ -252,9 +254,9 @@ qcaspi_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ring,
 {
 	struct qcaspi *qca = netdev_priv(dev);
 
-	ring->rx_max_pending = 4;
+	ring->rx_max_pending = QCASPI_RX_MAX_FRAMES;
 	ring->tx_max_pending = TX_RING_MAX_LEN;
-	ring->rx_pending = 4;
+	ring->rx_pending = QCASPI_RX_MAX_FRAMES;
 	ring->tx_pending = qca->txr.count;
 }
 
@@ -263,22 +265,21 @@ qcaspi_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ring,
 		     struct kernel_ethtool_ringparam *kernel_ring,
 		     struct netlink_ext_ack *extack)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
 	struct qcaspi *qca = netdev_priv(dev);
 
-	if ((ring->rx_pending) ||
+	if (ring->rx_pending != QCASPI_RX_MAX_FRAMES ||
 	    (ring->rx_mini_pending) ||
 	    (ring->rx_jumbo_pending))
 		return -EINVAL;
 
-	if (netif_running(dev))
-		ops->ndo_stop(dev);
+	if (qca->spi_thread)
+		kthread_park(qca->spi_thread);
 
 	qca->txr.count = max_t(u32, ring->tx_pending, TX_RING_MIN_LEN);
 	qca->txr.count = min_t(u16, qca->txr.count, TX_RING_MAX_LEN);
 
-	if (netif_running(dev))
-		ops->ndo_open(dev);
+	if (qca->spi_thread)
+		kthread_unpark(qca->spi_thread);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index bec723028e96c9..5f3c11fb3fa279 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -580,6 +580,18 @@ qcaspi_spi_thread(void *data)
 	netdev_info(qca->net_dev, "SPI thread created\n");
 	while (!kthread_should_stop()) {
 		set_current_state(TASK_INTERRUPTIBLE);
+		if (kthread_should_park()) {
+			netif_tx_disable(qca->net_dev);
+			netif_carrier_off(qca->net_dev);
+			qcaspi_flush_tx_ring(qca);
+			kthread_parkme();
+			if (qca->sync == QCASPI_SYNC_READY) {
+				netif_carrier_on(qca->net_dev);
+				netif_wake_queue(qca->net_dev);
+			}
+			continue;
+		}
+
 		if ((qca->intr_req == qca->intr_svc) &&
 		    !qca->txr.skb[qca->txr.head])
 			schedule();
@@ -608,11 +620,17 @@ qcaspi_spi_thread(void *data)
 			if (intr_cause & SPI_INT_CPU_ON) {
 				qcaspi_qca7k_sync(qca, QCASPI_EVENT_CPUON);
 
+				/* Frame decoding in progress */
+				if (qca->frm_handle.state != qca->frm_handle.init)
+					qca->net_dev->stats.rx_dropped++;
+
+				qcafrm_fsm_init_spi(&qca->frm_handle);
+				qca->stats.device_reset++;
+
 				/* not synced. */
 				if (qca->sync != QCASPI_SYNC_READY)
 					continue;
 
-				qca->stats.device_reset++;
 				netif_wake_queue(qca->net_dev);
 				netif_carrier_on(qca->net_dev);
 			}
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index a987defb575cfb..bb787a52bc7544 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -196,6 +196,7 @@ enum rtl_registers {
 					/* No threshold before first PCI xfer */
 #define	RX_FIFO_THRESH			(7 << RXCFG_FIFO_SHIFT)
 #define	RX_EARLY_OFF			(1 << 11)
+#define	RX_PAUSE_SLOT_ON		(1 << 11)	/* 8125b and later */
 #define	RXCFG_DMA_SHIFT			8
 					/* Unlimited maximum PCI burst. */
 #define	RX_DMA_BURST			(7 << RXCFG_DMA_SHIFT)
@@ -579,6 +580,7 @@ struct rtl8169_tc_offsets {
 enum rtl_flag {
 	RTL_FLAG_TASK_ENABLED = 0,
 	RTL_FLAG_TASK_RESET_PENDING,
+	RTL_FLAG_TASK_RESET_NO_QUEUE_WAKE,
 	RTL_FLAG_TASK_TX_TIMEOUT,
 	RTL_FLAG_MAX
 };
@@ -624,6 +626,7 @@ struct rtl8169_private {
 
 	unsigned supports_gmii:1;
 	unsigned aspm_manageable:1;
+	unsigned dash_enabled:1;
 	dma_addr_t counters_phys_addr;
 	struct rtl8169_counters *counters;
 	struct rtl8169_tc_offsets tc_offset;
@@ -1253,14 +1256,26 @@ static bool r8168ep_check_dash(struct rtl8169_private *tp)
 	return r8168ep_ocp_read(tp, 0x128) & BIT(0);
 }
 
-static enum rtl_dash_type rtl_check_dash(struct rtl8169_private *tp)
+static bool rtl_dash_is_enabled(struct rtl8169_private *tp)
+{
+	switch (tp->dash_type) {
+	case RTL_DASH_DP:
+		return r8168dp_check_dash(tp);
+	case RTL_DASH_EP:
+		return r8168ep_check_dash(tp);
+	default:
+		return false;
+	}
+}
+
+static enum rtl_dash_type rtl_get_dash_type(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_28:
 	case RTL_GIGA_MAC_VER_31:
-		return r8168dp_check_dash(tp) ? RTL_DASH_DP : RTL_DASH_NONE;
+		return RTL_DASH_DP;
 	case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_53:
-		return r8168ep_check_dash(tp) ? RTL_DASH_EP : RTL_DASH_NONE;
+		return RTL_DASH_EP;
 	default:
 		return RTL_DASH_NONE;
 	}
@@ -1453,7 +1468,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 
 	device_set_wakeup_enable(tp_to_dev(tp), wolopts);
 
-	if (tp->dash_type == RTL_DASH_NONE) {
+	if (!tp->dash_enabled) {
 		rtl_set_d3_pll_down(tp, !wolopts);
 		tp->dev->wol_enabled = wolopts ? 1 : 0;
 	}
@@ -2292,9 +2307,13 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53:
 		RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF);
 		break;
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_63:
+	case RTL_GIGA_MAC_VER_61:
 		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST);
 		break;
+	case RTL_GIGA_MAC_VER_63:
+		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST |
+			RX_PAUSE_SLOT_ON);
+		break;
 	default:
 		RTL_W32(tp, RxConfig, RX128_INT_EN | RX_DMA_BURST);
 		break;
@@ -2512,7 +2531,7 @@ static void rtl_wol_enable_rx(struct rtl8169_private *tp)
 
 static void rtl_prepare_power_down(struct rtl8169_private *tp)
 {
-	if (tp->dash_type != RTL_DASH_NONE)
+	if (tp->dash_enabled)
 		return;
 
 	if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
@@ -2582,6 +2601,8 @@ static void rtl_set_rx_mode(struct net_device *dev)
 
 	if (dev->flags & IFF_PROMISC) {
 		rx_mode |= AcceptAllPhys;
+	} else if (!(dev->flags & IFF_MULTICAST)) {
+		rx_mode &= ~AcceptMulticast;
 	} else if (netdev_mc_count(dev) > MC_FILTER_LIMIT ||
 		   dev->flags & IFF_ALLMULTI ||
 		   tp->mac_version == RTL_GIGA_MAC_VER_35) {
@@ -4567,6 +4588,8 @@ static void rtl_task(struct work_struct *work)
 reset:
 		rtl_reset_work(tp);
 		netif_wake_queue(tp->dev);
+	} else if (test_and_clear_bit(RTL_FLAG_TASK_RESET_NO_QUEUE_WAKE, tp->wk.flags)) {
+		rtl_reset_work(tp);
 	}
 out_unlock:
 	rtnl_unlock();
@@ -4600,7 +4623,7 @@ static void r8169_phylink_handler(struct net_device *ndev)
 	} else {
 		/* In few cases rx is broken after link-down otherwise */
 		if (rtl_is_8125(tp))
-			rtl_reset_work(tp);
+			rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_NO_QUEUE_WAKE);
 		pm_runtime_idle(d);
 	}
 
@@ -4644,10 +4667,16 @@ static void rtl8169_down(struct rtl8169_private *tp)
 	rtl8169_cleanup(tp);
 	rtl_disable_exit_l1(tp);
 	rtl_prepare_power_down(tp);
+
+	if (tp->dash_type != RTL_DASH_NONE)
+		rtl8168_driver_stop(tp);
 }
 
 static void rtl8169_up(struct rtl8169_private *tp)
 {
+	if (tp->dash_type != RTL_DASH_NONE)
+		rtl8168_driver_start(tp);
+
 	pci_set_master(tp->pci_dev);
 	phy_init_hw(tp->phydev);
 	phy_resume(tp->phydev);
@@ -4670,7 +4699,7 @@ static int rtl8169_close(struct net_device *dev)
 	rtl8169_down(tp);
 	rtl8169_rx_clear(tp);
 
-	cancel_work_sync(&tp->wk.work);
+	cancel_work(&tp->wk.work);
 
 	free_irq(tp->irq, tp);
 
@@ -4865,7 +4894,7 @@ static int rtl8169_runtime_idle(struct device *device)
 {
 	struct rtl8169_private *tp = dev_get_drvdata(device);
 
-	if (tp->dash_type != RTL_DASH_NONE)
+	if (tp->dash_enabled)
 		return -EBUSY;
 
 	if (!netif_running(tp->dev) || !netif_carrier_ok(tp->dev))
@@ -4891,8 +4920,7 @@ static void rtl_shutdown(struct pci_dev *pdev)
 	/* Restore original MAC address */
 	rtl_rar_set(tp, tp->dev->perm_addr);
 
-	if (system_state == SYSTEM_POWER_OFF &&
-	    tp->dash_type == RTL_DASH_NONE) {
+	if (system_state == SYSTEM_POWER_OFF && !tp->dash_enabled) {
 		pci_wake_from_d3(pdev, tp->saved_wolopts);
 		pci_set_power_state(pdev, PCI_D3hot);
 	}
@@ -4905,6 +4933,8 @@ static void rtl_remove_one(struct pci_dev *pdev)
 	if (pci_dev_run_wake(pdev))
 		pm_runtime_get_noresume(&pdev->dev);
 
+	cancel_work_sync(&tp->wk.work);
+
 	unregister_netdev(tp->dev);
 
 	if (tp->dash_type != RTL_DASH_NONE)
@@ -5250,7 +5280,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1);
 	tp->aspm_manageable = !rc;
 
-	tp->dash_type = rtl_check_dash(tp);
+	tp->dash_type = rtl_get_dash_type(tp);
+	tp->dash_enabled = rtl_dash_is_enabled(tp);
 
 	tp->cp_cmd = RTL_R16(tp, CPlusCmd) & CPCMD_MASK;
 
@@ -5321,7 +5352,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* configure chip for default features */
 	rtl8169_set_features(dev, dev->features);
 
-	if (tp->dash_type == RTL_DASH_NONE) {
+	if (!tp->dash_enabled) {
 		rtl_set_d3_pll_down(tp, true);
 	} else {
 		rtl_set_d3_pll_down(tp, false);
@@ -5361,7 +5392,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			    "ok" : "ko");
 
 	if (tp->dash_type != RTL_DASH_NONE) {
-		netdev_info(dev, "DASH enabled\n");
+		netdev_info(dev, "DASH %s\n",
+			    tp->dash_enabled ? "enabled" : "disabled");
 		rtl8168_driver_start(tp);
 	}
 
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index c70cff80cc9993..664eda4b5a114e 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -515,6 +515,15 @@ static void ravb_emac_init_gbeth(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 
+	if (priv->phy_interface == PHY_INTERFACE_MODE_MII) {
+		ravb_write(ndev, (1000 << 16) | CXR35_SEL_XMII_MII, CXR35);
+		ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1, 0);
+	} else {
+		ravb_write(ndev, (1000 << 16) | CXR35_SEL_XMII_RGMII, CXR35);
+		ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1,
+			    CXR31_SEL_LINK0);
+	}
+
 	/* Receive frame limit set register */
 	ravb_write(ndev, GBETH_RX_BUFF_MAX + ETH_FCS_LEN, RFLR);
 
@@ -537,14 +546,6 @@ static void ravb_emac_init_gbeth(struct net_device *ndev)
 
 	/* E-MAC interrupt enable register */
 	ravb_write(ndev, ECSIPR_ICDIP, ECSIPR);
-
-	if (priv->phy_interface == PHY_INTERFACE_MODE_MII) {
-		ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1, 0);
-		ravb_write(ndev, (1000 << 16) | CXR35_SEL_XMII_MII, CXR35);
-	} else {
-		ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1,
-			    CXR31_SEL_LINK0);
-	}
 }
 
 static void ravb_emac_init_rcar(struct net_device *ndev)
@@ -1811,19 +1812,20 @@ static int ravb_open(struct net_device *ndev)
 	if (info->gptp)
 		ravb_ptp_init(ndev, priv->pdev);
 
-	netif_tx_start_all_queues(ndev);
-
 	/* PHY control start */
 	error = ravb_phy_start(ndev);
 	if (error)
 		goto out_ptp_stop;
 
+	netif_tx_start_all_queues(ndev);
+
 	return 0;
 
 out_ptp_stop:
 	/* Stop PTP Clock driver */
 	if (info->gptp)
 		ravb_ptp_stop(ndev);
+	ravb_stop_dma(ndev);
 out_free_irq_mgmta:
 	if (!info->multi_irqs)
 		goto out_free_irq;
@@ -1874,6 +1876,12 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 	struct net_device *ndev = priv->ndev;
 	int error;
 
+	if (!rtnl_trylock()) {
+		usleep_range(1000, 2000);
+		schedule_work(&priv->work);
+		return;
+	}
+
 	netif_tx_stop_all_queues(ndev);
 
 	/* Stop PTP Clock driver */
@@ -1907,7 +1915,7 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 		 */
 		netdev_err(ndev, "%s: ravb_dmac_init() failed, error %d\n",
 			   __func__, error);
-		return;
+		goto out_unlock;
 	}
 	ravb_emac_init(ndev);
 
@@ -1917,6 +1925,9 @@ out:
 		ravb_ptp_init(ndev, priv->pdev);
 
 	netif_tx_start_all_queues(ndev);
+
+out_unlock:
+	rtnl_unlock();
 }
 
 /* Packet transmit function for Ethernet AVB */
@@ -2645,9 +2656,14 @@ static int ravb_probe(struct platform_device *pdev)
 	ndev->features = info->net_features;
 	ndev->hw_features = info->net_hw_features;
 
-	reset_control_deassert(rstc);
+	error = reset_control_deassert(rstc);
+	if (error)
+		goto out_free_netdev;
+
 	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
+	error = pm_runtime_resume_and_get(&pdev->dev);
+	if (error < 0)
+		goto out_rpm_disable;
 
 	if (info->multi_irqs) {
 		if (info->err_mgmt_irqs)
@@ -2872,11 +2888,12 @@ out_disable_gptp_clk:
 out_disable_refclk:
 	clk_disable_unprepare(priv->refclk);
 out_release:
-	free_netdev(ndev);
-
 	pm_runtime_put(&pdev->dev);
+out_rpm_disable:
 	pm_runtime_disable(&pdev->dev);
 	reset_control_assert(rstc);
+out_free_netdev:
+	free_netdev(ndev);
 	return error;
 }
 
@@ -2886,22 +2903,26 @@ static void ravb_remove(struct platform_device *pdev)
 	struct ravb_private *priv = netdev_priv(ndev);
 	const struct ravb_hw_info *info = priv->info;
 
-	/* Stop PTP Clock driver */
-	if (info->ccc_gac)
-		ravb_ptp_stop(ndev);
-
-	clk_disable_unprepare(priv->gptp_clk);
-	clk_disable_unprepare(priv->refclk);
-
-	/* Set reset mode */
-	ravb_write(ndev, CCC_OPC_RESET, CCC);
 	unregister_netdev(ndev);
 	if (info->nc_queues)
 		netif_napi_del(&priv->napi[RAVB_NC]);
 	netif_napi_del(&priv->napi[RAVB_BE]);
+
 	ravb_mdio_release(priv);
+
+	/* Stop PTP Clock driver */
+	if (info->ccc_gac)
+		ravb_ptp_stop(ndev);
+
 	dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat,
 			  priv->desc_bat_dma);
+
+	/* Set reset mode */
+	ravb_write(ndev, CCC_OPC_RESET, CCC);
+
+	clk_disable_unprepare(priv->gptp_clk);
+	clk_disable_unprepare(priv->refclk);
+
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	reset_control_assert(priv->rstc);
diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index 43a7795d65919e..e77c6ff93d81b6 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -1504,8 +1504,8 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd
 {
 	struct rswitch_device *rdev = netdev_priv(ndev);
 	struct rswitch_gwca_queue *gq = rdev->tx_queue;
+	netdev_tx_t ret = NETDEV_TX_OK;
 	struct rswitch_ext_desc *desc;
-	int ret = NETDEV_TX_OK;
 	dma_addr_t dma_addr;
 
 	if (rswitch_get_num_cur_queues(gq) >= gq->ring_size - 1) {
@@ -1517,10 +1517,8 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd
 		return ret;
 
 	dma_addr = dma_map_single(ndev->dev.parent, skb->data, skb->len, DMA_TO_DEVICE);
-	if (dma_mapping_error(ndev->dev.parent, dma_addr)) {
-		dev_kfree_skb_any(skb);
-		return ret;
-	}
+	if (dma_mapping_error(ndev->dev.parent, dma_addr))
+		goto err_kfree;
 
 	gq->skbs[gq->cur] = skb;
 	desc = &gq->tx_ring[gq->cur];
@@ -1533,10 +1531,8 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd
 		struct rswitch_gwca_ts_info *ts_info;
 
 		ts_info = kzalloc(sizeof(*ts_info), GFP_ATOMIC);
-		if (!ts_info) {
-			dma_unmap_single(ndev->dev.parent, dma_addr, skb->len, DMA_TO_DEVICE);
-			return -ENOMEM;
-		}
+		if (!ts_info)
+			goto err_unmap;
 
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		rdev->ts_tag++;
@@ -1559,6 +1555,14 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd
 	rswitch_modify(rdev->addr, GWTRC(gq->index), 0, BIT(gq->index % 32));
 
 	return ret;
+
+err_unmap:
+	dma_unmap_single(ndev->dev.parent, dma_addr, skb->len, DMA_TO_DEVICE);
+
+err_kfree:
+	dev_kfree_skb_any(skb);
+
+	return ret;
 }
 
 static struct net_device_stats *rswitch_get_stats(struct net_device *ndev)
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index a2b9e289aa36a9..85dcda51df0522 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -280,7 +280,7 @@ config DWMAC_INTEL
 config DWMAC_LOONGSON
 	tristate "Loongson PCI DWMAC support"
 	default MACH_LOONGSON64
-	depends on STMMAC_ETH && PCI
+	depends on (MACH_LOONGSON64 || COMPILE_TEST) && STMMAC_ETH && PCI
 	depends on COMMON_CLK
 	help
 	  This selects the LOONGSON PCI bus support for the stmmac driver,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 2cd6fce5c9934c..9e40c28d453ab1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -59,26 +59,19 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 		return -ENODEV;
 	}
 
-	if (!of_device_is_compatible(np, "loongson, pci-gmac")) {
-		pr_info("dwmac_loongson_pci: Incompatible OF node\n");
-		return -ENODEV;
-	}
-
 	plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
 	if (!plat)
 		return -ENOMEM;
 
+	plat->mdio_bus_data = devm_kzalloc(&pdev->dev,
+					   sizeof(*plat->mdio_bus_data),
+					   GFP_KERNEL);
+	if (!plat->mdio_bus_data)
+		return -ENOMEM;
+
 	plat->mdio_node = of_get_child_by_name(np, "mdio");
 	if (plat->mdio_node) {
 		dev_info(&pdev->dev, "Found MDIO subnode\n");
-
-		plat->mdio_bus_data = devm_kzalloc(&pdev->dev,
-						   sizeof(*plat->mdio_bus_data),
-						   GFP_KERNEL);
-		if (!plat->mdio_bus_data) {
-			ret = -ENOMEM;
-			goto err_put_node;
-		}
 		plat->mdio_bus_data->needs_reset = true;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index d3bf42d0fceb69..31631e3f89d0a4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -34,6 +34,7 @@
 #define RGMII_CONFIG_LOOPBACK_EN		BIT(2)
 #define RGMII_CONFIG_PROG_SWAP			BIT(1)
 #define RGMII_CONFIG_DDR_MODE			BIT(0)
+#define RGMII_CONFIG_SGMII_CLK_DVDR		GENMASK(18, 10)
 
 /* SDCC_HC_REG_DLL_CONFIG fields */
 #define SDCC_DLL_CONFIG_DLL_RST			BIT(30)
@@ -78,6 +79,8 @@
 #define ETHQOS_MAC_CTRL_SPEED_MODE		BIT(14)
 #define ETHQOS_MAC_CTRL_PORT_SEL		BIT(15)
 
+#define SGMII_10M_RX_CLK_DVDR			0x31
+
 struct ethqos_emac_por {
 	unsigned int offset;
 	unsigned int value;
@@ -598,6 +601,9 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos)
 	return 0;
 }
 
+/* On interface toggle MAC registers gets reset.
+ * Configure MAC block for SGMII on ethernet phy link up
+ */
 static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
 {
 	int val;
@@ -617,6 +623,10 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
 	case SPEED_10:
 		val |= ETHQOS_MAC_CTRL_PORT_SEL;
 		val &= ~ETHQOS_MAC_CTRL_SPEED_MODE;
+		rgmii_updatel(ethqos, RGMII_CONFIG_SGMII_CLK_DVDR,
+			      FIELD_PREP(RGMII_CONFIG_SGMII_CLK_DVDR,
+					 SGMII_10M_RX_CLK_DVDR),
+			      RGMII_IO_MACRO_CONFIG);
 		break;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
index e95d35f1e5a0c8..8fd167501fa0ea 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -710,28 +710,22 @@ void dwmac5_est_irq_status(void __iomem *ioaddr, struct net_device *dev,
 	}
 }
 
-void dwmac5_fpe_configure(void __iomem *ioaddr, u32 num_txq, u32 num_rxq,
+void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+			  u32 num_txq, u32 num_rxq,
 			  bool enable)
 {
 	u32 value;
 
-	if (!enable) {
-		value = readl(ioaddr + MAC_FPE_CTRL_STS);
-
-		value &= ~EFPE;
-
-		writel(value, ioaddr + MAC_FPE_CTRL_STS);
-		return;
+	if (enable) {
+		cfg->fpe_csr = EFPE;
+		value = readl(ioaddr + GMAC_RXQ_CTRL1);
+		value &= ~GMAC_RXQCTRL_FPRQ;
+		value |= (num_rxq - 1) << GMAC_RXQCTRL_FPRQ_SHIFT;
+		writel(value, ioaddr + GMAC_RXQ_CTRL1);
+	} else {
+		cfg->fpe_csr = 0;
 	}
-
-	value = readl(ioaddr + GMAC_RXQ_CTRL1);
-	value &= ~GMAC_RXQCTRL_FPRQ;
-	value |= (num_rxq - 1) << GMAC_RXQCTRL_FPRQ_SHIFT;
-	writel(value, ioaddr + GMAC_RXQ_CTRL1);
-
-	value = readl(ioaddr + MAC_FPE_CTRL_STS);
-	value |= EFPE;
-	writel(value, ioaddr + MAC_FPE_CTRL_STS);
+	writel(cfg->fpe_csr, ioaddr + MAC_FPE_CTRL_STS);
 }
 
 int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev)
@@ -741,6 +735,9 @@ int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev)
 
 	status = FPE_EVENT_UNKNOWN;
 
+	/* Reads from the MAC_FPE_CTRL_STS register should only be performed
+	 * here, since the status flags of MAC_FPE_CTRL_STS are "clear on read"
+	 */
 	value = readl(ioaddr + MAC_FPE_CTRL_STS);
 
 	if (value & TRSP) {
@@ -766,19 +763,15 @@ int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev)
 	return status;
 }
 
-void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, enum stmmac_mpacket_type type)
+void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+			     enum stmmac_mpacket_type type)
 {
-	u32 value;
+	u32 value = cfg->fpe_csr;
 
-	value = readl(ioaddr + MAC_FPE_CTRL_STS);
-
-	if (type == MPACKET_VERIFY) {
-		value &= ~SRSP;
+	if (type == MPACKET_VERIFY)
 		value |= SVER;
-	} else {
-		value &= ~SVER;
+	else if (type == MPACKET_RESPONSE)
 		value |= SRSP;
-	}
 
 	writel(value, ioaddr + MAC_FPE_CTRL_STS);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
index 53c138d0ff4808..34e620790eb371 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
@@ -153,9 +153,11 @@ int dwmac5_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg,
 			 unsigned int ptp_rate);
 void dwmac5_est_irq_status(void __iomem *ioaddr, struct net_device *dev,
 			   struct stmmac_extra_stats *x, u32 txqcnt);
-void dwmac5_fpe_configure(void __iomem *ioaddr, u32 num_txq, u32 num_rxq,
+void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+			  u32 num_txq, u32 num_rxq,
 			  bool enable);
 void dwmac5_fpe_send_mpacket(void __iomem *ioaddr,
+			     struct stmmac_fpe_cfg *cfg,
 			     enum stmmac_mpacket_type type);
 int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 7a8f47e7b728bd..a4e8b498dea964 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -259,7 +259,7 @@
 	((val) << XGMAC_PPS_MINIDX(x))
 #define XGMAC_PPSCMD_START		0x2
 #define XGMAC_PPSCMD_STOP		0x5
-#define XGMAC_PPSEN0			BIT(4)
+#define XGMAC_PPSENx(x)			BIT(4 + (x) * 8)
 #define XGMAC_PPSx_TARGET_TIME_SEC(x)	(0x00000d80 + (x) * 0x10)
 #define XGMAC_PPSx_TARGET_TIME_NSEC(x)	(0x00000d84 + (x) * 0x10)
 #define XGMAC_TRGTBUSY0			BIT(31)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index f352be269deb54..a74e71db79f949 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -1178,7 +1178,19 @@ static int dwxgmac2_flex_pps_config(void __iomem *ioaddr, int index,
 
 	val |= XGMAC_PPSCMDx(index, XGMAC_PPSCMD_START);
 	val |= XGMAC_TRGTMODSELx(index, XGMAC_PPSCMD_START);
-	val |= XGMAC_PPSEN0;
+
+	/* XGMAC Core has 4 PPS outputs at most.
+	 *
+	 * Prior XGMAC Core 3.20, Fixed mode or Flexible mode are selectable for
+	 * PPS0 only via PPSEN0. PPS{1,2,3} are in Flexible mode by default,
+	 * and can not be switched to Fixed mode, since PPSEN{1,2,3} are
+	 * read-only reserved to 0.
+	 * But we always set PPSEN{1,2,3} do not make things worse ;-)
+	 *
+	 * From XGMAC Core 3.20 and later, PPSEN{0,1,2,3} are writable and must
+	 * be set, or the PPS outputs stay in Fixed PPS mode by default.
+	 */
+	val |= XGMAC_PPSENx(index);
 
 	writel(cfg->start.tv_sec, ioaddr + XGMAC_PPSx_TARGET_TIME_SEC(index));
 
@@ -1472,7 +1484,8 @@ static int dwxgmac3_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg,
 	return 0;
 }
 
-static void dwxgmac3_fpe_configure(void __iomem *ioaddr, u32 num_txq,
+static void dwxgmac3_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+				   u32 num_txq,
 				   u32 num_rxq, bool enable)
 {
 	u32 value;
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index b95d3e1378136e..68aa2d5ca6e567 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -412,9 +412,11 @@ struct stmmac_ops {
 			     unsigned int ptp_rate);
 	void (*est_irq_status)(void __iomem *ioaddr, struct net_device *dev,
 			       struct stmmac_extra_stats *x, u32 txqcnt);
-	void (*fpe_configure)(void __iomem *ioaddr, u32 num_txq, u32 num_rxq,
+	void (*fpe_configure)(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+			      u32 num_txq, u32 num_rxq,
 			      bool enable);
 	void (*fpe_send_mpacket)(void __iomem *ioaddr,
+				 struct stmmac_fpe_cfg *cfg,
 				 enum stmmac_mpacket_type type);
 	int (*fpe_irq_status)(void __iomem *ioaddr, struct net_device *dev);
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
index ea4910ae0921ac..6a7c1d325c464e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
@@ -177,8 +177,10 @@
 #define MMC_XGMAC_RX_DISCARD_OCT_GB	0x1b4
 #define MMC_XGMAC_RX_ALIGN_ERR_PKT	0x1bc
 
+#define MMC_XGMAC_TX_FPE_INTR_MASK	0x204
 #define MMC_XGMAC_TX_FPE_FRAG		0x208
 #define MMC_XGMAC_TX_HOLD_REQ		0x20c
+#define MMC_XGMAC_RX_FPE_INTR_MASK	0x224
 #define MMC_XGMAC_RX_PKT_ASSEMBLY_ERR	0x228
 #define MMC_XGMAC_RX_PKT_SMD_ERR	0x22c
 #define MMC_XGMAC_RX_PKT_ASSEMBLY_OK	0x230
@@ -352,6 +354,8 @@ static void dwxgmac_mmc_intr_all_mask(void __iomem *mmcaddr)
 {
 	writel(0x0, mmcaddr + MMC_RX_INTR_MASK);
 	writel(0x0, mmcaddr + MMC_TX_INTR_MASK);
+	writel(MMC_DEFAULT_MASK, mmcaddr + MMC_XGMAC_TX_FPE_INTR_MASK);
+	writel(MMC_DEFAULT_MASK, mmcaddr + MMC_XGMAC_RX_FPE_INTR_MASK);
 	writel(MMC_DEFAULT_MASK, mmcaddr + MMC_XGMAC_RX_IPC_INTR_MASK);
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index 540f6a4ec0b81f..f05bd757dfe525 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -237,7 +237,7 @@ static void timestamp_interrupt(struct stmmac_priv *priv)
 	 */
 	ts_status = readl(priv->ioaddr + GMAC_TIMESTAMP_STATUS);
 
-	if (priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN)
+	if (!(priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN))
 		return;
 
 	num_snapshot = (ts_status & GMAC_TIMESTAMP_ATSNS_MASK) >>
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 3e50fd53a61744..37e64283f9107c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -964,7 +964,8 @@ static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up)
 	bool *hs_enable = &fpe_cfg->hs_enable;
 
 	if (is_up && *hs_enable) {
-		stmmac_fpe_send_mpacket(priv, priv->ioaddr, MPACKET_VERIFY);
+		stmmac_fpe_send_mpacket(priv, priv->ioaddr, fpe_cfg,
+					MPACKET_VERIFY);
 	} else {
 		*lo_state = FPE_STATE_OFF;
 		*lp_state = FPE_STATE_OFF;
@@ -5293,6 +5294,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 
 	dma_dir = page_pool_get_dma_dir(rx_q->page_pool);
 	buf_sz = DIV_ROUND_UP(priv->dma_conf.dma_buf_sz, PAGE_SIZE) * PAGE_SIZE;
+	limit = min(priv->dma_conf.dma_rx_size - 1, (unsigned int)limit);
 
 	if (netif_msg_rx_status(priv)) {
 		void *rx_head;
@@ -5328,10 +5330,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			len = 0;
 		}
 
+read_again:
 		if (count >= limit)
 			break;
 
-read_again:
 		buf1_len = 0;
 		buf2_len = 0;
 		entry = next_entry;
@@ -5838,6 +5840,7 @@ static void stmmac_fpe_event_status(struct stmmac_priv *priv, int status)
 		/* If user has requested FPE enable, quickly response */
 		if (*hs_enable)
 			stmmac_fpe_send_mpacket(priv, priv->ioaddr,
+						fpe_cfg,
 						MPACKET_RESPONSE);
 	}
 
@@ -7262,6 +7265,7 @@ static void stmmac_fpe_lp_task(struct work_struct *work)
 		if (*lo_state == FPE_STATE_ENTERING_ON &&
 		    *lp_state == FPE_STATE_ENTERING_ON) {
 			stmmac_fpe_configure(priv, priv->ioaddr,
+					     fpe_cfg,
 					     priv->plat->tx_queues_to_use,
 					     priv->plat->rx_queues_to_use,
 					     *enable);
@@ -7280,6 +7284,7 @@ static void stmmac_fpe_lp_task(struct work_struct *work)
 			netdev_info(priv->dev, SEND_VERIFY_MPAKCET_FMT,
 				    *lo_state, *lp_state);
 			stmmac_fpe_send_mpacket(priv, priv->ioaddr,
+						fpe_cfg,
 						MPACKET_VERIFY);
 		}
 		/* Sleep then retry */
@@ -7294,6 +7299,7 @@ void stmmac_fpe_handshake(struct stmmac_priv *priv, bool enable)
 	if (priv->plat->fpe_cfg->hs_enable != enable) {
 		if (enable) {
 			stmmac_fpe_send_mpacket(priv, priv->ioaddr,
+						priv->plat->fpe_cfg,
 						MPACKET_VERIFY);
 		} else {
 			priv->plat->fpe_cfg->lo_fpe_state = FPE_STATE_OFF;
@@ -7754,6 +7760,7 @@ int stmmac_suspend(struct device *dev)
 	if (priv->dma_cap.fpesel) {
 		/* Disable FPE */
 		stmmac_fpe_configure(priv, priv->ioaddr,
+				     priv->plat->fpe_cfg,
 				     priv->plat->tx_queues_to_use,
 				     priv->plat->rx_queues_to_use, false);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index fa9e7e7040b945..0542cfd1817e62 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -591,7 +591,11 @@ int stmmac_mdio_register(struct net_device *ndev)
 	new_bus->parent = priv->device;
 
 	err = of_mdiobus_register(new_bus, mdio_node);
-	if (err != 0) {
+	if (err == -ENODEV) {
+		err = 0;
+		dev_info(dev, "MDIO bus is disabled\n");
+		goto bus_register_fail;
+	} else if (err) {
 		dev_err_probe(dev, err, "Cannot register the MDIO bus\n");
 		goto bus_register_fail;
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index ac41ef4cbd2f02..6ad3e0a1193666 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -1079,6 +1079,7 @@ disable:
 
 	priv->plat->fpe_cfg->enable = false;
 	stmmac_fpe_configure(priv, priv->ioaddr,
+			     priv->plat->fpe_cfg,
 			     priv->plat->tx_queues_to_use,
 			     priv->plat->rx_queues_to_use,
 			     false);
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 24120605502f9e..ece9f8df98ae7d 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -1588,10 +1588,10 @@ static void am65_cpsw_nuss_mac_link_up(struct phylink_config *config, struct phy
 
 	/* rx_pause/tx_pause */
 	if (rx_pause)
-		mac_control |= CPSW_SL_CTL_RX_FLOW_EN;
+		mac_control |= CPSW_SL_CTL_TX_FLOW_EN;
 
 	if (tx_pause)
-		mac_control |= CPSW_SL_CTL_TX_FLOW_EN;
+		mac_control |= CPSW_SL_CTL_RX_FLOW_EN;
 
 	cpsw_sl_ctl_set(port->slave.mac_sl, mac_control);
 
diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index 4cf2a52e43783f..3025e9c189702b 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -177,7 +177,7 @@ static void icss_iep_set_counter(struct icss_iep *iep, u64 ns)
 	if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
 		writel(upper_32_bits(ns), iep->base +
 		       iep->plat_data->reg_offs[ICSS_IEP_COUNT_REG1]);
-	writel(upper_32_bits(ns), iep->base + iep->plat_data->reg_offs[ICSS_IEP_COUNT_REG0]);
+	writel(lower_32_bits(ns), iep->base + iep->plat_data->reg_offs[ICSS_IEP_COUNT_REG0]);
 }
 
 static void icss_iep_update_to_next_boundary(struct icss_iep *iep, u64 start_ns);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 6c4b64227ac886..411898a4f38caa 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -2063,7 +2063,7 @@ static int prueth_probe(struct platform_device *pdev)
 				       &prueth->shram);
 	if (ret) {
 		dev_err(dev, "unable to get PRUSS SHRD RAM2: %d\n", ret);
-		pruss_put(prueth->pruss);
+		goto put_pruss;
 	}
 
 	prueth->sram_pool = of_gen_pool_get(np, "sram", 0);
@@ -2105,10 +2105,7 @@ static int prueth_probe(struct platform_device *pdev)
 	prueth->iep1 = icss_iep_get_idx(np, 1);
 	if (IS_ERR(prueth->iep1)) {
 		ret = dev_err_probe(dev, PTR_ERR(prueth->iep1), "iep1 get failed\n");
-		icss_iep_put(prueth->iep0);
-		prueth->iep0 = NULL;
-		prueth->iep1 = NULL;
-		goto free_pool;
+		goto put_iep0;
 	}
 
 	if (prueth->pdata.quirk_10m_link_issue) {
@@ -2205,6 +2202,12 @@ netdev_exit:
 exit_iep:
 	if (prueth->pdata.quirk_10m_link_issue)
 		icss_iep_exit_fw(prueth->iep1);
+	icss_iep_put(prueth->iep1);
+
+put_iep0:
+	icss_iep_put(prueth->iep0);
+	prueth->iep0 = NULL;
+	prueth->iep1 = NULL;
 
 free_pool:
 	gen_pool_free(prueth->sram_pool,
@@ -2212,6 +2215,8 @@ free_pool:
 
 put_mem:
 	pruss_release_mem_region(prueth->pruss, &prueth->shram);
+
+put_pruss:
 	pruss_put(prueth->pruss);
 
 put_cores:
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index a3c5de9d547a4b..533e912af0893a 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -1769,10 +1769,12 @@ int wx_sw_init(struct wx *wx)
 		wx->subsystem_device_id = pdev->subsystem_device;
 	} else {
 		err = wx_flash_read_dword(wx, 0xfffdc, &ssid);
-		if (!err)
-			wx->subsystem_device_id = swab16((u16)ssid);
+		if (err < 0) {
+			wx_err(wx, "read of internal subsystem device id failed\n");
+			return err;
+		}
 
-		return err;
+		wx->subsystem_device_id = swab16((u16)ssid);
 	}
 
 	wx->mac_table = kcalloc(wx->mac.num_rar_entries,
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 2823861e5a92f5..347d3cec02a363 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -160,60 +160,6 @@ static __le32 wx_test_staterr(union wx_rx_desc *rx_desc,
 	return rx_desc->wb.upper.status_error & cpu_to_le32(stat_err_bits);
 }
 
-static bool wx_can_reuse_rx_page(struct wx_rx_buffer *rx_buffer,
-				 int rx_buffer_pgcnt)
-{
-	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
-	struct page *page = rx_buffer->page;
-
-	/* avoid re-using remote and pfmemalloc pages */
-	if (!dev_page_is_reusable(page))
-		return false;
-
-#if (PAGE_SIZE < 8192)
-	/* if we are only owner of page we can reuse it */
-	if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1))
-		return false;
-#endif
-
-	/* If we have drained the page fragment pool we need to update
-	 * the pagecnt_bias and page count so that we fully restock the
-	 * number of references the driver holds.
-	 */
-	if (unlikely(pagecnt_bias == 1)) {
-		page_ref_add(page, USHRT_MAX - 1);
-		rx_buffer->pagecnt_bias = USHRT_MAX;
-	}
-
-	return true;
-}
-
-/**
- * wx_reuse_rx_page - page flip buffer and store it back on the ring
- * @rx_ring: rx descriptor ring to store buffers on
- * @old_buff: donor buffer to have page reused
- *
- * Synchronizes page for reuse by the adapter
- **/
-static void wx_reuse_rx_page(struct wx_ring *rx_ring,
-			     struct wx_rx_buffer *old_buff)
-{
-	u16 nta = rx_ring->next_to_alloc;
-	struct wx_rx_buffer *new_buff;
-
-	new_buff = &rx_ring->rx_buffer_info[nta];
-
-	/* update, and store next to alloc */
-	nta++;
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	/* transfer page from old buffer to new buffer */
-	new_buff->page = old_buff->page;
-	new_buff->page_dma = old_buff->page_dma;
-	new_buff->page_offset = old_buff->page_offset;
-	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
-}
-
 static void wx_dma_sync_frag(struct wx_ring *rx_ring,
 			     struct wx_rx_buffer *rx_buffer)
 {
@@ -270,8 +216,6 @@ static struct wx_rx_buffer *wx_get_rx_buffer(struct wx_ring *rx_ring,
 				      size,
 				      DMA_FROM_DEVICE);
 skip_sync:
-	rx_buffer->pagecnt_bias--;
-
 	return rx_buffer;
 }
 
@@ -280,19 +224,9 @@ static void wx_put_rx_buffer(struct wx_ring *rx_ring,
 			     struct sk_buff *skb,
 			     int rx_buffer_pgcnt)
 {
-	if (wx_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) {
-		/* hand second half of page back to the ring */
-		wx_reuse_rx_page(rx_ring, rx_buffer);
-	} else {
-		if (!IS_ERR(skb) && WX_CB(skb)->dma == rx_buffer->dma)
-			/* the page has been released from the ring */
-			WX_CB(skb)->page_released = true;
-		else
-			page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false);
-
-		__page_frag_cache_drain(rx_buffer->page,
-					rx_buffer->pagecnt_bias);
-	}
+	if (!IS_ERR(skb) && WX_CB(skb)->dma == rx_buffer->dma)
+		/* the page has been released from the ring */
+		WX_CB(skb)->page_released = true;
 
 	/* clear contents of rx_buffer */
 	rx_buffer->page = NULL;
@@ -335,11 +269,12 @@ static struct sk_buff *wx_build_skb(struct wx_ring *rx_ring,
 		if (size <= WX_RXBUFFER_256) {
 			memcpy(__skb_put(skb, size), page_addr,
 			       ALIGN(size, sizeof(long)));
-			rx_buffer->pagecnt_bias++;
-
+			page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, true);
 			return skb;
 		}
 
+		skb_mark_for_recycle(skb);
+
 		if (!wx_test_staterr(rx_desc, WX_RXD_STAT_EOP))
 			WX_CB(skb)->dma = rx_buffer->dma;
 
@@ -382,8 +317,6 @@ static bool wx_alloc_mapped_page(struct wx_ring *rx_ring,
 	bi->page_dma = dma;
 	bi->page = page;
 	bi->page_offset = 0;
-	page_ref_add(page, USHRT_MAX - 1);
-	bi->pagecnt_bias = USHRT_MAX;
 
 	return true;
 }
@@ -723,7 +656,6 @@ static int wx_clean_rx_irq(struct wx_q_vector *q_vector,
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
 			rx_ring->rx_stats.alloc_rx_buff_failed++;
-			rx_buffer->pagecnt_bias++;
 			break;
 		}
 
@@ -1972,11 +1904,11 @@ void wx_reset_interrupt_capability(struct wx *wx)
 	if (!pdev->msi_enabled && !pdev->msix_enabled)
 		return;
 
-	pci_free_irq_vectors(wx->pdev);
 	if (pdev->msix_enabled) {
 		kfree(wx->msix_entries);
 		wx->msix_entries = NULL;
 	}
+	pci_free_irq_vectors(wx->pdev);
 }
 EXPORT_SYMBOL(wx_reset_interrupt_capability);
 
@@ -2248,8 +2180,6 @@ static void wx_clean_rx_ring(struct wx_ring *rx_ring)
 
 		/* free resources associated with mapping */
 		page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false);
-		__page_frag_cache_drain(rx_buffer->page,
-					rx_buffer->pagecnt_bias);
 
 		i++;
 		rx_buffer++;
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 165e82de772e6c..83f9bb7b3c22a0 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -787,7 +787,6 @@ struct wx_rx_buffer {
 	dma_addr_t page_dma;
 	struct page *page;
 	unsigned int page_offset;
-	u16 pagecnt_bias;
 };
 
 struct wx_queue_stats {
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index 3d43f808c86b78..8db804543e66da 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -121,10 +121,8 @@ static int ngbe_sw_init(struct wx *wx)
 
 	/* PCI config space info */
 	err = wx_sw_init(wx);
-	if (err < 0) {
-		wx_err(wx, "read of internal subsystem device id failed\n");
+	if (err < 0)
 		return err;
-	}
 
 	/* mac type, phy type , oem type */
 	ngbe_init_type_code(wx);
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index 70f0b5c01dacf2..526250102db27c 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -364,10 +364,8 @@ static int txgbe_sw_init(struct wx *wx)
 
 	/* PCI config space info */
 	err = wx_sw_init(wx);
-	if (err < 0) {
-		wx_err(wx, "read of internal subsystem device id failed\n");
+	if (err < 0)
 		return err;
-	}
 
 	txgbe_init_type_code(wx);
 
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 82d0d44b2b02f1..bf6e3399049092 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -822,7 +822,7 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		if (lp->features & XAE_FEATURE_FULL_TX_CSUM) {
 			/* Tx Full Checksum Offload Enabled */
 			cur_p->app0 |= 2;
-		} else if (lp->features & XAE_FEATURE_PARTIAL_RX_CSUM) {
+		} else if (lp->features & XAE_FEATURE_PARTIAL_TX_CSUM) {
 			csum_start_off = skb_transport_offset(skb);
 			csum_index_off = csum_start_off + skb->csum_offset;
 			/* Tx Partial Checksum Offload Enabled */
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index 531bf919aef509..e0d26148dfd95c 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -163,7 +163,6 @@ typedef void buffer_t;
 
 /* Information about built-in Ethernet MAC interfaces */
 struct eth_plat_info {
-	u8 phy;		/* MII PHY ID, 0 - 31 */
 	u8 rxq;		/* configurable, currently 0 - 31 only */
 	u8 txreadyq;
 	u8 hwaddr[ETH_ALEN];
@@ -1583,7 +1582,7 @@ static int ixp4xx_eth_probe(struct platform_device *pdev)
 	if ((err = register_netdev(ndev)))
 		goto err_phy_dis;
 
-	netdev_info(ndev, "%s: MII PHY %i on %s\n", ndev->name, plat->phy,
+	netdev_info(ndev, "%s: MII PHY %s on %s\n", ndev->name, phydev_name(phydev),
 		    npe_name(port->npe));
 
 	return 0;
diff --git a/drivers/net/hyperv/Kconfig b/drivers/net/hyperv/Kconfig
index ca7bf7f897d36b..c8cbd85adcf995 100644
--- a/drivers/net/hyperv/Kconfig
+++ b/drivers/net/hyperv/Kconfig
@@ -3,5 +3,6 @@ config HYPERV_NET
 	tristate "Microsoft Hyper-V virtual network driver"
 	depends on HYPERV
 	select UCS2_STRING
+	select NLS
 	help
 	  Select this option to enable the Hyper-V virtual network driver.
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 3ba3c8fb28a5d6..706ea5263e879d 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2206,9 +2206,6 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto upper_link_failed;
 	}
 
-	/* set slave flag before open to prevent IPv6 addrconf */
-	vf_netdev->flags |= IFF_SLAVE;
-
 	schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
 
 	call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
@@ -2315,16 +2312,18 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev)
 
 	}
 
-	/* Fallback path to check synthetic vf with
-	 * help of mac addr
+	/* Fallback path to check synthetic vf with help of mac addr.
+	 * Because this function can be called before vf_netdev is
+	 * initialized (NETDEV_POST_INIT) when its perm_addr has not been copied
+	 * from dev_addr, also try to match to its dev_addr.
+	 * Note: On Hyper-V and Azure, it's not possible to set a MAC address
+	 * on a VF that matches to the MAC of a unrelated NETVSC device.
 	 */
 	list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
 		ndev = hv_get_drvdata(ndev_ctx->device_ctx);
-		if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr)) {
-			netdev_notice(vf_netdev,
-				      "falling back to mac addr based matching\n");
+		if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr) ||
+		    ether_addr_equal(vf_netdev->dev_addr, ndev->perm_addr))
 			return ndev;
-		}
 	}
 
 	netdev_notice(vf_netdev,
@@ -2332,6 +2331,19 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev)
 	return NULL;
 }
 
+static int netvsc_prepare_bonding(struct net_device *vf_netdev)
+{
+	struct net_device *ndev;
+
+	ndev = get_netvsc_byslot(vf_netdev);
+	if (!ndev)
+		return NOTIFY_DONE;
+
+	/* set slave flag before open to prevent IPv6 addrconf */
+	vf_netdev->flags |= IFF_SLAVE;
+	return NOTIFY_DONE;
+}
+
 static int netvsc_register_vf(struct net_device *vf_netdev)
 {
 	struct net_device_context *net_device_ctx;
@@ -2531,15 +2543,6 @@ static int netvsc_probe(struct hv_device *dev,
 		goto devinfo_failed;
 	}
 
-	nvdev = rndis_filter_device_add(dev, device_info);
-	if (IS_ERR(nvdev)) {
-		ret = PTR_ERR(nvdev);
-		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
-		goto rndis_failed;
-	}
-
-	eth_hw_addr_set(net, device_info->mac_adr);
-
 	/* We must get rtnl lock before scheduling nvdev->subchan_work,
 	 * otherwise netvsc_subchan_work() can get rtnl lock first and wait
 	 * all subchannels to show up, but that may not happen because
@@ -2547,9 +2550,23 @@ static int netvsc_probe(struct hv_device *dev,
 	 * -> ... -> device_add() -> ... -> __device_attach() can't get
 	 * the device lock, so all the subchannels can't be processed --
 	 * finally netvsc_subchan_work() hangs forever.
+	 *
+	 * The rtnl lock also needs to be held before rndis_filter_device_add()
+	 * which advertises nvsp_2_vsc_capability / sriov bit, and triggers
+	 * VF NIC offering and registering. If VF NIC finished register_netdev()
+	 * earlier it may cause name based config failure.
 	 */
 	rtnl_lock();
 
+	nvdev = rndis_filter_device_add(dev, device_info);
+	if (IS_ERR(nvdev)) {
+		ret = PTR_ERR(nvdev);
+		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
+		goto rndis_failed;
+	}
+
+	eth_hw_addr_set(net, device_info->mac_adr);
+
 	if (nvdev->num_chn > 1)
 		schedule_work(&nvdev->subchan_work);
 
@@ -2586,9 +2603,9 @@ static int netvsc_probe(struct hv_device *dev,
 	return 0;
 
 register_failed:
-	rtnl_unlock();
 	rndis_filter_device_remove(dev, nvdev);
 rndis_failed:
+	rtnl_unlock();
 	netvsc_devinfo_put(device_info);
 devinfo_failed:
 	free_percpu(net_device_ctx->vf_stats);
@@ -2753,6 +2770,8 @@ static int netvsc_netdev_event(struct notifier_block *this,
 		return NOTIFY_DONE;
 
 	switch (event) {
+	case NETDEV_POST_INIT:
+		return netvsc_prepare_bonding(event_dev);
 	case NETDEV_REGISTER:
 		return netvsc_register_vf(event_dev);
 	case NETDEV_UNREGISTER:
@@ -2788,12 +2807,17 @@ static int __init netvsc_drv_init(void)
 	}
 	netvsc_ring_bytes = ring_size * PAGE_SIZE;
 
+	register_netdevice_notifier(&netvsc_netdev_notifier);
+
 	ret = vmbus_driver_register(&netvsc_drv);
 	if (ret)
-		return ret;
+		goto err_vmbus_reg;
 
-	register_netdevice_notifier(&netvsc_netdev_notifier);
 	return 0;
+
+err_vmbus_reg:
+	unregister_netdevice_notifier(&netvsc_netdev_notifier);
+	return ret;
 }
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ipa/reg/gsi_reg-v5.0.c b/drivers/net/ipa/reg/gsi_reg-v5.0.c
index d7b81a36d673bb..145eb0bd096d60 100644
--- a/drivers/net/ipa/reg/gsi_reg-v5.0.c
+++ b/drivers/net/ipa/reg/gsi_reg-v5.0.c
@@ -78,7 +78,7 @@ REG_STRIDE_FIELDS(EV_CH_E_CNTXT_0, ev_ch_e_cntxt_0,
 		  0x0001c000 + 0x12000 * GSI_EE_AP, 0x80);
 
 static const u32 reg_ev_ch_e_cntxt_1_fmask[] = {
-	[R_LENGTH]					= GENMASK(19, 0),
+	[R_LENGTH]					= GENMASK(23, 0),
 };
 
 REG_STRIDE_FIELDS(EV_CH_E_CNTXT_1, ev_ch_e_cntxt_1,
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 21e9cac7312186..2d5b021b4ea605 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -411,7 +411,7 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h,
 	return addr;
 }
 
-static int ipvlan_process_v4_outbound(struct sk_buff *skb)
+static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb)
 {
 	const struct iphdr *ip4h = ip_hdr(skb);
 	struct net_device *dev = skb->dev;
@@ -453,13 +453,11 @@ out:
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static int ipvlan_process_v6_outbound(struct sk_buff *skb)
+
+static noinline_for_stack int
+ipvlan_route_v6_outbound(struct net_device *dev, struct sk_buff *skb)
 {
 	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
-	struct net_device *dev = skb->dev;
-	struct net *net = dev_net(dev);
-	struct dst_entry *dst;
-	int err, ret = NET_XMIT_DROP;
 	struct flowi6 fl6 = {
 		.flowi6_oif = dev->ifindex,
 		.daddr = ip6h->daddr,
@@ -469,27 +467,38 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
 		.flowi6_mark = skb->mark,
 		.flowi6_proto = ip6h->nexthdr,
 	};
+	struct dst_entry *dst;
+	int err;
 
-	dst = ip6_route_output(net, NULL, &fl6);
-	if (dst->error) {
-		ret = dst->error;
+	dst = ip6_route_output(dev_net(dev), NULL, &fl6);
+	err = dst->error;
+	if (err) {
 		dst_release(dst);
-		goto err;
+		return err;
 	}
 	skb_dst_set(skb, dst);
+	return 0;
+}
+
+static int ipvlan_process_v6_outbound(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	int err, ret = NET_XMIT_DROP;
+
+	err = ipvlan_route_v6_outbound(dev, skb);
+	if (unlikely(err)) {
+		DEV_STATS_INC(dev, tx_errors);
+		kfree_skb(skb);
+		return err;
+	}
 
 	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 
-	err = ip6_local_out(net, skb->sk, skb);
+	err = ip6_local_out(dev_net(dev), skb->sk, skb);
 	if (unlikely(net_xmit_eval(err)))
 		DEV_STATS_INC(dev, tx_errors);
 	else
 		ret = NET_XMIT_SUCCESS;
-	goto out;
-err:
-	DEV_STATS_INC(dev, tx_errors);
-	kfree_skb(skb);
-out:
 	return ret;
 }
 #else
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 02bd201bc7e58e..c8da94af4161a5 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -780,7 +780,7 @@ static void macvlan_change_rx_flags(struct net_device *dev, int change)
 	if (dev->flags & IFF_UP) {
 		if (change & IFF_ALLMULTI)
 			dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
-		if (change & IFF_PROMISC)
+		if (!macvlan_passthru(vlan->port) && change & IFF_PROMISC)
 			dev_set_promiscuity(lowerdev,
 					    dev->flags & IFF_PROMISC ? 1 : -1);
 
diff --git a/drivers/net/mdio/acpi_mdio.c b/drivers/net/mdio/acpi_mdio.c
index 4630dde019749a..5d0f11f280cfc5 100644
--- a/drivers/net/mdio/acpi_mdio.c
+++ b/drivers/net/mdio/acpi_mdio.c
@@ -16,6 +16,7 @@
 
 MODULE_AUTHOR("Calvin Johnson <calvin.johnson@oss.nxp.com>");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ACPI MDIO bus (Ethernet PHY) accessors");
 
 /**
  * __acpi_mdiobus_register - Register mii_bus and create PHYs from the ACPI ASL.
diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c
index 1183ef5e203e3e..fd02f5cbc853a6 100644
--- a/drivers/net/mdio/fwnode_mdio.c
+++ b/drivers/net/mdio/fwnode_mdio.c
@@ -14,6 +14,7 @@
 
 MODULE_AUTHOR("Calvin Johnson <calvin.johnson@oss.nxp.com>");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("FWNODE MDIO bus (Ethernet PHY) accessors");
 
 static struct pse_control *
 fwnode_find_pse_control(struct fwnode_handle *fwnode)
diff --git a/drivers/net/mdio/mdio-aspeed.c b/drivers/net/mdio/mdio-aspeed.c
index 70edeeb7771e87..c2170650415cdb 100644
--- a/drivers/net/mdio/mdio-aspeed.c
+++ b/drivers/net/mdio/mdio-aspeed.c
@@ -205,3 +205,4 @@ module_platform_driver(aspeed_mdio_driver);
 
 MODULE_AUTHOR("Andrew Jeffery <andrew@aj.id.au>");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ASPEED MDIO bus controller");
diff --git a/drivers/net/mdio/mdio-bitbang.c b/drivers/net/mdio/mdio-bitbang.c
index 81b7748c10ce0e..f88639297ff2df 100644
--- a/drivers/net/mdio/mdio-bitbang.c
+++ b/drivers/net/mdio/mdio-bitbang.c
@@ -263,3 +263,4 @@ void free_mdio_bitbang(struct mii_bus *bus)
 EXPORT_SYMBOL(free_mdio_bitbang);
 
 MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Bitbanged MDIO buses");
diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c
index 7eb32ebb846d86..64ebcb6d235cc0 100644
--- a/drivers/net/mdio/of_mdio.c
+++ b/drivers/net/mdio/of_mdio.c
@@ -25,6 +25,7 @@
 
 MODULE_AUTHOR("Grant Likely <grant.likely@secretlab.ca>");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("OpenFirmware MDIO bus (Ethernet PHY) accessors");
 
 /* Extract the clause 22 phy ID from the compatible string of the form
  * ethernet-phy-idAAAA.BBBB */
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index f60eb97e3a627e..608953d4f98da9 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -93,7 +93,7 @@ static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded)
 {
 	struct nsim_bpf_bound_prog *state;
 
-	if (!prog || !prog->aux->offload)
+	if (!prog || !bpf_prog_is_offloaded(prog->aux))
 		return;
 
 	state = prog->aux->offload->dev_priv;
@@ -311,7 +311,7 @@ nsim_setup_prog_hw_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
 	if (!bpf->prog)
 		return 0;
 
-	if (!bpf->prog->aux->offload) {
+	if (!bpf_prog_is_offloaded(bpf->prog->aux)) {
 		NSIM_EA(bpf->extack, "xdpoffload of non-bound program");
 		return -EINVAL;
 	}
diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index 5a0f86f38f0931..39171380ccf29e 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -7,6 +7,7 @@
 #include <linux/filter.h>
 #include <linux/netfilter_netdev.h>
 #include <linux/bpf_mprog.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include <net/netkit.h>
 #include <net/dst.h>
@@ -68,6 +69,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev)
 	netdev_tx_t ret_dev = NET_XMIT_SUCCESS;
 	const struct bpf_mprog_entry *entry;
 	struct net_device *peer;
+	int len = skb->len;
 
 	rcu_read_lock();
 	peer = rcu_dereference(nk->peer);
@@ -85,15 +87,22 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev)
 	case NETKIT_PASS:
 		skb->protocol = eth_type_trans(skb, skb->dev);
 		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
-		__netif_rx(skb);
+		if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) {
+			dev_sw_netstats_tx_add(dev, 1, len);
+			dev_sw_netstats_rx_add(peer, len);
+		} else {
+			goto drop_stats;
+		}
 		break;
 	case NETKIT_REDIRECT:
+		dev_sw_netstats_tx_add(dev, 1, len);
 		skb_do_redirect(skb);
 		break;
 	case NETKIT_DROP:
 	default:
 drop:
 		kfree_skb(skb);
+drop_stats:
 		dev_core_stats_tx_dropped_inc(dev);
 		ret_dev = NET_XMIT_DROP;
 		break;
@@ -169,11 +178,18 @@ out:
 	rcu_read_unlock();
 }
 
-static struct net_device *netkit_peer_dev(struct net_device *dev)
+INDIRECT_CALLABLE_SCOPE struct net_device *netkit_peer_dev(struct net_device *dev)
 {
 	return rcu_dereference(netkit_priv(dev)->peer);
 }
 
+static void netkit_get_stats(struct net_device *dev,
+			     struct rtnl_link_stats64 *stats)
+{
+	dev_fetch_sw_netstats(stats, dev->tstats);
+	stats->tx_dropped = DEV_STATS_READ(dev, tx_dropped);
+}
+
 static void netkit_uninit(struct net_device *dev);
 
 static const struct net_device_ops netkit_netdev_ops = {
@@ -184,6 +200,7 @@ static const struct net_device_ops netkit_netdev_ops = {
 	.ndo_set_rx_headroom	= netkit_set_headroom,
 	.ndo_get_iflink		= netkit_get_iflink,
 	.ndo_get_peer_dev	= netkit_peer_dev,
+	.ndo_get_stats64	= netkit_get_stats,
 	.ndo_uninit		= netkit_uninit,
 	.ndo_features_check	= passthru_features_check,
 };
@@ -218,6 +235,7 @@ static void netkit_setup(struct net_device *dev)
 
 	ether_setup(dev);
 	dev->max_mtu = ETH_MAX_MTU;
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 
 	dev->flags |= IFF_NOARP;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
@@ -833,6 +851,12 @@ static int netkit_change_link(struct net_device *dev, struct nlattr *tb[],
 		return -EACCES;
 	}
 
+	if (data[IFLA_NETKIT_PEER_INFO]) {
+		NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_PEER_INFO],
+				    "netkit peer info cannot be changed after device creation");
+		return -EINVAL;
+	}
+
 	if (data[IFLA_NETKIT_POLICY]) {
 		attr = data[IFLA_NETKIT_POLICY];
 		policy = nla_get_u32(attr);
diff --git a/drivers/net/phy/bcm-phy-ptp.c b/drivers/net/phy/bcm-phy-ptp.c
index ef00d6163061fa..cb4b91af5e1733 100644
--- a/drivers/net/phy/bcm-phy-ptp.c
+++ b/drivers/net/phy/bcm-phy-ptp.c
@@ -942,3 +942,4 @@ struct bcm_ptp_private *bcm_ptp_probe(struct phy_device *phydev)
 EXPORT_SYMBOL_GPL(bcm_ptp_probe);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Broadcom PHY PTP driver");
diff --git a/drivers/net/phy/bcm87xx.c b/drivers/net/phy/bcm87xx.c
index cc28581076682f..e81404bf899474 100644
--- a/drivers/net/phy/bcm87xx.c
+++ b/drivers/net/phy/bcm87xx.c
@@ -223,3 +223,4 @@ static struct phy_driver bcm87xx_driver[] = {
 module_phy_driver(bcm87xx_driver);
 
 MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Broadcom BCM87xx PHY driver");
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 2ce74593d6e4a1..a42df2c1bd043c 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1548,7 +1548,8 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 		goto error;
 
 	phy_resume(phydev);
-	phy_led_triggers_register(phydev);
+	if (!phydev->is_on_sfp_module)
+		phy_led_triggers_register(phydev);
 
 	/**
 	 * If the external phy used by current mac interface is managed by
@@ -1817,7 +1818,8 @@ void phy_detach(struct phy_device *phydev)
 	}
 	phydev->phylink = NULL;
 
-	phy_led_triggers_unregister(phydev);
+	if (!phydev->is_on_sfp_module)
+		phy_led_triggers_unregister(phydev);
 
 	if (phydev->mdio.dev.driver)
 		module_put(phydev->mdio.dev.driver->owner);
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 6712883498bbe9..25c19496a33616 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1616,6 +1616,7 @@ struct phylink *phylink_create(struct phylink_config *config,
 	pl->config = config;
 	if (config->type == PHYLINK_NETDEV) {
 		pl->netdev = to_net_dev(config->dev);
+		netif_carrier_off(pl->netdev);
 	} else if (config->type == PHYLINK_DEV) {
 		pl->dev = config->dev;
 	} else {
@@ -3726,3 +3727,4 @@ static int __init phylink_init(void)
 module_init(phylink_init);
 
 MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("phylink models the MAC to optional PHY connection");
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index b8c0961daf5317..5468bd209fab87 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -3153,3 +3153,4 @@ module_exit(sfp_exit);
 MODULE_ALIAS("platform:sfp");
 MODULE_AUTHOR("Russell King");
 MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("SFP cage support");
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index a9beacd552cf82..0193af2d31c9bc 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -570,8 +570,8 @@ static struct bpf_prog *get_filter(struct sock_fprog *uprog)
 
 	/* uprog->len is unsigned short, so no overflow here */
 	fprog.len = uprog->len;
-	fprog.filter = memdup_user(uprog->filter,
-				   uprog->len * sizeof(struct sock_filter));
+	fprog.filter = memdup_array_user(uprog->filter,
+					 uprog->len, sizeof(struct sock_filter));
 	if (IS_ERR(fprog.filter))
 		return ERR_CAST(fprog.filter);
 
diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c
index ebcdffdf4f0e01..52d05ce4a28198 100644
--- a/drivers/net/ppp/ppp_synctty.c
+++ b/drivers/net/ppp/ppp_synctty.c
@@ -453,6 +453,10 @@ ppp_sync_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg)
 	case PPPIOCSMRU:
 		if (get_user(val, (int __user *) argp))
 			break;
+		if (val > U16_MAX) {
+			err = -EINVAL;
+			break;
+		}
 		if (val < PPP_MRU)
 			val = PPP_MRU;
 		ap->mru = val;
@@ -687,7 +691,7 @@ ppp_sync_input(struct syncppp *ap, const u8 *buf, const u8 *flags, int count)
 
 	/* strip address/control field if present */
 	p = skb->data;
-	if (p[0] == PPP_ALLSTATIONS && p[1] == PPP_UI) {
+	if (skb->len >= 2 && p[0] == PPP_ALLSTATIONS && p[1] == PPP_UI) {
 		/* chop off address/control */
 		if (skb->len < 3)
 			goto err;
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 508d9a392ab182..f575f225d41789 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -281,8 +281,10 @@ static int __team_options_register(struct team *team,
 	return 0;
 
 inst_rollback:
-	for (i--; i >= 0; i--)
+	for (i--; i >= 0; i--) {
 		__team_option_inst_del_option(team, dst_opts[i]);
+		list_del(&dst_opts[i]->list);
+	}
 
 	i = option_count;
 alloc_rollback:
diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index a017e9de2119d5..7b8afa589a53c4 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -1079,17 +1079,17 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	u16 pkt_count = 0;
 	u64 desc_hdr = 0;
 	u16 vlan_tag = 0;
-	u32 skb_len = 0;
+	u32 skb_len;
 
 	if (!skb)
 		goto err;
 
-	if (skb->len == 0)
+	skb_len = skb->len;
+	if (skb_len < sizeof(desc_hdr))
 		goto err;
 
-	skb_len = skb->len;
 	/* RX Descriptor Header */
-	skb_trim(skb, skb->len - sizeof(desc_hdr));
+	skb_trim(skb, skb_len - sizeof(desc_hdr));
 	desc_hdr = le64_to_cpup((u64 *)skb_tail_pointer(skb));
 
 	/* Check these packets */
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index aff39bf3161ded..5a1bf42ce15668 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -173,6 +173,7 @@ struct ax88179_data {
 	u8 in_pm;
 	u32 wol_supported;
 	u32 wolopts;
+	u8 disconnecting;
 };
 
 struct ax88179_int_data {
@@ -208,6 +209,7 @@ static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
 {
 	int ret;
 	int (*fn)(struct usbnet *, u8, u8, u16, u16, void *, u16);
+	struct ax88179_data *ax179_data = dev->driver_priv;
 
 	BUG_ON(!dev);
 
@@ -219,7 +221,7 @@ static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
 	ret = fn(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
 		 value, index, data, size);
 
-	if (unlikely(ret < 0))
+	if (unlikely((ret < 0) && !(ret == -ENODEV && ax179_data->disconnecting)))
 		netdev_warn(dev->net, "Failed to read reg index 0x%04x: %d\n",
 			    index, ret);
 
@@ -231,6 +233,7 @@ static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
 {
 	int ret;
 	int (*fn)(struct usbnet *, u8, u8, u16, u16, const void *, u16);
+	struct ax88179_data *ax179_data = dev->driver_priv;
 
 	BUG_ON(!dev);
 
@@ -242,7 +245,7 @@ static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
 	ret = fn(dev, cmd, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
 		 value, index, data, size);
 
-	if (unlikely(ret < 0))
+	if (unlikely((ret < 0) && !(ret == -ENODEV && ax179_data->disconnecting)))
 		netdev_warn(dev->net, "Failed to write reg index 0x%04x: %d\n",
 			    index, ret);
 
@@ -492,6 +495,20 @@ static int ax88179_resume(struct usb_interface *intf)
 	return usbnet_resume(intf);
 }
 
+static void ax88179_disconnect(struct usb_interface *intf)
+{
+	struct usbnet *dev = usb_get_intfdata(intf);
+	struct ax88179_data *ax179_data;
+
+	if (!dev)
+		return;
+
+	ax179_data = dev->driver_priv;
+	ax179_data->disconnecting = 1;
+
+	usbnet_disconnect(intf);
+}
+
 static void
 ax88179_get_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo)
 {
@@ -1583,11 +1600,11 @@ static int ax88179_reset(struct usbnet *dev)
 
 	*tmp16 = AX_PHYPWR_RSTCTL_IPRL;
 	ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_PHYPWR_RSTCTL, 2, 2, tmp16);
-	msleep(200);
+	msleep(500);
 
 	*tmp = AX_CLK_SELECT_ACS | AX_CLK_SELECT_BCS;
 	ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_CLK_SELECT, 1, 1, tmp);
-	msleep(100);
+	msleep(200);
 
 	/* Ethernet PHY Auto Detach*/
 	ax88179_auto_detach(dev);
@@ -1906,7 +1923,7 @@ static struct usb_driver ax88179_178a_driver = {
 	.suspend =	ax88179_suspend,
 	.resume =	ax88179_resume,
 	.reset_resume =	ax88179_resume,
-	.disconnect =	usbnet_disconnect,
+	.disconnect =	ax88179_disconnect,
 	.supports_autosuspend = 1,
 	.disable_hub_initiated_lpm = 1,
 };
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 344af3c5c83668..e2e181378f4124 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1289,6 +1289,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x0168, 4)},
 	{QMI_FIXED_INTF(0x19d2, 0x0176, 3)},
 	{QMI_FIXED_INTF(0x19d2, 0x0178, 3)},
+	{QMI_FIXED_INTF(0x19d2, 0x0189, 4)},    /* ZTE MF290 */
 	{QMI_FIXED_INTF(0x19d2, 0x0191, 4)},	/* ZTE EuFi890 */
 	{QMI_FIXED_INTF(0x19d2, 0x0199, 1)},	/* ZTE MF820S */
 	{QMI_FIXED_INTF(0x19d2, 0x0200, 1)},
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 2c5c1e91ded613..9bf2140fd0a1f4 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3000,6 +3000,8 @@ static void rtl8152_nic_reset(struct r8152 *tp)
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CR, CR_RST);
 
 		for (i = 0; i < 1000; i++) {
+			if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+				break;
 			if (!(ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CR) & CR_RST))
 				break;
 			usleep_range(100, 400);
@@ -3329,6 +3331,8 @@ static void rtl_disable(struct r8152 *tp)
 	rxdy_gated_en(tp, true);
 
 	for (i = 0; i < 1000; i++) {
+		if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+			break;
 		ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
 		if ((ocp_data & FIFO_EMPTY) == FIFO_EMPTY)
 			break;
@@ -3336,6 +3340,8 @@ static void rtl_disable(struct r8152 *tp)
 	}
 
 	for (i = 0; i < 1000; i++) {
+		if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+			break;
 		if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_TCR0) & TCR0_TX_EMPTY)
 			break;
 		usleep_range(1000, 2000);
@@ -5499,6 +5505,8 @@ static void wait_oob_link_list_ready(struct r8152 *tp)
 	int i;
 
 	for (i = 0; i < 1000; i++) {
+		if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+			break;
 		ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
 		if (ocp_data & LINK_LIST_READY)
 			break;
@@ -5513,6 +5521,8 @@ static void r8156b_wait_loading_flash(struct r8152 *tp)
 		int i;
 
 		for (i = 0; i < 100; i++) {
+			if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+				break;
 			if (ocp_read_word(tp, MCU_TYPE_USB, USB_GPHY_CTRL) & GPHY_PATCH_DONE)
 				break;
 			usleep_range(1000, 2000);
@@ -5635,6 +5645,8 @@ static int r8153_pre_firmware_1(struct r8152 *tp)
 	for (i = 0; i < 104; i++) {
 		u32 ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_WDT1_CTRL);
 
+		if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+			return -ENODEV;
 		if (!(ocp_data & WTD1_EN))
 			break;
 		usleep_range(1000, 2000);
@@ -5791,6 +5803,8 @@ static void r8153_aldps_en(struct r8152 *tp, bool enable)
 		data &= ~EN_ALDPS;
 		ocp_reg_write(tp, OCP_POWER_CFG, data);
 		for (i = 0; i < 20; i++) {
+			if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+				return;
 			usleep_range(1000, 2000);
 			if (ocp_read_word(tp, MCU_TYPE_PLA, 0xe000) & 0x0100)
 				break;
@@ -8397,6 +8411,8 @@ static int rtl8152_pre_reset(struct usb_interface *intf)
 	struct r8152 *tp = usb_get_intfdata(intf);
 	struct net_device *netdev;
 
+	rtnl_lock();
+
 	if (!tp || !test_bit(PROBED_WITH_NO_ERRORS, &tp->flags))
 		return 0;
 
@@ -8428,20 +8444,17 @@ static int rtl8152_post_reset(struct usb_interface *intf)
 	struct sockaddr sa;
 
 	if (!tp || !test_bit(PROBED_WITH_NO_ERRORS, &tp->flags))
-		return 0;
+		goto exit;
 
 	rtl_set_accessible(tp);
 
 	/* reset the MAC address in case of policy change */
-	if (determine_ethernet_addr(tp, &sa) >= 0) {
-		rtnl_lock();
+	if (determine_ethernet_addr(tp, &sa) >= 0)
 		dev_set_mac_address (tp->netdev, &sa, NULL);
-		rtnl_unlock();
-	}
 
 	netdev = tp->netdev;
 	if (!netif_running(netdev))
-		return 0;
+		goto exit;
 
 	set_bit(WORK_ENABLE, &tp->flags);
 	if (netif_carrier_ok(netdev)) {
@@ -8460,6 +8473,8 @@ static int rtl8152_post_reset(struct usb_interface *intf)
 	if (!list_empty(&tp->rx_done))
 		napi_schedule(&tp->napi);
 
+exit:
+	rtnl_unlock();
 	return 0;
 }
 
@@ -10034,6 +10049,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{ USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff) },
 	{ USB_DEVICE(VENDOR_ID_TPLINK,  0x0601) },
 	{ USB_DEVICE(VENDOR_ID_DLINK,   0xb301) },
+	{ USB_DEVICE(VENDOR_ID_ASUS,    0x1976) },
 	{}
 };
 
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 9980517ed8b0d1..977861c46b1fe1 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -236,8 +236,8 @@ static void veth_get_ethtool_stats(struct net_device *dev,
 				data[tx_idx + j] += *(u64 *)(base + offset);
 			}
 		} while (u64_stats_fetch_retry(&rq_stats->syncp, start));
-		pp_idx = tx_idx + VETH_TQ_STATS_LEN;
 	}
+	pp_idx = idx + dev->real_num_tx_queues * VETH_TQ_STATS_LEN;
 
 page_pool_stats:
 	veth_get_page_pool_stats(dev, &data[pp_idx]);
@@ -373,7 +373,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_tx_timestamp(skb);
 	if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) {
 		if (!use_napi)
-			dev_lstats_add(dev, length);
+			dev_sw_netstats_tx_add(dev, 1, length);
 		else
 			__veth_xdp_flush(rq);
 	} else {
@@ -387,14 +387,6 @@ drop:
 	return ret;
 }
 
-static u64 veth_stats_tx(struct net_device *dev, u64 *packets, u64 *bytes)
-{
-	struct veth_priv *priv = netdev_priv(dev);
-
-	dev_lstats_read(dev, packets, bytes);
-	return atomic64_read(&priv->dropped);
-}
-
 static void veth_stats_rx(struct veth_stats *result, struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
@@ -432,24 +424,24 @@ static void veth_get_stats64(struct net_device *dev,
 	struct veth_priv *priv = netdev_priv(dev);
 	struct net_device *peer;
 	struct veth_stats rx;
-	u64 packets, bytes;
 
-	tot->tx_dropped = veth_stats_tx(dev, &packets, &bytes);
-	tot->tx_bytes = bytes;
-	tot->tx_packets = packets;
+	tot->tx_dropped = atomic64_read(&priv->dropped);
+	dev_fetch_sw_netstats(tot, dev->tstats);
 
 	veth_stats_rx(&rx, dev);
 	tot->tx_dropped += rx.xdp_tx_err;
 	tot->rx_dropped = rx.rx_drops + rx.peer_tq_xdp_xmit_err;
-	tot->rx_bytes = rx.xdp_bytes;
-	tot->rx_packets = rx.xdp_packets;
+	tot->rx_bytes += rx.xdp_bytes;
+	tot->rx_packets += rx.xdp_packets;
 
 	rcu_read_lock();
 	peer = rcu_dereference(priv->peer);
 	if (peer) {
-		veth_stats_tx(peer, &packets, &bytes);
-		tot->rx_bytes += bytes;
-		tot->rx_packets += packets;
+		struct rtnl_link_stats64 tot_peer = {};
+
+		dev_fetch_sw_netstats(&tot_peer, peer->tstats);
+		tot->rx_bytes += tot_peer.tx_bytes;
+		tot->rx_packets += tot_peer.tx_packets;
 
 		veth_stats_rx(&rx, peer);
 		tot->tx_dropped += rx.peer_tq_xdp_xmit_err;
@@ -798,7 +790,8 @@ static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq,
 
 			skb_add_rx_frag(nskb, i, page, page_offset, size,
 					truesize);
-			if (skb_copy_bits(skb, off, page_address(page),
+			if (skb_copy_bits(skb, off,
+					  page_address(page) + page_offset,
 					  size)) {
 				consume_skb(nskb);
 				goto drop;
@@ -1506,25 +1499,12 @@ static void veth_free_queues(struct net_device *dev)
 
 static int veth_dev_init(struct net_device *dev)
 {
-	int err;
-
-	dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
-	if (!dev->lstats)
-		return -ENOMEM;
-
-	err = veth_alloc_queues(dev);
-	if (err) {
-		free_percpu(dev->lstats);
-		return err;
-	}
-
-	return 0;
+	return veth_alloc_queues(dev);
 }
 
 static void veth_dev_free(struct net_device *dev)
 {
 	veth_free_queues(dev);
-	free_percpu(dev->lstats);
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -1796,6 +1776,7 @@ static void veth_setup(struct net_device *dev)
 			       NETIF_F_HW_VLAN_STAG_RX);
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = veth_dev_free;
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 	dev->max_mtu = ETH_MAX_MTU;
 
 	dev->hw_features = VETH_FEATURES;
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index db766941b78f67..bb95ce43cd97d3 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -121,22 +121,12 @@ struct net_vrf {
 	int			ifindex;
 };
 
-struct pcpu_dstats {
-	u64			tx_pkts;
-	u64			tx_bytes;
-	u64			tx_drps;
-	u64			rx_pkts;
-	u64			rx_bytes;
-	u64			rx_drps;
-	struct u64_stats_sync	syncp;
-};
-
 static void vrf_rx_stats(struct net_device *dev, int len)
 {
 	struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
 
 	u64_stats_update_begin(&dstats->syncp);
-	dstats->rx_pkts++;
+	dstats->rx_packets++;
 	dstats->rx_bytes += len;
 	u64_stats_update_end(&dstats->syncp);
 }
@@ -161,10 +151,10 @@ static void vrf_get_stats64(struct net_device *dev,
 		do {
 			start = u64_stats_fetch_begin(&dstats->syncp);
 			tbytes = dstats->tx_bytes;
-			tpkts = dstats->tx_pkts;
-			tdrops = dstats->tx_drps;
+			tpkts = dstats->tx_packets;
+			tdrops = dstats->tx_drops;
 			rbytes = dstats->rx_bytes;
-			rpkts = dstats->rx_pkts;
+			rpkts = dstats->rx_packets;
 		} while (u64_stats_fetch_retry(&dstats->syncp, start));
 		stats->tx_bytes += tbytes;
 		stats->tx_packets += tpkts;
@@ -421,7 +411,7 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev,
 	if (likely(__netif_rx(skb) == NET_RX_SUCCESS))
 		vrf_rx_stats(dev, len);
 	else
-		this_cpu_inc(dev->dstats->rx_drps);
+		this_cpu_inc(dev->dstats->rx_drops);
 
 	return NETDEV_TX_OK;
 }
@@ -616,11 +606,11 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 		struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
 
 		u64_stats_update_begin(&dstats->syncp);
-		dstats->tx_pkts++;
+		dstats->tx_packets++;
 		dstats->tx_bytes += len;
 		u64_stats_update_end(&dstats->syncp);
 	} else {
-		this_cpu_inc(dev->dstats->tx_drps);
+		this_cpu_inc(dev->dstats->tx_drops);
 	}
 
 	return ret;
@@ -1174,22 +1164,15 @@ static void vrf_dev_uninit(struct net_device *dev)
 
 	vrf_rtable_release(dev, vrf);
 	vrf_rt6_release(dev, vrf);
-
-	free_percpu(dev->dstats);
-	dev->dstats = NULL;
 }
 
 static int vrf_dev_init(struct net_device *dev)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
 
-	dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats);
-	if (!dev->dstats)
-		goto out_nomem;
-
 	/* create the default dst which points back to us */
 	if (vrf_rtable_create(dev) != 0)
-		goto out_stats;
+		goto out_nomem;
 
 	if (vrf_rt6_create(dev) != 0)
 		goto out_rth;
@@ -1203,9 +1186,6 @@ static int vrf_dev_init(struct net_device *dev)
 
 out_rth:
 	vrf_rtable_release(dev, vrf);
-out_stats:
-	free_percpu(dev->dstats);
-	dev->dstats = NULL;
 out_nomem:
 	return -ENOMEM;
 }
@@ -1704,6 +1684,8 @@ static void vrf_setup(struct net_device *dev)
 	dev->min_mtu = IPV6_MIN_MTU;
 	dev->max_mtu = IP6_MAX_MTU;
 	dev->mtu = dev->max_mtu;
+
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS;
 }
 
 static int vrf_validate(struct nlattr *tb[], struct nlattr *data[],
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 258dcc1039216f..deb9636b0ecf8f 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -210,7 +210,7 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 	while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) {
 		dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue));
-		++dev->stats.tx_dropped;
+		DEV_STATS_INC(dev, tx_dropped);
 	}
 	skb_queue_splice_tail(&packets, &peer->staged_packet_queue);
 	spin_unlock_bh(&peer->staged_packet_queue.lock);
@@ -228,7 +228,7 @@ err_icmp:
 	else if (skb->protocol == htons(ETH_P_IPV6))
 		icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
 err:
-	++dev->stats.tx_errors;
+	DEV_STATS_INC(dev, tx_errors);
 	kfree_skb(skb);
 	return ret;
 }
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 0b3f0c84355095..a176653c88616b 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -416,20 +416,20 @@ dishonest_packet_peer:
 	net_dbg_skb_ratelimited("%s: Packet has unallowed src IP (%pISc) from peer %llu (%pISpfsc)\n",
 				dev->name, skb, peer->internal_id,
 				&peer->endpoint.addr);
-	++dev->stats.rx_errors;
-	++dev->stats.rx_frame_errors;
+	DEV_STATS_INC(dev, rx_errors);
+	DEV_STATS_INC(dev, rx_frame_errors);
 	goto packet_processed;
 dishonest_packet_type:
 	net_dbg_ratelimited("%s: Packet is neither ipv4 nor ipv6 from peer %llu (%pISpfsc)\n",
 			    dev->name, peer->internal_id, &peer->endpoint.addr);
-	++dev->stats.rx_errors;
-	++dev->stats.rx_frame_errors;
+	DEV_STATS_INC(dev, rx_errors);
+	DEV_STATS_INC(dev, rx_frame_errors);
 	goto packet_processed;
 dishonest_packet_size:
 	net_dbg_ratelimited("%s: Packet has incorrect size from peer %llu (%pISpfsc)\n",
 			    dev->name, peer->internal_id, &peer->endpoint.addr);
-	++dev->stats.rx_errors;
-	++dev->stats.rx_length_errors;
+	DEV_STATS_INC(dev, rx_errors);
+	DEV_STATS_INC(dev, rx_length_errors);
 	goto packet_processed;
 packet_processed:
 	dev_kfree_skb(skb);
diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c
index 95c853b59e1dae..0d48e0f4a1ba3e 100644
--- a/drivers/net/wireguard/send.c
+++ b/drivers/net/wireguard/send.c
@@ -333,7 +333,8 @@ err:
 void wg_packet_purge_staged_packets(struct wg_peer *peer)
 {
 	spin_lock_bh(&peer->staged_packet_queue.lock);
-	peer->device->dev->stats.tx_dropped += peer->staged_packet_queue.qlen;
+	DEV_STATS_ADD(peer->device->dev, tx_dropped,
+		      peer->staged_packet_queue.qlen);
 	__skb_queue_purge(&peer->staged_packet_queue);
 	spin_unlock_bh(&peer->staged_packet_queue.lock);
 }
diff --git a/drivers/net/wireless/ath/ath9k/Kconfig b/drivers/net/wireless/ath/ath9k/Kconfig
index e150d82eddb6c7..0c47be06c153be 100644
--- a/drivers/net/wireless/ath/ath9k/Kconfig
+++ b/drivers/net/wireless/ath/ath9k/Kconfig
@@ -57,8 +57,7 @@ config ATH9K_AHB
 
 config ATH9K_DEBUGFS
 	bool "Atheros ath9k debugging"
-	depends on ATH9K && DEBUG_FS
-	select MAC80211_DEBUGFS
+	depends on ATH9K && DEBUG_FS && MAC80211_DEBUGFS
 	select ATH9K_COMMON_DEBUG
 	help
 	  Say Y, if you need access to ath9k's statistics for
@@ -70,7 +69,6 @@ config ATH9K_DEBUGFS
 config ATH9K_STATION_STATISTICS
 	bool "Detailed station statistics"
 	depends on ATH9K && ATH9K_DEBUGFS && DEBUG_FS
-	select MAC80211_DEBUGFS
 	default n
 	help
 	  This option enables detailed statistics for association stations.
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
index ca5e4fbcf8ce53..6af606e5da657e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
@@ -707,8 +707,10 @@ int iwl_mvm_mld_add_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			rcu_dereference_protected(mvm_sta->link[link_id],
 						  lockdep_is_held(&mvm->mutex));
 
-		if (WARN_ON(!link_conf || !mvm_link_sta))
+		if (WARN_ON(!link_conf || !mvm_link_sta)) {
+			ret = -EINVAL;
 			goto err;
+		}
 
 		ret = iwl_mvm_mld_cfg_sta(mvm, sta, vif, link_sta, link_conf,
 					  mvm_link_sta);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index fef86a8b416393..1627b2f819db1d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -550,9 +550,9 @@ static const struct iwl_hcmd_names iwl_mvm_system_names[] = {
 	HCMD_NAME(RFI_CONFIG_CMD),
 	HCMD_NAME(RFI_GET_FREQ_TABLE_CMD),
 	HCMD_NAME(SYSTEM_FEATURES_CONTROL_CMD),
-	HCMD_NAME(RFI_DEACTIVATE_NOTIF),
 	HCMD_NAME(SYSTEM_STATISTICS_CMD),
 	HCMD_NAME(SYSTEM_STATISTICS_END_NOTIF),
+	HCMD_NAME(RFI_DEACTIVATE_NOTIF),
 };
 
 /* Please keep this array *SORTED* by hex value.
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 146bc7bd14fbc0..bc6a9f861711fd 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1385,7 +1385,7 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 		 * if it is true then one of the handlers took the page.
 		 */
 
-		if (reclaim) {
+		if (reclaim && txq) {
 			u16 sequence = le16_to_cpu(pkt->hdr.sequence);
 			int index = SEQ_TO_INDEX(sequence);
 			int cmd_index = iwl_txq_get_cmd_index(txq, index);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index a468e5efeecd4f..92253260f56832 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -3106,7 +3106,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans,
 	struct iwl_rxq *rxq = &trans_pcie->rxq[0];
 	u32 i, r, j, rb_len = 0;
 
-	spin_lock(&rxq->lock);
+	spin_lock_bh(&rxq->lock);
 
 	r = iwl_get_closed_rb_stts(trans, rxq);
 
@@ -3130,7 +3130,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans,
 		*data = iwl_fw_error_next_data(*data);
 	}
 
-	spin_unlock(&rxq->lock);
+	spin_unlock_bh(&rxq->lock);
 
 	return rb_len;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 511fe7e6e744b3..68ad915203aa54 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -783,7 +783,7 @@ mt76_dma_rx_reset(struct mt76_dev *dev, enum mt76_rxq_id qid)
 
 static void
 mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data,
-		  int len, bool more, u32 info)
+		  int len, bool more, u32 info, bool allow_direct)
 {
 	struct sk_buff *skb = q->rx_head;
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
@@ -795,7 +795,7 @@ mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data,
 
 		skb_add_rx_frag(skb, nr_frags, page, offset, len, q->buf_size);
 	} else {
-		mt76_put_page_pool_buf(data, true);
+		mt76_put_page_pool_buf(data, allow_direct);
 	}
 
 	if (more)
@@ -815,6 +815,7 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget)
 	struct sk_buff *skb;
 	unsigned char *data;
 	bool check_ddone = false;
+	bool allow_direct = !mt76_queue_is_wed_rx(q);
 	bool more;
 
 	if (IS_ENABLED(CONFIG_NET_MEDIATEK_SOC_WED) &&
@@ -855,7 +856,8 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget)
 		}
 
 		if (q->rx_head) {
-			mt76_add_fragment(dev, q, data, len, more, info);
+			mt76_add_fragment(dev, q, data, len, more, info,
+					  allow_direct);
 			continue;
 		}
 
@@ -884,7 +886,7 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget)
 		continue;
 
 free_frag:
-		mt76_put_page_pool_buf(data, true);
+		mt76_put_page_pool_buf(data, allow_direct);
 	}
 
 	mt76_dma_rx_fill(dev, q, true);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index 63f3d4a5c9aa6e..2cc2d2788f8312 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -375,6 +375,7 @@ static int mt7921_load_clc(struct mt792x_dev *dev, const char *fw_name)
 	int ret, i, len, offset = 0;
 	u8 *clc_base = NULL, hw_encap = 0;
 
+	dev->phy.clc_chan_conf = 0xff;
 	if (mt7921_disable_clc ||
 	    mt76_is_usb(&dev->mt76))
 		return 0;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 15c2fb0bcb1b98..aa918b9b0469f8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -14,7 +14,7 @@
 static void
 mt7925_init_he_caps(struct mt792x_phy *phy, enum nl80211_band band,
 		    struct ieee80211_sband_iftype_data *data,
-			enum nl80211_iftype iftype)
+		    enum nl80211_iftype iftype)
 {
 	struct ieee80211_sta_he_cap *he_cap = &data->he_cap;
 	struct ieee80211_he_cap_elem *he_cap_elem = &he_cap->he_cap_elem;
@@ -53,7 +53,7 @@ mt7925_init_he_caps(struct mt792x_phy *phy, enum nl80211_band band,
 		IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO |
 		IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO;
 
-	switch (i) {
+	switch (iftype) {
 	case NL80211_IFTYPE_AP:
 		he_cap_elem->mac_cap_info[2] |=
 			IEEE80211_HE_MAC_CAP2_BSR;
diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c
index b027be0b0b6ff7..590b038e449e5c 100644
--- a/drivers/nfc/virtual_ncidev.c
+++ b/drivers/nfc/virtual_ncidev.c
@@ -26,10 +26,14 @@ struct virtual_nci_dev {
 	struct mutex mtx;
 	struct sk_buff *send_buff;
 	struct wait_queue_head wq;
+	bool running;
 };
 
 static int virtual_nci_open(struct nci_dev *ndev)
 {
+	struct virtual_nci_dev *vdev = nci_get_drvdata(ndev);
+
+	vdev->running = true;
 	return 0;
 }
 
@@ -40,6 +44,7 @@ static int virtual_nci_close(struct nci_dev *ndev)
 	mutex_lock(&vdev->mtx);
 	kfree_skb(vdev->send_buff);
 	vdev->send_buff = NULL;
+	vdev->running = false;
 	mutex_unlock(&vdev->mtx);
 
 	return 0;
@@ -50,7 +55,7 @@ static int virtual_nci_send(struct nci_dev *ndev, struct sk_buff *skb)
 	struct virtual_nci_dev *vdev = nci_get_drvdata(ndev);
 
 	mutex_lock(&vdev->mtx);
-	if (vdev->send_buff) {
+	if (vdev->send_buff || !vdev->running) {
 		mutex_unlock(&vdev->mtx);
 		kfree_skb(skb);
 		return -1;
diff --git a/drivers/nvme/Makefile b/drivers/nvme/Makefile
index eedca8c720983c..74f59ceed3d5ae 100644
--- a/drivers/nvme/Makefile
+++ b/drivers/nvme/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-obj-$(CONFIG_NVME_COMMON)		+= common/
+obj-y		+= common/
 obj-y		+= host/
 obj-y		+= target/
diff --git a/drivers/nvme/common/Kconfig b/drivers/nvme/common/Kconfig
index 06c8df00d1e214..244432e0b73d8e 100644
--- a/drivers/nvme/common/Kconfig
+++ b/drivers/nvme/common/Kconfig
@@ -1,14 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-config NVME_COMMON
-       tristate
-
 config NVME_KEYRING
-       bool
+       tristate
        select KEYS
 
 config NVME_AUTH
-	bool
+	tristate
 	select CRYPTO
 	select CRYPTO_HMAC
 	select CRYPTO_SHA256
diff --git a/drivers/nvme/common/Makefile b/drivers/nvme/common/Makefile
index 0cbd0b0b8d4998..681514cf2e2f50 100644
--- a/drivers/nvme/common/Makefile
+++ b/drivers/nvme/common/Makefile
@@ -2,7 +2,8 @@
 
 ccflags-y			+= -I$(src)
 
-obj-$(CONFIG_NVME_COMMON)	+= nvme-common.o
+obj-$(CONFIG_NVME_AUTH)		+= nvme-auth.o
+obj-$(CONFIG_NVME_KEYRING)	+= nvme-keyring.o
 
-nvme-common-$(CONFIG_NVME_AUTH)	+= auth.o
-nvme-common-$(CONFIG_NVME_KEYRING) += keyring.o
+nvme-auth-y			+= auth.o
+nvme-keyring-y			+= keyring.o
diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c
index a8e87dfbeab2a4..a23ab5c968b945 100644
--- a/drivers/nvme/common/auth.c
+++ b/drivers/nvme/common/auth.c
@@ -341,7 +341,6 @@ int nvme_auth_augmented_challenge(u8 hmac_id, u8 *skey, size_t skey_len,
 		u8 *challenge, u8 *aug, size_t hlen)
 {
 	struct crypto_shash *tfm;
-	struct shash_desc *desc;
 	u8 *hashed_key;
 	const char *hmac_name;
 	int ret;
@@ -369,29 +368,11 @@ int nvme_auth_augmented_challenge(u8 hmac_id, u8 *skey, size_t skey_len,
 		goto out_free_key;
 	}
 
-	desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm),
-		       GFP_KERNEL);
-	if (!desc) {
-		ret = -ENOMEM;
-		goto out_free_hash;
-	}
-	desc->tfm = tfm;
-
 	ret = crypto_shash_setkey(tfm, hashed_key, hlen);
 	if (ret)
-		goto out_free_desc;
-
-	ret = crypto_shash_init(desc);
-	if (ret)
-		goto out_free_desc;
-
-	ret = crypto_shash_update(desc, challenge, hlen);
-	if (ret)
-		goto out_free_desc;
+		goto out_free_hash;
 
-	ret = crypto_shash_final(desc, aug);
-out_free_desc:
-	kfree_sensitive(desc);
+	ret = crypto_shash_tfm_digest(tfm, challenge, hlen, aug);
 out_free_hash:
 	crypto_free_shash(tfm);
 out_free_key:
diff --git a/drivers/nvme/common/keyring.c b/drivers/nvme/common/keyring.c
index f8d9a208397b4d..ee341b83eebaf5 100644
--- a/drivers/nvme/common/keyring.c
+++ b/drivers/nvme/common/keyring.c
@@ -151,7 +151,7 @@ key_serial_t nvme_tls_psk_default(struct key *keyring,
 }
 EXPORT_SYMBOL_GPL(nvme_tls_psk_default);
 
-int nvme_keyring_init(void)
+static int __init nvme_keyring_init(void)
 {
 	int err;
 
@@ -171,12 +171,15 @@ int nvme_keyring_init(void)
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(nvme_keyring_init);
 
-void nvme_keyring_exit(void)
+static void __exit nvme_keyring_exit(void)
 {
 	unregister_key_type(&nvme_tls_psk_key_type);
 	key_revoke(nvme_keyring);
 	key_put(nvme_keyring);
 }
-EXPORT_SYMBOL_GPL(nvme_keyring_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Hannes Reinecke <hare@suse.de>");
+module_init(nvme_keyring_init);
+module_exit(nvme_keyring_exit);
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index 48f7d72de5e9a5..b309c8be720f47 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -95,7 +95,6 @@ config NVME_TCP
 config NVME_TCP_TLS
 	bool "NVMe over Fabrics TCP TLS encryption support"
 	depends on NVME_TCP
-	select NVME_COMMON
 	select NVME_KEYRING
 	select NET_HANDSHAKE
 	select KEYS
@@ -108,12 +107,12 @@ config NVME_TCP_TLS
 	  If unsure, say N.
 
 config NVME_HOST_AUTH
-	bool "NVM Express over Fabrics In-Band Authentication"
+	bool "NVMe over Fabrics In-Band Authentication in host side"
 	depends on NVME_CORE
-	select NVME_COMMON
 	select NVME_AUTH
 	help
-	  This provides support for NVMe over Fabrics In-Band Authentication.
+	  This provides support for NVMe over Fabrics In-Band Authentication in
+	  host side.
 
 	  If unsure, say N.
 
diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index eaefebb2a799a2..72c0525c75f503 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -29,6 +29,7 @@ struct nvme_dhchap_queue_context {
 	int error;
 	u32 s1;
 	u32 s2;
+	bool bi_directional;
 	u16 transaction;
 	u8 status;
 	u8 dhgroup_id;
@@ -312,17 +313,17 @@ static int nvme_auth_set_dhchap_reply_data(struct nvme_ctrl *ctrl,
 	data->dhvlen = cpu_to_le16(chap->host_key_len);
 	memcpy(data->rval, chap->response, chap->hash_len);
 	if (ctrl->ctrl_key) {
+		chap->bi_directional = true;
 		get_random_bytes(chap->c2, chap->hash_len);
 		data->cvalid = 1;
-		chap->s2 = nvme_auth_get_seqnum();
 		memcpy(data->rval + chap->hash_len, chap->c2,
 		       chap->hash_len);
 		dev_dbg(ctrl->device, "%s: qid %d ctrl challenge %*ph\n",
 			__func__, chap->qid, (int)chap->hash_len, chap->c2);
 	} else {
 		memset(chap->c2, 0, chap->hash_len);
-		chap->s2 = 0;
 	}
+	chap->s2 = nvme_auth_get_seqnum();
 	data->seqnum = cpu_to_le32(chap->s2);
 	if (chap->host_key_len) {
 		dev_dbg(ctrl->device, "%s: qid %d host public key %*ph\n",
@@ -339,10 +340,7 @@ static int nvme_auth_process_dhchap_success1(struct nvme_ctrl *ctrl,
 		struct nvme_dhchap_queue_context *chap)
 {
 	struct nvmf_auth_dhchap_success1_data *data = chap->buf;
-	size_t size = sizeof(*data);
-
-	if (chap->s2)
-		size += chap->hash_len;
+	size_t size = sizeof(*data) + chap->hash_len;
 
 	if (size > CHAP_BUF_SIZE) {
 		chap->status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_PAYLOAD;
@@ -663,6 +661,7 @@ static void nvme_auth_reset_dhchap(struct nvme_dhchap_queue_context *chap)
 	chap->error = 0;
 	chap->s1 = 0;
 	chap->s2 = 0;
+	chap->bi_directional = false;
 	chap->transaction = 0;
 	memset(chap->c1, 0, sizeof(chap->c1));
 	memset(chap->c2, 0, sizeof(chap->c2));
@@ -758,12 +757,11 @@ static void nvme_queue_auth_work(struct work_struct *work)
 		__func__, chap->qid);
 	mutex_lock(&ctrl->dhchap_auth_mutex);
 	ret = nvme_auth_dhchap_setup_host_response(ctrl, chap);
+	mutex_unlock(&ctrl->dhchap_auth_mutex);
 	if (ret) {
-		mutex_unlock(&ctrl->dhchap_auth_mutex);
 		chap->error = ret;
 		goto fail2;
 	}
-	mutex_unlock(&ctrl->dhchap_auth_mutex);
 
 	/* DH-HMAC-CHAP Step 3: send reply */
 	dev_dbg(ctrl->device, "%s: qid %d send reply\n",
@@ -825,7 +823,7 @@ static void nvme_queue_auth_work(struct work_struct *work)
 		goto fail2;
 	}
 
-	if (chap->s2) {
+	if (chap->bi_directional) {
 		/* DH-HMAC-CHAP Step 5: send success2 */
 		dev_dbg(ctrl->device, "%s: qid %d send success2\n",
 			__func__, chap->qid);
@@ -840,6 +838,8 @@ static void nvme_queue_auth_work(struct work_struct *work)
 	}
 
 fail2:
+	if (chap->status == 0)
+		chap->status = NVME_AUTH_DHCHAP_FAILURE_FAILED;
 	dev_dbg(ctrl->device, "%s: qid %d send failure2, status %x\n",
 		__func__, chap->qid, chap->status);
 	tl = nvme_auth_set_dhchap_failure2_data(ctrl, chap);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 62612f87aafa22..60f14019f98166 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -25,7 +25,6 @@
 #include "nvme.h"
 #include "fabrics.h"
 #include <linux/nvme-auth.h>
-#include <linux/nvme-keyring.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -132,7 +131,7 @@ void nvme_queue_scan(struct nvme_ctrl *ctrl)
 	/*
 	 * Only new queue scan work when admin and IO queues are both alive
 	 */
-	if (ctrl->state == NVME_CTRL_LIVE && ctrl->tagset)
+	if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE && ctrl->tagset)
 		queue_work(nvme_wq, &ctrl->scan_work);
 }
 
@@ -144,7 +143,7 @@ void nvme_queue_scan(struct nvme_ctrl *ctrl)
  */
 int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
 {
-	if (ctrl->state != NVME_CTRL_RESETTING)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_RESETTING)
 		return -EBUSY;
 	if (!queue_work(nvme_reset_wq, &ctrl->reset_work))
 		return -EBUSY;
@@ -157,7 +156,7 @@ static void nvme_failfast_work(struct work_struct *work)
 	struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
 			struct nvme_ctrl, failfast_work);
 
-	if (ctrl->state != NVME_CTRL_CONNECTING)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_CONNECTING)
 		return;
 
 	set_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
@@ -201,7 +200,7 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
 	ret = nvme_reset_ctrl(ctrl);
 	if (!ret) {
 		flush_work(&ctrl->reset_work);
-		if (ctrl->state != NVME_CTRL_LIVE)
+		if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 			ret = -ENETRESET;
 	}
 
@@ -500,7 +499,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 
 	spin_lock_irqsave(&ctrl->lock, flags);
 
-	old_state = ctrl->state;
+	old_state = nvme_ctrl_state(ctrl);
 	switch (new_state) {
 	case NVME_CTRL_LIVE:
 		switch (old_state) {
@@ -568,7 +567,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	}
 
 	if (changed) {
-		ctrl->state = new_state;
+		WRITE_ONCE(ctrl->state, new_state);
 		wake_up_all(&ctrl->state_wq);
 	}
 
@@ -576,11 +575,11 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	if (!changed)
 		return false;
 
-	if (ctrl->state == NVME_CTRL_LIVE) {
+	if (new_state == NVME_CTRL_LIVE) {
 		if (old_state == NVME_CTRL_CONNECTING)
 			nvme_stop_failfast_work(ctrl);
 		nvme_kick_requeue_lists(ctrl);
-	} else if (ctrl->state == NVME_CTRL_CONNECTING &&
+	} else if (new_state == NVME_CTRL_CONNECTING &&
 		old_state == NVME_CTRL_RESETTING) {
 		nvme_start_failfast_work(ctrl);
 	}
@@ -593,7 +592,7 @@ EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
  */
 static bool nvme_state_terminal(struct nvme_ctrl *ctrl)
 {
-	switch (ctrl->state) {
+	switch (nvme_ctrl_state(ctrl)) {
 	case NVME_CTRL_NEW:
 	case NVME_CTRL_LIVE:
 	case NVME_CTRL_RESETTING:
@@ -618,7 +617,7 @@ bool nvme_wait_reset(struct nvme_ctrl *ctrl)
 	wait_event(ctrl->state_wq,
 		   nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING) ||
 		   nvme_state_terminal(ctrl));
-	return ctrl->state == NVME_CTRL_RESETTING;
+	return nvme_ctrl_state(ctrl) == NVME_CTRL_RESETTING;
 }
 EXPORT_SYMBOL_GPL(nvme_wait_reset);
 
@@ -705,9 +704,11 @@ EXPORT_SYMBOL_GPL(nvme_init_request);
 blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 		struct request *rq)
 {
-	if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
-	    ctrl->state != NVME_CTRL_DELETING &&
-	    ctrl->state != NVME_CTRL_DEAD &&
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+	if (state != NVME_CTRL_DELETING_NOIO &&
+	    state != NVME_CTRL_DELETING &&
+	    state != NVME_CTRL_DEAD &&
 	    !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
 	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
 		return BLK_STS_RESOURCE;
@@ -737,7 +738,7 @@ bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		 * command, which is require to set the queue live in the
 		 * appropinquate states.
 		 */
-		switch (ctrl->state) {
+		switch (nvme_ctrl_state(ctrl)) {
 		case NVME_CTRL_CONNECTING:
 			if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) &&
 			    (req->cmd->fabrics.fctype == nvme_fabrics_type_connect ||
@@ -1193,8 +1194,16 @@ static unsigned long nvme_keep_alive_work_period(struct nvme_ctrl *ctrl)
 
 static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
 {
-	queue_delayed_work(nvme_wq, &ctrl->ka_work,
-			   nvme_keep_alive_work_period(ctrl));
+	unsigned long now = jiffies;
+	unsigned long delay = nvme_keep_alive_work_period(ctrl);
+	unsigned long ka_next_check_tm = ctrl->ka_last_check_time + delay;
+
+	if (time_after(now, ka_next_check_tm))
+		delay = 0;
+	else
+		delay = ka_next_check_tm - now;
+
+	queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
 }
 
 static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
@@ -1480,7 +1489,8 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl,
 	if (id->ncap == 0) {
 		/* namespace not allocated or attached */
 		info->is_removed = true;
-		return -ENODEV;
+		ret = -ENODEV;
+		goto error;
 	}
 
 	info->anagrpid = id->anagrpid;
@@ -1498,8 +1508,10 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl,
 		    !memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
 			memcpy(ids->nguid, id->nguid, sizeof(ids->nguid));
 	}
+
+error:
 	kfree(id);
-	return 0;
+	return ret;
 }
 
 static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl,
@@ -1814,16 +1826,18 @@ set_pi:
 	return ret;
 }
 
-static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
+static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
+	int ret;
 
-	if (nvme_init_ms(ns, id))
-		return;
+	ret = nvme_init_ms(ns, id);
+	if (ret)
+		return ret;
 
 	ns->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
 	if (!ns->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
-		return;
+		return 0;
 
 	if (ctrl->ops->flags & NVME_F_FABRICS) {
 		/*
@@ -1832,7 +1846,7 @@ static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		 * remap the separate metadata buffer from the block layer.
 		 */
 		if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
-			return;
+			return 0;
 
 		ns->features |= NVME_NS_EXT_LBAS;
 
@@ -1859,6 +1873,7 @@ static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		else
 			ns->features |= NVME_NS_METADATA_SUPPORTED;
 	}
+	return 0;
 }
 
 static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
@@ -1888,9 +1903,10 @@ static void nvme_update_disk_info(struct gendisk *disk,
 
 	/*
 	 * The block layer can't support LBA sizes larger than the page size
-	 * yet, so catch this early and don't allow block I/O.
+	 * or smaller than a sector size yet, so catch this early and don't
+	 * allow block I/O.
 	 */
-	if (ns->lba_shift > PAGE_SHIFT) {
+	if (ns->lba_shift > PAGE_SHIFT || ns->lba_shift < SECTOR_SHIFT) {
 		capacity = 0;
 		bs = (1 << 9);
 	}
@@ -2027,12 +2043,23 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	if (ret)
 		return ret;
 
+	if (id->ncap == 0) {
+		/* namespace not allocated or attached */
+		info->is_removed = true;
+		ret = -ENODEV;
+		goto error;
+	}
+
 	blk_mq_freeze_queue(ns->disk->queue);
 	lbaf = nvme_lbaf_index(id->flbas);
 	ns->lba_shift = id->lbaf[lbaf].ds;
 	nvme_set_queue_limits(ns->ctrl, ns->queue);
 
-	nvme_configure_metadata(ns, id);
+	ret = nvme_configure_metadata(ns, id);
+	if (ret < 0) {
+		blk_mq_unfreeze_queue(ns->disk->queue);
+		goto out;
+	}
 	nvme_set_chunk_sectors(ns, id);
 	nvme_update_disk_info(ns->disk, ns, id);
 
@@ -2084,6 +2111,8 @@ out:
 		set_bit(NVME_NS_READY, &ns->flags);
 		ret = 0;
 	}
+
+error:
 	kfree(id);
 	return ret;
 }
@@ -2523,7 +2552,7 @@ static void nvme_set_latency_tolerance(struct device *dev, s32 val)
 
 	if (ctrl->ps_max_latency_us != latency) {
 		ctrl->ps_max_latency_us = latency;
-		if (ctrl->state == NVME_CTRL_LIVE)
+		if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE)
 			nvme_configure_apst(ctrl);
 	}
 }
@@ -3200,6 +3229,8 @@ int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl, bool was_suspended)
 	clear_bit(NVME_CTRL_DIRTY_CAPABILITY, &ctrl->flags);
 	ctrl->identified = true;
 
+	nvme_start_keep_alive(ctrl);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nvme_init_ctrl_finish);
@@ -3209,7 +3240,7 @@ static int nvme_dev_open(struct inode *inode, struct file *file)
 	struct nvme_ctrl *ctrl =
 		container_of(inode->i_cdev, struct nvme_ctrl, cdev);
 
-	switch (ctrl->state) {
+	switch (nvme_ctrl_state(ctrl)) {
 	case NVME_CTRL_LIVE:
 		break;
 	default:
@@ -3631,6 +3662,14 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 		goto out_unlink_ns;
 
 	down_write(&ctrl->namespaces_rwsem);
+	/*
+	 * Ensure that no namespaces are added to the ctrl list after the queues
+	 * are frozen, thereby avoiding a deadlock between scan and reset.
+	 */
+	if (test_bit(NVME_CTRL_FROZEN, &ctrl->flags)) {
+		up_write(&ctrl->namespaces_rwsem);
+		goto out_unlink_ns;
+	}
 	nvme_ns_add_to_ctrl_list(ns);
 	up_write(&ctrl->namespaces_rwsem);
 	nvme_get_ctrl(ctrl);
@@ -3895,7 +3934,7 @@ static void nvme_scan_work(struct work_struct *work)
 	int ret;
 
 	/* No tagset on a live ctrl means IO queues could not created */
-	if (ctrl->state != NVME_CTRL_LIVE || !ctrl->tagset)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE || !ctrl->tagset)
 		return;
 
 	/*
@@ -3965,7 +4004,7 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 	 * removing the namespaces' disks; fail all the queues now to avoid
 	 * potentially having to clean up the failed sync later.
 	 */
-	if (ctrl->state == NVME_CTRL_DEAD)
+	if (nvme_ctrl_state(ctrl) == NVME_CTRL_DEAD)
 		nvme_mark_namespaces_dead(ctrl);
 
 	/* this is a no-op when called from the controller reset handler */
@@ -4047,7 +4086,7 @@ static void nvme_async_event_work(struct work_struct *work)
 	 * flushing ctrl async_event_work after changing the controller state
 	 * from LIVE and before freeing the admin queue.
 	*/
-	if (ctrl->state == NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE)
 		ctrl->ops->submit_async_event(ctrl);
 }
 
@@ -4074,8 +4113,21 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 		return;
 
 	if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, NVME_CSI_NVM,
-			log, sizeof(*log), 0))
+			 log, sizeof(*log), 0)) {
 		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
+		goto out_free_log;
+	}
+
+	if (log->afi & 0x70 || !(log->afi & 0x7)) {
+		dev_info(ctrl->device,
+			 "Firmware is activated after next Controller Level Reset\n");
+		goto out_free_log;
+	}
+
+	memcpy(ctrl->subsys->firmware_rev, &log->frs[(log->afi & 0x7) - 1],
+		sizeof(ctrl->subsys->firmware_rev));
+
+out_free_log:
 	kfree(log);
 }
 
@@ -4085,6 +4137,8 @@ static void nvme_fw_act_work(struct work_struct *work)
 				struct nvme_ctrl, fw_act_work);
 	unsigned long fw_act_timeout;
 
+	nvme_auth_stop(ctrl);
+
 	if (ctrl->mtfa)
 		fw_act_timeout = jiffies +
 				msecs_to_jiffies(ctrl->mtfa * 100);
@@ -4140,7 +4194,6 @@ static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 		 * firmware activation.
 		 */
 		if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) {
-			nvme_auth_stop(ctrl);
 			requeue = false;
 			queue_work(nvme_wq, &ctrl->fw_act_work);
 		}
@@ -4344,8 +4397,6 @@ EXPORT_SYMBOL_GPL(nvme_stop_ctrl);
 
 void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 {
-	nvme_start_keep_alive(ctrl);
-
 	nvme_enable_aen(ctrl);
 
 	/*
@@ -4431,7 +4482,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 {
 	int ret;
 
-	ctrl->state = NVME_CTRL_NEW;
+	WRITE_ONCE(ctrl->state, NVME_CTRL_NEW);
 	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
@@ -4452,6 +4503,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	INIT_DELAYED_WORK(&ctrl->failfast_work, nvme_failfast_work);
 	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
 	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
+	ctrl->ka_last_check_time = jiffies;
 
 	BUILD_BUG_ON(NVME_DSM_MAX_RANGES * sizeof(struct nvme_dsm_range) >
 			PAGE_SIZE);
@@ -4540,6 +4592,7 @@ void nvme_unfreeze(struct nvme_ctrl *ctrl)
 	list_for_each_entry(ns, &ctrl->namespaces, list)
 		blk_mq_unfreeze_queue(ns->queue);
 	up_read(&ctrl->namespaces_rwsem);
+	clear_bit(NVME_CTRL_FROZEN, &ctrl->flags);
 }
 EXPORT_SYMBOL_GPL(nvme_unfreeze);
 
@@ -4573,6 +4626,7 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
+	set_bit(NVME_CTRL_FROZEN, &ctrl->flags);
 	down_read(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list)
 		blk_freeze_queue_start(ns->queue);
@@ -4724,16 +4778,11 @@ static int __init nvme_core_init(void)
 		result = PTR_ERR(nvme_ns_chr_class);
 		goto unregister_generic_ns;
 	}
-	result = nvme_keyring_init();
-	if (result)
-		goto destroy_ns_chr;
 	result = nvme_init_auth();
 	if (result)
-		goto keyring_exit;
+		goto destroy_ns_chr;
 	return 0;
 
-keyring_exit:
-	nvme_keyring_exit();
 destroy_ns_chr:
 	class_destroy(nvme_ns_chr_class);
 unregister_generic_ns:
@@ -4757,7 +4806,6 @@ out:
 static void __exit nvme_core_exit(void)
 {
 	nvme_exit_auth();
-	nvme_keyring_exit();
 	class_destroy(nvme_ns_chr_class);
 	class_destroy(nvme_subsys_class);
 	class_destroy(nvme_class);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 4673ead69c5f9d..aa88606a44c40f 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -667,8 +667,10 @@ static const match_table_t opt_tokens = {
 #endif
 	{ NVMF_OPT_FAIL_FAST_TMO,	"fast_io_fail_tmo=%d"	},
 	{ NVMF_OPT_DISCOVERY,		"discovery"		},
+#ifdef CONFIG_NVME_HOST_AUTH
 	{ NVMF_OPT_DHCHAP_SECRET,	"dhchap_secret=%s"	},
 	{ NVMF_OPT_DHCHAP_CTRL_SECRET,	"dhchap_ctrl_secret=%s"	},
+#endif
 #ifdef CONFIG_NVME_TCP_TLS
 	{ NVMF_OPT_TLS,			"tls"			},
 #endif
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index a15b37750d6e93..1d51925ea67fd1 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -557,7 +557,7 @@ nvme_fc_rport_get(struct nvme_fc_rport *rport)
 static void
 nvme_fc_resume_controller(struct nvme_fc_ctrl *ctrl)
 {
-	switch (ctrl->ctrl.state) {
+	switch (nvme_ctrl_state(&ctrl->ctrl)) {
 	case NVME_CTRL_NEW:
 	case NVME_CTRL_CONNECTING:
 		/*
@@ -793,7 +793,7 @@ nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
 		"NVME-FC{%d}: controller connectivity lost. Awaiting "
 		"Reconnect", ctrl->cnum);
 
-	switch (ctrl->ctrl.state) {
+	switch (nvme_ctrl_state(&ctrl->ctrl)) {
 	case NVME_CTRL_NEW:
 	case NVME_CTRL_LIVE:
 		/*
@@ -2548,24 +2548,17 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 	 * the controller.  Abort any ios on the association and let the
 	 * create_association error path resolve things.
 	 */
-	enum nvme_ctrl_state state;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ctrl->lock, flags);
-	state = ctrl->ctrl.state;
-	if (state == NVME_CTRL_CONNECTING) {
-		set_bit(ASSOC_FAILED, &ctrl->flags);
-		spin_unlock_irqrestore(&ctrl->lock, flags);
+	if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
 		__nvme_fc_abort_outstanding_ios(ctrl, true);
+		set_bit(ASSOC_FAILED, &ctrl->flags);
 		dev_warn(ctrl->ctrl.device,
 			"NVME-FC{%d}: transport error during (re)connect\n",
 			ctrl->cnum);
 		return;
 	}
-	spin_unlock_irqrestore(&ctrl->lock, flags);
 
 	/* Otherwise, only proceed if in LIVE state - e.g. on first error */
-	if (state != NVME_CTRL_LIVE)
+	if (ctrl->ctrl.state != NVME_CTRL_LIVE)
 		return;
 
 	dev_warn(ctrl->ctrl.device,
@@ -3132,11 +3125,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	nvme_unquiesce_admin_queue(&ctrl->ctrl);
 
 	ret = nvme_init_ctrl_finish(&ctrl->ctrl, false);
-	if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
-		ret = -EIO;
 	if (ret)
 		goto out_disconnect_admin_queue;
-
+	if (test_bit(ASSOC_FAILED, &ctrl->flags)) {
+		ret = -EIO;
+		goto out_stop_keep_alive;
+	}
 	/* sanity checks */
 
 	/* FC-NVME does not have other data in the capsule */
@@ -3144,7 +3138,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n",
 				ctrl->ctrl.icdoff);
 		ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
-		goto out_disconnect_admin_queue;
+		goto out_stop_keep_alive;
 	}
 
 	/* FC-NVME supports normal SGL Data Block Descriptors */
@@ -3152,7 +3146,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		dev_err(ctrl->ctrl.device,
 			"Mandatory sgls are not supported!\n");
 		ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
-		goto out_disconnect_admin_queue;
+		goto out_stop_keep_alive;
 	}
 
 	if (opts->queue_size > ctrl->ctrl.maxcmd) {
@@ -3179,16 +3173,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		else
 			ret = nvme_fc_recreate_io_queues(ctrl);
 	}
-
-	spin_lock_irqsave(&ctrl->lock, flags);
 	if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
 		ret = -EIO;
-	if (ret) {
-		spin_unlock_irqrestore(&ctrl->lock, flags);
+	if (ret)
 		goto out_term_aen_ops;
-	}
+
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	spin_unlock_irqrestore(&ctrl->lock, flags);
 
 	ctrl->ctrl.nr_reconnects = 0;
 
@@ -3199,6 +3189,8 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 
 out_term_aen_ops:
 	nvme_fc_term_aen_ops(ctrl);
+out_stop_keep_alive:
+	nvme_stop_keep_alive(&ctrl->ctrl);
 out_disconnect_admin_queue:
 	dev_warn(ctrl->ctrl.device,
 		"NVME-FC{%d}: create_assoc failed, assoc_id %llx ret %d\n",
@@ -3316,7 +3308,7 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
 	unsigned long recon_delay = ctrl->ctrl.opts->reconnect_delay * HZ;
 	bool recon = true;
 
-	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING)
+	if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_CONNECTING)
 		return;
 
 	if (portptr->port_state == FC_OBJSTATE_ONLINE) {
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 747c879e8982b8..4939ed35638f16 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -18,15 +18,12 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 {
 	u32 effects;
 
-	if (capable(CAP_SYS_ADMIN))
-		return true;
-
 	/*
 	 * Do not allow unprivileged passthrough on partitions, as that allows an
 	 * escape from the containment of the partition.
 	 */
 	if (flags & NVME_IOCTL_PARTITION)
-		return false;
+		goto admin;
 
 	/*
 	 * Do not allow unprivileged processes to send vendor specific or fabrics
@@ -34,7 +31,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 	 */
 	if (c->common.opcode >= nvme_cmd_vendor_start ||
 	    c->common.opcode == nvme_fabrics_command)
-		return false;
+		goto admin;
 
 	/*
 	 * Do not allow unprivileged passthrough of admin commands except
@@ -53,7 +50,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 				return true;
 			}
 		}
-		return false;
+		goto admin;
 	}
 
 	/*
@@ -63,7 +60,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 	 */
 	effects = nvme_command_effects(ns->ctrl, ns, c->common.opcode);
 	if (!(effects & NVME_CMD_EFFECTS_CSUPP))
-		return false;
+		goto admin;
 
 	/*
 	 * Don't allow passthrough for command that have intrusive (or unknown)
@@ -72,16 +69,20 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 	if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC |
 			NVME_CMD_EFFECTS_UUID_SEL |
 			NVME_CMD_EFFECTS_SCOPE_MASK))
-		return false;
+		goto admin;
 
 	/*
 	 * Only allow I/O commands that transfer data to the controller or that
 	 * change the logical block contents if the file descriptor is open for
 	 * writing.
 	 */
-	if (nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC))
-		return open_for_write;
+	if ((nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC)) &&
+	    !open_for_write)
+		goto admin;
+
 	return true;
+admin:
+	return capable(CAP_SYS_ADMIN);
 }
 
 /*
@@ -510,10 +511,13 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
 
 	req->bio = pdu->bio;
-	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
+	if (nvme_req(req)->flags & NVME_REQ_CANCELLED) {
 		pdu->nvme_status = -EINTR;
-	else
+	} else {
 		pdu->nvme_status = nvme_req(req)->status;
+		if (!pdu->nvme_status)
+			pdu->nvme_status = blk_status_to_errno(err);
+	}
 	pdu->u.result = le64_to_cpu(nvme_req(req)->result.u64);
 
 	/*
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 39a90b7cb1254e..e7411dac00f725 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -156,6 +156,11 @@ enum nvme_quirks {
 	 * No temperature thresholds for channels other than 0 (Composite).
 	 */
 	NVME_QUIRK_NO_SECONDARY_TEMP_THRESH	= (1 << 19),
+
+	/*
+	 * Disables simple suspend/resume path.
+	 */
+	NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND	= (1 << 20),
 };
 
 /*
@@ -251,6 +256,7 @@ enum nvme_ctrl_flags {
 	NVME_CTRL_STOPPED		= 3,
 	NVME_CTRL_SKIP_ID_CNS_CS	= 4,
 	NVME_CTRL_DIRTY_CAPABILITY	= 5,
+	NVME_CTRL_FROZEN		= 6,
 };
 
 struct nvme_ctrl {
@@ -387,6 +393,11 @@ struct nvme_ctrl {
 	enum nvme_dctype dctype;
 };
 
+static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
+{
+	return READ_ONCE(ctrl->state);
+}
+
 enum nvme_iopolicy {
 	NVME_IOPOLICY_NUMA,
 	NVME_IOPOLICY_RR,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 507bc149046dc8..61af7ff1a9d6ba 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1233,7 +1233,7 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
 	bool nssro = dev->subsystem && (csts & NVME_CSTS_NSSRO);
 
 	/* If there is a reset/reinit ongoing, we shouldn't reset again. */
-	switch (dev->ctrl.state) {
+	switch (nvme_ctrl_state(&dev->ctrl)) {
 	case NVME_CTRL_RESETTING:
 	case NVME_CTRL_CONNECTING:
 		return false;
@@ -1321,7 +1321,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 * cancellation error. All outstanding requests are completed on
 	 * shutdown, so we return BLK_EH_DONE.
 	 */
-	switch (dev->ctrl.state) {
+	switch (nvme_ctrl_state(&dev->ctrl)) {
 	case NVME_CTRL_CONNECTING:
 		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
 		fallthrough;
@@ -1593,7 +1593,7 @@ static int nvme_setup_io_queues_trylock(struct nvme_dev *dev)
 	/*
 	 * Controller is in wrong state, fail early.
 	 */
-	if (dev->ctrl.state != NVME_CTRL_CONNECTING) {
+	if (nvme_ctrl_state(&dev->ctrl) != NVME_CTRL_CONNECTING) {
 		mutex_unlock(&dev->shutdown_lock);
 		return -ENODEV;
 	}
@@ -2573,13 +2573,13 @@ static bool nvme_pci_ctrl_is_dead(struct nvme_dev *dev)
 
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(&dev->ctrl);
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	bool dead;
 
 	mutex_lock(&dev->shutdown_lock);
 	dead = nvme_pci_ctrl_is_dead(dev);
-	if (dev->ctrl.state == NVME_CTRL_LIVE ||
-	    dev->ctrl.state == NVME_CTRL_RESETTING) {
+	if (state == NVME_CTRL_LIVE || state == NVME_CTRL_RESETTING) {
 		if (pci_is_enabled(pdev))
 			nvme_start_freeze(&dev->ctrl);
 		/*
@@ -2690,7 +2690,7 @@ static void nvme_reset_work(struct work_struct *work)
 	bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
 	int result;
 
-	if (dev->ctrl.state != NVME_CTRL_RESETTING) {
+	if (nvme_ctrl_state(&dev->ctrl) != NVME_CTRL_RESETTING) {
 		dev_warn(dev->ctrl.device, "ctrl state %d is not RESETTING\n",
 			 dev->ctrl.state);
 		result = -ENODEV;
@@ -2902,6 +2902,18 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
 		if ((dmi_match(DMI_BOARD_VENDOR, "LENOVO")) &&
 		     dmi_match(DMI_BOARD_NAME, "LNVNB161216"))
 			return NVME_QUIRK_SIMPLE_SUSPEND;
+	} else if (pdev->vendor == 0x2646 && (pdev->device == 0x2263 ||
+		   pdev->device == 0x500f)) {
+		/*
+		 * Exclude some Kingston NV1 and A2000 devices from
+		 * NVME_QUIRK_SIMPLE_SUSPEND. Do a full suspend to save a
+		 * lot fo energy with s2idle sleep on some TUXEDO platforms.
+		 */
+		if (dmi_match(DMI_BOARD_NAME, "NS5X_NS7XAU") ||
+		    dmi_match(DMI_BOARD_NAME, "NS5x_7xAU") ||
+		    dmi_match(DMI_BOARD_NAME, "NS5x_7xPU") ||
+		    dmi_match(DMI_BOARD_NAME, "PH4PRX1_PH6PRX1"))
+			return NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND;
 	}
 
 	return 0;
@@ -2932,7 +2944,9 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
 	dev->dev = get_device(&pdev->dev);
 
 	quirks |= check_vendor_combination_bug(pdev);
-	if (!noacpi && acpi_storage_d3(&pdev->dev)) {
+	if (!noacpi &&
+	    !(quirks & NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND) &&
+	    acpi_storage_d3(&pdev->dev)) {
 		/*
 		 * Some systems use a bios work around to ask for D3 on
 		 * platforms that support kernel managed suspend.
@@ -3192,7 +3206,7 @@ static int nvme_suspend(struct device *dev)
 	nvme_wait_freeze(ctrl);
 	nvme_sync_queues(ctrl);
 
-	if (ctrl->state != NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 		goto unfreeze;
 
 	/*
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index a7fea4cbacd753..81e2621169e5d3 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -984,10 +984,11 @@ free_ctrl:
 
 static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
+
 	/* If we are resetting/deleting then do nothing */
-	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) {
-		WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW ||
-			ctrl->ctrl.state == NVME_CTRL_LIVE);
+	if (state != NVME_CTRL_CONNECTING) {
+		WARN_ON_ONCE(state == NVME_CTRL_NEW || state == NVME_CTRL_LIVE);
 		return;
 	}
 
@@ -1059,8 +1060,10 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 		 * unless we're during creation of a new controller to
 		 * avoid races with teardown flow.
 		 */
-		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING &&
-			     ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO);
+		enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
+
+		WARN_ON_ONCE(state != NVME_CTRL_DELETING &&
+			     state != NVME_CTRL_DELETING_NOIO);
 		WARN_ON_ONCE(new);
 		ret = -EINVAL;
 		goto destroy_io;
@@ -1080,6 +1083,7 @@ destroy_io:
 		nvme_rdma_free_io_queues(ctrl);
 	}
 destroy_admin:
+	nvme_stop_keep_alive(&ctrl->ctrl);
 	nvme_quiesce_admin_queue(&ctrl->ctrl);
 	blk_sync_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
@@ -1128,8 +1132,10 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure is ok if we started ctrl delete */
-		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING &&
-			     ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO);
+		enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
+
+		WARN_ON_ONCE(state != NVME_CTRL_DELETING &&
+			     state != NVME_CTRL_DELETING_NOIO);
 		return;
 	}
 
@@ -1161,7 +1167,7 @@ static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc,
 	struct nvme_rdma_queue *queue = wc->qp->qp_context;
 	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
 
-	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(&ctrl->ctrl) == NVME_CTRL_LIVE)
 		dev_info(ctrl->ctrl.device,
 			     "%s for CQE 0x%p failed with status %s (%d)\n",
 			     op, wc->wr_cqe,
@@ -1944,7 +1950,7 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq)
 	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
 		 rq->tag, nvme_rdma_queue_idx(queue));
 
-	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
+	if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_LIVE) {
 		/*
 		 * If we are resetting, connecting or deleting we should
 		 * complete immediately because we may block controller
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 4714a902f4caa8..08805f02781064 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -36,11 +36,11 @@ static int so_priority;
 module_param(so_priority, int, 0644);
 MODULE_PARM_DESC(so_priority, "nvme tcp socket optimize priority");
 
-#ifdef CONFIG_NVME_TCP_TLS
 /*
  * TLS handshake timeout
  */
 static int tls_handshake_timeout = 10;
+#ifdef CONFIG_NVME_TCP_TLS
 module_param(tls_handshake_timeout, int, 0644);
 MODULE_PARM_DESC(tls_handshake_timeout,
 		 "nvme TLS handshake timeout in seconds (default 10)");
@@ -161,10 +161,8 @@ struct nvme_tcp_queue {
 	struct ahash_request	*snd_hash;
 	__le32			exp_ddgst;
 	__le32			recv_ddgst;
-#ifdef CONFIG_NVME_TCP_TLS
 	struct completion       tls_complete;
 	int                     tls_err;
-#endif
 	struct page_frag_cache	pf_cache;
 
 	void (*state_change)(struct sock *);
@@ -207,6 +205,14 @@ static inline int nvme_tcp_queue_id(struct nvme_tcp_queue *queue)
 	return queue - queue->ctrl->queues;
 }
 
+static inline bool nvme_tcp_tls(struct nvme_ctrl *ctrl)
+{
+	if (!IS_ENABLED(CONFIG_NVME_TCP_TLS))
+		return 0;
+
+	return ctrl->opts->tls;
+}
+
 static inline struct blk_mq_tags *nvme_tcp_tagset(struct nvme_tcp_queue *queue)
 {
 	u32 queue_idx = nvme_tcp_queue_id(queue);
@@ -1412,7 +1418,7 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 	memset(&msg, 0, sizeof(msg));
 	iov.iov_base = icresp;
 	iov.iov_len = sizeof(*icresp);
-	if (queue->ctrl->ctrl.opts->tls) {
+	if (nvme_tcp_tls(&queue->ctrl->ctrl)) {
 		msg.msg_control = cbuf;
 		msg.msg_controllen = sizeof(cbuf);
 	}
@@ -1423,13 +1429,14 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 			nvme_tcp_queue_id(queue), ret);
 		goto free_icresp;
 	}
-	if (queue->ctrl->ctrl.opts->tls) {
+	ret = -ENOTCONN;
+	if (nvme_tcp_tls(&queue->ctrl->ctrl)) {
 		ctype = tls_get_record_type(queue->sock->sk,
 					    (struct cmsghdr *)cbuf);
 		if (ctype != TLS_RECORD_TYPE_DATA) {
 			pr_err("queue %d: unhandled TLS record %d\n",
 			       nvme_tcp_queue_id(queue), ctype);
-			return -ENOTCONN;
+			goto free_icresp;
 		}
 	}
 	ret = -EINVAL;
@@ -1547,7 +1554,6 @@ static void nvme_tcp_set_queue_io_cpu(struct nvme_tcp_queue *queue)
 	queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
 }
 
-#ifdef CONFIG_NVME_TCP_TLS
 static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid)
 {
 	struct nvme_tcp_queue *queue = data;
@@ -1624,14 +1630,6 @@ static int nvme_tcp_start_tls(struct nvme_ctrl *nctrl,
 	}
 	return ret;
 }
-#else
-static int nvme_tcp_start_tls(struct nvme_ctrl *nctrl,
-			      struct nvme_tcp_queue *queue,
-			      key_serial_t pskid)
-{
-	return -EPROTONOSUPPORT;
-}
-#endif
 
 static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
 				key_serial_t pskid)
@@ -1758,7 +1756,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
 	}
 
 	/* If PSKs are configured try to start TLS */
-	if (pskid) {
+	if (IS_ENABLED(CONFIG_NVME_TCP_TLS) && pskid) {
 		ret = nvme_tcp_start_tls(nctrl, queue, pskid);
 		if (ret)
 			goto err_init_connect;
@@ -1915,7 +1913,7 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl)
 	int ret;
 	key_serial_t pskid = 0;
 
-	if (ctrl->opts->tls) {
+	if (nvme_tcp_tls(ctrl)) {
 		if (ctrl->opts->tls_key)
 			pskid = key_serial(ctrl->opts->tls_key);
 		else
@@ -1948,7 +1946,7 @@ static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl)
 {
 	int i, ret;
 
-	if (ctrl->opts->tls && !ctrl->tls_key) {
+	if (nvme_tcp_tls(ctrl) && !ctrl->tls_key) {
 		dev_err(ctrl->device, "no PSK negotiated\n");
 		return -ENOKEY;
 	}
@@ -2154,10 +2152,11 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 
 static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
 	/* If we are resetting/deleting then do nothing */
-	if (ctrl->state != NVME_CTRL_CONNECTING) {
-		WARN_ON_ONCE(ctrl->state == NVME_CTRL_NEW ||
-			ctrl->state == NVME_CTRL_LIVE);
+	if (state != NVME_CTRL_CONNECTING) {
+		WARN_ON_ONCE(state == NVME_CTRL_NEW || state == NVME_CTRL_LIVE);
 		return;
 	}
 
@@ -2217,8 +2216,10 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new)
 		 * unless we're during creation of a new controller to
 		 * avoid races with teardown flow.
 		 */
-		WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
-			     ctrl->state != NVME_CTRL_DELETING_NOIO);
+		enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+		WARN_ON_ONCE(state != NVME_CTRL_DELETING &&
+			     state != NVME_CTRL_DELETING_NOIO);
 		WARN_ON_ONCE(new);
 		ret = -EINVAL;
 		goto destroy_io;
@@ -2236,11 +2237,8 @@ destroy_io:
 		nvme_tcp_destroy_io_queues(ctrl, new);
 	}
 destroy_admin:
-	nvme_quiesce_admin_queue(ctrl);
-	blk_sync_queue(ctrl->admin_q);
-	nvme_tcp_stop_queue(ctrl, 0);
-	nvme_cancel_admin_tagset(ctrl);
-	nvme_tcp_destroy_admin_queue(ctrl, new);
+	nvme_stop_keep_alive(ctrl);
+	nvme_tcp_teardown_admin_queue(ctrl, false);
 	return ret;
 }
 
@@ -2285,8 +2283,10 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
 
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure is ok if we started ctrl delete */
-		WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
-			     ctrl->state != NVME_CTRL_DELETING_NOIO);
+		enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+		WARN_ON_ONCE(state != NVME_CTRL_DELETING &&
+			     state != NVME_CTRL_DELETING_NOIO);
 		return;
 	}
 
@@ -2316,8 +2316,10 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
 
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure is ok if we started ctrl delete */
-		WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
-			     ctrl->state != NVME_CTRL_DELETING_NOIO);
+		enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+		WARN_ON_ONCE(state != NVME_CTRL_DELETING &&
+			     state != NVME_CTRL_DELETING_NOIO);
 		return;
 	}
 
@@ -2435,7 +2437,7 @@ static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq)
 		nvme_tcp_queue_id(req->queue), nvme_cid(rq), pdu->hdr.type,
 		opc, nvme_opcode_str(qid, opc, fctype));
 
-	if (ctrl->state != NVME_CTRL_LIVE) {
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) {
 		/*
 		 * If we are resetting, connecting or deleting we should
 		 * complete immediately because we may block controller
diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig
index fa479c9f5c3d32..872dd1a0acd804 100644
--- a/drivers/nvme/target/Kconfig
+++ b/drivers/nvme/target/Kconfig
@@ -4,6 +4,8 @@ config NVME_TARGET
 	tristate "NVMe Target support"
 	depends on BLOCK
 	depends on CONFIGFS_FS
+	select NVME_KEYRING if NVME_TARGET_TCP_TLS
+	select KEYS if NVME_TARGET_TCP_TLS
 	select BLK_DEV_INTEGRITY_T10 if BLK_DEV_INTEGRITY
 	select SGL_ALLOC
 	help
@@ -87,10 +89,7 @@ config NVME_TARGET_TCP
 config NVME_TARGET_TCP_TLS
 	bool "NVMe over Fabrics TCP target TLS encryption support"
 	depends on NVME_TARGET_TCP
-	select NVME_COMMON
-	select NVME_KEYRING
 	select NET_HANDSHAKE
-	select KEYS
 	help
 	  Enables TLS encryption for the NVMe TCP target using the netlink handshake API.
 
@@ -100,11 +99,11 @@ config NVME_TARGET_TCP_TLS
 	  If unsure, say N.
 
 config NVME_TARGET_AUTH
-	bool "NVMe over Fabrics In-band Authentication support"
+	bool "NVMe over Fabrics In-band Authentication in target side"
 	depends on NVME_TARGET
-	select NVME_COMMON
 	select NVME_AUTH
 	help
-	  This enables support for NVMe over Fabrics In-band Authentication
+	  This enables support for NVMe over Fabrics In-band Authentication in
+	  target side.
 
 	  If unsure, say N.
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 9eed6e6765eaa7..d937fe05129e4d 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -18,6 +18,7 @@
 #include <linux/nvme-keyring.h>
 #include <crypto/hash.h>
 #include <crypto/kpp.h>
+#include <linux/nospec.h>
 
 #include "nvmet.h"
 
@@ -621,6 +622,7 @@ static ssize_t nvmet_ns_ana_grpid_store(struct config_item *item,
 
 	down_write(&nvmet_ana_sem);
 	oldgrpid = ns->anagrpid;
+	newgrpid = array_index_nospec(newgrpid, NVMET_MAX_ANAGRPS);
 	nvmet_ana_group_enabled[newgrpid]++;
 	ns->anagrpid = newgrpid;
 	nvmet_ana_group_enabled[oldgrpid]--;
@@ -1812,6 +1814,7 @@ static struct config_group *nvmet_ana_groups_make_group(
 	grp->grpid = grpid;
 
 	down_write(&nvmet_ana_sem);
+	grpid = array_index_nospec(grpid, NVMET_MAX_ANAGRPS);
 	nvmet_ana_group_enabled[grpid]++;
 	up_write(&nvmet_ana_sem);
 
@@ -1893,7 +1896,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	if (nvme_keyring_id()) {
+	if (IS_ENABLED(CONFIG_NVME_TARGET_TCP_TLS) && nvme_keyring_id()) {
 		port->keyring = key_lookup(nvme_keyring_id());
 		if (IS_ERR(port->keyring)) {
 			pr_warn("NVMe keyring not available, disabling TLS\n");
diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c
index 1d9854484e2e83..eb7785be0ca770 100644
--- a/drivers/nvme/target/fabrics-cmd-auth.c
+++ b/drivers/nvme/target/fabrics-cmd-auth.c
@@ -163,11 +163,11 @@ static u16 nvmet_auth_reply(struct nvmet_req *req, void *d)
 		pr_debug("%s: ctrl %d qid %d challenge %*ph\n",
 			 __func__, ctrl->cntlid, req->sq->qid, data->hl,
 			 req->sq->dhchap_c2);
-		req->sq->dhchap_s2 = le32_to_cpu(data->seqnum);
 	} else {
 		req->sq->authenticated = true;
 		req->sq->dhchap_c2 = NULL;
 	}
+	req->sq->dhchap_s2 = le32_to_cpu(data->seqnum);
 
 	return 0;
 }
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 43b5bd8bb6a52d..d8da840a1c0ed1 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -244,6 +244,8 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 		goto out;
 	}
 
+	d->subsysnqn[NVMF_NQN_FIELD_LEN - 1] = '\0';
+	d->hostnqn[NVMF_NQN_FIELD_LEN - 1] = '\0';
 	status = nvmet_alloc_ctrl(d->subsysnqn, d->hostnqn, req,
 				  le32_to_cpu(c->kato), &ctrl);
 	if (status)
@@ -313,6 +315,8 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
 		goto out;
 	}
 
+	d->subsysnqn[NVMF_NQN_FIELD_LEN - 1] = '\0';
+	d->hostnqn[NVMF_NQN_FIELD_LEN - 1] = '\0';
 	ctrl = nvmet_ctrl_find_get(d->subsysnqn, d->hostnqn,
 				   le16_to_cpu(d->cntlid), req);
 	if (!ctrl) {
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 48d5df054cd024..9cb434c5807514 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -466,6 +466,8 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
 out_destroy_io:
 	nvme_loop_destroy_io_queues(ctrl);
 out_destroy_admin:
+	nvme_quiesce_admin_queue(&ctrl->ctrl);
+	nvme_cancel_admin_tagset(&ctrl->ctrl);
 	nvme_loop_destroy_admin_queue(ctrl);
 out_disable:
 	dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
@@ -600,6 +602,8 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 	return &ctrl->ctrl;
 
 out_remove_admin_queue:
+	nvme_quiesce_admin_queue(&ctrl->ctrl);
+	nvme_cancel_admin_tagset(&ctrl->ctrl);
 	nvme_loop_destroy_admin_queue(ctrl);
 out_free_queues:
 	kfree(ctrl->queues);
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 92b74d0b8686a6..4cc27856aa8fef 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1854,6 +1854,8 @@ static int nvmet_tcp_tls_handshake(struct nvmet_tcp_queue *queue)
 	}
 	return ret;
 }
+#else
+static void nvmet_tcp_tls_handshake_timeout(struct work_struct *w) {}
 #endif
 
 static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
@@ -1911,9 +1913,9 @@ static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 	list_add_tail(&queue->queue_list, &nvmet_tcp_queue_list);
 	mutex_unlock(&nvmet_tcp_queue_mutex);
 
-#ifdef CONFIG_NVME_TARGET_TCP_TLS
 	INIT_DELAYED_WORK(&queue->tls_handshake_tmo_work,
 			  nvmet_tcp_tls_handshake_timeout);
+#ifdef CONFIG_NVME_TARGET_TCP_TLS
 	if (queue->state == NVMET_TCP_Q_TLS_HANDSHAKE) {
 		struct sock *sk = queue->sock->sk;
 
diff --git a/drivers/nvmem/brcm_nvram.c b/drivers/nvmem/brcm_nvram.c
index 9737104f3b76b3..5cdf339cfbec0e 100644
--- a/drivers/nvmem/brcm_nvram.c
+++ b/drivers/nvmem/brcm_nvram.c
@@ -17,9 +17,23 @@
 
 #define NVRAM_MAGIC			"FLSH"
 
+/**
+ * struct brcm_nvram - driver state internal struct
+ *
+ * @dev:		NVMEM device pointer
+ * @nvmem_size:		Size of the whole space available for NVRAM
+ * @data:		NVRAM data copy stored to avoid poking underlaying flash controller
+ * @data_len:		NVRAM data size
+ * @padding_byte:	Padding value used to fill remaining space
+ * @cells:		Array of discovered NVMEM cells
+ * @ncells:		Number of elements in cells
+ */
 struct brcm_nvram {
 	struct device *dev;
-	void __iomem *base;
+	size_t nvmem_size;
+	uint8_t *data;
+	size_t data_len;
+	uint8_t padding_byte;
 	struct nvmem_cell_info *cells;
 	int ncells;
 };
@@ -36,10 +50,47 @@ static int brcm_nvram_read(void *context, unsigned int offset, void *val,
 			   size_t bytes)
 {
 	struct brcm_nvram *priv = context;
-	u8 *dst = val;
+	size_t to_copy;
+
+	if (offset + bytes > priv->data_len)
+		to_copy = max_t(ssize_t, (ssize_t)priv->data_len - offset, 0);
+	else
+		to_copy = bytes;
+
+	memcpy(val, priv->data + offset, to_copy);
+
+	memset((uint8_t *)val + to_copy, priv->padding_byte, bytes - to_copy);
+
+	return 0;
+}
+
+static int brcm_nvram_copy_data(struct brcm_nvram *priv, struct platform_device *pdev)
+{
+	struct resource *res;
+	void __iomem *base;
+
+	base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	priv->nvmem_size = resource_size(res);
+
+	priv->padding_byte = readb(base + priv->nvmem_size - 1);
+	for (priv->data_len = priv->nvmem_size;
+	     priv->data_len;
+	     priv->data_len--) {
+		if (readb(base + priv->data_len - 1) != priv->padding_byte)
+			break;
+	}
+	WARN(priv->data_len > SZ_128K, "Unexpected (big) NVRAM size: %zu B\n", priv->data_len);
+
+	priv->data = devm_kzalloc(priv->dev, priv->data_len, GFP_KERNEL);
+	if (!priv->data)
+		return -ENOMEM;
+
+	memcpy_fromio(priv->data, base, priv->data_len);
 
-	while (bytes--)
-		*dst++ = readb(priv->base + offset++);
+	bcm47xx_nvram_init_from_iomem(base, priv->data_len);
 
 	return 0;
 }
@@ -67,8 +118,13 @@ static int brcm_nvram_add_cells(struct brcm_nvram *priv, uint8_t *data,
 				size_t len)
 {
 	struct device *dev = priv->dev;
-	char *var, *value, *eq;
+	char *var, *value;
+	uint8_t tmp;
 	int idx;
+	int err = 0;
+
+	tmp = priv->data[len - 1];
+	priv->data[len - 1] = '\0';
 
 	priv->ncells = 0;
 	for (var = data + sizeof(struct brcm_nvram_header);
@@ -78,67 +134,68 @@ static int brcm_nvram_add_cells(struct brcm_nvram *priv, uint8_t *data,
 	}
 
 	priv->cells = devm_kcalloc(dev, priv->ncells, sizeof(*priv->cells), GFP_KERNEL);
-	if (!priv->cells)
-		return -ENOMEM;
+	if (!priv->cells) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	for (var = data + sizeof(struct brcm_nvram_header), idx = 0;
 	     var < (char *)data + len && *var;
 	     var = value + strlen(value) + 1, idx++) {
+		char *eq, *name;
+
 		eq = strchr(var, '=');
 		if (!eq)
 			break;
 		*eq = '\0';
+		name = devm_kstrdup(dev, var, GFP_KERNEL);
+		*eq = '=';
+		if (!name) {
+			err = -ENOMEM;
+			goto out;
+		}
 		value = eq + 1;
 
-		priv->cells[idx].name = devm_kstrdup(dev, var, GFP_KERNEL);
-		if (!priv->cells[idx].name)
-			return -ENOMEM;
+		priv->cells[idx].name = name;
 		priv->cells[idx].offset = value - (char *)data;
 		priv->cells[idx].bytes = strlen(value);
 		priv->cells[idx].np = of_get_child_by_name(dev->of_node, priv->cells[idx].name);
-		if (!strcmp(var, "et0macaddr") ||
-		    !strcmp(var, "et1macaddr") ||
-		    !strcmp(var, "et2macaddr")) {
+		if (!strcmp(name, "et0macaddr") ||
+		    !strcmp(name, "et1macaddr") ||
+		    !strcmp(name, "et2macaddr")) {
 			priv->cells[idx].raw_len = strlen(value);
 			priv->cells[idx].bytes = ETH_ALEN;
 			priv->cells[idx].read_post_process = brcm_nvram_read_post_process_macaddr;
 		}
 	}
 
-	return 0;
+out:
+	priv->data[len - 1] = tmp;
+	return err;
 }
 
 static int brcm_nvram_parse(struct brcm_nvram *priv)
 {
+	struct brcm_nvram_header *header = (struct brcm_nvram_header *)priv->data;
 	struct device *dev = priv->dev;
-	struct brcm_nvram_header header;
-	uint8_t *data;
 	size_t len;
 	int err;
 
-	memcpy_fromio(&header, priv->base, sizeof(header));
-
-	if (memcmp(header.magic, NVRAM_MAGIC, 4)) {
+	if (memcmp(header->magic, NVRAM_MAGIC, 4)) {
 		dev_err(dev, "Invalid NVRAM magic\n");
 		return -EINVAL;
 	}
 
-	len = le32_to_cpu(header.len);
-
-	data = kzalloc(len, GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
-
-	memcpy_fromio(data, priv->base, len);
-	data[len - 1] = '\0';
-
-	err = brcm_nvram_add_cells(priv, data, len);
-	if (err) {
-		dev_err(dev, "Failed to add cells: %d\n", err);
-		return err;
+	len = le32_to_cpu(header->len);
+	if (len > priv->nvmem_size) {
+		dev_err(dev, "NVRAM length (%zd) exceeds mapped size (%zd)\n", len,
+			priv->nvmem_size);
+		return -EINVAL;
 	}
 
-	kfree(data);
+	err = brcm_nvram_add_cells(priv, priv->data, len);
+	if (err)
+		dev_err(dev, "Failed to add cells: %d\n", err);
 
 	return 0;
 }
@@ -150,7 +207,6 @@ static int brcm_nvram_probe(struct platform_device *pdev)
 		.reg_read = brcm_nvram_read,
 	};
 	struct device *dev = &pdev->dev;
-	struct resource *res;
 	struct brcm_nvram *priv;
 	int err;
 
@@ -159,21 +215,19 @@ static int brcm_nvram_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	priv->dev = dev;
 
-	priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
-	if (IS_ERR(priv->base))
-		return PTR_ERR(priv->base);
+	err = brcm_nvram_copy_data(priv, pdev);
+	if (err)
+		return err;
 
 	err = brcm_nvram_parse(priv);
 	if (err)
 		return err;
 
-	bcm47xx_nvram_init_from_iomem(priv->base, resource_size(res));
-
 	config.dev = dev;
 	config.cells = priv->cells;
 	config.ncells = priv->ncells;
 	config.priv = priv;
-	config.size = resource_size(res);
+	config.size = priv->nvmem_size;
 
 	return PTR_ERR_OR_ZERO(devm_nvmem_register(dev, &config));
 }
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index bf42b7e826dbd2..608b352a7d91fd 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -796,6 +796,12 @@ static struct nvmem_layout *nvmem_layout_get(struct nvmem_device *nvmem)
 	if (!layout_np)
 		return NULL;
 
+	/* Fixed layouts don't have a matching driver */
+	if (of_device_is_compatible(layout_np, "fixed-layout")) {
+		of_node_put(layout_np);
+		return NULL;
+	}
+
 	/*
 	 * In case the nvmem device was built-in while the layout was built as a
 	 * module, we shall manually request the layout driver loading otherwise
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index f63250c650cafd..3bf27052832f30 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -98,8 +98,9 @@ int of_reconfig_notify(unsigned long action, struct of_reconfig_data *p)
  *
  * Returns the new state of a device based on the notifier used.
  *
- * Return: 0 on device going from enabled to disabled, 1 on device
- * going from disabled to enabled and -1 on no change.
+ * Return: OF_RECONFIG_CHANGE_REMOVE on device going from enabled to
+ * disabled, OF_RECONFIG_CHANGE_ADD on device going from disabled to
+ * enabled and OF_RECONFIG_NO_CHANGE on no change.
  */
 int of_reconfig_get_state_change(unsigned long action, struct of_reconfig_data *pr)
 {
diff --git a/drivers/of/property.c b/drivers/of/property.c
index cf8dacf3e3b84d..afdaefbd03f615 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -1267,6 +1267,7 @@ DEFINE_SIMPLE_PROP(resets, "resets", "#reset-cells")
 DEFINE_SIMPLE_PROP(leds, "leds", NULL)
 DEFINE_SIMPLE_PROP(backlight, "backlight", NULL)
 DEFINE_SIMPLE_PROP(panel, "panel", NULL)
+DEFINE_SIMPLE_PROP(msi_parent, "msi-parent", "#msi-cells")
 DEFINE_SUFFIX_PROP(regulators, "-supply", NULL)
 DEFINE_SUFFIX_PROP(gpio, "-gpio", "#gpio-cells")
 
@@ -1356,6 +1357,7 @@ static const struct supplier_bindings of_supplier_bindings[] = {
 	{ .parse_prop = parse_leds, },
 	{ .parse_prop = parse_backlight, },
 	{ .parse_prop = parse_panel, },
+	{ .parse_prop = parse_msi_parent, },
 	{ .parse_prop = parse_gpio_compat, },
 	{ .parse_prop = parse_interrupts, },
 	{ .parse_prop = parse_regulators, },
diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c
index 539d8920c2029b..bb0d92461b08b3 100644
--- a/drivers/parisc/power.c
+++ b/drivers/parisc/power.c
@@ -176,7 +176,7 @@ static struct notifier_block parisc_panic_block = {
 static int qemu_power_off(struct sys_off_data *data)
 {
 	/* this turns the system off via SeaBIOS */
-	*(int *)data->cb_data = 0;
+	gsc_writel(0, (unsigned long) data->cb_data);
 	pdc_soft_power_button(1);
 	return NOTIFY_DONE;
 }
diff --git a/drivers/parport/parport_gsc.c b/drivers/parport/parport_gsc.c
index 5e4475254bd0a3..c7e18382dc014a 100644
--- a/drivers/parport/parport_gsc.c
+++ b/drivers/parport/parport_gsc.c
@@ -392,7 +392,7 @@ static struct parisc_driver parport_driver __refdata = {
 	.remove		= __exit_p(parport_remove_chip),
 };
 
-int parport_gsc_init(void)
+static int parport_gsc_init(void)
 {
 	return register_parisc_driver(&parport_driver);
 }
diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c
index 1f236aaf7867a7..f33b5d1ddfc16f 100644
--- a/drivers/parport/parport_pc.c
+++ b/drivers/parport/parport_pc.c
@@ -2658,6 +2658,8 @@ enum parport_pc_pci_cards {
 	asix_ax99100,
 	quatech_sppxp100,
 	wch_ch382l,
+	brainboxes_uc146,
+	brainboxes_px203,
 };
 
 
@@ -2737,6 +2739,8 @@ static struct parport_pc_pci {
 	/* asix_ax99100 */		{ 1, { { 0, 1 }, } },
 	/* quatech_sppxp100 */		{ 1, { { 0, 1 }, } },
 	/* wch_ch382l */		{ 1, { { 2, -1 }, } },
+	/* brainboxes_uc146 */	{ 1, { { 3, -1 }, } },
+	/* brainboxes_px203 */	{ 1, { { 0, -1 }, } },
 };
 
 static const struct pci_device_id parport_pc_pci_tbl[] = {
@@ -2833,6 +2837,23 @@ static const struct pci_device_id parport_pc_pci_tbl[] = {
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, quatech_sppxp100 },
 	/* WCH CH382L PCI-E single parallel port card */
 	{ 0x1c00, 0x3050, 0x1c00, 0x3050, 0, 0, wch_ch382l },
+	/* Brainboxes IX-500/550 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x402a,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
+	/* Brainboxes UC-146/UC-157 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0be1,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc146 },
+	{ PCI_VENDOR_ID_INTASHIELD, 0x0be2,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc146 },
+	/* Brainboxes PX-146/PX-257 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x401c,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
+	/* Brainboxes PX-203 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x4007,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_px203 },
+	/* Brainboxes PX-475 */
+	{ PCI_VENDOR_ID_INTASHIELD, 0x401f,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
 	{ 0, } /* terminate list */
 };
 MODULE_DEVICE_TABLE(pci, parport_pc_pci_tbl);
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 6902e97719d136..11c80555d97543 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -968,9 +968,12 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie)
 
 static int qcom_pcie_enable_aspm(struct pci_dev *pdev, void *userdata)
 {
-	/* Downstream devices need to be in D0 state before enabling PCI PM substates */
+	/*
+	 * Downstream devices need to be in D0 state before enabling PCI PM
+	 * substates.
+	 */
 	pci_set_power_state(pdev, PCI_D0);
-	pci_enable_link_state(pdev, PCIE_LINK_STATE_ALL);
+	pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL);
 
 	return 0;
 }
diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c
index d45e7b8dc530d6..8b34ccff073a99 100644
--- a/drivers/pci/controller/pci-loongson.c
+++ b/drivers/pci/controller/pci-loongson.c
@@ -80,13 +80,49 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON,
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON,
 			DEV_LS7A_LPC, system_bus_quirk);
 
+/*
+ * Some Loongson PCIe ports have hardware limitations on their Maximum Read
+ * Request Size. They can't handle anything larger than this.  Sane
+ * firmware will set proper MRRS at boot, so we only need no_inc_mrrs for
+ * bridges. However, some MIPS Loongson firmware doesn't set MRRS properly,
+ * so we have to enforce maximum safe MRRS, which is 256 bytes.
+ */
+#ifdef CONFIG_MIPS
+static void loongson_set_min_mrrs_quirk(struct pci_dev *pdev)
+{
+	struct pci_bus *bus = pdev->bus;
+	struct pci_dev *bridge;
+	static const struct pci_device_id bridge_devids[] = {
+		{ PCI_VDEVICE(LOONGSON, DEV_LS2K_PCIE_PORT0) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT0) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT1) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT2) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT3) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT4) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT5) },
+		{ PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT6) },
+		{ 0, },
+	};
+
+	/* look for the matching bridge */
+	while (!pci_is_root_bus(bus)) {
+		bridge = bus->self;
+		bus = bus->parent;
+
+		if (pci_match_id(bridge_devids, bridge)) {
+			if (pcie_get_readrq(pdev) > 256) {
+				pci_info(pdev, "limiting MRRS to 256\n");
+				pcie_set_readrq(pdev, 256);
+			}
+			break;
+		}
+	}
+}
+DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, loongson_set_min_mrrs_quirk);
+#endif
+
 static void loongson_mrrs_quirk(struct pci_dev *pdev)
 {
-	/*
-	 * Some Loongson PCIe ports have h/w limitations of maximum read
-	 * request size. They can't handle anything larger than this. So
-	 * force this limit on any devices attached under these ports.
-	 */
 	struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus);
 
 	bridge->no_inc_mrrs = 1;
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 94ba61fe1c4411..0452cbc362eef7 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -751,7 +751,7 @@ static int vmd_pm_enable_quirk(struct pci_dev *pdev, void *userdata)
 	if (!(features & VMD_FEAT_BIOS_PM_QUIRK))
 		return 0;
 
-	pci_enable_link_state(pdev, PCIE_LINK_STATE_ALL);
+	pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL);
 
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_LTR);
 	if (!pos)
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 601129772b2d50..5b1f271c6034be 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -512,15 +512,12 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge)
 				if (pass && dev->subordinate) {
 					check_hotplug_bridge(slot, dev);
 					pcibios_resource_survey_bus(dev->subordinate);
-					if (pci_is_root_bus(bus))
-						__pci_bus_size_bridges(dev->subordinate, &add_list);
+					__pci_bus_size_bridges(dev->subordinate,
+							       &add_list);
 				}
 			}
 		}
-		if (pci_is_root_bus(bus))
-			__pci_bus_assign_resources(bus, &add_list, NULL);
-		else
-			pci_assign_unassigned_bridge_resources(bus->self);
+		__pci_bus_assign_resources(bus, &add_list, NULL);
 	}
 
 	acpiphp_sanitize_bus(bus);
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 50b04ae5c394e3..5dab531c8654d6 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -1041,7 +1041,7 @@ static struct pcie_link_state *pcie_aspm_get_link(struct pci_dev *pdev)
 	return bridge->link_state;
 }
 
-static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem)
+static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool locked)
 {
 	struct pcie_link_state *link = pcie_aspm_get_link(pdev);
 
@@ -1060,7 +1060,7 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem)
 		return -EPERM;
 	}
 
-	if (sem)
+	if (!locked)
 		down_read(&pci_bus_sem);
 	mutex_lock(&aspm_lock);
 	if (state & PCIE_LINK_STATE_L0S)
@@ -1082,7 +1082,7 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem)
 		link->clkpm_disable = 1;
 	pcie_set_clkpm(link, policy_to_clkpm_state(link));
 	mutex_unlock(&aspm_lock);
-	if (sem)
+	if (!locked)
 		up_read(&pci_bus_sem);
 
 	return 0;
@@ -1090,7 +1090,9 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem)
 
 int pci_disable_link_state_locked(struct pci_dev *pdev, int state)
 {
-	return __pci_disable_link_state(pdev, state, false);
+	lockdep_assert_held_read(&pci_bus_sem);
+
+	return __pci_disable_link_state(pdev, state, true);
 }
 EXPORT_SYMBOL(pci_disable_link_state_locked);
 
@@ -1105,21 +1107,11 @@ EXPORT_SYMBOL(pci_disable_link_state_locked);
  */
 int pci_disable_link_state(struct pci_dev *pdev, int state)
 {
-	return __pci_disable_link_state(pdev, state, true);
+	return __pci_disable_link_state(pdev, state, false);
 }
 EXPORT_SYMBOL(pci_disable_link_state);
 
-/**
- * pci_enable_link_state - Clear and set the default device link state so that
- * the link may be allowed to enter the specified states. Note that if the
- * BIOS didn't grant ASPM control to the OS, this does nothing because we can't
- * touch the LNKCTL register. Also note that this does not enable states
- * disabled by pci_disable_link_state(). Return 0 or a negative errno.
- *
- * @pdev: PCI device
- * @state: Mask of ASPM link states to enable
- */
-int pci_enable_link_state(struct pci_dev *pdev, int state)
+static int __pci_enable_link_state(struct pci_dev *pdev, int state, bool locked)
 {
 	struct pcie_link_state *link = pcie_aspm_get_link(pdev);
 
@@ -1136,7 +1128,8 @@ int pci_enable_link_state(struct pci_dev *pdev, int state)
 		return -EPERM;
 	}
 
-	down_read(&pci_bus_sem);
+	if (!locked)
+		down_read(&pci_bus_sem);
 	mutex_lock(&aspm_lock);
 	link->aspm_default = 0;
 	if (state & PCIE_LINK_STATE_L0S)
@@ -1157,12 +1150,48 @@ int pci_enable_link_state(struct pci_dev *pdev, int state)
 	link->clkpm_default = (state & PCIE_LINK_STATE_CLKPM) ? 1 : 0;
 	pcie_set_clkpm(link, policy_to_clkpm_state(link));
 	mutex_unlock(&aspm_lock);
-	up_read(&pci_bus_sem);
+	if (!locked)
+		up_read(&pci_bus_sem);
 
 	return 0;
 }
+
+/**
+ * pci_enable_link_state - Clear and set the default device link state so that
+ * the link may be allowed to enter the specified states. Note that if the
+ * BIOS didn't grant ASPM control to the OS, this does nothing because we can't
+ * touch the LNKCTL register. Also note that this does not enable states
+ * disabled by pci_disable_link_state(). Return 0 or a negative errno.
+ *
+ * @pdev: PCI device
+ * @state: Mask of ASPM link states to enable
+ */
+int pci_enable_link_state(struct pci_dev *pdev, int state)
+{
+	return __pci_enable_link_state(pdev, state, false);
+}
 EXPORT_SYMBOL(pci_enable_link_state);
 
+/**
+ * pci_enable_link_state_locked - Clear and set the default device link state
+ * so that the link may be allowed to enter the specified states. Note that if
+ * the BIOS didn't grant ASPM control to the OS, this does nothing because we
+ * can't touch the LNKCTL register. Also note that this does not enable states
+ * disabled by pci_disable_link_state(). Return 0 or a negative errno.
+ *
+ * @pdev: PCI device
+ * @state: Mask of ASPM link states to enable
+ *
+ * Context: Caller holds pci_bus_sem read lock.
+ */
+int pci_enable_link_state_locked(struct pci_dev *pdev, int state)
+{
+	lockdep_assert_held_read(&pci_bus_sem);
+
+	return __pci_enable_link_state(pdev, state, true);
+}
+EXPORT_SYMBOL(pci_enable_link_state_locked);
+
 static int pcie_aspm_set_policy(const char *val,
 				const struct kernel_param *kp)
 {
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index 014010d0358823..847b0dc41293d2 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -1816,7 +1816,7 @@ static int arm_cmn_event_add(struct perf_event *event, int flags)
 			idx = 0;
 			while (cmn->dtc[j].counters[idx])
 				if (++idx == CMN_DT_NUM_COUNTERS)
-					goto free_dtms;
+					return -ENOSPC;
 		}
 		hw->dtc_idx[j] = idx;
 	}
diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c
index 42b72042f6b375..2cc35dded0079f 100644
--- a/drivers/perf/arm_cspmu/arm_cspmu.c
+++ b/drivers/perf/arm_cspmu/arm_cspmu.c
@@ -676,6 +676,9 @@ static int arm_cspmu_event_init(struct perf_event *event)
 
 	cspmu = to_arm_cspmu(event->pmu);
 
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
 	/*
 	 * Following other "uncore" PMUs, we do not support sampling mode or
 	 * attach to a task (per-process mode).
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 18b91b56af1d46..6ca7be05229c10 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -428,12 +428,12 @@ static inline bool armv8pmu_event_is_chained(struct perf_event *event)
 #define	ARMV8_IDX_TO_COUNTER(x)	\
 	(((x) - ARMV8_IDX_COUNTER0) & ARMV8_PMU_COUNTER_MASK)
 
-static inline u32 armv8pmu_pmcr_read(void)
+static inline u64 armv8pmu_pmcr_read(void)
 {
 	return read_pmcr();
 }
 
-static inline void armv8pmu_pmcr_write(u32 val)
+static inline void armv8pmu_pmcr_write(u64 val)
 {
 	val &= ARMV8_PMU_PMCR_MASK;
 	isb();
@@ -957,7 +957,7 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 static void armv8pmu_reset(void *info)
 {
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
-	u32 pmcr;
+	u64 pmcr;
 
 	/* The counter and interrupt enable registers are unknown at reset. */
 	armv8pmu_disable_counter(U32_MAX);
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 96c7f670c8f0d1..16acd4dcdb96c7 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -22,7 +22,7 @@
 
 #include <asm/errata_list.h>
 #include <asm/sbi.h>
-#include <asm/hwcap.h>
+#include <asm/cpufeature.h>
 
 #define SYSCTL_NO_USER_ACCESS	0
 #define SYSCTL_USER_ACCESS	1
@@ -543,8 +543,7 @@ static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival)
 
 	if ((hwc->flags & PERF_EVENT_FLAG_USER_ACCESS) &&
 	    (hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT))
-		on_each_cpu_mask(mm_cpumask(event->owner->mm),
-				 pmu_sbi_set_scounteren, (void *)event, 1);
+		pmu_sbi_set_scounteren((void *)event);
 }
 
 static void pmu_sbi_ctr_stop(struct perf_event *event, unsigned long flag)
@@ -554,8 +553,7 @@ static void pmu_sbi_ctr_stop(struct perf_event *event, unsigned long flag)
 
 	if ((hwc->flags & PERF_EVENT_FLAG_USER_ACCESS) &&
 	    (hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT))
-		on_each_cpu_mask(mm_cpumask(event->owner->mm),
-				 pmu_sbi_reset_scounteren, (void *)event, 1);
+		pmu_sbi_reset_scounteren((void *)event);
 
 	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, hwc->idx, 1, flag, 0, 0, 0);
 	if (ret.error && (ret.error != SBI_ERR_ALREADY_STOPPED) &&
@@ -689,6 +687,11 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 
 	/* Firmware counter don't support overflow yet */
 	fidx = find_first_bit(cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS);
+	if (fidx == RISCV_MAX_COUNTERS) {
+		csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num));
+		return IRQ_NONE;
+	}
+
 	event = cpu_hw_evt->events[fidx];
 	if (!event) {
 		csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num));
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index 787354b849c75c..4cef568231bf08 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -87,7 +87,6 @@ source "drivers/phy/motorola/Kconfig"
 source "drivers/phy/mscc/Kconfig"
 source "drivers/phy/qualcomm/Kconfig"
 source "drivers/phy/ralink/Kconfig"
-source "drivers/phy/realtek/Kconfig"
 source "drivers/phy/renesas/Kconfig"
 source "drivers/phy/rockchip/Kconfig"
 source "drivers/phy/samsung/Kconfig"
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index 868a220ed0f6df..fb3dc9de611154 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -26,7 +26,6 @@ obj-y					+= allwinner/	\
 					   mscc/	\
 					   qualcomm/	\
 					   ralink/	\
-					   realtek/	\
 					   renesas/	\
 					   rockchip/	\
 					   samsung/	\
diff --git a/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c b/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c
index f021ec5a70e5c3..553725e1269c9d 100644
--- a/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c
+++ b/drivers/phy/mediatek/phy-mtk-mipi-dsi-mt8183.c
@@ -100,7 +100,7 @@ static void mtk_mipi_tx_pll_disable(struct clk_hw *hw)
 static long mtk_mipi_tx_pll_round_rate(struct clk_hw *hw, unsigned long rate,
 				       unsigned long *prate)
 {
-	return clamp_val(rate, 50000000, 1600000000);
+	return clamp_val(rate, 125000000, 1600000000);
 }
 
 static const struct clk_ops mtk_mipi_tx_pll_ops = {
diff --git a/drivers/phy/realtek/Kconfig b/drivers/phy/realtek/Kconfig
deleted file mode 100644
index 75ac7e7c31aec6..00000000000000
--- a/drivers/phy/realtek/Kconfig
+++ /dev/null
@@ -1,32 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Phy drivers for Realtek platforms
-#
-
-if ARCH_REALTEK || COMPILE_TEST
-
-config PHY_RTK_RTD_USB2PHY
-	tristate "Realtek RTD USB2 PHY Transceiver Driver"
-	depends on USB_SUPPORT
-	select GENERIC_PHY
-	select USB_PHY
-	select USB_COMMON
-	help
-	  Enable this to support Realtek SoC USB2 phy transceiver.
-	  The DHC (digital home center) RTD series SoCs used the Synopsys
-	  DWC3 USB IP. This driver will do the PHY initialization
-	  of the parameters.
-
-config PHY_RTK_RTD_USB3PHY
-	tristate "Realtek RTD USB3 PHY Transceiver Driver"
-	depends on USB_SUPPORT
-	select GENERIC_PHY
-	select USB_PHY
-	select USB_COMMON
-	help
-	  Enable this to support Realtek SoC USB3 phy transceiver.
-	  The DHC (digital home center) RTD series SoCs used the Synopsys
-	  DWC3 USB IP. This driver will do the PHY initialization
-	  of the parameters.
-
-endif # ARCH_REALTEK || COMPILE_TEST
diff --git a/drivers/phy/realtek/Makefile b/drivers/phy/realtek/Makefile
deleted file mode 100644
index ed7b47ff8a2685..00000000000000
--- a/drivers/phy/realtek/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_PHY_RTK_RTD_USB2PHY)	+= phy-rtk-usb2.o
-obj-$(CONFIG_PHY_RTK_RTD_USB3PHY)	+= phy-rtk-usb3.o
diff --git a/drivers/phy/realtek/phy-rtk-usb2.c b/drivers/phy/realtek/phy-rtk-usb2.c
deleted file mode 100644
index 0a6426285c67fc..00000000000000
--- a/drivers/phy/realtek/phy-rtk-usb2.c
+++ /dev/null
@@ -1,1325 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *  phy-rtk-usb2.c RTK usb2.0 PHY driver
- *
- * Copyright (C) 2023 Realtek Semiconductor Corporation
- *
- */
-
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/platform_device.h>
-#include <linux/uaccess.h>
-#include <linux/debugfs.h>
-#include <linux/nvmem-consumer.h>
-#include <linux/regmap.h>
-#include <linux/sys_soc.h>
-#include <linux/mfd/syscon.h>
-#include <linux/phy/phy.h>
-#include <linux/usb.h>
-#include <linux/usb/phy.h>
-#include <linux/usb/hcd.h>
-
-/* GUSB2PHYACCn register */
-#define PHY_NEW_REG_REQ BIT(25)
-#define PHY_VSTS_BUSY   BIT(23)
-#define PHY_VCTRL_SHIFT 8
-#define PHY_REG_DATA_MASK 0xff
-
-#define GET_LOW_NIBBLE(addr) ((addr) & 0x0f)
-#define GET_HIGH_NIBBLE(addr) (((addr) & 0xf0) >> 4)
-
-#define EFUS_USB_DC_CAL_RATE 2
-#define EFUS_USB_DC_CAL_MAX 7
-
-#define EFUS_USB_DC_DIS_RATE 1
-#define EFUS_USB_DC_DIS_MAX 7
-
-#define MAX_PHY_DATA_SIZE 20
-#define OFFEST_PHY_READ 0x20
-
-#define MAX_USB_PHY_NUM 4
-#define MAX_USB_PHY_PAGE0_DATA_SIZE 16
-#define MAX_USB_PHY_PAGE1_DATA_SIZE 16
-#define MAX_USB_PHY_PAGE2_DATA_SIZE 8
-
-#define SET_PAGE_OFFSET 0xf4
-#define SET_PAGE_0 0x9b
-#define SET_PAGE_1 0xbb
-#define SET_PAGE_2 0xdb
-
-#define PAGE_START 0xe0
-#define PAGE0_0XE4 0xe4
-#define PAGE0_0XE6 0xe6
-#define PAGE0_0XE7 0xe7
-#define PAGE1_0XE0 0xe0
-#define PAGE1_0XE2 0xe2
-
-#define SENSITIVITY_CTRL (BIT(4) | BIT(5) | BIT(6))
-#define ENABLE_AUTO_SENSITIVITY_CALIBRATION BIT(2)
-#define DEFAULT_DC_DRIVING_VALUE (0x8)
-#define DEFAULT_DC_DISCONNECTION_VALUE (0x6)
-#define HS_CLK_SELECT BIT(6)
-
-struct phy_reg {
-	void __iomem *reg_wrap_vstatus;
-	void __iomem *reg_gusb2phyacc0;
-	int vstatus_index;
-};
-
-struct phy_data {
-	u8 addr;
-	u8 data;
-};
-
-struct phy_cfg {
-	int page0_size;
-	struct phy_data page0[MAX_USB_PHY_PAGE0_DATA_SIZE];
-	int page1_size;
-	struct phy_data page1[MAX_USB_PHY_PAGE1_DATA_SIZE];
-	int page2_size;
-	struct phy_data page2[MAX_USB_PHY_PAGE2_DATA_SIZE];
-
-	int num_phy;
-
-	bool check_efuse;
-	int check_efuse_version;
-#define CHECK_EFUSE_V1 1
-#define CHECK_EFUSE_V2 2
-	int efuse_dc_driving_rate;
-	int efuse_dc_disconnect_rate;
-	int dc_driving_mask;
-	int dc_disconnect_mask;
-	bool usb_dc_disconnect_at_page0;
-	int driving_updated_for_dev_dis;
-
-	bool do_toggle;
-	bool do_toggle_driving;
-	bool use_default_parameter;
-	bool is_double_sensitivity_mode;
-};
-
-struct phy_parameter {
-	struct phy_reg phy_reg;
-
-	/* Get from efuse */
-	s8 efuse_usb_dc_cal;
-	s8 efuse_usb_dc_dis;
-
-	/* Get from dts */
-	bool inverse_hstx_sync_clock;
-	u32 driving_level;
-	s32 driving_level_compensate;
-	s32 disconnection_compensate;
-};
-
-struct rtk_phy {
-	struct usb_phy phy;
-	struct device *dev;
-
-	struct phy_cfg *phy_cfg;
-	int num_phy;
-	struct phy_parameter *phy_parameter;
-
-	struct dentry *debug_dir;
-};
-
-/* mapping 0xE0 to 0 ... 0xE7 to 7, 0xF0 to 8 ,,, 0xF7 to 15 */
-static inline int page_addr_to_array_index(u8 addr)
-{
-	return (int)((((addr) - PAGE_START) & 0x7) +
-		((((addr) - PAGE_START) & 0x10) >> 1));
-}
-
-static inline u8 array_index_to_page_addr(int index)
-{
-	return ((((index) + PAGE_START) & 0x7) +
-		((((index) & 0x8) << 1) + PAGE_START));
-}
-
-#define PHY_IO_TIMEOUT_USEC		(50000)
-#define PHY_IO_DELAY_US			(100)
-
-static inline int utmi_wait_register(void __iomem *reg, u32 mask, u32 result)
-{
-	int ret;
-	unsigned int val;
-
-	ret = read_poll_timeout(readl, val, ((val & mask) == result),
-				PHY_IO_DELAY_US, PHY_IO_TIMEOUT_USEC, false, reg);
-	if (ret) {
-		pr_err("%s can't program USB phy\n", __func__);
-		return -ETIMEDOUT;
-	}
-
-	return 0;
-}
-
-static char rtk_phy_read(struct phy_reg *phy_reg, char addr)
-{
-	void __iomem *reg_gusb2phyacc0 = phy_reg->reg_gusb2phyacc0;
-	unsigned int val;
-	int ret = 0;
-
-	addr -= OFFEST_PHY_READ;
-
-	/* polling until VBusy == 0 */
-	ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0);
-	if (ret)
-		return (char)ret;
-
-	/* VCtrl = low nibble of addr, and set PHY_NEW_REG_REQ */
-	val = PHY_NEW_REG_REQ | (GET_LOW_NIBBLE(addr) << PHY_VCTRL_SHIFT);
-	writel(val, reg_gusb2phyacc0);
-	ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0);
-	if (ret)
-		return (char)ret;
-
-	/* VCtrl = high nibble of addr, and set PHY_NEW_REG_REQ */
-	val = PHY_NEW_REG_REQ | (GET_HIGH_NIBBLE(addr) << PHY_VCTRL_SHIFT);
-	writel(val, reg_gusb2phyacc0);
-	ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0);
-	if (ret)
-		return (char)ret;
-
-	val = readl(reg_gusb2phyacc0);
-
-	return (char)(val & PHY_REG_DATA_MASK);
-}
-
-static int rtk_phy_write(struct phy_reg *phy_reg, char addr, char data)
-{
-	unsigned int val;
-	void __iomem *reg_wrap_vstatus = phy_reg->reg_wrap_vstatus;
-	void __iomem *reg_gusb2phyacc0 = phy_reg->reg_gusb2phyacc0;
-	int shift_bits = phy_reg->vstatus_index * 8;
-	int ret = 0;
-
-	/* write data to VStatusOut2 (data output to phy) */
-	writel((u32)data << shift_bits, reg_wrap_vstatus);
-
-	ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0);
-	if (ret)
-		return ret;
-
-	/* VCtrl = low nibble of addr, set PHY_NEW_REG_REQ */
-	val = PHY_NEW_REG_REQ | (GET_LOW_NIBBLE(addr) << PHY_VCTRL_SHIFT);
-
-	writel(val, reg_gusb2phyacc0);
-	ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0);
-	if (ret)
-		return ret;
-
-	/* VCtrl = high nibble of addr, set PHY_NEW_REG_REQ */
-	val = PHY_NEW_REG_REQ | (GET_HIGH_NIBBLE(addr) << PHY_VCTRL_SHIFT);
-
-	writel(val, reg_gusb2phyacc0);
-	ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-static int rtk_phy_set_page(struct phy_reg *phy_reg, int page)
-{
-	switch (page) {
-	case 0:
-		return rtk_phy_write(phy_reg, SET_PAGE_OFFSET, SET_PAGE_0);
-	case 1:
-		return rtk_phy_write(phy_reg, SET_PAGE_OFFSET, SET_PAGE_1);
-	case 2:
-		return rtk_phy_write(phy_reg, SET_PAGE_OFFSET, SET_PAGE_2);
-	default:
-		pr_err("%s error page=%d\n", __func__, page);
-	}
-
-	return -EINVAL;
-}
-
-static u8 __updated_dc_disconnect_level_page0_0xe4(struct phy_cfg *phy_cfg,
-						   struct phy_parameter *phy_parameter, u8 data)
-{
-	u8 ret;
-	s32 val;
-	s32 dc_disconnect_mask = phy_cfg->dc_disconnect_mask;
-	int offset = 4;
-
-	val = (s32)((data >> offset) & dc_disconnect_mask)
-		     + phy_parameter->efuse_usb_dc_dis
-		     + phy_parameter->disconnection_compensate;
-
-	if (val > dc_disconnect_mask)
-		val = dc_disconnect_mask;
-	else if (val < 0)
-		val = 0;
-
-	ret = (data & (~(dc_disconnect_mask << offset))) |
-		    (val & dc_disconnect_mask) << offset;
-
-	return ret;
-}
-
-/* updated disconnect level at page0 */
-static void update_dc_disconnect_level_at_page0(struct rtk_phy *rtk_phy,
-						struct phy_parameter *phy_parameter, bool update)
-{
-	struct phy_cfg *phy_cfg;
-	struct phy_reg *phy_reg;
-	struct phy_data *phy_data_page;
-	struct phy_data *phy_data;
-	u8 addr, data;
-	int offset = 4;
-	s32 dc_disconnect_mask;
-	int i;
-
-	phy_cfg = rtk_phy->phy_cfg;
-	phy_reg = &phy_parameter->phy_reg;
-
-	/* Set page 0 */
-	phy_data_page = phy_cfg->page0;
-	rtk_phy_set_page(phy_reg, 0);
-
-	i = page_addr_to_array_index(PAGE0_0XE4);
-	phy_data = phy_data_page + i;
-	if (!phy_data->addr) {
-		phy_data->addr = PAGE0_0XE4;
-		phy_data->data = rtk_phy_read(phy_reg, PAGE0_0XE4);
-	}
-
-	addr = phy_data->addr;
-	data = phy_data->data;
-	dc_disconnect_mask = phy_cfg->dc_disconnect_mask;
-
-	if (update)
-		data = __updated_dc_disconnect_level_page0_0xe4(phy_cfg, phy_parameter, data);
-	else
-		data = (data & ~(dc_disconnect_mask << offset)) |
-			(DEFAULT_DC_DISCONNECTION_VALUE << offset);
-
-	if (rtk_phy_write(phy_reg, addr, data))
-		dev_err(rtk_phy->dev,
-			"%s: Error to set page1 parameter addr=0x%x value=0x%x\n",
-			__func__, addr, data);
-}
-
-static u8 __updated_dc_disconnect_level_page1_0xe2(struct phy_cfg *phy_cfg,
-						   struct phy_parameter *phy_parameter, u8 data)
-{
-	u8 ret;
-	s32 val;
-	s32 dc_disconnect_mask = phy_cfg->dc_disconnect_mask;
-
-	if (phy_cfg->check_efuse_version == CHECK_EFUSE_V1) {
-		val = (s32)(data & dc_disconnect_mask)
-			    + phy_parameter->efuse_usb_dc_dis
-			    + phy_parameter->disconnection_compensate;
-	} else { /* for CHECK_EFUSE_V2 or no efuse */
-		if (phy_parameter->efuse_usb_dc_dis)
-			val = (s32)(phy_parameter->efuse_usb_dc_dis +
-				    phy_parameter->disconnection_compensate);
-		else
-			val = (s32)((data & dc_disconnect_mask) +
-				    phy_parameter->disconnection_compensate);
-	}
-
-	if (val > dc_disconnect_mask)
-		val = dc_disconnect_mask;
-	else if (val < 0)
-		val = 0;
-
-	ret = (data & (~dc_disconnect_mask)) | (val & dc_disconnect_mask);
-
-	return ret;
-}
-
-/* updated disconnect level at page1 */
-static void update_dc_disconnect_level_at_page1(struct rtk_phy *rtk_phy,
-						struct phy_parameter *phy_parameter, bool update)
-{
-	struct phy_cfg *phy_cfg;
-	struct phy_data *phy_data_page;
-	struct phy_data *phy_data;
-	struct phy_reg *phy_reg;
-	u8 addr, data;
-	s32 dc_disconnect_mask;
-	int i;
-
-	phy_cfg = rtk_phy->phy_cfg;
-	phy_reg = &phy_parameter->phy_reg;
-
-	/* Set page 1 */
-	phy_data_page = phy_cfg->page1;
-	rtk_phy_set_page(phy_reg, 1);
-
-	i = page_addr_to_array_index(PAGE1_0XE2);
-	phy_data = phy_data_page + i;
-	if (!phy_data->addr) {
-		phy_data->addr = PAGE1_0XE2;
-		phy_data->data = rtk_phy_read(phy_reg, PAGE1_0XE2);
-	}
-
-	addr = phy_data->addr;
-	data = phy_data->data;
-	dc_disconnect_mask = phy_cfg->dc_disconnect_mask;
-
-	if (update)
-		data = __updated_dc_disconnect_level_page1_0xe2(phy_cfg, phy_parameter, data);
-	else
-		data = (data & ~dc_disconnect_mask) | DEFAULT_DC_DISCONNECTION_VALUE;
-
-	if (rtk_phy_write(phy_reg, addr, data))
-		dev_err(rtk_phy->dev,
-			"%s: Error to set page1 parameter addr=0x%x value=0x%x\n",
-			__func__, addr, data);
-}
-
-static void update_dc_disconnect_level(struct rtk_phy *rtk_phy,
-				       struct phy_parameter *phy_parameter, bool update)
-{
-	struct phy_cfg *phy_cfg = rtk_phy->phy_cfg;
-
-	if (phy_cfg->usb_dc_disconnect_at_page0)
-		update_dc_disconnect_level_at_page0(rtk_phy, phy_parameter, update);
-	else
-		update_dc_disconnect_level_at_page1(rtk_phy, phy_parameter, update);
-}
-
-static u8 __update_dc_driving_page0_0xe4(struct phy_cfg *phy_cfg,
-					 struct phy_parameter *phy_parameter, u8 data)
-{
-	s32 driving_level_compensate = phy_parameter->driving_level_compensate;
-	s32 dc_driving_mask = phy_cfg->dc_driving_mask;
-	s32 val;
-	u8 ret;
-
-	if (phy_cfg->check_efuse_version == CHECK_EFUSE_V1) {
-		val = (s32)(data & dc_driving_mask) + driving_level_compensate
-			    + phy_parameter->efuse_usb_dc_cal;
-	} else { /* for CHECK_EFUSE_V2 or no efuse */
-		if (phy_parameter->efuse_usb_dc_cal)
-			val = (s32)((phy_parameter->efuse_usb_dc_cal & dc_driving_mask)
-				    + driving_level_compensate);
-		else
-			val = (s32)(data & dc_driving_mask);
-	}
-
-	if (val > dc_driving_mask)
-		val = dc_driving_mask;
-	else if (val < 0)
-		val = 0;
-
-	ret = (data & (~dc_driving_mask)) | (val & dc_driving_mask);
-
-	return ret;
-}
-
-static void update_dc_driving_level(struct rtk_phy *rtk_phy,
-				    struct phy_parameter *phy_parameter)
-{
-	struct phy_cfg *phy_cfg;
-	struct phy_reg *phy_reg;
-
-	phy_reg = &phy_parameter->phy_reg;
-	phy_cfg = rtk_phy->phy_cfg;
-	if (!phy_cfg->page0[4].addr) {
-		rtk_phy_set_page(phy_reg, 0);
-		phy_cfg->page0[4].addr = PAGE0_0XE4;
-		phy_cfg->page0[4].data = rtk_phy_read(phy_reg, PAGE0_0XE4);
-	}
-
-	if (phy_parameter->driving_level != DEFAULT_DC_DRIVING_VALUE) {
-		u32 dc_driving_mask;
-		u8 driving_level;
-		u8 data;
-
-		data = phy_cfg->page0[4].data;
-		dc_driving_mask = phy_cfg->dc_driving_mask;
-		driving_level = data & dc_driving_mask;
-
-		dev_dbg(rtk_phy->dev, "%s driving_level=%d => dts driving_level=%d\n",
-			__func__, driving_level, phy_parameter->driving_level);
-
-		phy_cfg->page0[4].data = (data & (~dc_driving_mask)) |
-			    (phy_parameter->driving_level & dc_driving_mask);
-	}
-
-	phy_cfg->page0[4].data = __update_dc_driving_page0_0xe4(phy_cfg,
-								phy_parameter,
-								phy_cfg->page0[4].data);
-}
-
-static void update_hs_clk_select(struct rtk_phy *rtk_phy,
-				 struct phy_parameter *phy_parameter)
-{
-	struct phy_cfg *phy_cfg;
-	struct phy_reg *phy_reg;
-
-	phy_cfg = rtk_phy->phy_cfg;
-	phy_reg = &phy_parameter->phy_reg;
-
-	if (phy_parameter->inverse_hstx_sync_clock) {
-		if (!phy_cfg->page0[6].addr) {
-			rtk_phy_set_page(phy_reg, 0);
-			phy_cfg->page0[6].addr = PAGE0_0XE6;
-			phy_cfg->page0[6].data = rtk_phy_read(phy_reg, PAGE0_0XE6);
-		}
-
-		phy_cfg->page0[6].data = phy_cfg->page0[6].data | HS_CLK_SELECT;
-	}
-}
-
-static void do_rtk_phy_toggle(struct rtk_phy *rtk_phy,
-			      int index, bool connect)
-{
-	struct phy_parameter *phy_parameter;
-	struct phy_cfg *phy_cfg;
-	struct phy_reg *phy_reg;
-	struct phy_data *phy_data_page;
-	u8 addr, data;
-	int i;
-
-	phy_cfg = rtk_phy->phy_cfg;
-	phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-	phy_reg = &phy_parameter->phy_reg;
-
-	if (!phy_cfg->do_toggle)
-		goto out;
-
-	if (phy_cfg->is_double_sensitivity_mode)
-		goto do_toggle_driving;
-
-	/* Set page 0 */
-	rtk_phy_set_page(phy_reg, 0);
-
-	addr = PAGE0_0XE7;
-	data = rtk_phy_read(phy_reg, addr);
-
-	if (connect)
-		rtk_phy_write(phy_reg, addr, data & (~SENSITIVITY_CTRL));
-	else
-		rtk_phy_write(phy_reg, addr, data | (SENSITIVITY_CTRL));
-
-do_toggle_driving:
-
-	if (!phy_cfg->do_toggle_driving)
-		goto do_toggle;
-
-	/* Page 0 addr 0xE4 driving capability */
-
-	/* Set page 0 */
-	phy_data_page = phy_cfg->page0;
-	rtk_phy_set_page(phy_reg, 0);
-
-	i = page_addr_to_array_index(PAGE0_0XE4);
-	addr = phy_data_page[i].addr;
-	data = phy_data_page[i].data;
-
-	if (connect) {
-		rtk_phy_write(phy_reg, addr, data);
-	} else {
-		u8 value;
-		s32 tmp;
-		s32 driving_updated =
-			    phy_cfg->driving_updated_for_dev_dis;
-		s32 dc_driving_mask = phy_cfg->dc_driving_mask;
-
-		tmp = (s32)(data & dc_driving_mask) + driving_updated;
-
-		if (tmp > dc_driving_mask)
-			tmp = dc_driving_mask;
-		else if (tmp < 0)
-			tmp = 0;
-
-		value = (data & (~dc_driving_mask)) | (tmp & dc_driving_mask);
-
-		rtk_phy_write(phy_reg, addr, value);
-	}
-
-do_toggle:
-	/* restore dc disconnect level before toggle */
-	update_dc_disconnect_level(rtk_phy, phy_parameter, false);
-
-	/* Set page 1 */
-	rtk_phy_set_page(phy_reg, 1);
-
-	addr = PAGE1_0XE0;
-	data = rtk_phy_read(phy_reg, addr);
-
-	rtk_phy_write(phy_reg, addr, data &
-		      (~ENABLE_AUTO_SENSITIVITY_CALIBRATION));
-	mdelay(1);
-	rtk_phy_write(phy_reg, addr, data |
-		      (ENABLE_AUTO_SENSITIVITY_CALIBRATION));
-
-	/* update dc disconnect level after toggle */
-	update_dc_disconnect_level(rtk_phy, phy_parameter, true);
-
-out:
-	return;
-}
-
-static int do_rtk_phy_init(struct rtk_phy *rtk_phy, int index)
-{
-	struct phy_parameter *phy_parameter;
-	struct phy_cfg *phy_cfg;
-	struct phy_data *phy_data_page;
-	struct phy_reg *phy_reg;
-	int i;
-
-	phy_cfg = rtk_phy->phy_cfg;
-	phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-	phy_reg = &phy_parameter->phy_reg;
-
-	if (phy_cfg->use_default_parameter) {
-		dev_dbg(rtk_phy->dev, "%s phy#%d use default parameter\n",
-			__func__, index);
-		goto do_toggle;
-	}
-
-	/* Set page 0 */
-	phy_data_page = phy_cfg->page0;
-	rtk_phy_set_page(phy_reg, 0);
-
-	for (i = 0; i < phy_cfg->page0_size; i++) {
-		struct phy_data *phy_data = phy_data_page + i;
-		u8 addr = phy_data->addr;
-		u8 data = phy_data->data;
-
-		if (!addr)
-			continue;
-
-		if (rtk_phy_write(phy_reg, addr, data)) {
-			dev_err(rtk_phy->dev,
-				"%s: Error to set page0 parameter addr=0x%x value=0x%x\n",
-				__func__, addr, data);
-			return -EINVAL;
-		}
-	}
-
-	/* Set page 1 */
-	phy_data_page = phy_cfg->page1;
-	rtk_phy_set_page(phy_reg, 1);
-
-	for (i = 0; i < phy_cfg->page1_size; i++) {
-		struct phy_data *phy_data = phy_data_page + i;
-		u8 addr = phy_data->addr;
-		u8 data = phy_data->data;
-
-		if (!addr)
-			continue;
-
-		if (rtk_phy_write(phy_reg, addr, data)) {
-			dev_err(rtk_phy->dev,
-				"%s: Error to set page1 parameter addr=0x%x value=0x%x\n",
-				__func__, addr, data);
-			return -EINVAL;
-		}
-	}
-
-	if (phy_cfg->page2_size == 0)
-		goto do_toggle;
-
-	/* Set page 2 */
-	phy_data_page = phy_cfg->page2;
-	rtk_phy_set_page(phy_reg, 2);
-
-	for (i = 0; i < phy_cfg->page2_size; i++) {
-		struct phy_data *phy_data = phy_data_page + i;
-		u8 addr = phy_data->addr;
-		u8 data = phy_data->data;
-
-		if (!addr)
-			continue;
-
-		if (rtk_phy_write(phy_reg, addr, data)) {
-			dev_err(rtk_phy->dev,
-				"%s: Error to set page2 parameter addr=0x%x value=0x%x\n",
-				__func__, addr, data);
-			return -EINVAL;
-		}
-	}
-
-do_toggle:
-	do_rtk_phy_toggle(rtk_phy, index, false);
-
-	return 0;
-}
-
-static int rtk_phy_init(struct phy *phy)
-{
-	struct rtk_phy *rtk_phy = phy_get_drvdata(phy);
-	unsigned long phy_init_time = jiffies;
-	int i, ret = 0;
-
-	if (!rtk_phy)
-		return -EINVAL;
-
-	for (i = 0; i < rtk_phy->num_phy; i++)
-		ret = do_rtk_phy_init(rtk_phy, i);
-
-	dev_dbg(rtk_phy->dev, "Initialized RTK USB 2.0 PHY (take %dms)\n",
-		jiffies_to_msecs(jiffies - phy_init_time));
-	return ret;
-}
-
-static int rtk_phy_exit(struct phy *phy)
-{
-	return 0;
-}
-
-static const struct phy_ops ops = {
-	.init		= rtk_phy_init,
-	.exit		= rtk_phy_exit,
-	.owner		= THIS_MODULE,
-};
-
-static void rtk_phy_toggle(struct usb_phy *usb2_phy, bool connect, int port)
-{
-	int index = port;
-	struct rtk_phy *rtk_phy = NULL;
-
-	rtk_phy = dev_get_drvdata(usb2_phy->dev);
-
-	if (index > rtk_phy->num_phy) {
-		dev_err(rtk_phy->dev, "%s: The port=%d is not in usb phy (num_phy=%d)\n",
-			__func__, index, rtk_phy->num_phy);
-		return;
-	}
-
-	do_rtk_phy_toggle(rtk_phy, index, connect);
-}
-
-static int rtk_phy_notify_port_status(struct usb_phy *x, int port,
-				      u16 portstatus, u16 portchange)
-{
-	bool connect = false;
-
-	pr_debug("%s port=%d portstatus=0x%x portchange=0x%x\n",
-		 __func__, port, (int)portstatus, (int)portchange);
-	if (portstatus & USB_PORT_STAT_CONNECTION)
-		connect = true;
-
-	if (portchange & USB_PORT_STAT_C_CONNECTION)
-		rtk_phy_toggle(x, connect, port);
-
-	return 0;
-}
-
-#ifdef CONFIG_DEBUG_FS
-static struct dentry *create_phy_debug_root(void)
-{
-	struct dentry *phy_debug_root;
-
-	phy_debug_root = debugfs_lookup("phy", usb_debug_root);
-	if (!phy_debug_root)
-		phy_debug_root = debugfs_create_dir("phy", usb_debug_root);
-
-	return phy_debug_root;
-}
-
-static int rtk_usb2_parameter_show(struct seq_file *s, void *unused)
-{
-	struct rtk_phy *rtk_phy = s->private;
-	struct phy_cfg *phy_cfg;
-	int i, index;
-
-	phy_cfg = rtk_phy->phy_cfg;
-
-	seq_puts(s, "Property:\n");
-	seq_printf(s, "  check_efuse: %s\n",
-		   phy_cfg->check_efuse ? "Enable" : "Disable");
-	seq_printf(s, "  check_efuse_version: %d\n",
-		   phy_cfg->check_efuse_version);
-	seq_printf(s, "  efuse_dc_driving_rate: %d\n",
-		   phy_cfg->efuse_dc_driving_rate);
-	seq_printf(s, "  dc_driving_mask: 0x%x\n",
-		   phy_cfg->dc_driving_mask);
-	seq_printf(s, "  efuse_dc_disconnect_rate: %d\n",
-		   phy_cfg->efuse_dc_disconnect_rate);
-	seq_printf(s, "  dc_disconnect_mask: 0x%x\n",
-		   phy_cfg->dc_disconnect_mask);
-	seq_printf(s, "  usb_dc_disconnect_at_page0: %s\n",
-		   phy_cfg->usb_dc_disconnect_at_page0 ? "true" : "false");
-	seq_printf(s, "  do_toggle: %s\n",
-		   phy_cfg->do_toggle ? "Enable" : "Disable");
-	seq_printf(s, "  do_toggle_driving: %s\n",
-		   phy_cfg->do_toggle_driving ? "Enable" : "Disable");
-	seq_printf(s, "  driving_updated_for_dev_dis: 0x%x\n",
-		   phy_cfg->driving_updated_for_dev_dis);
-	seq_printf(s, "  use_default_parameter: %s\n",
-		   phy_cfg->use_default_parameter ? "Enable" : "Disable");
-	seq_printf(s, "  is_double_sensitivity_mode: %s\n",
-		   phy_cfg->is_double_sensitivity_mode ? "Enable" : "Disable");
-
-	for (index = 0; index < rtk_phy->num_phy; index++) {
-		struct phy_parameter *phy_parameter;
-		struct phy_reg *phy_reg;
-		struct phy_data *phy_data_page;
-
-		phy_parameter =  &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-		phy_reg = &phy_parameter->phy_reg;
-
-		seq_printf(s, "PHY %d:\n", index);
-
-		seq_puts(s, "Page 0:\n");
-		/* Set page 0 */
-		phy_data_page = phy_cfg->page0;
-		rtk_phy_set_page(phy_reg, 0);
-
-		for (i = 0; i < phy_cfg->page0_size; i++) {
-			struct phy_data *phy_data = phy_data_page + i;
-			u8 addr = array_index_to_page_addr(i);
-			u8 data = phy_data->data;
-			u8 value = rtk_phy_read(phy_reg, addr);
-
-			if (phy_data->addr)
-				seq_printf(s, "  Page 0: addr=0x%x data=0x%02x ==> read value=0x%02x\n",
-					   addr, data, value);
-			else
-				seq_printf(s, "  Page 0: addr=0x%x data=none ==> read value=0x%02x\n",
-					   addr, value);
-		}
-
-		seq_puts(s, "Page 1:\n");
-		/* Set page 1 */
-		phy_data_page = phy_cfg->page1;
-		rtk_phy_set_page(phy_reg, 1);
-
-		for (i = 0; i < phy_cfg->page1_size; i++) {
-			struct phy_data *phy_data = phy_data_page + i;
-			u8 addr = array_index_to_page_addr(i);
-			u8 data = phy_data->data;
-			u8 value = rtk_phy_read(phy_reg, addr);
-
-			if (phy_data->addr)
-				seq_printf(s, "  Page 1: addr=0x%x data=0x%02x ==> read value=0x%02x\n",
-					   addr, data, value);
-			else
-				seq_printf(s, "  Page 1: addr=0x%x data=none ==> read value=0x%02x\n",
-					   addr, value);
-		}
-
-		if (phy_cfg->page2_size == 0)
-			goto out;
-
-		seq_puts(s, "Page 2:\n");
-		/* Set page 2 */
-		phy_data_page = phy_cfg->page2;
-		rtk_phy_set_page(phy_reg, 2);
-
-		for (i = 0; i < phy_cfg->page2_size; i++) {
-			struct phy_data *phy_data = phy_data_page + i;
-			u8 addr = array_index_to_page_addr(i);
-			u8 data = phy_data->data;
-			u8 value = rtk_phy_read(phy_reg, addr);
-
-			if (phy_data->addr)
-				seq_printf(s, "  Page 2: addr=0x%x data=0x%02x ==> read value=0x%02x\n",
-					   addr, data, value);
-			else
-				seq_printf(s, "  Page 2: addr=0x%x data=none ==> read value=0x%02x\n",
-					   addr, value);
-		}
-
-out:
-		seq_puts(s, "PHY Property:\n");
-		seq_printf(s, "  efuse_usb_dc_cal: %d\n",
-			   (int)phy_parameter->efuse_usb_dc_cal);
-		seq_printf(s, "  efuse_usb_dc_dis: %d\n",
-			   (int)phy_parameter->efuse_usb_dc_dis);
-		seq_printf(s, "  inverse_hstx_sync_clock: %s\n",
-			   phy_parameter->inverse_hstx_sync_clock ? "Enable" : "Disable");
-		seq_printf(s, "  driving_level: %d\n",
-			   phy_parameter->driving_level);
-		seq_printf(s, "  driving_level_compensate: %d\n",
-			   phy_parameter->driving_level_compensate);
-		seq_printf(s, "  disconnection_compensate: %d\n",
-			   phy_parameter->disconnection_compensate);
-	}
-
-	return 0;
-}
-DEFINE_SHOW_ATTRIBUTE(rtk_usb2_parameter);
-
-static inline void create_debug_files(struct rtk_phy *rtk_phy)
-{
-	struct dentry *phy_debug_root = NULL;
-
-	phy_debug_root = create_phy_debug_root();
-	if (!phy_debug_root)
-		return;
-
-	rtk_phy->debug_dir = debugfs_create_dir(dev_name(rtk_phy->dev),
-						phy_debug_root);
-
-	debugfs_create_file("parameter", 0444, rtk_phy->debug_dir, rtk_phy,
-			    &rtk_usb2_parameter_fops);
-
-	return;
-}
-
-static inline void remove_debug_files(struct rtk_phy *rtk_phy)
-{
-	debugfs_remove_recursive(rtk_phy->debug_dir);
-}
-#else
-static inline void create_debug_files(struct rtk_phy *rtk_phy) { }
-static inline void remove_debug_files(struct rtk_phy *rtk_phy) { }
-#endif /* CONFIG_DEBUG_FS */
-
-static int get_phy_data_by_efuse(struct rtk_phy *rtk_phy,
-				 struct phy_parameter *phy_parameter, int index)
-{
-	struct phy_cfg *phy_cfg = rtk_phy->phy_cfg;
-	u8 value = 0;
-	struct nvmem_cell *cell;
-	struct soc_device_attribute rtk_soc_groot[] = {
-		    { .family = "Realtek Groot",},
-		    { /* empty */ } };
-
-	if (!phy_cfg->check_efuse)
-		goto out;
-
-	/* Read efuse for usb dc cal */
-	cell = nvmem_cell_get(rtk_phy->dev, "usb-dc-cal");
-	if (IS_ERR(cell)) {
-		dev_dbg(rtk_phy->dev, "%s no usb-dc-cal: %ld\n",
-			__func__, PTR_ERR(cell));
-	} else {
-		unsigned char *buf;
-		size_t buf_size;
-
-		buf = nvmem_cell_read(cell, &buf_size);
-		if (!IS_ERR(buf)) {
-			value = buf[0] & phy_cfg->dc_driving_mask;
-			kfree(buf);
-		}
-		nvmem_cell_put(cell);
-	}
-
-	if (phy_cfg->check_efuse_version == CHECK_EFUSE_V1) {
-		int rate = phy_cfg->efuse_dc_driving_rate;
-
-		if (value <= EFUS_USB_DC_CAL_MAX)
-			phy_parameter->efuse_usb_dc_cal = (int8_t)(value * rate);
-		else
-			phy_parameter->efuse_usb_dc_cal = -(int8_t)
-				    ((EFUS_USB_DC_CAL_MAX & value) * rate);
-
-		if (soc_device_match(rtk_soc_groot)) {
-			dev_dbg(rtk_phy->dev, "For groot IC we need a workaround to adjust efuse_usb_dc_cal\n");
-
-			/* We don't multiple dc_cal_rate=2 for positive dc cal compensate */
-			if (value <= EFUS_USB_DC_CAL_MAX)
-				phy_parameter->efuse_usb_dc_cal = (int8_t)(value);
-
-			/* We set max dc cal compensate is 0x8 if otp is 0x7 */
-			if (value == 0x7)
-				phy_parameter->efuse_usb_dc_cal = (int8_t)(value + 1);
-		}
-	} else { /* for CHECK_EFUSE_V2 */
-		phy_parameter->efuse_usb_dc_cal = value & phy_cfg->dc_driving_mask;
-	}
-
-	/* Read efuse for usb dc disconnect level */
-	value = 0;
-	cell = nvmem_cell_get(rtk_phy->dev, "usb-dc-dis");
-	if (IS_ERR(cell)) {
-		dev_dbg(rtk_phy->dev, "%s no usb-dc-dis: %ld\n",
-			__func__, PTR_ERR(cell));
-	} else {
-		unsigned char *buf;
-		size_t buf_size;
-
-		buf = nvmem_cell_read(cell, &buf_size);
-		if (!IS_ERR(buf)) {
-			value = buf[0] & phy_cfg->dc_disconnect_mask;
-			kfree(buf);
-		}
-		nvmem_cell_put(cell);
-	}
-
-	if (phy_cfg->check_efuse_version == CHECK_EFUSE_V1) {
-		int rate = phy_cfg->efuse_dc_disconnect_rate;
-
-		if (value <= EFUS_USB_DC_DIS_MAX)
-			phy_parameter->efuse_usb_dc_dis = (int8_t)(value * rate);
-		else
-			phy_parameter->efuse_usb_dc_dis = -(int8_t)
-				    ((EFUS_USB_DC_DIS_MAX & value) * rate);
-	} else { /* for CHECK_EFUSE_V2 */
-		phy_parameter->efuse_usb_dc_dis = value & phy_cfg->dc_disconnect_mask;
-	}
-
-out:
-	return 0;
-}
-
-static int parse_phy_data(struct rtk_phy *rtk_phy)
-{
-	struct device *dev = rtk_phy->dev;
-	struct device_node *np = dev->of_node;
-	struct phy_parameter *phy_parameter;
-	int ret = 0;
-	int index;
-
-	rtk_phy->phy_parameter = devm_kzalloc(dev, sizeof(struct phy_parameter) *
-						rtk_phy->num_phy, GFP_KERNEL);
-	if (!rtk_phy->phy_parameter)
-		return -ENOMEM;
-
-	for (index = 0; index < rtk_phy->num_phy; index++) {
-		phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-
-		phy_parameter->phy_reg.reg_wrap_vstatus = of_iomap(np, 0);
-		phy_parameter->phy_reg.reg_gusb2phyacc0 = of_iomap(np, 1) + index;
-		phy_parameter->phy_reg.vstatus_index = index;
-
-		if (of_property_read_bool(np, "realtek,inverse-hstx-sync-clock"))
-			phy_parameter->inverse_hstx_sync_clock = true;
-		else
-			phy_parameter->inverse_hstx_sync_clock = false;
-
-		if (of_property_read_u32_index(np, "realtek,driving-level",
-					       index, &phy_parameter->driving_level))
-			phy_parameter->driving_level = DEFAULT_DC_DRIVING_VALUE;
-
-		if (of_property_read_u32_index(np, "realtek,driving-level-compensate",
-					       index, &phy_parameter->driving_level_compensate))
-			phy_parameter->driving_level_compensate = 0;
-
-		if (of_property_read_u32_index(np, "realtek,disconnection-compensate",
-					       index, &phy_parameter->disconnection_compensate))
-			phy_parameter->disconnection_compensate = 0;
-
-		get_phy_data_by_efuse(rtk_phy, phy_parameter, index);
-
-		update_dc_driving_level(rtk_phy, phy_parameter);
-
-		update_hs_clk_select(rtk_phy, phy_parameter);
-	}
-
-	return ret;
-}
-
-static int rtk_usb2phy_probe(struct platform_device *pdev)
-{
-	struct rtk_phy *rtk_phy;
-	struct device *dev = &pdev->dev;
-	struct phy *generic_phy;
-	struct phy_provider *phy_provider;
-	const struct phy_cfg *phy_cfg;
-	int ret = 0;
-
-	phy_cfg = of_device_get_match_data(dev);
-	if (!phy_cfg) {
-		dev_err(dev, "phy config are not assigned!\n");
-		return -EINVAL;
-	}
-
-	rtk_phy = devm_kzalloc(dev, sizeof(*rtk_phy), GFP_KERNEL);
-	if (!rtk_phy)
-		return -ENOMEM;
-
-	rtk_phy->dev			= &pdev->dev;
-	rtk_phy->phy.dev		= rtk_phy->dev;
-	rtk_phy->phy.label		= "rtk-usb2phy";
-	rtk_phy->phy.notify_port_status = rtk_phy_notify_port_status;
-
-	rtk_phy->phy_cfg = devm_kzalloc(dev, sizeof(*phy_cfg), GFP_KERNEL);
-
-	memcpy(rtk_phy->phy_cfg, phy_cfg, sizeof(*phy_cfg));
-
-	rtk_phy->num_phy = phy_cfg->num_phy;
-
-	ret = parse_phy_data(rtk_phy);
-	if (ret)
-		goto err;
-
-	platform_set_drvdata(pdev, rtk_phy);
-
-	generic_phy = devm_phy_create(rtk_phy->dev, NULL, &ops);
-	if (IS_ERR(generic_phy))
-		return PTR_ERR(generic_phy);
-
-	phy_set_drvdata(generic_phy, rtk_phy);
-
-	phy_provider = devm_of_phy_provider_register(rtk_phy->dev,
-						     of_phy_simple_xlate);
-	if (IS_ERR(phy_provider))
-		return PTR_ERR(phy_provider);
-
-	ret = usb_add_phy_dev(&rtk_phy->phy);
-	if (ret)
-		goto err;
-
-	create_debug_files(rtk_phy);
-
-err:
-	return ret;
-}
-
-static void rtk_usb2phy_remove(struct platform_device *pdev)
-{
-	struct rtk_phy *rtk_phy = platform_get_drvdata(pdev);
-
-	remove_debug_files(rtk_phy);
-
-	usb_remove_phy(&rtk_phy->phy);
-}
-
-static const struct phy_cfg rtd1295_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [0] = {0xe0, 0x90},
-		   [3] = {0xe3, 0x3a},
-		   [4] = {0xe4, 0x68},
-		   [6] = {0xe6, 0x91},
-		  [13] = {0xf5, 0x81},
-		  [15] = {0xf7, 0x02}, },
-	.page1_size = 8,
-	.page1 = { /* default parameter */ },
-	.page2_size = 0,
-	.page2 = { /* no parameter */ },
-	.num_phy = 1,
-	.check_efuse = false,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = 1,
-	.dc_driving_mask = 0xf,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = true,
-	.do_toggle = true,
-	.do_toggle_driving = false,
-	.driving_updated_for_dev_dis = 0xf,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = false,
-};
-
-static const struct phy_cfg rtd1395_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [4] = {0xe4, 0xac},
-		  [13] = {0xf5, 0x00},
-		  [15] = {0xf7, 0x02}, },
-	.page1_size = 8,
-	.page1 = { /* default parameter */ },
-	.page2_size = 0,
-	.page2 = { /* no parameter */ },
-	.num_phy = 1,
-	.check_efuse = false,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = 1,
-	.dc_driving_mask = 0xf,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = true,
-	.do_toggle = true,
-	.do_toggle_driving = false,
-	.driving_updated_for_dev_dis = 0xf,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = false,
-};
-
-static const struct phy_cfg rtd1395_phy_cfg_2port = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [4] = {0xe4, 0xac},
-		  [13] = {0xf5, 0x00},
-		  [15] = {0xf7, 0x02}, },
-	.page1_size = 8,
-	.page1 = { /* default parameter */ },
-	.page2_size = 0,
-	.page2 = { /* no parameter */ },
-	.num_phy = 2,
-	.check_efuse = false,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = 1,
-	.dc_driving_mask = 0xf,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = true,
-	.do_toggle = true,
-	.do_toggle_driving = false,
-	.driving_updated_for_dev_dis = 0xf,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = false,
-};
-
-static const struct phy_cfg rtd1619_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [4] = {0xe4, 0x68}, },
-	.page1_size = 8,
-	.page1 = { /* default parameter */ },
-	.page2_size = 0,
-	.page2 = { /* no parameter */ },
-	.num_phy = 1,
-	.check_efuse = true,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = 1,
-	.dc_driving_mask = 0xf,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = true,
-	.do_toggle = true,
-	.do_toggle_driving = false,
-	.driving_updated_for_dev_dis = 0xf,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = false,
-};
-
-static const struct phy_cfg rtd1319_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [0] = {0xe0, 0x18},
-		   [4] = {0xe4, 0x6a},
-		   [7] = {0xe7, 0x71},
-		  [13] = {0xf5, 0x15},
-		  [15] = {0xf7, 0x32}, },
-	.page1_size = 8,
-	.page1 = { [3] = {0xe3, 0x44}, },
-	.page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE,
-	.page2 = { [0] = {0xe0, 0x01}, },
-	.num_phy = 1,
-	.check_efuse = true,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = 1,
-	.dc_driving_mask = 0xf,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = true,
-	.do_toggle = true,
-	.do_toggle_driving = true,
-	.driving_updated_for_dev_dis = 0xf,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = true,
-};
-
-static const struct phy_cfg rtd1312c_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [0] = {0xe0, 0x14},
-		   [4] = {0xe4, 0x67},
-		   [5] = {0xe5, 0x55}, },
-	.page1_size = 8,
-	.page1 = { [3] = {0xe3, 0x23},
-		   [6] = {0xe6, 0x58}, },
-	.page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE,
-	.page2 = { /* default parameter */ },
-	.num_phy = 1,
-	.check_efuse = true,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = 1,
-	.dc_driving_mask = 0xf,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = true,
-	.do_toggle = true,
-	.do_toggle_driving = true,
-	.driving_updated_for_dev_dis = 0xf,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = true,
-};
-
-static const struct phy_cfg rtd1619b_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [0] = {0xe0, 0xa3},
-		   [4] = {0xe4, 0x88},
-		   [5] = {0xe5, 0x4f},
-		   [6] = {0xe6, 0x02}, },
-	.page1_size = 8,
-	.page1 = { [3] = {0xe3, 0x64}, },
-	.page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE,
-	.page2 = { [7] = {0xe7, 0x45}, },
-	.num_phy = 1,
-	.check_efuse = true,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = EFUS_USB_DC_CAL_RATE,
-	.dc_driving_mask = 0x1f,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = false,
-	.do_toggle = true,
-	.do_toggle_driving = true,
-	.driving_updated_for_dev_dis = 0x8,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = true,
-};
-
-static const struct phy_cfg rtd1319d_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [0] = {0xe0, 0xa3},
-		   [4] = {0xe4, 0x8e},
-		   [5] = {0xe5, 0x4f},
-		   [6] = {0xe6, 0x02}, },
-	.page1_size = MAX_USB_PHY_PAGE1_DATA_SIZE,
-	.page1 = { [14] = {0xf5, 0x1}, },
-	.page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE,
-	.page2 = { [7] = {0xe7, 0x44}, },
-	.check_efuse = true,
-	.num_phy = 1,
-	.check_efuse_version = CHECK_EFUSE_V1,
-	.efuse_dc_driving_rate = EFUS_USB_DC_CAL_RATE,
-	.dc_driving_mask = 0x1f,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = false,
-	.do_toggle = true,
-	.do_toggle_driving = false,
-	.driving_updated_for_dev_dis = 0x8,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = true,
-};
-
-static const struct phy_cfg rtd1315e_phy_cfg = {
-	.page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE,
-	.page0 = { [0] = {0xe0, 0xa3},
-		   [4] = {0xe4, 0x8c},
-		   [5] = {0xe5, 0x4f},
-		   [6] = {0xe6, 0x02}, },
-	.page1_size = MAX_USB_PHY_PAGE1_DATA_SIZE,
-	.page1 = { [3] = {0xe3, 0x7f},
-		  [14] = {0xf5, 0x01}, },
-	.page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE,
-	.page2 = { [7] = {0xe7, 0x44}, },
-	.num_phy = 1,
-	.check_efuse = true,
-	.check_efuse_version = CHECK_EFUSE_V2,
-	.efuse_dc_driving_rate = EFUS_USB_DC_CAL_RATE,
-	.dc_driving_mask = 0x1f,
-	.efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE,
-	.dc_disconnect_mask = 0xf,
-	.usb_dc_disconnect_at_page0 = false,
-	.do_toggle = true,
-	.do_toggle_driving = false,
-	.driving_updated_for_dev_dis = 0x8,
-	.use_default_parameter = false,
-	.is_double_sensitivity_mode = true,
-};
-
-static const struct of_device_id usbphy_rtk_dt_match[] = {
-	{ .compatible = "realtek,rtd1295-usb2phy", .data = &rtd1295_phy_cfg },
-	{ .compatible = "realtek,rtd1312c-usb2phy", .data = &rtd1312c_phy_cfg },
-	{ .compatible = "realtek,rtd1315e-usb2phy", .data = &rtd1315e_phy_cfg },
-	{ .compatible = "realtek,rtd1319-usb2phy", .data = &rtd1319_phy_cfg },
-	{ .compatible = "realtek,rtd1319d-usb2phy", .data = &rtd1319d_phy_cfg },
-	{ .compatible = "realtek,rtd1395-usb2phy", .data = &rtd1395_phy_cfg },
-	{ .compatible = "realtek,rtd1395-usb2phy-2port", .data = &rtd1395_phy_cfg_2port },
-	{ .compatible = "realtek,rtd1619-usb2phy", .data = &rtd1619_phy_cfg },
-	{ .compatible = "realtek,rtd1619b-usb2phy", .data = &rtd1619b_phy_cfg },
-	{},
-};
-MODULE_DEVICE_TABLE(of, usbphy_rtk_dt_match);
-
-static struct platform_driver rtk_usb2phy_driver = {
-	.probe		= rtk_usb2phy_probe,
-	.remove_new	= rtk_usb2phy_remove,
-	.driver		= {
-		.name	= "rtk-usb2phy",
-		.of_match_table = usbphy_rtk_dt_match,
-	},
-};
-
-module_platform_driver(rtk_usb2phy_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform: rtk-usb2phy");
-MODULE_AUTHOR("Stanley Chang <stanley_chang@realtek.com>");
-MODULE_DESCRIPTION("Realtek usb 2.0 phy driver");
diff --git a/drivers/phy/realtek/phy-rtk-usb3.c b/drivers/phy/realtek/phy-rtk-usb3.c
deleted file mode 100644
index 67446a85e96885..00000000000000
--- a/drivers/phy/realtek/phy-rtk-usb3.c
+++ /dev/null
@@ -1,761 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *  phy-rtk-usb3.c RTK usb3.0 phy driver
- *
- * copyright (c) 2023 realtek semiconductor corporation
- *
- */
-
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/platform_device.h>
-#include <linux/uaccess.h>
-#include <linux/debugfs.h>
-#include <linux/nvmem-consumer.h>
-#include <linux/regmap.h>
-#include <linux/sys_soc.h>
-#include <linux/mfd/syscon.h>
-#include <linux/phy/phy.h>
-#include <linux/usb.h>
-#include <linux/usb/hcd.h>
-#include <linux/usb/phy.h>
-
-#define USB_MDIO_CTRL_PHY_BUSY BIT(7)
-#define USB_MDIO_CTRL_PHY_WRITE BIT(0)
-#define USB_MDIO_CTRL_PHY_ADDR_SHIFT 8
-#define USB_MDIO_CTRL_PHY_DATA_SHIFT 16
-
-#define MAX_USB_PHY_DATA_SIZE 0x30
-#define PHY_ADDR_0X09 0x09
-#define PHY_ADDR_0X0B 0x0b
-#define PHY_ADDR_0X0D 0x0d
-#define PHY_ADDR_0X10 0x10
-#define PHY_ADDR_0X1F 0x1f
-#define PHY_ADDR_0X20 0x20
-#define PHY_ADDR_0X21 0x21
-#define PHY_ADDR_0X30 0x30
-
-#define REG_0X09_FORCE_CALIBRATION BIT(9)
-#define REG_0X0B_RX_OFFSET_RANGE_MASK 0xc
-#define REG_0X0D_RX_DEBUG_TEST_EN BIT(6)
-#define REG_0X10_DEBUG_MODE_SETTING 0x3c0
-#define REG_0X10_DEBUG_MODE_SETTING_MASK 0x3f8
-#define REG_0X1F_RX_OFFSET_CODE_MASK 0x1e
-
-#define USB_U3_TX_LFPS_SWING_TRIM_SHIFT 4
-#define USB_U3_TX_LFPS_SWING_TRIM_MASK 0xf
-#define AMPLITUDE_CONTROL_COARSE_MASK 0xff
-#define AMPLITUDE_CONTROL_FINE_MASK 0xffff
-#define AMPLITUDE_CONTROL_COARSE_DEFAULT 0xff
-#define AMPLITUDE_CONTROL_FINE_DEFAULT 0xffff
-
-#define PHY_ADDR_MAP_ARRAY_INDEX(addr) (addr)
-#define ARRAY_INDEX_MAP_PHY_ADDR(index) (index)
-
-struct phy_reg {
-	void __iomem *reg_mdio_ctl;
-};
-
-struct phy_data {
-	u8 addr;
-	u16 data;
-};
-
-struct phy_cfg {
-	int param_size;
-	struct phy_data param[MAX_USB_PHY_DATA_SIZE];
-
-	bool check_efuse;
-	bool do_toggle;
-	bool do_toggle_once;
-	bool use_default_parameter;
-	bool check_rx_front_end_offset;
-};
-
-struct phy_parameter {
-	struct phy_reg phy_reg;
-
-	/* Get from efuse */
-	u8 efuse_usb_u3_tx_lfps_swing_trim;
-
-	/* Get from dts */
-	u32 amplitude_control_coarse;
-	u32 amplitude_control_fine;
-};
-
-struct rtk_phy {
-	struct usb_phy phy;
-	struct device *dev;
-
-	struct phy_cfg *phy_cfg;
-	int num_phy;
-	struct phy_parameter *phy_parameter;
-
-	struct dentry *debug_dir;
-};
-
-#define PHY_IO_TIMEOUT_USEC		(50000)
-#define PHY_IO_DELAY_US			(100)
-
-static inline int utmi_wait_register(void __iomem *reg, u32 mask, u32 result)
-{
-	int ret;
-	unsigned int val;
-
-	ret = read_poll_timeout(readl, val, ((val & mask) == result),
-				PHY_IO_DELAY_US, PHY_IO_TIMEOUT_USEC, false, reg);
-	if (ret) {
-		pr_err("%s can't program USB phy\n", __func__);
-		return -ETIMEDOUT;
-	}
-
-	return 0;
-}
-
-static int rtk_phy3_wait_vbusy(struct phy_reg *phy_reg)
-{
-	return utmi_wait_register(phy_reg->reg_mdio_ctl, USB_MDIO_CTRL_PHY_BUSY, 0);
-}
-
-static u16 rtk_phy_read(struct phy_reg *phy_reg, char addr)
-{
-	unsigned int tmp;
-	u32 value;
-
-	tmp = (addr << USB_MDIO_CTRL_PHY_ADDR_SHIFT);
-
-	writel(tmp, phy_reg->reg_mdio_ctl);
-
-	rtk_phy3_wait_vbusy(phy_reg);
-
-	value = readl(phy_reg->reg_mdio_ctl);
-	value = value >> USB_MDIO_CTRL_PHY_DATA_SHIFT;
-
-	return (u16)value;
-}
-
-static int rtk_phy_write(struct phy_reg *phy_reg, char addr, u16 data)
-{
-	unsigned int val;
-
-	val = USB_MDIO_CTRL_PHY_WRITE |
-		    (addr << USB_MDIO_CTRL_PHY_ADDR_SHIFT) |
-		    (data << USB_MDIO_CTRL_PHY_DATA_SHIFT);
-
-	writel(val, phy_reg->reg_mdio_ctl);
-
-	rtk_phy3_wait_vbusy(phy_reg);
-
-	return 0;
-}
-
-static void do_rtk_usb3_phy_toggle(struct rtk_phy *rtk_phy, int index, bool connect)
-{
-	struct phy_cfg *phy_cfg = rtk_phy->phy_cfg;
-	struct phy_reg *phy_reg;
-	struct phy_parameter *phy_parameter;
-	struct phy_data *phy_data;
-	u8 addr;
-	u16 data;
-	int i;
-
-	phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-	phy_reg = &phy_parameter->phy_reg;
-
-	if (!phy_cfg->do_toggle)
-		return;
-
-	i = PHY_ADDR_MAP_ARRAY_INDEX(PHY_ADDR_0X09);
-	phy_data = phy_cfg->param + i;
-	addr = phy_data->addr;
-	data = phy_data->data;
-
-	if (!addr && !data) {
-		addr = PHY_ADDR_0X09;
-		data = rtk_phy_read(phy_reg, addr);
-		phy_data->addr = addr;
-		phy_data->data = data;
-	}
-
-	rtk_phy_write(phy_reg, addr, data & (~REG_0X09_FORCE_CALIBRATION));
-	mdelay(1);
-	rtk_phy_write(phy_reg, addr, data | REG_0X09_FORCE_CALIBRATION);
-}
-
-static int do_rtk_phy_init(struct rtk_phy *rtk_phy, int index)
-{
-	struct phy_cfg *phy_cfg;
-	struct phy_reg *phy_reg;
-	struct phy_parameter *phy_parameter;
-	int i = 0;
-
-	phy_cfg = rtk_phy->phy_cfg;
-	phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-	phy_reg = &phy_parameter->phy_reg;
-
-	if (phy_cfg->use_default_parameter)
-		goto do_toggle;
-
-	for (i = 0; i < phy_cfg->param_size; i++) {
-		struct phy_data *phy_data = phy_cfg->param + i;
-		u8 addr = phy_data->addr;
-		u16 data = phy_data->data;
-
-		if (!addr && !data)
-			continue;
-
-		rtk_phy_write(phy_reg, addr, data);
-	}
-
-do_toggle:
-	if (phy_cfg->do_toggle_once)
-		phy_cfg->do_toggle = true;
-
-	do_rtk_usb3_phy_toggle(rtk_phy, index, false);
-
-	if (phy_cfg->do_toggle_once) {
-		u16 check_value = 0;
-		int count = 10;
-		u16 value_0x0d, value_0x10;
-
-		/* Enable Debug mode by set 0x0D and 0x10 */
-		value_0x0d = rtk_phy_read(phy_reg, PHY_ADDR_0X0D);
-		value_0x10 = rtk_phy_read(phy_reg, PHY_ADDR_0X10);
-
-		rtk_phy_write(phy_reg, PHY_ADDR_0X0D,
-			      value_0x0d | REG_0X0D_RX_DEBUG_TEST_EN);
-		rtk_phy_write(phy_reg, PHY_ADDR_0X10,
-			      (value_0x10 & ~REG_0X10_DEBUG_MODE_SETTING_MASK) |
-			      REG_0X10_DEBUG_MODE_SETTING);
-
-		check_value = rtk_phy_read(phy_reg, PHY_ADDR_0X30);
-
-		while (!(check_value & BIT(15))) {
-			check_value = rtk_phy_read(phy_reg, PHY_ADDR_0X30);
-			mdelay(1);
-			if (count-- < 0)
-				break;
-		}
-
-		if (!(check_value & BIT(15)))
-			dev_info(rtk_phy->dev, "toggle fail addr=0x%02x, data=0x%04x\n",
-				 PHY_ADDR_0X30, check_value);
-
-		/* Disable Debug mode by set 0x0D and 0x10 to default*/
-		rtk_phy_write(phy_reg, PHY_ADDR_0X0D, value_0x0d);
-		rtk_phy_write(phy_reg, PHY_ADDR_0X10, value_0x10);
-
-		phy_cfg->do_toggle = false;
-	}
-
-	if (phy_cfg->check_rx_front_end_offset) {
-		u16 rx_offset_code, rx_offset_range;
-		u16 code_mask = REG_0X1F_RX_OFFSET_CODE_MASK;
-		u16 range_mask = REG_0X0B_RX_OFFSET_RANGE_MASK;
-		bool do_update = false;
-
-		rx_offset_code = rtk_phy_read(phy_reg, PHY_ADDR_0X1F);
-		if (((rx_offset_code & code_mask) == 0x0) ||
-		    ((rx_offset_code & code_mask) == code_mask))
-			do_update = true;
-
-		rx_offset_range = rtk_phy_read(phy_reg, PHY_ADDR_0X0B);
-		if (((rx_offset_range & range_mask) == range_mask) && do_update) {
-			dev_warn(rtk_phy->dev, "Don't update rx_offset_range (rx_offset_code=0x%x, rx_offset_range=0x%x)\n",
-				 rx_offset_code, rx_offset_range);
-			do_update = false;
-		}
-
-		if (do_update) {
-			u16 tmp1, tmp2;
-
-			tmp1 = rx_offset_range & (~range_mask);
-			tmp2 = rx_offset_range & range_mask;
-			tmp2 += (1 << 2);
-			rx_offset_range = tmp1 | (tmp2 & range_mask);
-			rtk_phy_write(phy_reg, PHY_ADDR_0X0B, rx_offset_range);
-			goto do_toggle;
-		}
-	}
-
-	return 0;
-}
-
-static int rtk_phy_init(struct phy *phy)
-{
-	struct rtk_phy *rtk_phy = phy_get_drvdata(phy);
-	int ret = 0;
-	int i;
-	unsigned long phy_init_time = jiffies;
-
-	for (i = 0; i < rtk_phy->num_phy; i++)
-		ret = do_rtk_phy_init(rtk_phy, i);
-
-	dev_dbg(rtk_phy->dev, "Initialized RTK USB 3.0 PHY (take %dms)\n",
-		jiffies_to_msecs(jiffies - phy_init_time));
-
-	return ret;
-}
-
-static int rtk_phy_exit(struct phy *phy)
-{
-	return 0;
-}
-
-static const struct phy_ops ops = {
-	.init		= rtk_phy_init,
-	.exit		= rtk_phy_exit,
-	.owner		= THIS_MODULE,
-};
-
-static void rtk_phy_toggle(struct usb_phy *usb3_phy, bool connect, int port)
-{
-	int index = port;
-	struct rtk_phy *rtk_phy = NULL;
-
-	rtk_phy = dev_get_drvdata(usb3_phy->dev);
-
-	if (index > rtk_phy->num_phy) {
-		dev_err(rtk_phy->dev, "%s: The port=%d is not in usb phy (num_phy=%d)\n",
-			__func__, index, rtk_phy->num_phy);
-		return;
-	}
-
-	do_rtk_usb3_phy_toggle(rtk_phy, index, connect);
-}
-
-static int rtk_phy_notify_port_status(struct usb_phy *x, int port,
-				      u16 portstatus, u16 portchange)
-{
-	bool connect = false;
-
-	pr_debug("%s port=%d portstatus=0x%x portchange=0x%x\n",
-		 __func__, port, (int)portstatus, (int)portchange);
-	if (portstatus & USB_PORT_STAT_CONNECTION)
-		connect = true;
-
-	if (portchange & USB_PORT_STAT_C_CONNECTION)
-		rtk_phy_toggle(x, connect, port);
-
-	return 0;
-}
-
-#ifdef CONFIG_DEBUG_FS
-static struct dentry *create_phy_debug_root(void)
-{
-	struct dentry *phy_debug_root;
-
-	phy_debug_root = debugfs_lookup("phy", usb_debug_root);
-	if (!phy_debug_root)
-		phy_debug_root = debugfs_create_dir("phy", usb_debug_root);
-
-	return phy_debug_root;
-}
-
-static int rtk_usb3_parameter_show(struct seq_file *s, void *unused)
-{
-	struct rtk_phy *rtk_phy = s->private;
-	struct phy_cfg *phy_cfg;
-	int i, index;
-
-	phy_cfg = rtk_phy->phy_cfg;
-
-	seq_puts(s, "Property:\n");
-	seq_printf(s, "  check_efuse: %s\n",
-		   phy_cfg->check_efuse ? "Enable" : "Disable");
-	seq_printf(s, "  do_toggle: %s\n",
-		   phy_cfg->do_toggle ? "Enable" : "Disable");
-	seq_printf(s, "  do_toggle_once: %s\n",
-		   phy_cfg->do_toggle_once ? "Enable" : "Disable");
-	seq_printf(s, "  use_default_parameter: %s\n",
-		   phy_cfg->use_default_parameter ? "Enable" : "Disable");
-
-	for (index = 0; index < rtk_phy->num_phy; index++) {
-		struct phy_reg *phy_reg;
-		struct phy_parameter *phy_parameter;
-
-		phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-		phy_reg = &phy_parameter->phy_reg;
-
-		seq_printf(s, "PHY %d:\n", index);
-
-		for (i = 0; i < phy_cfg->param_size; i++) {
-			struct phy_data *phy_data = phy_cfg->param + i;
-			u8 addr = ARRAY_INDEX_MAP_PHY_ADDR(i);
-			u16 data = phy_data->data;
-
-			if (!phy_data->addr && !data)
-				seq_printf(s, "  addr = 0x%02x, data = none   ==> read value = 0x%04x\n",
-					   addr, rtk_phy_read(phy_reg, addr));
-			else
-				seq_printf(s, "  addr = 0x%02x, data = 0x%04x ==> read value = 0x%04x\n",
-					   addr, data, rtk_phy_read(phy_reg, addr));
-		}
-
-		seq_puts(s, "PHY Property:\n");
-		seq_printf(s, "  efuse_usb_u3_tx_lfps_swing_trim: 0x%x\n",
-			   (int)phy_parameter->efuse_usb_u3_tx_lfps_swing_trim);
-		seq_printf(s, "  amplitude_control_coarse: 0x%x\n",
-			   (int)phy_parameter->amplitude_control_coarse);
-		seq_printf(s, "  amplitude_control_fine: 0x%x\n",
-			   (int)phy_parameter->amplitude_control_fine);
-	}
-
-	return 0;
-}
-DEFINE_SHOW_ATTRIBUTE(rtk_usb3_parameter);
-
-static inline void create_debug_files(struct rtk_phy *rtk_phy)
-{
-	struct dentry *phy_debug_root = NULL;
-
-	phy_debug_root = create_phy_debug_root();
-
-	if (!phy_debug_root)
-		return;
-
-	rtk_phy->debug_dir = debugfs_create_dir(dev_name(rtk_phy->dev), phy_debug_root);
-
-	debugfs_create_file("parameter", 0444, rtk_phy->debug_dir, rtk_phy,
-			    &rtk_usb3_parameter_fops);
-
-	return;
-}
-
-static inline void remove_debug_files(struct rtk_phy *rtk_phy)
-{
-	debugfs_remove_recursive(rtk_phy->debug_dir);
-}
-#else
-static inline void create_debug_files(struct rtk_phy *rtk_phy) { }
-static inline void remove_debug_files(struct rtk_phy *rtk_phy) { }
-#endif /* CONFIG_DEBUG_FS */
-
-static int get_phy_data_by_efuse(struct rtk_phy *rtk_phy,
-				 struct phy_parameter *phy_parameter, int index)
-{
-	struct phy_cfg *phy_cfg = rtk_phy->phy_cfg;
-	u8 value = 0;
-	struct nvmem_cell *cell;
-
-	if (!phy_cfg->check_efuse)
-		goto out;
-
-	cell = nvmem_cell_get(rtk_phy->dev, "usb_u3_tx_lfps_swing_trim");
-	if (IS_ERR(cell)) {
-		dev_dbg(rtk_phy->dev, "%s no usb_u3_tx_lfps_swing_trim: %ld\n",
-			__func__, PTR_ERR(cell));
-	} else {
-		unsigned char *buf;
-		size_t buf_size;
-
-		buf = nvmem_cell_read(cell, &buf_size);
-		if (!IS_ERR(buf)) {
-			value = buf[0] & USB_U3_TX_LFPS_SWING_TRIM_MASK;
-			kfree(buf);
-		}
-		nvmem_cell_put(cell);
-	}
-
-	if (value > 0 && value < 0x8)
-		phy_parameter->efuse_usb_u3_tx_lfps_swing_trim = 0x8;
-	else
-		phy_parameter->efuse_usb_u3_tx_lfps_swing_trim = (u8)value;
-
-out:
-	return 0;
-}
-
-static void update_amplitude_control_value(struct rtk_phy *rtk_phy,
-					   struct phy_parameter *phy_parameter)
-{
-	struct phy_cfg *phy_cfg;
-	struct phy_reg *phy_reg;
-
-	phy_reg = &phy_parameter->phy_reg;
-	phy_cfg = rtk_phy->phy_cfg;
-
-	if (phy_parameter->amplitude_control_coarse != AMPLITUDE_CONTROL_COARSE_DEFAULT) {
-		u16 val_mask = AMPLITUDE_CONTROL_COARSE_MASK;
-		u16 data;
-
-		if (!phy_cfg->param[PHY_ADDR_0X20].addr && !phy_cfg->param[PHY_ADDR_0X20].data) {
-			phy_cfg->param[PHY_ADDR_0X20].addr = PHY_ADDR_0X20;
-			data = rtk_phy_read(phy_reg, PHY_ADDR_0X20);
-		} else {
-			data = phy_cfg->param[PHY_ADDR_0X20].data;
-		}
-
-		data &= (~val_mask);
-		data |= (phy_parameter->amplitude_control_coarse & val_mask);
-
-		phy_cfg->param[PHY_ADDR_0X20].data = data;
-	}
-
-	if (phy_parameter->efuse_usb_u3_tx_lfps_swing_trim) {
-		u8 efuse_val = phy_parameter->efuse_usb_u3_tx_lfps_swing_trim;
-		u16 val_mask = USB_U3_TX_LFPS_SWING_TRIM_MASK;
-		int val_shift = USB_U3_TX_LFPS_SWING_TRIM_SHIFT;
-		u16 data;
-
-		if (!phy_cfg->param[PHY_ADDR_0X20].addr && !phy_cfg->param[PHY_ADDR_0X20].data) {
-			phy_cfg->param[PHY_ADDR_0X20].addr = PHY_ADDR_0X20;
-			data = rtk_phy_read(phy_reg, PHY_ADDR_0X20);
-		} else {
-			data = phy_cfg->param[PHY_ADDR_0X20].data;
-		}
-
-		data &= ~(val_mask << val_shift);
-		data |= ((efuse_val & val_mask) << val_shift);
-
-		phy_cfg->param[PHY_ADDR_0X20].data = data;
-	}
-
-	if (phy_parameter->amplitude_control_fine != AMPLITUDE_CONTROL_FINE_DEFAULT) {
-		u16 val_mask = AMPLITUDE_CONTROL_FINE_MASK;
-
-		if (!phy_cfg->param[PHY_ADDR_0X21].addr && !phy_cfg->param[PHY_ADDR_0X21].data)
-			phy_cfg->param[PHY_ADDR_0X21].addr = PHY_ADDR_0X21;
-
-		phy_cfg->param[PHY_ADDR_0X21].data =
-			    phy_parameter->amplitude_control_fine & val_mask;
-	}
-}
-
-static int parse_phy_data(struct rtk_phy *rtk_phy)
-{
-	struct device *dev = rtk_phy->dev;
-	struct phy_parameter *phy_parameter;
-	int ret = 0;
-	int index;
-
-	rtk_phy->phy_parameter = devm_kzalloc(dev, sizeof(struct phy_parameter) *
-					      rtk_phy->num_phy, GFP_KERNEL);
-	if (!rtk_phy->phy_parameter)
-		return -ENOMEM;
-
-	for (index = 0; index < rtk_phy->num_phy; index++) {
-		phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index];
-
-		phy_parameter->phy_reg.reg_mdio_ctl = of_iomap(dev->of_node, 0) + index;
-
-		/* Amplitude control address 0x20 bit 0 to bit 7 */
-		if (of_property_read_u32(dev->of_node, "realtek,amplitude-control-coarse-tuning",
-					 &phy_parameter->amplitude_control_coarse))
-			phy_parameter->amplitude_control_coarse = AMPLITUDE_CONTROL_COARSE_DEFAULT;
-
-		/* Amplitude control address 0x21 bit 0 to bit 16 */
-		if (of_property_read_u32(dev->of_node, "realtek,amplitude-control-fine-tuning",
-					 &phy_parameter->amplitude_control_fine))
-			phy_parameter->amplitude_control_fine = AMPLITUDE_CONTROL_FINE_DEFAULT;
-
-		get_phy_data_by_efuse(rtk_phy, phy_parameter, index);
-
-		update_amplitude_control_value(rtk_phy, phy_parameter);
-	}
-
-	return ret;
-}
-
-static int rtk_usb3phy_probe(struct platform_device *pdev)
-{
-	struct rtk_phy *rtk_phy;
-	struct device *dev = &pdev->dev;
-	struct phy *generic_phy;
-	struct phy_provider *phy_provider;
-	const struct phy_cfg *phy_cfg;
-	int ret;
-
-	phy_cfg = of_device_get_match_data(dev);
-	if (!phy_cfg) {
-		dev_err(dev, "phy config are not assigned!\n");
-		return -EINVAL;
-	}
-
-	rtk_phy = devm_kzalloc(dev, sizeof(*rtk_phy), GFP_KERNEL);
-	if (!rtk_phy)
-		return -ENOMEM;
-
-	rtk_phy->dev			= &pdev->dev;
-	rtk_phy->phy.dev		= rtk_phy->dev;
-	rtk_phy->phy.label		= "rtk-usb3phy";
-	rtk_phy->phy.notify_port_status = rtk_phy_notify_port_status;
-
-	rtk_phy->phy_cfg = devm_kzalloc(dev, sizeof(*phy_cfg), GFP_KERNEL);
-
-	memcpy(rtk_phy->phy_cfg, phy_cfg, sizeof(*phy_cfg));
-
-	rtk_phy->num_phy = 1;
-
-	ret = parse_phy_data(rtk_phy);
-	if (ret)
-		goto err;
-
-	platform_set_drvdata(pdev, rtk_phy);
-
-	generic_phy = devm_phy_create(rtk_phy->dev, NULL, &ops);
-	if (IS_ERR(generic_phy))
-		return PTR_ERR(generic_phy);
-
-	phy_set_drvdata(generic_phy, rtk_phy);
-
-	phy_provider = devm_of_phy_provider_register(rtk_phy->dev, of_phy_simple_xlate);
-	if (IS_ERR(phy_provider))
-		return PTR_ERR(phy_provider);
-
-	ret = usb_add_phy_dev(&rtk_phy->phy);
-	if (ret)
-		goto err;
-
-	create_debug_files(rtk_phy);
-
-err:
-	return ret;
-}
-
-static void rtk_usb3phy_remove(struct platform_device *pdev)
-{
-	struct rtk_phy *rtk_phy = platform_get_drvdata(pdev);
-
-	remove_debug_files(rtk_phy);
-
-	usb_remove_phy(&rtk_phy->phy);
-}
-
-static const struct phy_cfg rtd1295_phy_cfg = {
-	.param_size = MAX_USB_PHY_DATA_SIZE,
-	.param = {  [0] = {0x01, 0x4008},  [1] = {0x01, 0xe046},
-		    [2] = {0x02, 0x6046},  [3] = {0x03, 0x2779},
-		    [4] = {0x04, 0x72f5},  [5] = {0x05, 0x2ad3},
-		    [6] = {0x06, 0x000e},  [7] = {0x07, 0x2e00},
-		    [8] = {0x08, 0x3591},  [9] = {0x09, 0x525c},
-		   [10] = {0x0a, 0xa600}, [11] = {0x0b, 0xa904},
-		   [12] = {0x0c, 0xc000}, [13] = {0x0d, 0xef1c},
-		   [14] = {0x0e, 0x2000}, [15] = {0x0f, 0x0000},
-		   [16] = {0x10, 0x000c}, [17] = {0x11, 0x4c00},
-		   [18] = {0x12, 0xfc00}, [19] = {0x13, 0x0c81},
-		   [20] = {0x14, 0xde01}, [21] = {0x15, 0x0000},
-		   [22] = {0x16, 0x0000}, [23] = {0x17, 0x0000},
-		   [24] = {0x18, 0x0000}, [25] = {0x19, 0x4004},
-		   [26] = {0x1a, 0x1260}, [27] = {0x1b, 0xff00},
-		   [28] = {0x1c, 0xcb00}, [29] = {0x1d, 0xa03f},
-		   [30] = {0x1e, 0xc2e0}, [31] = {0x1f, 0x2807},
-		   [32] = {0x20, 0x947a}, [33] = {0x21, 0x88aa},
-		   [34] = {0x22, 0x0057}, [35] = {0x23, 0xab66},
-		   [36] = {0x24, 0x0800}, [37] = {0x25, 0x0000},
-		   [38] = {0x26, 0x040a}, [39] = {0x27, 0x01d6},
-		   [40] = {0x28, 0xf8c2}, [41] = {0x29, 0x3080},
-		   [42] = {0x2a, 0x3082}, [43] = {0x2b, 0x2078},
-		   [44] = {0x2c, 0xffff}, [45] = {0x2d, 0xffff},
-		   [46] = {0x2e, 0x0000}, [47] = {0x2f, 0x0040}, },
-	.check_efuse = false,
-	.do_toggle = true,
-	.do_toggle_once = false,
-	.use_default_parameter = false,
-	.check_rx_front_end_offset = false,
-};
-
-static const struct phy_cfg rtd1619_phy_cfg = {
-	.param_size = MAX_USB_PHY_DATA_SIZE,
-	.param = {  [8] = {0x08, 0x3591},
-		   [38] = {0x26, 0x840b},
-		   [40] = {0x28, 0xf842}, },
-	.check_efuse = false,
-	.do_toggle = true,
-	.do_toggle_once = false,
-	.use_default_parameter = false,
-	.check_rx_front_end_offset = false,
-};
-
-static const struct phy_cfg rtd1319_phy_cfg = {
-	.param_size = MAX_USB_PHY_DATA_SIZE,
-	.param = {  [1] = {0x01, 0xac86},
-		    [6] = {0x06, 0x0003},
-		    [9] = {0x09, 0x924c},
-		   [10] = {0x0a, 0xa608},
-		   [11] = {0x0b, 0xb905},
-		   [14] = {0x0e, 0x2010},
-		   [32] = {0x20, 0x705a},
-		   [33] = {0x21, 0xf645},
-		   [34] = {0x22, 0x0013},
-		   [35] = {0x23, 0xcb66},
-		   [41] = {0x29, 0xff00}, },
-	.check_efuse = true,
-	.do_toggle = true,
-	.do_toggle_once = false,
-	.use_default_parameter = false,
-	.check_rx_front_end_offset = false,
-};
-
-static const struct phy_cfg rtd1619b_phy_cfg = {
-	.param_size = MAX_USB_PHY_DATA_SIZE,
-	.param = {  [1] = {0x01, 0xac8c},
-		    [6] = {0x06, 0x0017},
-		    [9] = {0x09, 0x724c},
-		   [10] = {0x0a, 0xb610},
-		   [11] = {0x0b, 0xb90d},
-		   [13] = {0x0d, 0xef2a},
-		   [15] = {0x0f, 0x9050},
-		   [16] = {0x10, 0x000c},
-		   [32] = {0x20, 0x70ff},
-		   [34] = {0x22, 0x0013},
-		   [35] = {0x23, 0xdb66},
-		   [38] = {0x26, 0x8609},
-		   [41] = {0x29, 0xff13},
-		   [42] = {0x2a, 0x3070}, },
-	.check_efuse = true,
-	.do_toggle = false,
-	.do_toggle_once = true,
-	.use_default_parameter = false,
-	.check_rx_front_end_offset = false,
-};
-
-static const  struct phy_cfg rtd1319d_phy_cfg = {
-	.param_size = MAX_USB_PHY_DATA_SIZE,
-	.param = {  [1] = {0x01, 0xac89},
-		    [4] = {0x04, 0xf2f5},
-		    [6] = {0x06, 0x0017},
-		    [9] = {0x09, 0x424c},
-		   [10] = {0x0a, 0x9610},
-		   [11] = {0x0b, 0x9901},
-		   [12] = {0x0c, 0xf000},
-		   [13] = {0x0d, 0xef2a},
-		   [14] = {0x0e, 0x1000},
-		   [15] = {0x0f, 0x9050},
-		   [32] = {0x20, 0x7077},
-		   [35] = {0x23, 0x0b62},
-		   [37] = {0x25, 0x10ec},
-		   [42] = {0x2a, 0x3070}, },
-	.check_efuse = true,
-	.do_toggle = false,
-	.do_toggle_once = true,
-	.use_default_parameter = false,
-	.check_rx_front_end_offset = true,
-};
-
-static const struct of_device_id usbphy_rtk_dt_match[] = {
-	{ .compatible = "realtek,rtd1295-usb3phy", .data = &rtd1295_phy_cfg },
-	{ .compatible = "realtek,rtd1319-usb3phy", .data = &rtd1319_phy_cfg },
-	{ .compatible = "realtek,rtd1319d-usb3phy", .data = &rtd1319d_phy_cfg },
-	{ .compatible = "realtek,rtd1619-usb3phy", .data = &rtd1619_phy_cfg },
-	{ .compatible = "realtek,rtd1619b-usb3phy", .data = &rtd1619b_phy_cfg },
-	{},
-};
-MODULE_DEVICE_TABLE(of, usbphy_rtk_dt_match);
-
-static struct platform_driver rtk_usb3phy_driver = {
-	.probe		= rtk_usb3phy_probe,
-	.remove_new	= rtk_usb3phy_remove,
-	.driver		= {
-		.name	= "rtk-usb3phy",
-		.of_match_table = usbphy_rtk_dt_match,
-	},
-};
-
-module_platform_driver(rtk_usb3phy_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform: rtk-usb3phy");
-MODULE_AUTHOR("Stanley Chang <stanley_chang@realtek.com>");
-MODULE_DESCRIPTION("Realtek usb 3.0 phy driver");
diff --git a/drivers/phy/sunplus/phy-sunplus-usb2.c b/drivers/phy/sunplus/phy-sunplus-usb2.c
index 0efe74ac9c6afc..637a5fbae6d9a9 100644
--- a/drivers/phy/sunplus/phy-sunplus-usb2.c
+++ b/drivers/phy/sunplus/phy-sunplus-usb2.c
@@ -275,7 +275,7 @@ static int sp_usb_phy_probe(struct platform_device *pdev)
 
 	phy = devm_phy_create(&pdev->dev, NULL, &sp_uphy_ops);
 	if (IS_ERR(phy)) {
-		ret = -PTR_ERR(phy);
+		ret = PTR_ERR(phy);
 		return ret;
 	}
 
diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c
index 555b323f45da1e..bc847d3879f79c 100644
--- a/drivers/phy/ti/phy-gmii-sel.c
+++ b/drivers/phy/ti/phy-gmii-sel.c
@@ -64,6 +64,7 @@ struct phy_gmii_sel_priv {
 	u32 num_ports;
 	u32 reg_offset;
 	u32 qsgmii_main_ports;
+	bool no_offset;
 };
 
 static int phy_gmii_sel_mode(struct phy *phy, enum phy_mode mode, int submode)
@@ -402,7 +403,8 @@ static int phy_gmii_sel_init_ports(struct phy_gmii_sel_priv *priv)
 		priv->num_ports = size / sizeof(u32);
 		if (!priv->num_ports)
 			return -EINVAL;
-		priv->reg_offset = __be32_to_cpu(*offset);
+		if (!priv->no_offset)
+			priv->reg_offset = __be32_to_cpu(*offset);
 	}
 
 	if_phys = devm_kcalloc(dev, priv->num_ports,
@@ -471,6 +473,7 @@ static int phy_gmii_sel_probe(struct platform_device *pdev)
 			dev_err(dev, "Failed to get syscon %d\n", ret);
 			return ret;
 		}
+		priv->no_offset = true;
 	}
 
 	ret = phy_gmii_sel_init_ports(priv);
diff --git a/drivers/pinctrl/cirrus/Kconfig b/drivers/pinctrl/cirrus/Kconfig
index d6318cb57aff2a..e7e827a8877a0e 100644
--- a/drivers/pinctrl/cirrus/Kconfig
+++ b/drivers/pinctrl/cirrus/Kconfig
@@ -12,7 +12,8 @@ config PINCTRL_CS42L43
 
 config PINCTRL_LOCHNAGAR
 	tristate "Cirrus Logic Lochnagar pinctrl driver"
-	depends on MFD_LOCHNAGAR
+	# Avoid clash caused by MIPS defining RST, which is used in the driver
+	depends on MFD_LOCHNAGAR && !MIPS
 	select GPIOLIB
 	select PINMUX
 	select PINCONF
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 1fa89be29b8f98..f2977eb65522e2 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -1262,17 +1262,17 @@ static void pinctrl_link_add(struct pinctrl_dev *pctldev,
 static int pinctrl_commit_state(struct pinctrl *p, struct pinctrl_state *state)
 {
 	struct pinctrl_setting *setting, *setting2;
-	struct pinctrl_state *old_state = p->state;
+	struct pinctrl_state *old_state = READ_ONCE(p->state);
 	int ret;
 
-	if (p->state) {
+	if (old_state) {
 		/*
 		 * For each pinmux setting in the old state, forget SW's record
 		 * of mux owner for that pingroup. Any pingroups which are
 		 * still owned by the new state will be re-acquired by the call
 		 * to pinmux_enable_setting() in the loop below.
 		 */
-		list_for_each_entry(setting, &p->state->settings, node) {
+		list_for_each_entry(setting, &old_state->settings, node) {
 			if (setting->type != PIN_MAP_TYPE_MUX_GROUP)
 				continue;
 			pinmux_disable_setting(setting);
diff --git a/drivers/pinctrl/nxp/pinctrl-s32cc.c b/drivers/pinctrl/nxp/pinctrl-s32cc.c
index 7daff9f186cd86..f0cad2c501f766 100644
--- a/drivers/pinctrl/nxp/pinctrl-s32cc.c
+++ b/drivers/pinctrl/nxp/pinctrl-s32cc.c
@@ -843,8 +843,8 @@ static int s32_pinctrl_probe_dt(struct platform_device *pdev,
 	if (!np)
 		return -ENODEV;
 
-	if (mem_regions == 0) {
-		dev_err(&pdev->dev, "mem_regions is 0\n");
+	if (mem_regions == 0 || mem_regions >= 10000) {
+		dev_err(&pdev->dev, "mem_regions is invalid: %u\n", mem_regions);
 		return -EINVAL;
 	}
 
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index fb58acb843d90a..03ecb3d1aaf60d 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -923,6 +923,15 @@ static int amd_gpio_suspend(struct device *dev)
 
 		raw_spin_lock_irqsave(&gpio_dev->lock, flags);
 		gpio_dev->saved_regs[i] = readl(gpio_dev->base + pin * 4) & ~PIN_IRQ_PENDING;
+
+		/* mask any interrupts not intended to be a wake source */
+		if (!(gpio_dev->saved_regs[i] & WAKE_SOURCE)) {
+			writel(gpio_dev->saved_regs[i] & ~BIT(INTERRUPT_MASK_OFF),
+			       gpio_dev->base + pin * 4);
+			pm_pr_dbg("Disabling GPIO #%d interrupt for suspend.\n",
+				  pin);
+		}
+
 		raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 	}
 
diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h
index 34c5c3e71fb261..cf59089f277639 100644
--- a/drivers/pinctrl/pinctrl-amd.h
+++ b/drivers/pinctrl/pinctrl-amd.h
@@ -80,6 +80,11 @@
 #define FUNCTION_MASK		GENMASK(1, 0)
 #define FUNCTION_INVALID	GENMASK(7, 0)
 
+#define WAKE_SOURCE	(BIT(WAKE_CNTRL_OFF_S0I3) | \
+			 BIT(WAKE_CNTRL_OFF_S3)   | \
+			 BIT(WAKE_CNTRL_OFF_S4)   | \
+			 BIT(WAKECNTRL_Z_OFF))
+
 struct amd_function {
 	const char *name;
 	const char * const groups[NSELECTS];
diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c
index 383309e533c3d7..a27c01fcbb47ed 100644
--- a/drivers/pinctrl/pinctrl-at91-pio4.c
+++ b/drivers/pinctrl/pinctrl-at91-pio4.c
@@ -1068,6 +1068,13 @@ static const struct of_device_id atmel_pctrl_of_match[] = {
 	}
 };
 
+/*
+ * This lock class allows to tell lockdep that parent IRQ and children IRQ do
+ * not share the same class so it does not raise false positive
+ */
+static struct lock_class_key atmel_lock_key;
+static struct lock_class_key atmel_request_key;
+
 static int atmel_pinctrl_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -1214,6 +1221,7 @@ static int atmel_pinctrl_probe(struct platform_device *pdev)
 		irq_set_chip_and_handler(irq, &atmel_gpio_irq_chip,
 					 handle_simple_irq);
 		irq_set_chip_data(irq, atmel_pioctrl);
+		irq_set_lockdep_class(irq, &atmel_lock_key, &atmel_request_key);
 		dev_dbg(dev,
 			"atmel gpio irq domain: hwirq: %d, linux irq: %d\n",
 			i, irq);
diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index 04285c930e945e..fe9545c630a2fa 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -143,6 +143,7 @@ static const struct dmi_system_id cy8c95x0_dmi_acpi_irq_info[] = {
  * @pinctrl_desc:   pin controller description
  * @name:           Chip controller name
  * @tpin:           Total number of pins
+ * @gpio_reset:     GPIO line handler that can reset the IC
  */
 struct cy8c95x0_pinctrl {
 	struct regmap *regmap;
@@ -307,6 +308,9 @@ static const char * const cy8c95x0_groups[] = {
 	"gp77",
 };
 
+static int cy8c95x0_pinmux_direction(struct cy8c95x0_pinctrl *chip,
+				     unsigned int pin, bool input);
+
 static inline u8 cypress_get_port(struct cy8c95x0_pinctrl *chip, unsigned int pin)
 {
 	/* Account for GPORT2 which only has 4 bits */
@@ -711,6 +715,8 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 	ret = regmap_read(chip->regmap, reg, &reg_val);
 	if (reg_val & bit)
 		arg = 1;
+	if (param == PIN_CONFIG_OUTPUT_ENABLE)
+		arg = !arg;
 
 	*config = pinconf_to_config_packed(param, (u16)arg);
 out:
@@ -726,6 +732,7 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip,
 	u8 port = cypress_get_port(chip, off);
 	u8 bit = cypress_get_pin_mask(chip, off);
 	unsigned long param = pinconf_to_config_param(config);
+	unsigned long arg = pinconf_to_config_argument(config);
 	unsigned int reg;
 	int ret;
 
@@ -764,6 +771,12 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip,
 	case PIN_CONFIG_MODE_PWM:
 		reg = CY8C95X0_PWMSEL;
 		break;
+	case PIN_CONFIG_OUTPUT_ENABLE:
+		ret = cy8c95x0_pinmux_direction(chip, off, !arg);
+		goto out;
+	case PIN_CONFIG_INPUT_ENABLE:
+		ret = cy8c95x0_pinmux_direction(chip, off, arg);
+		goto out;
 	default:
 		ret = -ENOTSUPP;
 		goto out;
@@ -821,7 +834,7 @@ static int cy8c95x0_setup_gpiochip(struct cy8c95x0_pinctrl *chip)
 	gc->get_direction = cy8c95x0_gpio_get_direction;
 	gc->get_multiple = cy8c95x0_gpio_get_multiple;
 	gc->set_multiple = cy8c95x0_gpio_set_multiple;
-	gc->set_config = gpiochip_generic_config,
+	gc->set_config = gpiochip_generic_config;
 	gc->can_sleep = true;
 	gc->add_pin_ranges = cy8c95x0_add_pin_ranges;
 
diff --git a/drivers/pinctrl/realtek/pinctrl-rtd.c b/drivers/pinctrl/realtek/pinctrl-rtd.c
index 9c7a1af4ba692a..208896593b61ec 100644
--- a/drivers/pinctrl/realtek/pinctrl-rtd.c
+++ b/drivers/pinctrl/realtek/pinctrl-rtd.c
@@ -146,7 +146,7 @@ static int rtd_pinctrl_get_function_groups(struct pinctrl_dev *pcdev,
 
 static const struct rtd_pin_desc *rtd_pinctrl_find_mux(struct rtd_pinctrl *data, unsigned int pin)
 {
-	if (!data->info->muxes[pin].name)
+	if (data->info->muxes[pin].name)
 		return &data->info->muxes[pin];
 
 	return NULL;
@@ -249,7 +249,7 @@ static const struct pinctrl_pin_desc
 static const struct rtd_pin_config_desc
 	*rtd_pinctrl_find_config(struct rtd_pinctrl *data, unsigned int pin)
 {
-	if (!data->info->configs[pin].name)
+	if (data->info->configs[pin].name)
 		return &data->info->configs[pin];
 
 	return NULL;
diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
index ea70b8c61679f0..b29b0ab9892b8e 100644
--- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
+++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
@@ -492,7 +492,7 @@ static int starfive_dt_node_to_map(struct pinctrl_dev *pctldev,
 
 	nmaps = 0;
 	ngroups = 0;
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		int npinmux = of_property_count_u32_elems(child, "pinmux");
 		int npins   = of_property_count_u32_elems(child, "pins");
 
@@ -527,7 +527,7 @@ static int starfive_dt_node_to_map(struct pinctrl_dev *pctldev,
 	nmaps = 0;
 	ngroups = 0;
 	mutex_lock(&sfp->mutex);
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		int npins;
 		int i;
 
diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
index 9d71e8c1331020..6de11a4057346d 100644
--- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
+++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
@@ -135,7 +135,7 @@ static int jh7110_dt_node_to_map(struct pinctrl_dev *pctldev,
 	int ret;
 
 	ngroups = 0;
-	for_each_child_of_node(np, child)
+	for_each_available_child_of_node(np, child)
 		ngroups += 1;
 	nmaps = 2 * ngroups;
 
@@ -150,7 +150,7 @@ static int jh7110_dt_node_to_map(struct pinctrl_dev *pctldev,
 	nmaps = 0;
 	ngroups = 0;
 	mutex_lock(&sfp->mutex);
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		int npins = of_property_count_u32_elems(child, "pinmux");
 		int *pins;
 		u32 *pinmux;
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index 64e8201c7eacd3..603f900e88c18a 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -1273,9 +1273,11 @@ static struct stm32_desc_pin *stm32_pctrl_get_desc_pin_from_gpio(struct stm32_pi
 	int i;
 
 	/* With few exceptions (e.g. bank 'Z'), pin number matches with pin index in array */
-	pin_desc = pctl->pins + stm32_pin_nb;
-	if (pin_desc->pin.number == stm32_pin_nb)
-		return pin_desc;
+	if (stm32_pin_nb < pctl->npins) {
+		pin_desc = pctl->pins + stm32_pin_nb;
+		if (pin_desc->pin.number == stm32_pin_nb)
+			return pin_desc;
+	}
 
 	/* Otherwise, loop all array to find the pin with the right number */
 	for (i = 0; i < pctl->npins; i++) {
@@ -1368,6 +1370,11 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, struct fwnode
 	}
 
 	names = devm_kcalloc(dev, npins, sizeof(char *), GFP_KERNEL);
+	if (!names) {
+		err = -ENOMEM;
+		goto err_clk;
+	}
+
 	for (i = 0; i < npins; i++) {
 		stm32_pin = stm32_pctrl_get_desc_pin_from_gpio(pctl, bank, i);
 		if (stm32_pin && stm32_pin->pin.name)
diff --git a/drivers/platform/mellanox/mlxbf-bootctl.c b/drivers/platform/mellanox/mlxbf-bootctl.c
index 1ac7dab22c637e..c1aef3a8fb2de2 100644
--- a/drivers/platform/mellanox/mlxbf-bootctl.c
+++ b/drivers/platform/mellanox/mlxbf-bootctl.c
@@ -20,6 +20,7 @@
 
 #define MLXBF_BOOTCTL_SB_SECURE_MASK		0x03
 #define MLXBF_BOOTCTL_SB_TEST_MASK		0x0c
+#define MLXBF_BOOTCTL_SB_DEV_MASK		BIT(4)
 
 #define MLXBF_SB_KEY_NUM			4
 
@@ -40,11 +41,18 @@ static struct mlxbf_bootctl_name boot_names[] = {
 	{ MLXBF_BOOTCTL_NONE, "none" },
 };
 
+enum {
+	MLXBF_BOOTCTL_SB_LIFECYCLE_PRODUCTION = 0,
+	MLXBF_BOOTCTL_SB_LIFECYCLE_GA_SECURE = 1,
+	MLXBF_BOOTCTL_SB_LIFECYCLE_GA_NON_SECURE = 2,
+	MLXBF_BOOTCTL_SB_LIFECYCLE_RMA = 3
+};
+
 static const char * const mlxbf_bootctl_lifecycle_states[] = {
-	[0] = "Production",
-	[1] = "GA Secured",
-	[2] = "GA Non-Secured",
-	[3] = "RMA",
+	[MLXBF_BOOTCTL_SB_LIFECYCLE_PRODUCTION] = "Production",
+	[MLXBF_BOOTCTL_SB_LIFECYCLE_GA_SECURE] = "GA Secured",
+	[MLXBF_BOOTCTL_SB_LIFECYCLE_GA_NON_SECURE] = "GA Non-Secured",
+	[MLXBF_BOOTCTL_SB_LIFECYCLE_RMA] = "RMA",
 };
 
 /* Log header format. */
@@ -247,25 +255,30 @@ static ssize_t second_reset_action_store(struct device *dev,
 static ssize_t lifecycle_state_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
+	int status_bits;
+	int use_dev_key;
+	int test_state;
 	int lc_state;
 
-	lc_state = mlxbf_bootctl_smc(MLXBF_BOOTCTL_GET_TBB_FUSE_STATUS,
-				     MLXBF_BOOTCTL_FUSE_STATUS_LIFECYCLE);
-	if (lc_state < 0)
-		return lc_state;
+	status_bits = mlxbf_bootctl_smc(MLXBF_BOOTCTL_GET_TBB_FUSE_STATUS,
+					MLXBF_BOOTCTL_FUSE_STATUS_LIFECYCLE);
+	if (status_bits < 0)
+		return status_bits;
 
-	lc_state &=
-		MLXBF_BOOTCTL_SB_TEST_MASK | MLXBF_BOOTCTL_SB_SECURE_MASK;
+	use_dev_key = status_bits & MLXBF_BOOTCTL_SB_DEV_MASK;
+	test_state = status_bits & MLXBF_BOOTCTL_SB_TEST_MASK;
+	lc_state = status_bits & MLXBF_BOOTCTL_SB_SECURE_MASK;
 
 	/*
 	 * If the test bits are set, we specify that the current state may be
 	 * due to using the test bits.
 	 */
-	if (lc_state & MLXBF_BOOTCTL_SB_TEST_MASK) {
-		lc_state &= MLXBF_BOOTCTL_SB_SECURE_MASK;
-
+	if (test_state) {
 		return sprintf(buf, "%s(test)\n",
 			       mlxbf_bootctl_lifecycle_states[lc_state]);
+	} else if (use_dev_key &&
+		   (lc_state == MLXBF_BOOTCTL_SB_LIFECYCLE_GA_SECURE)) {
+		return sprintf(buf, "Secured (development)\n");
 	}
 
 	return sprintf(buf, "%s\n", mlxbf_bootctl_lifecycle_states[lc_state]);
diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c
index 0b427fc24a96e7..1dd84c7a79de97 100644
--- a/drivers/platform/mellanox/mlxbf-pmc.c
+++ b/drivers/platform/mellanox/mlxbf-pmc.c
@@ -1771,6 +1771,8 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, int blk_num)
 	attr->dev_attr.show = mlxbf_pmc_event_list_show;
 	attr->nr = blk_num;
 	attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL, "event_list");
+	if (!attr->dev_attr.attr.name)
+		return -ENOMEM;
 	pmc->block[blk_num].block_attr[i] = &attr->dev_attr.attr;
 	attr = NULL;
 
@@ -1784,6 +1786,8 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, int blk_num)
 		attr->nr = blk_num;
 		attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
 							  "enable");
+		if (!attr->dev_attr.attr.name)
+			return -ENOMEM;
 		pmc->block[blk_num].block_attr[++i] = &attr->dev_attr.attr;
 		attr = NULL;
 	}
@@ -1810,6 +1814,8 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, int blk_num)
 		attr->nr = blk_num;
 		attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
 							  "counter%d", j);
+		if (!attr->dev_attr.attr.name)
+			return -ENOMEM;
 		pmc->block[blk_num].block_attr[++i] = &attr->dev_attr.attr;
 		attr = NULL;
 
@@ -1821,6 +1827,8 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, int blk_num)
 		attr->nr = blk_num;
 		attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
 							  "event%d", j);
+		if (!attr->dev_attr.attr.name)
+			return -ENOMEM;
 		pmc->block[blk_num].block_attr[++i] = &attr->dev_attr.attr;
 		attr = NULL;
 	}
@@ -1853,6 +1861,8 @@ static int mlxbf_pmc_init_perftype_reg(struct device *dev, int blk_num)
 		attr->nr = blk_num;
 		attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
 							  events[j].evt_name);
+		if (!attr->dev_attr.attr.name)
+			return -ENOMEM;
 		pmc->block[blk_num].block_attr[i] = &attr->dev_attr.attr;
 		attr = NULL;
 		i++;
@@ -1882,6 +1892,8 @@ static int mlxbf_pmc_create_groups(struct device *dev, int blk_num)
 	pmc->block[blk_num].block_attr_grp.attrs = pmc->block[blk_num].block_attr;
 	pmc->block[blk_num].block_attr_grp.name = devm_kasprintf(
 		dev, GFP_KERNEL, pmc->block_name[blk_num]);
+	if (!pmc->block[blk_num].block_attr_grp.name)
+		return -ENOMEM;
 	pmc->groups[pmc->group_num] = &pmc->block[blk_num].block_attr_grp;
 	pmc->group_num++;
 
@@ -2063,6 +2075,8 @@ static int mlxbf_pmc_probe(struct platform_device *pdev)
 
 	pmc->hwmon_dev = devm_hwmon_device_register_with_groups(
 		dev, "bfperf", pmc, pmc->groups);
+	if (IS_ERR(pmc->hwmon_dev))
+		return PTR_ERR(pmc->hwmon_dev);
 	platform_set_drvdata(pdev, pmc);
 
 	return 0;
diff --git a/drivers/platform/surface/aggregator/core.c b/drivers/platform/surface/aggregator/core.c
index 1a6373dea109cc..6152be38398c48 100644
--- a/drivers/platform/surface/aggregator/core.c
+++ b/drivers/platform/surface/aggregator/core.c
@@ -231,9 +231,12 @@ static int ssam_receive_buf(struct serdev_device *dev, const unsigned char *buf,
 			    size_t n)
 {
 	struct ssam_controller *ctrl;
+	int ret;
 
 	ctrl = serdev_device_get_drvdata(dev);
-	return ssam_controller_receive_buf(ctrl, buf, n);
+	ret = ssam_controller_receive_buf(ctrl, buf, n);
+
+	return ret < 0 ? 0 : ret;
 }
 
 static void ssam_write_wakeup(struct serdev_device *dev)
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 7e69fdaccdd535..c94f31a5c6a336 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -263,6 +263,7 @@ config ASUS_WMI
 	depends on RFKILL || RFKILL = n
 	depends on HOTPLUG_PCI
 	depends on ACPI_VIDEO || ACPI_VIDEO = n
+	depends on SERIO_I8042 || SERIO_I8042 = n
 	select INPUT_SPARSEKMAP
 	select LEDS_CLASS
 	select NEW_LEDS
@@ -279,7 +280,6 @@ config ASUS_WMI
 config ASUS_NB_WMI
 	tristate "Asus Notebook WMI Driver"
 	depends on ASUS_WMI
-	depends on SERIO_I8042 || SERIO_I8042 = n
 	help
 	  This is a driver for newer Asus notebooks. It adds extra features
 	  like wireless radio and bluetooth control, leds, hotkeys, backlight...
diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index 6bbffb081053e5..b456370166b6bb 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -16,12 +16,17 @@
 
 struct quirk_entry {
 	u32 s2idle_bug_mmio;
+	bool spurious_8042;
 };
 
 static struct quirk_entry quirk_s2idle_bug = {
 	.s2idle_bug_mmio = 0xfed80380,
 };
 
+static struct quirk_entry quirk_spurious_8042 = {
+	.spurious_8042 = true,
+};
+
 static const struct dmi_system_id fwbug_list[] = {
 	{
 		.ident = "L14 Gen2 AMD",
@@ -193,6 +198,16 @@ static const struct dmi_system_id fwbug_list[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "HP Laptop 15s-eq2xxx"),
 		}
 	},
+	/* https://community.frame.work/t/tracking-framework-amd-ryzen-7040-series-lid-wakeup-behavior-feedback/39128 */
+	{
+		.ident = "Framework Laptop 13 (Phoenix)",
+		.driver_data = &quirk_spurious_8042,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Framework"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Laptop 13 (AMD Ryzen 7040Series)"),
+			DMI_MATCH(DMI_BIOS_VERSION, "03.03"),
+		}
+	},
 	{}
 };
 
@@ -235,6 +250,9 @@ void amd_pmc_quirks_init(struct amd_pmc_dev *dev)
 {
 	const struct dmi_system_id *dmi_id;
 
+	if (dev->cpu_id == AMD_CPU_ID_CZN)
+		dev->disable_8042_wakeup = true;
+
 	dmi_id = dmi_first_match(fwbug_list);
 	if (!dmi_id)
 		return;
@@ -242,4 +260,6 @@ void amd_pmc_quirks_init(struct amd_pmc_dev *dev)
 	if (dev->quirks->s2idle_bug_mmio)
 		pr_info("Using s2idle quirk to avoid %s platform firmware bug\n",
 			dmi_id->ident);
+	if (dev->quirks->spurious_8042)
+		dev->disable_8042_wakeup = true;
 }
diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c
index cd6ac04c14680d..864c8cc2f8a3c5 100644
--- a/drivers/platform/x86/amd/pmc/pmc.c
+++ b/drivers/platform/x86/amd/pmc/pmc.c
@@ -91,16 +91,6 @@
 #define SMU_MSG_LOG_RESET		0x07
 #define SMU_MSG_LOG_DUMP_DATA		0x08
 #define SMU_MSG_GET_SUP_CONSTRAINTS	0x09
-/* List of supported CPU ids */
-#define AMD_CPU_ID_RV			0x15D0
-#define AMD_CPU_ID_RN			0x1630
-#define AMD_CPU_ID_PCO			AMD_CPU_ID_RV
-#define AMD_CPU_ID_CZN			AMD_CPU_ID_RN
-#define AMD_CPU_ID_YC			0x14B5
-#define AMD_CPU_ID_CB			0x14D8
-#define AMD_CPU_ID_PS			0x14E8
-#define AMD_CPU_ID_SP			0x14A4
-#define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507
 
 #define PMC_MSG_DELAY_MIN_US		50
 #define RESPONSE_REGISTER_LOOP_MAX	20000
@@ -766,19 +756,22 @@ static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev)
 	return -EINVAL;
 }
 
-static int amd_pmc_czn_wa_irq1(struct amd_pmc_dev *pdev)
+static int amd_pmc_wa_irq1(struct amd_pmc_dev *pdev)
 {
 	struct device *d;
 	int rc;
 
-	if (!pdev->major) {
-		rc = amd_pmc_get_smu_version(pdev);
-		if (rc)
-			return rc;
-	}
+	/* cezanne platform firmware has a fix in 64.66.0 */
+	if (pdev->cpu_id == AMD_CPU_ID_CZN) {
+		if (!pdev->major) {
+			rc = amd_pmc_get_smu_version(pdev);
+			if (rc)
+				return rc;
+		}
 
-	if (pdev->major > 64 || (pdev->major == 64 && pdev->minor > 65))
-		return 0;
+		if (pdev->major > 64 || (pdev->major == 64 && pdev->minor > 65))
+			return 0;
+	}
 
 	d = bus_find_device_by_name(&serio_bus, NULL, "serio0");
 	if (!d)
@@ -937,8 +930,8 @@ static int amd_pmc_suspend_handler(struct device *dev)
 {
 	struct amd_pmc_dev *pdev = dev_get_drvdata(dev);
 
-	if (pdev->cpu_id == AMD_CPU_ID_CZN && !disable_workarounds) {
-		int rc = amd_pmc_czn_wa_irq1(pdev);
+	if (pdev->disable_8042_wakeup && !disable_workarounds) {
+		int rc = amd_pmc_wa_irq1(pdev);
 
 		if (rc) {
 			dev_err(pdev->dev, "failed to adjust keyboard wakeup: %d\n", rc);
@@ -964,33 +957,6 @@ static const struct pci_device_id pmc_pci_ids[] = {
 	{ }
 };
 
-static int amd_pmc_get_dram_size(struct amd_pmc_dev *dev)
-{
-	int ret;
-
-	switch (dev->cpu_id) {
-	case AMD_CPU_ID_YC:
-		if (!(dev->major > 90 || (dev->major == 90 && dev->minor > 39))) {
-			ret = -EINVAL;
-			goto err_dram_size;
-		}
-		break;
-	default:
-		ret = -EINVAL;
-		goto err_dram_size;
-	}
-
-	ret = amd_pmc_send_cmd(dev, S2D_DRAM_SIZE, &dev->dram_size, dev->s2d_msg_id, true);
-	if (ret || !dev->dram_size)
-		goto err_dram_size;
-
-	return 0;
-
-err_dram_size:
-	dev_err(dev->dev, "DRAM size command not supported for this platform\n");
-	return ret;
-}
-
 static int amd_pmc_s2d_init(struct amd_pmc_dev *dev)
 {
 	u32 phys_addr_low, phys_addr_hi;
@@ -1009,8 +975,8 @@ static int amd_pmc_s2d_init(struct amd_pmc_dev *dev)
 		return -EIO;
 
 	/* Get DRAM size */
-	ret = amd_pmc_get_dram_size(dev);
-	if (ret)
+	ret = amd_pmc_send_cmd(dev, S2D_DRAM_SIZE, &dev->dram_size, dev->s2d_msg_id, true);
+	if (ret || !dev->dram_size)
 		dev->dram_size = S2D_TELEMETRY_DRAMBYTES_MAX;
 
 	/* Get STB DRAM address */
diff --git a/drivers/platform/x86/amd/pmc/pmc.h b/drivers/platform/x86/amd/pmc/pmc.h
index c27bd6a5642f48..b4794f118739f6 100644
--- a/drivers/platform/x86/amd/pmc/pmc.h
+++ b/drivers/platform/x86/amd/pmc/pmc.h
@@ -36,9 +36,21 @@ struct amd_pmc_dev {
 	struct mutex lock; /* generic mutex lock */
 	struct dentry *dbgfs_dir;
 	struct quirk_entry *quirks;
+	bool disable_8042_wakeup;
 };
 
 void amd_pmc_process_restore_quirks(struct amd_pmc_dev *dev);
 void amd_pmc_quirks_init(struct amd_pmc_dev *dev);
 
+/* List of supported CPU ids */
+#define AMD_CPU_ID_RV			0x15D0
+#define AMD_CPU_ID_RN			0x1630
+#define AMD_CPU_ID_PCO			AMD_CPU_ID_RV
+#define AMD_CPU_ID_CZN			AMD_CPU_ID_RN
+#define AMD_CPU_ID_YC			0x14B5
+#define AMD_CPU_ID_CB			0x14D8
+#define AMD_CPU_ID_PS			0x14E8
+#define AMD_CPU_ID_SP			0x14A4
+#define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507
+
 #endif /* PMC_H */
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 9aa1226e74e6c5..fceffe2082ec58 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -48,25 +48,43 @@ module_param(tablet_mode_sw, uint, 0444);
 MODULE_PARM_DESC(tablet_mode_sw, "Tablet mode detect: -1:auto 0:disable 1:kbd-dock 2:lid-flip 3:lid-flip-rog");
 
 static struct quirk_entry *quirks;
+static bool atkbd_reports_vol_keys;
 
-static bool asus_q500a_i8042_filter(unsigned char data, unsigned char str,
-			      struct serio *port)
+static bool asus_i8042_filter(unsigned char data, unsigned char str, struct serio *port)
 {
-	static bool extended;
-	bool ret = false;
+	static bool extended_e0;
+	static bool extended_e1;
 
 	if (str & I8042_STR_AUXDATA)
 		return false;
 
-	if (unlikely(data == 0xe1)) {
-		extended = true;
-		ret = true;
-	} else if (unlikely(extended)) {
-		extended = false;
-		ret = true;
+	if (quirks->filter_i8042_e1_extended_codes) {
+		if (data == 0xe1) {
+			extended_e1 = true;
+			return true;
+		}
+
+		if (extended_e1) {
+			extended_e1 = false;
+			return true;
+		}
 	}
 
-	return ret;
+	if (data == 0xe0) {
+		extended_e0 = true;
+	} else if (extended_e0) {
+		extended_e0 = false;
+
+		switch (data & 0x7f) {
+		case 0x20: /* e0 20 / e0 a0, Volume Mute press / release */
+		case 0x2e: /* e0 2e / e0 ae, Volume Down press / release */
+		case 0x30: /* e0 30 / e0 b0, Volume Up press / release */
+			atkbd_reports_vol_keys = true;
+			break;
+		}
+	}
+
+	return false;
 }
 
 static struct quirk_entry quirk_asus_unknown = {
@@ -75,7 +93,7 @@ static struct quirk_entry quirk_asus_unknown = {
 };
 
 static struct quirk_entry quirk_asus_q500a = {
-	.i8042_filter = asus_q500a_i8042_filter,
+	.filter_i8042_e1_extended_codes = true,
 	.wmi_backlight_set_devstate = true,
 };
 
@@ -503,8 +521,6 @@ static const struct dmi_system_id asus_quirks[] = {
 
 static void asus_nb_wmi_quirks(struct asus_wmi_driver *driver)
 {
-	int ret;
-
 	quirks = &quirk_asus_unknown;
 	dmi_check_system(asus_quirks);
 
@@ -519,15 +535,6 @@ static void asus_nb_wmi_quirks(struct asus_wmi_driver *driver)
 
 	if (tablet_mode_sw != -1)
 		quirks->tablet_switch_mode = tablet_mode_sw;
-
-	if (quirks->i8042_filter) {
-		ret = i8042_install_filter(quirks->i8042_filter);
-		if (ret) {
-			pr_warn("Unable to install key filter\n");
-			return;
-		}
-		pr_info("Using i8042 filter function for receiving events\n");
-	}
 }
 
 static const struct key_entry asus_nb_wmi_keymap[] = {
@@ -618,6 +625,13 @@ static void asus_nb_wmi_key_filter(struct asus_wmi_driver *asus_wmi, int *code,
 			*code = ASUS_WMI_KEY_IGNORE;
 
 		break;
+	case 0x30: /* Volume Up */
+	case 0x31: /* Volume Down */
+	case 0x32: /* Volume Mute */
+		if (atkbd_reports_vol_keys)
+			*code = ASUS_WMI_KEY_IGNORE;
+
+		break;
 	}
 }
 
@@ -630,6 +644,7 @@ static struct asus_wmi_driver asus_nb_wmi_driver = {
 	.input_phys = ASUS_NB_WMI_FILE "/input0",
 	.detect_quirks = asus_nb_wmi_quirks,
 	.key_filter = asus_nb_wmi_key_filter,
+	.i8042_filter = asus_i8042_filter,
 };
 
 
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 6a79f16233abf7..9f7e23c5c6b4da 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -16,6 +16,7 @@
 #include <linux/acpi.h>
 #include <linux/backlight.h>
 #include <linux/debugfs.h>
+#include <linux/delay.h>
 #include <linux/dmi.h>
 #include <linux/fb.h>
 #include <linux/hwmon.h>
@@ -132,6 +133,11 @@ module_param(fnlock_default, bool, 0444);
 #define ASUS_SCREENPAD_BRIGHT_MAX 255
 #define ASUS_SCREENPAD_BRIGHT_DEFAULT 60
 
+/* Controls the power state of the USB0 hub on ROG Ally which input is on */
+#define ASUS_USB0_PWR_EC0_CSEE "\\_SB.PCI0.SBRG.EC0.CSEE"
+/* 300ms so far seems to produce a reliable result on AC and battery */
+#define ASUS_USB0_PWR_EC0_CSEE_WAIT 300
+
 static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL };
 
 static int throttle_thermal_policy_write(struct asus_wmi *);
@@ -300,6 +306,9 @@ struct asus_wmi {
 
 	bool fnlock_locked;
 
+	/* The ROG Ally device requires the MCU USB device be disconnected before suspend */
+	bool ally_mcu_usb_switch;
+
 	struct asus_wmi_debug debug;
 
 	struct asus_wmi_driver *driver;
@@ -4488,6 +4497,8 @@ static int asus_wmi_add(struct platform_device *pdev)
 	asus->nv_temp_tgt_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_NV_THERM_TARGET);
 	asus->panel_overdrive_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_PANEL_OD);
 	asus->mini_led_mode_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_MINI_LED_MODE);
+	asus->ally_mcu_usb_switch = acpi_has_method(NULL, ASUS_USB0_PWR_EC0_CSEE)
+						&& dmi_match(DMI_BOARD_NAME, "RC71L");
 
 	err = fan_boost_mode_check_present(asus);
 	if (err)
@@ -4567,6 +4578,12 @@ static int asus_wmi_add(struct platform_device *pdev)
 		goto fail_wmi_handler;
 	}
 
+	if (asus->driver->i8042_filter) {
+		err = i8042_install_filter(asus->driver->i8042_filter);
+		if (err)
+			pr_warn("Unable to install key filter - %d\n", err);
+	}
+
 	asus_wmi_battery_init(asus);
 
 	asus_wmi_debugfs_init(asus);
@@ -4603,6 +4620,8 @@ static int asus_wmi_remove(struct platform_device *device)
 	struct asus_wmi *asus;
 
 	asus = platform_get_drvdata(device);
+	if (asus->driver->i8042_filter)
+		i8042_remove_filter(asus->driver->i8042_filter);
 	wmi_remove_notify_handler(asus->driver->event_guid);
 	asus_wmi_backlight_exit(asus);
 	asus_screenpad_exit(asus);
@@ -4654,6 +4673,43 @@ static int asus_hotk_resume(struct device *device)
 		asus_wmi_fnlock_update(asus);
 
 	asus_wmi_tablet_mode_get_state(asus);
+
+	return 0;
+}
+
+static int asus_hotk_resume_early(struct device *device)
+{
+	struct asus_wmi *asus = dev_get_drvdata(device);
+
+	if (asus->ally_mcu_usb_switch) {
+		if (ACPI_FAILURE(acpi_execute_simple_method(NULL, ASUS_USB0_PWR_EC0_CSEE, 0xB8)))
+			dev_err(device, "ROG Ally MCU failed to connect USB dev\n");
+		else
+			msleep(ASUS_USB0_PWR_EC0_CSEE_WAIT);
+	}
+	return 0;
+}
+
+static int asus_hotk_prepare(struct device *device)
+{
+	struct asus_wmi *asus = dev_get_drvdata(device);
+	int result, err;
+
+	if (asus->ally_mcu_usb_switch) {
+		/* When powersave is enabled it causes many issues with resume of USB hub */
+		result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_MCU_POWERSAVE);
+		if (result == 1) {
+			dev_warn(device, "MCU powersave enabled, disabling to prevent resume issues");
+			err = asus_wmi_set_devstate(ASUS_WMI_DEVID_MCU_POWERSAVE, 0, &result);
+			if (err || result != 1)
+				dev_err(device, "Failed to set MCU powersave mode: %d\n", err);
+		}
+		/* sleep required to ensure USB0 is disabled before sleep continues */
+		if (ACPI_FAILURE(acpi_execute_simple_method(NULL, ASUS_USB0_PWR_EC0_CSEE, 0xB7)))
+			dev_err(device, "ROG Ally MCU failed to disconnect USB dev\n");
+		else
+			msleep(ASUS_USB0_PWR_EC0_CSEE_WAIT);
+	}
 	return 0;
 }
 
@@ -4701,6 +4757,8 @@ static const struct dev_pm_ops asus_pm_ops = {
 	.thaw = asus_hotk_thaw,
 	.restore = asus_hotk_restore,
 	.resume = asus_hotk_resume,
+	.resume_early = asus_hotk_resume_early,
+	.prepare = asus_hotk_prepare,
 };
 
 /* Registration ***************************************************************/
diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h
index adb67c92572487..cc30f185384723 100644
--- a/drivers/platform/x86/asus-wmi.h
+++ b/drivers/platform/x86/asus-wmi.h
@@ -39,6 +39,7 @@ struct quirk_entry {
 	bool wmi_backlight_set_devstate;
 	bool wmi_force_als_set;
 	bool wmi_ignore_fan;
+	bool filter_i8042_e1_extended_codes;
 	enum asus_wmi_tablet_switch_mode tablet_switch_mode;
 	int wapf;
 	/*
@@ -49,9 +50,6 @@ struct quirk_entry {
 	 */
 	int no_display_toggle;
 	u32 xusb2pr;
-
-	bool (*i8042_filter)(unsigned char data, unsigned char str,
-			     struct serio *serio);
 };
 
 struct asus_wmi_driver {
@@ -73,6 +71,9 @@ struct asus_wmi_driver {
 	 * Return ASUS_WMI_KEY_IGNORE in code if event should be ignored. */
 	void (*key_filter) (struct asus_wmi_driver *driver, int *code,
 			    unsigned int *value, bool *autorelease);
+	/* Optional standard i8042 filter */
+	bool (*i8042_filter)(unsigned char data, unsigned char str,
+			     struct serio *serio);
 
 	int (*probe) (struct platform_device *device);
 	void (*detect_quirks) (struct asus_wmi_driver *driver);
diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
index 5798b49ddaba90..8c9f4f3227fc6d 100644
--- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
+++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
@@ -588,17 +588,14 @@ static void release_attributes_data(void)
 static int hp_add_other_attributes(int attr_type)
 {
 	struct kobject *attr_name_kobj;
-	union acpi_object *obj = NULL;
 	int ret;
 	char *attr_name;
 
-	mutex_lock(&bioscfg_drv.mutex);
-
 	attr_name_kobj = kzalloc(sizeof(*attr_name_kobj), GFP_KERNEL);
-	if (!attr_name_kobj) {
-		ret = -ENOMEM;
-		goto err_other_attr_init;
-	}
+	if (!attr_name_kobj)
+		return -ENOMEM;
+
+	mutex_lock(&bioscfg_drv.mutex);
 
 	/* Check if attribute type is supported */
 	switch (attr_type) {
@@ -615,14 +612,14 @@ static int hp_add_other_attributes(int attr_type)
 	default:
 		pr_err("Error: Unknown attr_type: %d\n", attr_type);
 		ret = -EINVAL;
-		goto err_other_attr_init;
+		kfree(attr_name_kobj);
+		goto unlock_drv_mutex;
 	}
 
 	ret = kobject_init_and_add(attr_name_kobj, &attr_name_ktype,
 				   NULL, "%s", attr_name);
 	if (ret) {
 		pr_err("Error encountered [%d]\n", ret);
-		kobject_put(attr_name_kobj);
 		goto err_other_attr_init;
 	}
 
@@ -630,27 +627,26 @@ static int hp_add_other_attributes(int attr_type)
 	switch (attr_type) {
 	case HPWMI_SECURE_PLATFORM_TYPE:
 		ret = hp_populate_secure_platform_data(attr_name_kobj);
-		if (ret)
-			goto err_other_attr_init;
 		break;
 
 	case HPWMI_SURE_START_TYPE:
 		ret = hp_populate_sure_start_data(attr_name_kobj);
-		if (ret)
-			goto err_other_attr_init;
 		break;
 
 	default:
 		ret = -EINVAL;
-		goto err_other_attr_init;
 	}
 
+	if (ret)
+		goto err_other_attr_init;
+
 	mutex_unlock(&bioscfg_drv.mutex);
 	return 0;
 
 err_other_attr_init:
+	kobject_put(attr_name_kobj);
+unlock_drv_mutex:
 	mutex_unlock(&bioscfg_drv.mutex);
-	kfree(obj);
 	return ret;
 }
 
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index ac037540acfc60..88eefccb6ed276 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -1425,18 +1425,17 @@ static int ideapad_kbd_bl_init(struct ideapad_private *priv)
 	if (WARN_ON(priv->kbd_bl.initialized))
 		return -EEXIST;
 
-	brightness = ideapad_kbd_bl_brightness_get(priv);
-	if (brightness < 0)
-		return brightness;
-
-	priv->kbd_bl.last_brightness = brightness;
-
 	if (ideapad_kbd_bl_check_tristate(priv->kbd_bl.type)) {
 		priv->kbd_bl.led.max_brightness = 2;
 	} else {
 		priv->kbd_bl.led.max_brightness = 1;
 	}
 
+	brightness = ideapad_kbd_bl_brightness_get(priv);
+	if (brightness < 0)
+		return brightness;
+
+	priv->kbd_bl.last_brightness = brightness;
 	priv->kbd_bl.led.name                    = "platform::" LED_FUNCTION_KBD_BACKLIGHT;
 	priv->kbd_bl.led.brightness_get          = ideapad_kbd_bl_led_cdev_brightness_get;
 	priv->kbd_bl.led.brightness_set_blocking = ideapad_kbd_bl_led_cdev_brightness_set;
diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c
index 84c175b9721a0b..e95d3011b9997d 100644
--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@@ -472,7 +472,7 @@ int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value)
 	 * is based on the contiguous indexes from ltr_show output.
 	 * pmc index and ltr index needs to be calculated from it.
 	 */
-	for (pmc_index = 0; pmc_index < ARRAY_SIZE(pmcdev->pmcs) && ltr_index > 0; pmc_index++) {
+	for (pmc_index = 0; pmc_index < ARRAY_SIZE(pmcdev->pmcs) && ltr_index >= 0; pmc_index++) {
 		pmc = pmcdev->pmcs[pmc_index];
 
 		if (!pmc)
diff --git a/drivers/platform/x86/intel/telemetry/core.c b/drivers/platform/x86/intel/telemetry/core.c
index fdf55b5d69480e..e4be40f73eebfc 100644
--- a/drivers/platform/x86/intel/telemetry/core.c
+++ b/drivers/platform/x86/intel/telemetry/core.c
@@ -102,7 +102,7 @@ static const struct telemetry_core_ops telm_defpltops = {
 /**
  * telemetry_update_events() - Update telemetry Configuration
  * @pss_evtconfig: PSS related config. No change if num_evts = 0.
- * @pss_evtconfig: IOSS related config. No change if num_evts = 0.
+ * @ioss_evtconfig: IOSS related config. No change if num_evts = 0.
  *
  * This API updates the IOSS & PSS Telemetry configuration. Old config
  * is overwritten. Call telemetry_reset_events when logging is over
@@ -176,7 +176,7 @@ EXPORT_SYMBOL_GPL(telemetry_reset_events);
 /**
  * telemetry_get_eventconfig() - Returns the pss and ioss events enabled
  * @pss_evtconfig: Pointer to PSS related configuration.
- * @pss_evtconfig: Pointer to IOSS related configuration.
+ * @ioss_evtconfig: Pointer to IOSS related configuration.
  * @pss_len:	   Number of u32 elements allocated for pss_evtconfig array
  * @ioss_len:	   Number of u32 elements allocated for ioss_evtconfig array
  *
diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c
index 6fa1735ad7a49a..210b0a81b7ecbe 100644
--- a/drivers/platform/x86/intel/vbtn.c
+++ b/drivers/platform/x86/intel/vbtn.c
@@ -73,10 +73,10 @@ struct intel_vbtn_priv {
 	bool wakeup_mode;
 };
 
-static void detect_tablet_mode(struct platform_device *device)
+static void detect_tablet_mode(struct device *dev)
 {
-	struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev);
-	acpi_handle handle = ACPI_HANDLE(&device->dev);
+	struct intel_vbtn_priv *priv = dev_get_drvdata(dev);
+	acpi_handle handle = ACPI_HANDLE(dev);
 	unsigned long long vgbs;
 	acpi_status status;
 	int m;
@@ -89,6 +89,8 @@ static void detect_tablet_mode(struct platform_device *device)
 	input_report_switch(priv->switches_dev, SW_TABLET_MODE, m);
 	m = (vgbs & VGBS_DOCK_MODE_FLAG) ? 1 : 0;
 	input_report_switch(priv->switches_dev, SW_DOCK, m);
+
+	input_sync(priv->switches_dev);
 }
 
 /*
@@ -134,7 +136,7 @@ static int intel_vbtn_input_setup(struct platform_device *device)
 	priv->switches_dev->id.bustype = BUS_HOST;
 
 	if (priv->has_switches) {
-		detect_tablet_mode(device);
+		detect_tablet_mode(&device->dev);
 
 		ret = input_register_device(priv->switches_dev);
 		if (ret)
@@ -198,6 +200,9 @@ static void notify_handler(acpi_handle handle, u32 event, void *context)
 	autorelease = val && (!ke_rel || ke_rel->type == KE_IGNORE);
 
 	sparse_keymap_report_event(input_dev, event, val, autorelease);
+
+	/* Some devices need this to report further events */
+	acpi_evaluate_object(handle, "VBDL", NULL, NULL);
 }
 
 /*
@@ -352,7 +357,13 @@ static void intel_vbtn_pm_complete(struct device *dev)
 
 static int intel_vbtn_pm_resume(struct device *dev)
 {
+	struct intel_vbtn_priv *priv = dev_get_drvdata(dev);
+
 	intel_vbtn_pm_complete(dev);
+
+	if (priv->has_switches)
+		detect_tablet_mode(dev);
+
 	return 0;
 }
 
diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c
index 4dfdbfca684172..c66808601fdd08 100644
--- a/drivers/platform/x86/intel_ips.c
+++ b/drivers/platform/x86/intel_ips.c
@@ -590,6 +590,8 @@ static void ips_disable_gpu_turbo(struct ips_driver *ips)
  * @ips: IPS driver struct
  *
  * Check whether the MCP is over its thermal or power budget.
+ *
+ * Returns: %true if the temp or power has exceeded its maximum, else %false
  */
 static bool mcp_exceeded(struct ips_driver *ips)
 {
@@ -619,6 +621,8 @@ static bool mcp_exceeded(struct ips_driver *ips)
  * @cpu: CPU number to check
  *
  * Check a given CPU's average temp or power is over its limit.
+ *
+ * Returns: %true if the temp or power has exceeded its maximum, else %false
  */
 static bool cpu_exceeded(struct ips_driver *ips, int cpu)
 {
@@ -645,6 +649,8 @@ static bool cpu_exceeded(struct ips_driver *ips, int cpu)
  * @ips: IPS driver struct
  *
  * Check the MCH temp & power against their maximums.
+ *
+ * Returns: %true if the temp or power has exceeded its maximum, else %false
  */
 static bool mch_exceeded(struct ips_driver *ips)
 {
@@ -742,12 +748,13 @@ static void update_turbo_limits(struct ips_driver *ips)
  *   - down (at TDP limit)
  *     - adjust both CPU and GPU down if possible
  *
-		cpu+ gpu+	cpu+gpu-	cpu-gpu+	cpu-gpu-
-cpu < gpu <	cpu+gpu+	cpu+		gpu+		nothing
-cpu < gpu >=	cpu+gpu-(mcp<)	cpu+gpu-(mcp<)	gpu-		gpu-
-cpu >= gpu <	cpu-gpu+(mcp<)	cpu-		cpu-gpu+(mcp<)	cpu-
-cpu >= gpu >=	cpu-gpu-	cpu-gpu-	cpu-gpu-	cpu-gpu-
+ *              |cpu+ gpu+      cpu+gpu-        cpu-gpu+        cpu-gpu-
+ * cpu < gpu <  |cpu+gpu+       cpu+            gpu+            nothing
+ * cpu < gpu >= |cpu+gpu-(mcp<) cpu+gpu-(mcp<)  gpu-            gpu-
+ * cpu >= gpu < |cpu-gpu+(mcp<) cpu-            cpu-gpu+(mcp<)  cpu-
+ * cpu >= gpu >=|cpu-gpu-       cpu-gpu-        cpu-gpu-        cpu-gpu-
  *
+ * Returns: %0
  */
 static int ips_adjust(void *data)
 {
@@ -935,11 +942,13 @@ static void monitor_timeout(struct timer_list *t)
  * @data: ips driver structure
  *
  * This is the main function for the IPS driver.  It monitors power and
- * tempurature in the MCP and adjusts CPU and GPU power clams accordingly.
+ * temperature in the MCP and adjusts CPU and GPU power clamps accordingly.
  *
- * We keep a 5s moving average of power consumption and tempurature.  Using
+ * We keep a 5s moving average of power consumption and temperature.  Using
  * that data, along with CPU vs GPU preference, we adjust the power clamps
  * up or down.
+ *
+ * Returns: %0 on success or -errno on error
  */
 static int ips_monitor(void *data)
 {
@@ -1146,6 +1155,8 @@ static void dump_thermal_info(struct ips_driver *ips)
  * Handle temperature limit trigger events, generally by lowering the clamps.
  * If we're at a critical limit, we clamp back to the lowest possible value
  * to prevent emergency shutdown.
+ *
+ * Returns: IRQ_NONE or IRQ_HANDLED
  */
 static irqreturn_t ips_irq_handler(int irq, void *arg)
 {
@@ -1293,9 +1304,12 @@ static void ips_debugfs_init(struct ips_driver *ips)
 
 /**
  * ips_detect_cpu - detect whether CPU supports IPS
+ * @ips: IPS driver struct
  *
  * Walk our list and see if we're on a supported CPU.  If we find one,
  * return the limits for it.
+ *
+ * Returns: the &ips_mcp_limits struct that matches the boot CPU or %NULL
  */
 static struct ips_mcp_limits *ips_detect_cpu(struct ips_driver *ips)
 {
@@ -1352,6 +1366,8 @@ static struct ips_mcp_limits *ips_detect_cpu(struct ips_driver *ips)
  * monitor and control graphics turbo mode.  If we can find them, we can
  * enable graphics turbo, otherwise we must disable it to avoid exceeding
  * thermal and power limits in the MCP.
+ *
+ * Returns: %true if the required symbols are found, else %false
  */
 static bool ips_get_i915_syms(struct ips_driver *ips)
 {
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index d0b5fd4137bcdc..c4895e9bc7148a 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -512,10 +512,10 @@ struct tpacpi_quirk {
  * Iterates over a quirks list until one is found that matches the
  * ThinkPad's vendor, BIOS and EC model.
  *
- * Returns 0 if nothing matches, otherwise returns the quirks field of
+ * Returns: %0 if nothing matches, otherwise returns the quirks field of
  * the matching &struct tpacpi_quirk entry.
  *
- * The match criteria is: vendor, ec and bios much match.
+ * The match criteria is: vendor, ec and bios must match.
  */
 static unsigned long __init tpacpi_check_quirks(
 			const struct tpacpi_quirk *qlist,
@@ -7948,8 +7948,19 @@ static struct ibm_struct volume_driver_data = {
  * 	TPACPI_FAN_WR_TPEC is also available and should be used to
  * 	command the fan.  The X31/X40/X41 seems to have 8 fan levels,
  * 	but the ACPI tables just mention level 7.
+ *
+ * TPACPI_FAN_RD_TPEC_NS:
+ *	This mode is used for a few ThinkPads (L13 Yoga Gen2, X13 Yoga Gen2 etc.)
+ *	that are using non-standard EC locations for reporting fan speeds.
+ *	Currently these platforms only provide fan rpm reporting.
+ *
  */
 
+#define FAN_RPM_CAL_CONST 491520	/* FAN RPM calculation offset for some non-standard ECFW */
+
+#define FAN_NS_CTRL_STATUS	BIT(2)		/* Bit which determines control is enabled or not */
+#define FAN_NS_CTRL		BIT(4)		/* Bit which determines control is by host or EC */
+
 enum {					/* Fan control constants */
 	fan_status_offset = 0x2f,	/* EC register 0x2f */
 	fan_rpm_offset = 0x84,		/* EC register 0x84: LSB, 0x85 MSB (RPM)
@@ -7957,6 +7968,11 @@ enum {					/* Fan control constants */
 	fan_select_offset = 0x31,	/* EC register 0x31 (Firmware 7M)
 					   bit 0 selects which fan is active */
 
+	fan_status_offset_ns = 0x93,	/* Special status/control offset for non-standard EC Fan1 */
+	fan2_status_offset_ns = 0x96,	/* Special status/control offset for non-standard EC Fan2 */
+	fan_rpm_status_ns = 0x95,	/* Special offset for Fan1 RPM status for non-standard EC */
+	fan2_rpm_status_ns = 0x98,	/* Special offset for Fan2 RPM status for non-standard EC */
+
 	TP_EC_FAN_FULLSPEED = 0x40,	/* EC fan mode: full speed */
 	TP_EC_FAN_AUTO	    = 0x80,	/* EC fan mode: auto fan control */
 
@@ -7967,6 +7983,7 @@ enum fan_status_access_mode {
 	TPACPI_FAN_NONE = 0,		/* No fan status or control */
 	TPACPI_FAN_RD_ACPI_GFAN,	/* Use ACPI GFAN */
 	TPACPI_FAN_RD_TPEC,		/* Use ACPI EC regs 0x2f, 0x84-0x85 */
+	TPACPI_FAN_RD_TPEC_NS,		/* Use non-standard ACPI EC regs (eg: L13 Yoga gen2 etc.) */
 };
 
 enum fan_control_access_mode {
@@ -7994,6 +8011,8 @@ static u8 fan_control_desired_level;
 static u8 fan_control_resume_level;
 static int fan_watchdog_maxinterval;
 
+static bool fan_with_ns_addr;
+
 static struct mutex fan_mutex;
 
 static void fan_watchdog_fire(struct work_struct *ignored);
@@ -8123,6 +8142,15 @@ static int fan_get_status(u8 *status)
 		}
 
 		break;
+	case TPACPI_FAN_RD_TPEC_NS:
+		/* Default mode is AUTO which means controlled by EC */
+		if (!acpi_ec_read(fan_status_offset_ns, &s))
+			return -EIO;
+
+		if (status)
+			*status = s;
+
+		break;
 
 	default:
 		return -ENXIO;
@@ -8139,7 +8167,8 @@ static int fan_get_status_safe(u8 *status)
 	if (mutex_lock_killable(&fan_mutex))
 		return -ERESTARTSYS;
 	rc = fan_get_status(&s);
-	if (!rc)
+	/* NS EC doesn't have register with level settings */
+	if (!rc && !fan_with_ns_addr)
 		fan_update_desired_level(s);
 	mutex_unlock(&fan_mutex);
 
@@ -8166,7 +8195,13 @@ static int fan_get_speed(unsigned int *speed)
 
 		if (likely(speed))
 			*speed = (hi << 8) | lo;
+		break;
+	case TPACPI_FAN_RD_TPEC_NS:
+		if (!acpi_ec_read(fan_rpm_status_ns, &lo))
+			return -EIO;
 
+		if (speed)
+			*speed = lo ? FAN_RPM_CAL_CONST / lo : 0;
 		break;
 
 	default:
@@ -8178,7 +8213,7 @@ static int fan_get_speed(unsigned int *speed)
 
 static int fan2_get_speed(unsigned int *speed)
 {
-	u8 hi, lo;
+	u8 hi, lo, status;
 	bool rc;
 
 	switch (fan_status_access_mode) {
@@ -8194,7 +8229,21 @@ static int fan2_get_speed(unsigned int *speed)
 
 		if (likely(speed))
 			*speed = (hi << 8) | lo;
+		break;
 
+	case TPACPI_FAN_RD_TPEC_NS:
+		rc = !acpi_ec_read(fan2_status_offset_ns, &status);
+		if (rc)
+			return -EIO;
+		if (!(status & FAN_NS_CTRL_STATUS)) {
+			pr_info("secondary fan control not supported\n");
+			return -EIO;
+		}
+		rc = !acpi_ec_read(fan2_rpm_status_ns, &lo);
+		if (rc)
+			return -EIO;
+		if (speed)
+			*speed = lo ? FAN_RPM_CAL_CONST / lo : 0;
 		break;
 
 	default:
@@ -8697,6 +8746,7 @@ static const struct attribute_group fan_driver_attr_group = {
 #define TPACPI_FAN_2FAN		0x0002		/* EC 0x31 bit 0 selects fan2 */
 #define TPACPI_FAN_2CTL		0x0004		/* selects fan2 control */
 #define TPACPI_FAN_NOFAN	0x0008		/* no fan available */
+#define TPACPI_FAN_NS		0x0010		/* For EC with non-Standard register addresses */
 
 static const struct tpacpi_quirk fan_quirk_table[] __initconst = {
 	TPACPI_QEC_IBM('1', 'Y', TPACPI_FAN_Q1),
@@ -8715,6 +8765,8 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = {
 	TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL),	/* P1 / X1 Extreme (2nd gen) */
 	TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL),	/* P15 (1st gen) / P15v (1st gen) */
 	TPACPI_Q_LNV3('N', '3', '7', TPACPI_FAN_2CTL),  /* T15g (2nd gen) */
+	TPACPI_Q_LNV3('R', '1', 'F', TPACPI_FAN_NS),	/* L13 Yoga Gen 2 */
+	TPACPI_Q_LNV3('N', '2', 'U', TPACPI_FAN_NS),	/* X13 Yoga Gen 2*/
 	TPACPI_Q_LNV3('N', '1', 'O', TPACPI_FAN_NOFAN),	/* X1 Tablet (2nd gen) */
 };
 
@@ -8749,18 +8801,27 @@ static int __init fan_init(struct ibm_init_struct *iibm)
 		return -ENODEV;
 	}
 
+	if (quirks & TPACPI_FAN_NS) {
+		pr_info("ECFW with non-standard fan reg control found\n");
+		fan_with_ns_addr = 1;
+		/* Fan ctrl support from host is undefined for now */
+		tp_features.fan_ctrl_status_undef = 1;
+	}
+
 	if (gfan_handle) {
 		/* 570, 600e/x, 770e, 770x */
 		fan_status_access_mode = TPACPI_FAN_RD_ACPI_GFAN;
 	} else {
 		/* all other ThinkPads: note that even old-style
 		 * ThinkPad ECs supports the fan control register */
-		if (likely(acpi_ec_read(fan_status_offset,
-					&fan_control_initial_status))) {
+		if (fan_with_ns_addr ||
+		    likely(acpi_ec_read(fan_status_offset, &fan_control_initial_status))) {
 			int res;
 			unsigned int speed;
 
-			fan_status_access_mode = TPACPI_FAN_RD_TPEC;
+			fan_status_access_mode = fan_with_ns_addr ?
+				TPACPI_FAN_RD_TPEC_NS : TPACPI_FAN_RD_TPEC;
+
 			if (quirks & TPACPI_FAN_Q1)
 				fan_quirk1_setup();
 			/* Try and probe the 2nd fan */
@@ -8769,7 +8830,8 @@ static int __init fan_init(struct ibm_init_struct *iibm)
 			if (res >= 0 && speed != FAN_NOT_PRESENT) {
 				/* It responded - so let's assume it's there */
 				tp_features.second_fan = 1;
-				tp_features.second_fan_ctl = 1;
+				/* fan control not currently available for ns ECFW */
+				tp_features.second_fan_ctl = !fan_with_ns_addr;
 				pr_info("secondary fan control detected & enabled\n");
 			} else {
 				/* Fan not auto-detected */
@@ -8944,6 +9006,7 @@ static int fan_read(struct seq_file *m)
 			       str_enabled_disabled(status), status);
 		break;
 
+	case TPACPI_FAN_RD_TPEC_NS:
 	case TPACPI_FAN_RD_TPEC:
 		/* all except 570, 600e/x, 770e, 770x */
 		rc = fan_get_status_safe(&status);
@@ -8958,13 +9021,22 @@ static int fan_read(struct seq_file *m)
 
 		seq_printf(m, "speed:\t\t%d\n", speed);
 
-		if (status & TP_EC_FAN_FULLSPEED)
-			/* Disengaged mode takes precedence */
-			seq_printf(m, "level:\t\tdisengaged\n");
-		else if (status & TP_EC_FAN_AUTO)
-			seq_printf(m, "level:\t\tauto\n");
-		else
-			seq_printf(m, "level:\t\t%d\n", status);
+		if (fan_status_access_mode == TPACPI_FAN_RD_TPEC_NS) {
+			/*
+			 * No full speed bit in NS EC
+			 * EC Auto mode is set by default.
+			 * No other levels settings available
+			 */
+			seq_printf(m, "level:\t\t%s\n", status & FAN_NS_CTRL ? "unknown" : "auto");
+		} else {
+			if (status & TP_EC_FAN_FULLSPEED)
+				/* Disengaged mode takes precedence */
+				seq_printf(m, "level:\t\tdisengaged\n");
+			else if (status & TP_EC_FAN_AUTO)
+				seq_printf(m, "level:\t\tauto\n");
+			else
+				seq_printf(m, "level:\t\t%d\n", status);
+		}
 		break;
 
 	case TPACPI_FAN_NONE:
@@ -9303,7 +9375,7 @@ static struct tpacpi_battery_driver_data battery_info;
 
 /* ACPI helpers/functions/probes */
 
-/**
+/*
  * This evaluates a ACPI method call specific to the battery
  * ACPI extension. The specifics are that an error is marked
  * in the 32rd bit of the response, so we just check that here.
diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index 5c27b4aa969049..5dd22258cb3bc2 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -1340,6 +1340,11 @@ static int parse_wdg(struct device *wmi_bus_dev, struct platform_device *pdev)
 		if (debug_dump_wdg)
 			wmi_dump_wdg(&gblock[i]);
 
+		if (!gblock[i].instance_count) {
+			dev_info(wmi_bus_dev, FW_INFO "%pUL has zero instances\n", &gblock[i].guid);
+			continue;
+		}
+
 		if (guid_already_parsed_for_legacy(device, &gblock[i].guid))
 			continue;
 
diff --git a/drivers/pmdomain/arm/scmi_perf_domain.c b/drivers/pmdomain/arm/scmi_perf_domain.c
index bc3f78abb6dac8..709bbc448fad43 100644
--- a/drivers/pmdomain/arm/scmi_perf_domain.c
+++ b/drivers/pmdomain/arm/scmi_perf_domain.c
@@ -35,7 +35,7 @@ scmi_pd_set_perf_state(struct generic_pm_domain *genpd, unsigned int state)
 	if (!state)
 		return -EINVAL;
 
-	ret = pd->perf_ops->level_set(pd->ph, pd->domain_id, state, true);
+	ret = pd->perf_ops->level_set(pd->ph, pd->domain_id, state, false);
 	if (ret)
 		dev_warn(&genpd->dev, "Failed with %d when trying to set %d perf level",
 			 ret, state);
diff --git a/drivers/pmdomain/qcom/rpmpd.c b/drivers/pmdomain/qcom/rpmpd.c
index 07590a3ef19c26..7796d65f96e8cf 100644
--- a/drivers/pmdomain/qcom/rpmpd.c
+++ b/drivers/pmdomain/qcom/rpmpd.c
@@ -1044,6 +1044,7 @@ static int rpmpd_probe(struct platform_device *pdev)
 		rpmpds[i]->pd.power_off = rpmpd_power_off;
 		rpmpds[i]->pd.power_on = rpmpd_power_on;
 		rpmpds[i]->pd.set_performance_state = rpmpd_set_performance;
+		rpmpds[i]->pd.flags = GENPD_FLAG_ACTIVE_WAKEUP;
 		pm_genpd_init(&rpmpds[i]->pd, NULL, true);
 
 		data->domains[i] = &rpmpds[i]->pd;
diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
index 2ff7717530bf85..9193c3b8edebe9 100644
--- a/drivers/powercap/dtpm_cpu.c
+++ b/drivers/powercap/dtpm_cpu.c
@@ -24,7 +24,6 @@
 #include <linux/of.h>
 #include <linux/pm_qos.h>
 #include <linux/slab.h>
-#include <linux/units.h>
 
 struct dtpm_cpu {
 	struct dtpm dtpm;
@@ -104,8 +103,7 @@ static u64 get_pd_power_uw(struct dtpm *dtpm)
 		if (pd->table[i].frequency < freq)
 			continue;
 
-		return scale_pd_power_uw(pd_mask, pd->table[i].power *
-					 MICROWATT_PER_MILLIWATT);
+		return scale_pd_power_uw(pd_mask, pd->table[i].power);
 	}
 
 	return 0;
@@ -122,11 +120,9 @@ static int update_pd_power_uw(struct dtpm *dtpm)
 	nr_cpus = cpumask_weight(&cpus);
 
 	dtpm->power_min = em->table[0].power;
-	dtpm->power_min *= MICROWATT_PER_MILLIWATT;
 	dtpm->power_min *= nr_cpus;
 
 	dtpm->power_max = em->table[em->nr_perf_states - 1].power;
-	dtpm->power_max *= MICROWATT_PER_MILLIWATT;
 	dtpm->power_max *= nr_cpus;
 
 	return 0;
@@ -144,6 +140,8 @@ static void pd_release(struct dtpm *dtpm)
 	if (policy) {
 		for_each_cpu(dtpm_cpu->cpu, policy->related_cpus)
 			per_cpu(dtpm_per_cpu, dtpm_cpu->cpu) = NULL;
+
+		cpufreq_cpu_put(policy);
 	}
 	
 	kfree(dtpm_cpu);
@@ -195,12 +193,16 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent)
 		return 0;
 
 	pd = em_cpu_get(cpu);
-	if (!pd || em_is_artificial(pd))
-		return -EINVAL;
+	if (!pd || em_is_artificial(pd)) {
+		ret = -EINVAL;
+		goto release_policy;
+	}
 
 	dtpm_cpu = kzalloc(sizeof(*dtpm_cpu), GFP_KERNEL);
-	if (!dtpm_cpu)
-		return -ENOMEM;
+	if (!dtpm_cpu) {
+		ret = -ENOMEM;
+		goto release_policy;
+	}
 
 	dtpm_init(&dtpm_cpu->dtpm, &dtpm_ops);
 	dtpm_cpu->cpu = cpu;
@@ -220,6 +222,7 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent)
 	if (ret)
 		goto out_dtpm_unregister;
 
+	cpufreq_cpu_put(policy);
 	return 0;
 
 out_dtpm_unregister:
@@ -231,6 +234,8 @@ out_kfree_dtpm_cpu:
 		per_cpu(dtpm_per_cpu, cpu) = NULL;
 	kfree(dtpm_cpu);
 
+release_policy:
+	cpufreq_cpu_put(policy);
 	return ret;
 }
 
diff --git a/drivers/powercap/dtpm_devfreq.c b/drivers/powercap/dtpm_devfreq.c
index 91276761a31d94..612c3b59dd5bef 100644
--- a/drivers/powercap/dtpm_devfreq.c
+++ b/drivers/powercap/dtpm_devfreq.c
@@ -39,10 +39,8 @@ static int update_pd_power_uw(struct dtpm *dtpm)
 	struct em_perf_domain *pd = em_pd_get(dev);
 
 	dtpm->power_min = pd->table[0].power;
-	dtpm->power_min *= MICROWATT_PER_MILLIWATT;
 
 	dtpm->power_max = pd->table[pd->nr_perf_states - 1].power;
-	dtpm->power_max *= MICROWATT_PER_MILLIWATT;
 
 	return 0;
 }
@@ -54,13 +52,10 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
 	struct device *dev = devfreq->dev.parent;
 	struct em_perf_domain *pd = em_pd_get(dev);
 	unsigned long freq;
-	u64 power;
 	int i;
 
 	for (i = 0; i < pd->nr_perf_states; i++) {
-
-		power = pd->table[i].power * MICROWATT_PER_MILLIWATT;
-		if (power > power_limit)
+		if (pd->table[i].power > power_limit)
 			break;
 	}
 
@@ -68,7 +63,7 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
 
 	dev_pm_qos_update_request(&dtpm_devfreq->qos_req, freq);
 
-	power_limit = pd->table[i - 1].power * MICROWATT_PER_MILLIWATT;
+	power_limit = pd->table[i - 1].power;
 
 	return power_limit;
 }
@@ -110,7 +105,7 @@ static u64 get_pd_power_uw(struct dtpm *dtpm)
 		if (pd->table[i].frequency < freq)
 			continue;
 
-		power = pd->table[i].power * MICROWATT_PER_MILLIWATT;
+		power = pd->table[i].power;
 		power *= status.busy_time;
 		power >>= 10;
 
diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 282cd7d2407738..7513018c9f9ac7 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -108,6 +108,7 @@ int ptp_open(struct posix_clock_context *pccontext, fmode_t fmode)
 		container_of(pccontext->clk, struct ptp_clock, clock);
 	struct timestamp_event_queue *queue;
 	char debugfsname[32];
+	unsigned long flags;
 
 	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
 	if (!queue)
@@ -119,7 +120,9 @@ int ptp_open(struct posix_clock_context *pccontext, fmode_t fmode)
 	}
 	bitmap_set(queue->mask, 0, PTP_MAX_CHANNELS);
 	spin_lock_init(&queue->lock);
+	spin_lock_irqsave(&ptp->tsevqs_lock, flags);
 	list_add_tail(&queue->qlist, &ptp->tsevqs);
+	spin_unlock_irqrestore(&ptp->tsevqs_lock, flags);
 	pccontext->private_clkdata = queue;
 
 	/* Debugfs contents */
@@ -139,16 +142,16 @@ int ptp_release(struct posix_clock_context *pccontext)
 {
 	struct timestamp_event_queue *queue = pccontext->private_clkdata;
 	unsigned long flags;
+	struct ptp_clock *ptp =
+		container_of(pccontext->clk, struct ptp_clock, clock);
 
-	if (queue) {
-		debugfs_remove(queue->debugfs_instance);
-		pccontext->private_clkdata = NULL;
-		spin_lock_irqsave(&queue->lock, flags);
-		list_del(&queue->qlist);
-		spin_unlock_irqrestore(&queue->lock, flags);
-		bitmap_free(queue->mask);
-		kfree(queue);
-	}
+	debugfs_remove(queue->debugfs_instance);
+	pccontext->private_clkdata = NULL;
+	spin_lock_irqsave(&ptp->tsevqs_lock, flags);
+	list_del(&queue->qlist);
+	spin_unlock_irqrestore(&ptp->tsevqs_lock, flags);
+	bitmap_free(queue->mask);
+	kfree(queue);
 	return 0;
 }
 
@@ -569,7 +572,8 @@ ssize_t ptp_read(struct posix_clock_context *pccontext, uint rdflags,
 
 	for (i = 0; i < cnt; i++) {
 		event[i] = queue->buf[queue->head];
-		queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS;
+		/* Paired with READ_ONCE() in queue_cnt() */
+		WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS);
 	}
 
 	spin_unlock_irqrestore(&queue->lock, flags);
@@ -585,7 +589,5 @@ ssize_t ptp_read(struct posix_clock_context *pccontext, uint rdflags,
 free_event:
 	kfree(event);
 exit:
-	if (result < 0)
-		ptp_release(pccontext);
 	return result;
 }
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 3d1b0a97301c95..15b804ba48685e 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -57,10 +57,11 @@ static void enqueue_external_timestamp(struct timestamp_event_queue *queue,
 	dst->t.sec = seconds;
 	dst->t.nsec = remainder;
 
+	/* Both WRITE_ONCE() are paired with READ_ONCE() in queue_cnt() */
 	if (!queue_free(queue))
-		queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS;
+		WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS);
 
-	queue->tail = (queue->tail + 1) % PTP_MAX_TIMESTAMPS;
+	WRITE_ONCE(queue->tail, (queue->tail + 1) % PTP_MAX_TIMESTAMPS);
 
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
@@ -179,11 +180,11 @@ static void ptp_clock_release(struct device *dev)
 	mutex_destroy(&ptp->pincfg_mux);
 	mutex_destroy(&ptp->n_vclocks_mux);
 	/* Delete first entry */
+	spin_lock_irqsave(&ptp->tsevqs_lock, flags);
 	tsevq = list_first_entry(&ptp->tsevqs, struct timestamp_event_queue,
 				 qlist);
-	spin_lock_irqsave(&tsevq->lock, flags);
 	list_del(&tsevq->qlist);
-	spin_unlock_irqrestore(&tsevq->lock, flags);
+	spin_unlock_irqrestore(&ptp->tsevqs_lock, flags);
 	bitmap_free(tsevq->mask);
 	kfree(tsevq);
 	debugfs_remove(ptp->debugfs_root);
@@ -247,6 +248,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 	if (!queue)
 		goto no_memory_queue;
 	list_add_tail(&queue->qlist, &ptp->tsevqs);
+	spin_lock_init(&ptp->tsevqs_lock);
 	queue->mask = bitmap_alloc(PTP_MAX_CHANNELS, GFP_KERNEL);
 	if (!queue->mask)
 		goto no_memory_bitmap;
@@ -407,6 +409,7 @@ void ptp_clock_event(struct ptp_clock *ptp, struct ptp_clock_event *event)
 {
 	struct timestamp_event_queue *tsevq;
 	struct pps_event_time evt;
+	unsigned long flags;
 
 	switch (event->type) {
 
@@ -415,10 +418,12 @@ void ptp_clock_event(struct ptp_clock *ptp, struct ptp_clock_event *event)
 
 	case PTP_CLOCK_EXTTS:
 		/* Enqueue timestamp on selected queues */
+		spin_lock_irqsave(&ptp->tsevqs_lock, flags);
 		list_for_each_entry(tsevq, &ptp->tsevqs, qlist) {
 			if (test_bit((unsigned int)event->index, tsevq->mask))
 				enqueue_external_timestamp(tsevq, event);
 		}
+		spin_unlock_irqrestore(&ptp->tsevqs_lock, flags);
 		wake_up_interruptible(&ptp->tsev_wq);
 		break;
 
diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h
index 52f87e394aa641..45f9002a5dcaea 100644
--- a/drivers/ptp/ptp_private.h
+++ b/drivers/ptp/ptp_private.h
@@ -44,6 +44,7 @@ struct ptp_clock {
 	struct pps_device *pps_source;
 	long dialed_frequency; /* remembers the frequency adjustment */
 	struct list_head tsevqs; /* timestamp fifo list */
+	spinlock_t tsevqs_lock; /* protects tsevqs from concurrent access */
 	struct mutex pincfg_mux; /* protect concurrent info->pin_config access */
 	wait_queue_head_t tsev_wq;
 	int defunct; /* tells readers to go away when clock is being removed */
@@ -84,9 +85,13 @@ struct ptp_vclock {
  * that a writer might concurrently increment the tail does not
  * matter, since the queue remains nonempty nonetheless.
  */
-static inline int queue_cnt(struct timestamp_event_queue *q)
+static inline int queue_cnt(const struct timestamp_event_queue *q)
 {
-	int cnt = q->tail - q->head;
+	/*
+	 * Paired with WRITE_ONCE() in enqueue_external_timestamp(),
+	 * ptp_read(), extts_fifo_show().
+	 */
+	int cnt = READ_ONCE(q->tail) - READ_ONCE(q->head);
 	return cnt < 0 ? PTP_MAX_TIMESTAMPS + cnt : cnt;
 }
 
diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c
index 7d023d9d0acbfb..f7a499a1bd39ec 100644
--- a/drivers/ptp/ptp_sysfs.c
+++ b/drivers/ptp/ptp_sysfs.c
@@ -94,7 +94,8 @@ static ssize_t extts_fifo_show(struct device *dev,
 	qcnt = queue_cnt(queue);
 	if (qcnt) {
 		event = queue->buf[queue->head];
-		queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS;
+		/* Paired with READ_ONCE() in queue_cnt() */
+		WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS);
 	}
 	spin_unlock_irqrestore(&queue->lock, flags);
 
diff --git a/drivers/pwm/pwm-bcm2835.c b/drivers/pwm/pwm-bcm2835.c
index 9777babd5b95cd..ab30667f4f951c 100644
--- a/drivers/pwm/pwm-bcm2835.c
+++ b/drivers/pwm/pwm-bcm2835.c
@@ -155,6 +155,8 @@ static int bcm2835_pwm_probe(struct platform_device *pdev)
 	pc->chip.ops = &bcm2835_pwm_ops;
 	pc->chip.npwm = 2;
 
+	platform_set_drvdata(pdev, pc);
+
 	ret = devm_pwmchip_add(&pdev->dev, &pc->chip);
 	if (ret < 0)
 		return dev_err_probe(&pdev->dev, ret,
diff --git a/drivers/pwm/pwm-samsung.c b/drivers/pwm/pwm-samsung.c
index 568491ed6829e9..69d9f4577b3479 100644
--- a/drivers/pwm/pwm-samsung.c
+++ b/drivers/pwm/pwm-samsung.c
@@ -631,7 +631,7 @@ static int pwm_samsung_resume(struct device *dev)
 		struct pwm_device *pwm = &chip->pwms[i];
 		struct samsung_pwm_channel *chan = &our_chip->channel[i];
 
-		if (!(pwm->flags & PWMF_REQUESTED))
+		if (!test_bit(PWMF_REQUESTED, &pwm->flags))
 			continue;
 
 		if (our_chip->variant.output_mask & BIT(i))
diff --git a/drivers/reset/core.c b/drivers/reset/core.c
index 7ece6a8e985855..4d5a78d3c085bc 100644
--- a/drivers/reset/core.c
+++ b/drivers/reset/core.c
@@ -807,6 +807,9 @@ static void __reset_control_put_internal(struct reset_control *rstc)
 {
 	lockdep_assert_held(&reset_list_mutex);
 
+	if (IS_ERR_OR_NULL(rstc))
+		return;
+
 	kref_put(&rstc->refcnt, __reset_control_release);
 }
 
@@ -1017,11 +1020,8 @@ EXPORT_SYMBOL_GPL(reset_control_put);
 void reset_control_bulk_put(int num_rstcs, struct reset_control_bulk_data *rstcs)
 {
 	mutex_lock(&reset_list_mutex);
-	while (num_rstcs--) {
-		if (IS_ERR_OR_NULL(rstcs[num_rstcs].rstc))
-			continue;
+	while (num_rstcs--)
 		__reset_control_put_internal(rstcs[num_rstcs].rstc);
-	}
 	mutex_unlock(&reset_list_mutex);
 }
 EXPORT_SYMBOL_GPL(reset_control_bulk_put);
diff --git a/drivers/reset/hisilicon/hi6220_reset.c b/drivers/reset/hisilicon/hi6220_reset.c
index 8d1fce18ded78c..5c3267acd2b1c2 100644
--- a/drivers/reset/hisilicon/hi6220_reset.c
+++ b/drivers/reset/hisilicon/hi6220_reset.c
@@ -163,7 +163,7 @@ static int hi6220_reset_probe(struct platform_device *pdev)
 	if (!data)
 		return -ENOMEM;
 
-	type = (enum hi6220_reset_ctrl_type)of_device_get_match_data(dev);
+	type = (uintptr_t)of_device_get_match_data(dev);
 
 	regmap = syscon_node_to_regmap(np);
 	if (IS_ERR(regmap)) {
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index d440319a7945b8..833cfab7d8776d 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -676,18 +676,20 @@ static void dasd_profile_start(struct dasd_block *block,
 	 * we count each request only once.
 	 */
 	device = cqr->startdev;
-	if (device->profile.data) {
-		counter = 1; /* request is not yet queued on the start device */
-		list_for_each(l, &device->ccw_queue)
-			if (++counter >= 31)
-				break;
-	}
+	if (!device->profile.data)
+		return;
+
+	spin_lock(get_ccwdev_lock(device->cdev));
+	counter = 1; /* request is not yet queued on the start device */
+	list_for_each(l, &device->ccw_queue)
+		if (++counter >= 31)
+			break;
+	spin_unlock(get_ccwdev_lock(device->cdev));
+
 	spin_lock(&device->profile.lock);
-	if (device->profile.data) {
-		device->profile.data->dasd_io_nr_req[counter]++;
-		if (rq_data_dir(req) == READ)
-			device->profile.data->dasd_read_nr_req[counter]++;
-	}
+	device->profile.data->dasd_io_nr_req[counter]++;
+	if (rq_data_dir(req) == READ)
+		device->profile.data->dasd_read_nr_req[counter]++;
 	spin_unlock(&device->profile.lock);
 }
 
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 2e663131adaf67..1b1b8a41c4d42e 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -283,7 +283,7 @@ struct dasd_pprc_dev_info {
 	__u8 secondary;		/* 7       Secondary device address */
 	__u16 pprc_id;		/* 8-9     Peer-to-Peer Remote Copy ID */
 	__u8 reserved2[12];	/* 10-21   reserved */
-	__u16 prim_cu_ssid;	/* 22-23   Pimary Control Unit SSID */
+	__u16 prim_cu_ssid;	/* 22-23   Primary Control Unit SSID */
 	__u8 reserved3[12];	/* 24-35   reserved */
 	__u16 sec_cu_ssid;	/* 36-37   Secondary Control Unit SSID */
 	__u8 reserved4[90];	/* 38-127  reserved */
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index 3a9cc8a4a23022..ade95e91b3c8db 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -17,6 +17,7 @@
 #include <linux/blk-mq.h>
 #include <linux/slab.h>
 #include <linux/list.h>
+#include <linux/io.h>
 #include <asm/eadm.h>
 #include "scm_blk.h"
 
@@ -130,7 +131,7 @@ static void scm_request_done(struct scm_request *scmrq)
 
 	for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++) {
 		msb = &scmrq->aob->msb[i];
-		aidaw = msb->data_addr;
+		aidaw = (u64)phys_to_virt(msb->data_addr);
 
 		if ((msb->flags & MSB_FLAG_IDA) && aidaw &&
 		    IS_ALIGNED(aidaw, PAGE_SIZE))
@@ -195,12 +196,12 @@ static int scm_request_prepare(struct scm_request *scmrq)
 	msb->scm_addr = scmdev->address + ((u64) blk_rq_pos(req) << 9);
 	msb->oc = (rq_data_dir(req) == READ) ? MSB_OC_READ : MSB_OC_WRITE;
 	msb->flags |= MSB_FLAG_IDA;
-	msb->data_addr = (u64) aidaw;
+	msb->data_addr = (u64)virt_to_phys(aidaw);
 
 	rq_for_each_segment(bv, req, iter) {
 		WARN_ON(bv.bv_offset);
 		msb->blk_count += bv.bv_len >> 12;
-		aidaw->data_addr = (u64) page_address(bv.bv_page);
+		aidaw->data_addr = virt_to_phys(page_address(bv.bv_page));
 		aidaw++;
 	}
 
diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig
index 4902d45e929ce2..c61e6427384c34 100644
--- a/drivers/s390/net/Kconfig
+++ b/drivers/s390/net/Kconfig
@@ -103,10 +103,11 @@ config CCWGROUP
 config ISM
 	tristate "Support for ISM vPCI Adapter"
 	depends on PCI
+	imply SMC
 	default n
 	help
 	  Select this option if you want to use the Internal Shared Memory
-	  vPCI Adapter.
+	  vPCI Adapter. The adapter can be used with the SMC network protocol.
 
 	  To compile as a module choose M. The module name is ism.
 	  If unsure, choose N.
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index 6df7f377d2f90c..81aabbfbbe2ca4 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -30,7 +30,6 @@ static const struct pci_device_id ism_device_table[] = {
 MODULE_DEVICE_TABLE(pci, ism_device_table);
 
 static debug_info_t *ism_debug_info;
-static const struct smcd_ops ism_ops;
 
 #define NO_CLIENT		0xff		/* must be >= MAX_CLIENTS */
 static struct ism_client *clients[MAX_CLIENTS];	/* use an array rather than */
@@ -289,22 +288,6 @@ out:
 	return ret;
 }
 
-static int ism_query_rgid(struct ism_dev *ism, u64 rgid, u32 vid_valid,
-			  u32 vid)
-{
-	union ism_query_rgid cmd;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.request.hdr.cmd = ISM_QUERY_RGID;
-	cmd.request.hdr.len = sizeof(cmd.request);
-
-	cmd.request.rgid = rgid;
-	cmd.request.vlan_valid = vid_valid;
-	cmd.request.vlan_id = vid;
-
-	return ism_cmd(ism, &cmd);
-}
-
 static void ism_free_dmb(struct ism_dev *ism, struct ism_dmb *dmb)
 {
 	clear_bit(dmb->sba_idx, ism->sba_bitmap);
@@ -429,23 +412,6 @@ static int ism_del_vlan_id(struct ism_dev *ism, u64 vlan_id)
 	return ism_cmd(ism, &cmd);
 }
 
-static int ism_signal_ieq(struct ism_dev *ism, u64 rgid, u32 trigger_irq,
-			  u32 event_code, u64 info)
-{
-	union ism_sig_ieq cmd;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.request.hdr.cmd = ISM_SIGNAL_IEQ;
-	cmd.request.hdr.len = sizeof(cmd.request);
-
-	cmd.request.rgid = rgid;
-	cmd.request.trigger_irq = trigger_irq;
-	cmd.request.event_code = event_code;
-	cmd.request.info = info;
-
-	return ism_cmd(ism, &cmd);
-}
-
 static unsigned int max_bytes(unsigned int start, unsigned int len,
 			      unsigned int boundary)
 {
@@ -503,14 +469,6 @@ u8 *ism_get_seid(void)
 }
 EXPORT_SYMBOL_GPL(ism_get_seid);
 
-static u16 ism_get_chid(struct ism_dev *ism)
-{
-	if (!ism || !ism->pdev)
-		return 0;
-
-	return to_zpci(ism->pdev)->pchid;
-}
-
 static void ism_handle_event(struct ism_dev *ism)
 {
 	struct ism_event *entry;
@@ -569,11 +527,6 @@ static irqreturn_t ism_handle_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static u64 ism_get_local_gid(struct ism_dev *ism)
-{
-	return ism->local_gid;
-}
-
 static int ism_dev_init(struct ism_dev *ism)
 {
 	struct pci_dev *pdev = ism->pdev;
@@ -774,6 +727,22 @@ module_exit(ism_exit);
 /*************************** SMC-D Implementation *****************************/
 
 #if IS_ENABLED(CONFIG_SMC)
+static int ism_query_rgid(struct ism_dev *ism, u64 rgid, u32 vid_valid,
+			  u32 vid)
+{
+	union ism_query_rgid cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_QUERY_RGID;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.rgid = rgid;
+	cmd.request.vlan_valid = vid_valid;
+	cmd.request.vlan_id = vid;
+
+	return ism_cmd(ism, &cmd);
+}
+
 static int smcd_query_rgid(struct smcd_dev *smcd, u64 rgid, u32 vid_valid,
 			   u32 vid)
 {
@@ -811,6 +780,23 @@ static int smcd_reset_vlan_required(struct smcd_dev *smcd)
 	return ism_cmd_simple(smcd->priv, ISM_RESET_VLAN);
 }
 
+static int ism_signal_ieq(struct ism_dev *ism, u64 rgid, u32 trigger_irq,
+			  u32 event_code, u64 info)
+{
+	union ism_sig_ieq cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_SIGNAL_IEQ;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.rgid = rgid;
+	cmd.request.trigger_irq = trigger_irq;
+	cmd.request.event_code = event_code;
+	cmd.request.info = info;
+
+	return ism_cmd(ism, &cmd);
+}
+
 static int smcd_signal_ieq(struct smcd_dev *smcd, u64 rgid, u32 trigger_irq,
 			   u32 event_code, u64 info)
 {
@@ -830,11 +816,24 @@ static int smcd_supports_v2(void)
 		SYSTEM_EID.type[0] != '0';
 }
 
+static u64 ism_get_local_gid(struct ism_dev *ism)
+{
+	return ism->local_gid;
+}
+
 static u64 smcd_get_local_gid(struct smcd_dev *smcd)
 {
 	return ism_get_local_gid(smcd->priv);
 }
 
+static u16 ism_get_chid(struct ism_dev *ism)
+{
+	if (!ism || !ism->pdev)
+		return 0;
+
+	return to_zpci(ism->pdev)->pchid;
+}
+
 static u16 smcd_get_chid(struct smcd_dev *smcd)
 {
 	return ism_get_chid(smcd->priv);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 6af2511e070cc2..cf8506d0f185c0 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -3675,7 +3675,7 @@ static void qeth_flush_queue(struct qeth_qdio_out_q *queue)
 static void qeth_check_outbound_queue(struct qeth_qdio_out_q *queue)
 {
 	/*
-	 * check if weed have to switch to non-packing mode or if
+	 * check if we have to switch to non-packing mode or if
 	 * we have to get a pci flag out on the queue
 	 */
 	if ((atomic_read(&queue->used_buffers) <= QETH_LOW_WATERMARK_PACK) ||
diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index 73b6ac0c01f549..7d5a155073c627 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -1678,7 +1678,6 @@ struct aac_dev
 	u32			handle_pci_error;
 	bool			init_reset;
 	u8			soft_reset_support;
-	u8			use_map_queue;
 };
 
 #define aac_adapter_interrupt(dev) \
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 013a9a334972eb..25cee03d7f9737 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -223,12 +223,8 @@ int aac_fib_setup(struct aac_dev * dev)
 struct fib *aac_fib_alloc_tag(struct aac_dev *dev, struct scsi_cmnd *scmd)
 {
 	struct fib *fibptr;
-	u32 blk_tag;
-	int i;
 
-	blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd));
-	i = blk_mq_unique_tag_to_tag(blk_tag);
-	fibptr = &dev->fibs[i];
+	fibptr = &dev->fibs[scsi_cmd_to_rq(scmd)->tag];
 	/*
 	 *	Null out fields that depend on being zero at the start of
 	 *	each I/O
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index c4a36c0be527cd..68f4dbcfff4925 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -19,7 +19,6 @@
 
 #include <linux/compat.h>
 #include <linux/blkdev.h>
-#include <linux/blk-mq-pci.h>
 #include <linux/completion.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -505,15 +504,6 @@ common_config:
 	return 0;
 }
 
-static void aac_map_queues(struct Scsi_Host *shost)
-{
-	struct aac_dev *aac = (struct aac_dev *)shost->hostdata;
-
-	blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
-			      aac->pdev, 0);
-	aac->use_map_queue = true;
-}
-
 /**
  *	aac_change_queue_depth		-	alter queue depths
  *	@sdev:	SCSI device we are considering
@@ -1498,7 +1488,6 @@ static const struct scsi_host_template aac_driver_template = {
 	.bios_param			= aac_biosparm,
 	.shost_groups			= aac_host_groups,
 	.slave_configure		= aac_slave_configure,
-	.map_queues			= aac_map_queues,
 	.change_queue_depth		= aac_change_queue_depth,
 	.sdev_groups			= aac_dev_groups,
 	.eh_abort_handler		= aac_eh_abort,
@@ -1786,8 +1775,6 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	shost->max_lun = AAC_MAX_LUN;
 
 	pci_set_drvdata(pdev, shost);
-	shost->nr_hw_queues = aac->max_msix;
-	shost->host_tagset = 1;
 
 	error = scsi_add_host(shost, &pdev->dev);
 	if (error)
@@ -1919,7 +1906,6 @@ static void aac_remove_one(struct pci_dev *pdev)
 	struct aac_dev *aac = (struct aac_dev *)shost->hostdata;
 
 	aac_cancel_rescan_worker(aac);
-	aac->use_map_queue = false;
 	scsi_remove_host(shost);
 
 	__aac_shutdown(aac);
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 61949f3741886b..11ef58204e96f1 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -493,10 +493,6 @@ static int aac_src_deliver_message(struct fib *fib)
 #endif
 
 	u16 vector_no;
-	struct scsi_cmnd *scmd;
-	u32 blk_tag;
-	struct Scsi_Host *shost = dev->scsi_host_ptr;
-	struct blk_mq_queue_map *qmap;
 
 	atomic_inc(&q->numpending);
 
@@ -509,25 +505,8 @@ static int aac_src_deliver_message(struct fib *fib)
 		if ((dev->comm_interface == AAC_COMM_MESSAGE_TYPE3)
 			&& dev->sa_firmware)
 			vector_no = aac_get_vector(dev);
-		else {
-			if (!fib->vector_no || !fib->callback_data) {
-				if (shost && dev->use_map_queue) {
-					qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
-					vector_no = qmap->mq_map[raw_smp_processor_id()];
-				}
-				/*
-				 *	We hardcode the vector_no for
-				 *	reserved commands as a valid shost is
-				 *	absent during the init
-				 */
-				else
-					vector_no = 0;
-			} else {
-				scmd = (struct scsi_cmnd *)fib->callback_data;
-				blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd));
-				vector_no = blk_mq_unique_tag_to_hwq(blk_tag);
-			}
-		}
+		else
+			vector_no = fib->vector_no;
 
 		if (native_hba) {
 			if (fib->flags & FIB_CONTEXT_FLAG_NATIVE_HBA_TMF) {
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index e48f14ad6dfd89..06acb5ff609ee7 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -2710,6 +2710,7 @@ init_wrb_hndl_failed:
 		kfree(pwrb_context->pwrb_handle_base);
 		kfree(pwrb_context->pwrb_handle_basestd);
 	}
+	kfree(phwi_ctxt->be_wrbq);
 	return -ENOMEM;
 }
 
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 05ddbb9bb7d8aa..451a58e0fd9691 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -429,7 +429,6 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct fcoe_ctlr *ctlr;
 	struct fcoe_rcv_info *fr;
 	struct fcoe_percpu_s *bg;
-	struct sk_buff *tmp_skb;
 
 	interface = container_of(ptype, struct bnx2fc_interface,
 				 fcoe_packet_type);
@@ -441,11 +440,9 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev,
 		goto err;
 	}
 
-	tmp_skb = skb_share_check(skb, GFP_ATOMIC);
-	if (!tmp_skb)
-		goto err;
-
-	skb = tmp_skb;
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		return -1;
 
 	if (unlikely(eth_hdr(skb)->h_proto != htons(ETH_P_FCOE))) {
 		printk(KERN_ERR PFX "bnx2fc_rcv: Wrong FC type frame\n");
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 32d1e73e46eecd..03348f605c2e9a 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1837,8 +1837,16 @@ static void qla2x00_abort_srb(struct qla_qpair *qp, srb_t *sp, const int res,
 		}
 
 		spin_lock_irqsave(qp->qp_lock_ptr, *flags);
-		if (ret_cmd && blk_mq_request_started(scsi_cmd_to_rq(cmd)))
-			sp->done(sp, res);
+		switch (sp->type) {
+		case SRB_SCSI_CMD:
+			if (ret_cmd && blk_mq_request_started(scsi_cmd_to_rq(cmd)))
+				sp->done(sp, res);
+			break;
+		default:
+			if (ret_cmd)
+				sp->done(sp, res);
+			break;
+		}
 	} else {
 		sp->done(sp, res);
 	}
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 67922e2c4c1915..6d8218a4412264 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -1019,7 +1019,7 @@ static ssize_t sdebug_error_write(struct file *file, const char __user *ubuf,
 	struct sdebug_err_inject *inject;
 	struct scsi_device *sdev = (struct scsi_device *)file->f_inode->i_private;
 
-	buf = kmalloc(count, GFP_KERNEL);
+	buf = kzalloc(count + 1, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -1132,7 +1132,6 @@ static const struct file_operations sdebug_target_reset_fail_fops = {
 static int sdebug_target_alloc(struct scsi_target *starget)
 {
 	struct sdebug_target_info *targetip;
-	struct dentry *dentry;
 
 	targetip = kzalloc(sizeof(struct sdebug_target_info), GFP_KERNEL);
 	if (!targetip)
@@ -1140,15 +1139,9 @@ static int sdebug_target_alloc(struct scsi_target *starget)
 
 	targetip->debugfs_entry = debugfs_create_dir(dev_name(&starget->dev),
 				sdebug_debugfs_root);
-	if (IS_ERR_OR_NULL(targetip->debugfs_entry))
-		pr_info("%s: failed to create debugfs directory for target %s\n",
-			__func__, dev_name(&starget->dev));
 
 	debugfs_create_file("fail_reset", 0600, targetip->debugfs_entry, starget,
 				&sdebug_target_reset_fail_fops);
-	if (IS_ERR_OR_NULL(dentry))
-		pr_info("%s: failed to create fail_reset file for target %s\n",
-			__func__, dev_name(&starget->dev));
 
 	starget->hostdata = targetip;
 
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index c67cdcdc3ba86d..1223d34c04da33 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1152,6 +1152,7 @@ retry:
 
 	scsi_log_send(scmd);
 	scmd->submitter = SUBMITTED_BY_SCSI_ERROR_HANDLER;
+	scmd->flags |= SCMD_LAST;
 
 	/*
 	 * Lock sdev->state_mutex to avoid that scsi_device_quiesce() can
@@ -2459,6 +2460,7 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg)
 	scsi_init_command(dev, scmd);
 
 	scmd->submitter = SUBMITTED_BY_SCSI_RESET_IOCTL;
+	scmd->flags |= SCMD_LAST;
 	memset(&scmd->sdb, 0, sizeof(scmd->sdb));
 
 	scmd->cmd_len			= 0;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 530918cbfce2d1..542a4bbb21bce8 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1643,24 +1643,21 @@ out:
 	return disk_changed ? DISK_EVENT_MEDIA_CHANGE : 0;
 }
 
-static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr)
+static int sd_sync_cache(struct scsi_disk *sdkp)
 {
 	int retries, res;
 	struct scsi_device *sdp = sdkp->device;
 	const int timeout = sdp->request_queue->rq_timeout
 		* SD_FLUSH_TIMEOUT_MULTIPLIER;
-	struct scsi_sense_hdr my_sshdr;
+	struct scsi_sense_hdr sshdr;
 	const struct scsi_exec_args exec_args = {
 		.req_flags = BLK_MQ_REQ_PM,
-		/* caller might not be interested in sense, but we need it */
-		.sshdr = sshdr ? : &my_sshdr,
+		.sshdr = &sshdr,
 	};
 
 	if (!scsi_device_online(sdp))
 		return -ENODEV;
 
-	sshdr = exec_args.sshdr;
-
 	for (retries = 3; retries > 0; --retries) {
 		unsigned char cmd[16] = { 0 };
 
@@ -1685,15 +1682,23 @@ static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr)
 			return res;
 
 		if (scsi_status_is_check_condition(res) &&
-		    scsi_sense_valid(sshdr)) {
-			sd_print_sense_hdr(sdkp, sshdr);
+		    scsi_sense_valid(&sshdr)) {
+			sd_print_sense_hdr(sdkp, &sshdr);
 
 			/* we need to evaluate the error return  */
-			if (sshdr->asc == 0x3a ||	/* medium not present */
-			    sshdr->asc == 0x20 ||	/* invalid command */
-			    (sshdr->asc == 0x74 && sshdr->ascq == 0x71))	/* drive is password locked */
+			if (sshdr.asc == 0x3a ||	/* medium not present */
+			    sshdr.asc == 0x20 ||	/* invalid command */
+			    (sshdr.asc == 0x74 && sshdr.ascq == 0x71))	/* drive is password locked */
 				/* this is no error here */
 				return 0;
+			/*
+			 * This drive doesn't support sync and there's not much
+			 * we can do because this is called during shutdown
+			 * or suspend so just return success so those operations
+			 * can proceed.
+			 */
+			if (sshdr.sense_key == ILLEGAL_REQUEST)
+				return 0;
 		}
 
 		switch (host_byte(res)) {
@@ -3853,7 +3858,7 @@ static void sd_shutdown(struct device *dev)
 
 	if (sdkp->WCE && sdkp->media_present) {
 		sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
-		sd_sync_cache(sdkp, NULL);
+		sd_sync_cache(sdkp);
 	}
 
 	if ((system_state != SYSTEM_RESTART &&
@@ -3874,7 +3879,6 @@ static inline bool sd_do_start_stop(struct scsi_device *sdev, bool runtime)
 static int sd_suspend_common(struct device *dev, bool runtime)
 {
 	struct scsi_disk *sdkp = dev_get_drvdata(dev);
-	struct scsi_sense_hdr sshdr;
 	int ret = 0;
 
 	if (!sdkp)	/* E.g.: runtime suspend following sd_remove() */
@@ -3883,24 +3887,13 @@ static int sd_suspend_common(struct device *dev, bool runtime)
 	if (sdkp->WCE && sdkp->media_present) {
 		if (!sdkp->device->silence_suspend)
 			sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");
-		ret = sd_sync_cache(sdkp, &sshdr);
-
-		if (ret) {
-			/* ignore OFFLINE device */
-			if (ret == -ENODEV)
-				return 0;
-
-			if (!scsi_sense_valid(&sshdr) ||
-			    sshdr.sense_key != ILLEGAL_REQUEST)
-				return ret;
+		ret = sd_sync_cache(sdkp);
+		/* ignore OFFLINE device */
+		if (ret == -ENODEV)
+			return 0;
 
-			/*
-			 * sshdr.sense_key == ILLEGAL_REQUEST means this drive
-			 * doesn't support sync. There's not much to do and
-			 * suspend shouldn't fail.
-			 */
-			ret = 0;
-		}
+		if (ret)
+			return ret;
 	}
 
 	if (sd_do_start_stop(sdkp->device, runtime)) {
@@ -3956,8 +3949,15 @@ static int sd_resume(struct device *dev, bool runtime)
 
 static int sd_resume_system(struct device *dev)
 {
-	if (pm_runtime_suspended(dev))
+	if (pm_runtime_suspended(dev)) {
+		struct scsi_disk *sdkp = dev_get_drvdata(dev);
+		struct scsi_device *sdp = sdkp ? sdkp->device : NULL;
+
+		if (sdp && sdp->force_runtime_start_on_system_start)
+			pm_request_resume(dev);
+
 		return 0;
+	}
 
 	return sd_resume(dev, false);
 }
diff --git a/drivers/soundwire/intel_ace2x.c b/drivers/soundwire/intel_ace2x.c
index 82672fcbc2aa27..8280baa3254b0b 100644
--- a/drivers/soundwire/intel_ace2x.c
+++ b/drivers/soundwire/intel_ace2x.c
@@ -23,8 +23,9 @@
 static void intel_shim_vs_init(struct sdw_intel *sdw)
 {
 	void __iomem *shim_vs = sdw->link_res->shim_vs;
-	u16 act = 0;
+	u16 act;
 
+	act = intel_readw(shim_vs, SDW_SHIM2_INTEL_VS_ACTMCTL);
 	u16p_replace_bits(&act, 0x1, SDW_SHIM2_INTEL_VS_ACTMCTL_DOAIS);
 	act |= SDW_SHIM2_INTEL_VS_ACTMCTL_DACTQE;
 	act |=  SDW_SHIM2_INTEL_VS_ACTMCTL_DODS;
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index 69719b335bcb1e..f048b3d55b2edc 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -742,14 +742,15 @@ error_1:
  * sdw_ml_sync_bank_switch: Multilink register bank switch
  *
  * @bus: SDW bus instance
+ * @multi_link: whether this is a multi-link stream with hardware-based sync
  *
  * Caller function should free the buffers on error
  */
-static int sdw_ml_sync_bank_switch(struct sdw_bus *bus)
+static int sdw_ml_sync_bank_switch(struct sdw_bus *bus, bool multi_link)
 {
 	unsigned long time_left;
 
-	if (!bus->multi_link)
+	if (!multi_link)
 		return 0;
 
 	/* Wait for completion of transfer */
@@ -847,7 +848,7 @@ static int do_bank_switch(struct sdw_stream_runtime *stream)
 			bus->bank_switch_timeout = DEFAULT_BANK_SWITCH_TIMEOUT;
 
 		/* Check if bank switch was successful */
-		ret = sdw_ml_sync_bank_switch(bus);
+		ret = sdw_ml_sync_bank_switch(bus, multi_link);
 		if (ret < 0) {
 			dev_err(bus->dev,
 				"multi link bank switch failed: %d\n", ret);
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 35dbfacecf1cd5..70c9dd6b6a31e7 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -1169,6 +1169,7 @@ config SPI_XTENSA_XTFPGA
 config SPI_ZYNQ_QSPI
 	tristate "Xilinx Zynq QSPI controller"
 	depends on ARCH_ZYNQ || COMPILE_TEST
+	depends on SPI_MEM
 	help
 	  This enables support for the Zynq Quad SPI controller
 	  in master mode.
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index 6aa8adbe4170cd..bad34998454a80 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -22,6 +22,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/pm_runtime.h>
+#include <linux/iopoll.h>
 #include <trace/events/spi.h>
 
 /* SPI register offsets */
@@ -233,9 +234,6 @@
  */
 #define DMA_MIN_BYTES	16
 
-#define SPI_DMA_MIN_TIMEOUT	(msecs_to_jiffies(1000))
-#define SPI_DMA_TIMEOUT_PER_10K	(msecs_to_jiffies(4))
-
 #define AUTOSUSPEND_TIMEOUT	2000
 
 struct atmel_spi_caps {
@@ -279,6 +277,7 @@ struct atmel_spi {
 	bool			keep_cs;
 
 	u32			fifo_size;
+	bool			last_polarity;
 	u8			native_cs_free;
 	u8			native_cs_for_gpio;
 };
@@ -292,6 +291,22 @@ struct atmel_spi_device {
 #define INVALID_DMA_ADDRESS	0xffffffff
 
 /*
+ * This frequency can be anything supported by the controller, but to avoid
+ * unnecessary delay, the highest possible frequency is chosen.
+ *
+ * This frequency is the highest possible which is not interfering with other
+ * chip select registers (see Note for Serial Clock Bit Rate configuration in
+ * Atmel-11121F-ATARM-SAMA5D3-Series-Datasheet_02-Feb-16, page 1283)
+ */
+#define DUMMY_MSG_FREQUENCY	0x02
+/*
+ * 8 bits is the minimum data the controller is capable of sending.
+ *
+ * This message can be anything as it should not be treated by any SPI device.
+ */
+#define DUMMY_MSG		0xAA
+
+/*
  * Version 2 of the SPI controller has
  *  - CR.LASTXFER
  *  - SPI_MR.DIV32 may become FDIV or must-be-zero (here: always zero)
@@ -305,6 +320,43 @@ static bool atmel_spi_is_v2(struct atmel_spi *as)
 }
 
 /*
+ * Send a dummy message.
+ *
+ * This is sometimes needed when using a CS GPIO to force clock transition when
+ * switching between devices with different polarities.
+ */
+static void atmel_spi_send_dummy(struct atmel_spi *as, struct spi_device *spi, int chip_select)
+{
+	u32 status;
+	u32 csr;
+
+	/*
+	 * Set a clock frequency to allow sending message on SPI bus.
+	 * The frequency here can be anything, but is needed for
+	 * the controller to send the data.
+	 */
+	csr = spi_readl(as, CSR0 + 4 * chip_select);
+	csr = SPI_BFINS(SCBR, DUMMY_MSG_FREQUENCY, csr);
+	spi_writel(as, CSR0 + 4 * chip_select, csr);
+
+	/*
+	 * Read all data coming from SPI bus, needed to be able to send
+	 * the message.
+	 */
+	spi_readl(as, RDR);
+	while (spi_readl(as, SR) & SPI_BIT(RDRF)) {
+		spi_readl(as, RDR);
+		cpu_relax();
+	}
+
+	spi_writel(as, TDR, DUMMY_MSG);
+
+	readl_poll_timeout_atomic(as->regs + SPI_SR, status,
+				  (status & SPI_BIT(TXEMPTY)), 1, 1000);
+}
+
+
+/*
  * Earlier SPI controllers (e.g. on at91rm9200) have a design bug whereby
  * they assume that spi slave device state will not change on deselect, so
  * that automagic deselection is OK.  ("NPCSx rises if no data is to be
@@ -320,11 +372,17 @@ static bool atmel_spi_is_v2(struct atmel_spi *as)
  * Master on Chip Select 0.")  No workaround exists for that ... so for
  * nCS0 on that chip, we (a) don't use the GPIO, (b) can't support CS_HIGH,
  * and (c) will trigger that first erratum in some cases.
+ *
+ * When changing the clock polarity, the SPI controller waits for the next
+ * transmission to enforce the default clock state. This may be an issue when
+ * using a GPIO as Chip Select: the clock level is applied only when the first
+ * packet is sent, once the CS has already been asserted. The workaround is to
+ * avoid this by sending a first (dummy) message before toggling the CS state.
  */
-
 static void cs_activate(struct atmel_spi *as, struct spi_device *spi)
 {
 	struct atmel_spi_device *asd = spi->controller_state;
+	bool new_polarity;
 	int chip_select;
 	u32 mr;
 
@@ -353,6 +411,25 @@ static void cs_activate(struct atmel_spi *as, struct spi_device *spi)
 		}
 
 		mr = spi_readl(as, MR);
+
+		/*
+		 * Ensures the clock polarity is valid before we actually
+		 * assert the CS to avoid spurious clock edges to be
+		 * processed by the spi devices.
+		 */
+		if (spi_get_csgpiod(spi, 0)) {
+			new_polarity = (asd->csr & SPI_BIT(CPOL)) != 0;
+			if (new_polarity != as->last_polarity) {
+				/*
+				 * Need to disable the GPIO before sending the dummy
+				 * message because it is already set by the spi core.
+				 */
+				gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), 0);
+				atmel_spi_send_dummy(as, spi, chip_select);
+				as->last_polarity = new_polarity;
+				gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), 1);
+			}
+		}
 	} else {
 		u32 cpol = (spi->mode & SPI_CPOL) ? SPI_BIT(CPOL) : 0;
 		int i;
@@ -1336,12 +1413,10 @@ static int atmel_spi_one_transfer(struct spi_controller *host,
 		}
 
 		dma_timeout = msecs_to_jiffies(spi_controller_xfer_timeout(host, xfer));
-		ret_timeout = wait_for_completion_interruptible_timeout(&as->xfer_completion,
-									dma_timeout);
-		if (ret_timeout <= 0) {
-			dev_err(&spi->dev, "spi transfer %s\n",
-				!ret_timeout ? "timeout" : "canceled");
-			as->done_status = ret_timeout < 0 ? ret_timeout : -EIO;
+		ret_timeout = wait_for_completion_timeout(&as->xfer_completion, dma_timeout);
+		if (!ret_timeout) {
+			dev_err(&spi->dev, "spi transfer timeout\n");
+			as->done_status = -EIO;
 		}
 
 		if (as->done_status)
diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index 1f2f8c717df61f..a50eb4db79de8e 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -451,7 +451,6 @@ static int cdns_transfer_one(struct spi_controller *ctlr,
 		udelay(10);
 
 	cdns_spi_process_fifo(xspi, xspi->tx_fifo_depth, 0);
-	spi_transfer_delay_exec(transfer);
 
 	cdns_spi_write(xspi, CDNS_SPI_IER, CDNS_SPI_IXR_DEFAULT);
 	return transfer->len;
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 498e35c8db2c1d..272bc871a848b8 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -659,11 +659,18 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx,
 		ctrl |= (spi_imx->target_burst * 8 - 1)
 			<< MX51_ECSPI_CTRL_BL_OFFSET;
 	else {
-		if (spi_imx->count >= 512)
-			ctrl |= 0xFFF << MX51_ECSPI_CTRL_BL_OFFSET;
-		else
-			ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1)
+		if (spi_imx->usedma) {
+			ctrl |= (spi_imx->bits_per_word *
+				spi_imx_bytes_per_word(spi_imx->bits_per_word) - 1)
 				<< MX51_ECSPI_CTRL_BL_OFFSET;
+		} else {
+			if (spi_imx->count >= MX51_ECSPI_CTRL_MAX_BURST)
+				ctrl |= (MX51_ECSPI_CTRL_MAX_BURST - 1)
+						<< MX51_ECSPI_CTRL_BL_OFFSET;
+			else
+				ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1)
+						<< MX51_ECSPI_CTRL_BL_OFFSET;
+		}
 	}
 
 	/* set clock speed */
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 791df0e6910547..8ead7acb99f348 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -3317,33 +3317,52 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 }
 EXPORT_SYMBOL_GPL(spi_unregister_controller);
 
+static inline int __spi_check_suspended(const struct spi_controller *ctlr)
+{
+	return ctlr->flags & SPI_CONTROLLER_SUSPENDED ? -ESHUTDOWN : 0;
+}
+
+static inline void __spi_mark_suspended(struct spi_controller *ctlr)
+{
+	mutex_lock(&ctlr->bus_lock_mutex);
+	ctlr->flags |= SPI_CONTROLLER_SUSPENDED;
+	mutex_unlock(&ctlr->bus_lock_mutex);
+}
+
+static inline void __spi_mark_resumed(struct spi_controller *ctlr)
+{
+	mutex_lock(&ctlr->bus_lock_mutex);
+	ctlr->flags &= ~SPI_CONTROLLER_SUSPENDED;
+	mutex_unlock(&ctlr->bus_lock_mutex);
+}
+
 int spi_controller_suspend(struct spi_controller *ctlr)
 {
-	int ret;
+	int ret = 0;
 
 	/* Basically no-ops for non-queued controllers */
-	if (!ctlr->queued)
-		return 0;
-
-	ret = spi_stop_queue(ctlr);
-	if (ret)
-		dev_err(&ctlr->dev, "queue stop failed\n");
+	if (ctlr->queued) {
+		ret = spi_stop_queue(ctlr);
+		if (ret)
+			dev_err(&ctlr->dev, "queue stop failed\n");
+	}
 
+	__spi_mark_suspended(ctlr);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(spi_controller_suspend);
 
 int spi_controller_resume(struct spi_controller *ctlr)
 {
-	int ret;
-
-	if (!ctlr->queued)
-		return 0;
+	int ret = 0;
 
-	ret = spi_start_queue(ctlr);
-	if (ret)
-		dev_err(&ctlr->dev, "queue restart failed\n");
+	__spi_mark_resumed(ctlr);
 
+	if (ctlr->queued) {
+		ret = spi_start_queue(ctlr);
+		if (ret)
+			dev_err(&ctlr->dev, "queue restart failed\n");
+	}
 	return ret;
 }
 EXPORT_SYMBOL_GPL(spi_controller_resume);
@@ -4147,8 +4166,7 @@ static void __spi_transfer_message_noqueue(struct spi_controller *ctlr, struct s
 	ctlr->cur_msg = msg;
 	ret = __spi_pump_transfer_message(ctlr, msg, was_busy);
 	if (ret)
-		goto out;
-
+		dev_err(&ctlr->dev, "noqueue transfer failed\n");
 	ctlr->cur_msg = NULL;
 	ctlr->fallback = false;
 
@@ -4164,7 +4182,6 @@ static void __spi_transfer_message_noqueue(struct spi_controller *ctlr, struct s
 		spi_idle_runtime_pm(ctlr);
 	}
 
-out:
 	mutex_unlock(&ctlr->io_mutex);
 }
 
@@ -4187,6 +4204,11 @@ static int __spi_sync(struct spi_device *spi, struct spi_message *message)
 	int status;
 	struct spi_controller *ctlr = spi->controller;
 
+	if (__spi_check_suspended(ctlr)) {
+		dev_warn_once(&spi->dev, "Attempted to sync while suspend\n");
+		return -ESHUTDOWN;
+	}
+
 	status = __spi_validate(spi, message);
 	if (status != 0)
 		return status;
diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c
index 64f0e047c23d2a..4b10921276942e 100644
--- a/drivers/tee/optee/device.c
+++ b/drivers/tee/optee/device.c
@@ -60,7 +60,16 @@ static void optee_release_device(struct device *dev)
 	kfree(optee_device);
 }
 
-static int optee_register_device(const uuid_t *device_uuid)
+static ssize_t need_supplicant_show(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	return 0;
+}
+
+static DEVICE_ATTR_RO(need_supplicant);
+
+static int optee_register_device(const uuid_t *device_uuid, u32 func)
 {
 	struct tee_client_device *optee_device = NULL;
 	int rc;
@@ -83,6 +92,10 @@ static int optee_register_device(const uuid_t *device_uuid)
 		put_device(&optee_device->dev);
 	}
 
+	if (func == PTA_CMD_GET_DEVICES_SUPP)
+		device_create_file(&optee_device->dev,
+				   &dev_attr_need_supplicant);
+
 	return rc;
 }
 
@@ -142,7 +155,7 @@ static int __optee_enumerate_devices(u32 func)
 	num_devices = shm_size / sizeof(uuid_t);
 
 	for (idx = 0; idx < num_devices; idx++) {
-		rc = optee_register_device(&device_uuid[idx]);
+		rc = optee_register_device(&device_uuid[idx], func);
 		if (rc)
 			goto out_shm;
 	}
diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c
index c9ddd49138d822..e324cd89971937 100644
--- a/drivers/thunderbolt/debugfs.c
+++ b/drivers/thunderbolt/debugfs.c
@@ -959,7 +959,7 @@ static void margining_port_remove(struct tb_port *port)
 	snprintf(dir_name, sizeof(dir_name), "port%d", port->port);
 	parent = debugfs_lookup(dir_name, port->sw->debugfs_dir);
 	if (parent)
-		debugfs_remove_recursive(debugfs_lookup("margining", parent));
+		debugfs_lookup_and_remove("margining", parent);
 
 	kfree(port->usb4->margining);
 	port->usb4->margining = NULL;
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 1e15ffa792955d..44e9b09de47a5a 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -1143,7 +1143,7 @@ int tb_port_lane_bonding_enable(struct tb_port *port)
 	 * Only set bonding if the link was not already bonded. This
 	 * avoids the lane adapter to re-enter bonding state.
 	 */
-	if (width == TB_LINK_WIDTH_SINGLE) {
+	if (width == TB_LINK_WIDTH_SINGLE && !tb_is_upstream_port(port)) {
 		ret = tb_port_set_lane_bonding(port, true);
 		if (ret)
 			goto err_lane1;
@@ -2880,6 +2880,7 @@ static int tb_switch_lane_bonding_disable(struct tb_switch *sw)
 	return tb_port_wait_for_link_width(down, TB_LINK_WIDTH_SINGLE, 100);
 }
 
+/* Note updating sw->link_width done in tb_switch_update_link_attributes() */
 static int tb_switch_asym_enable(struct tb_switch *sw, enum tb_link_width width)
 {
 	struct tb_port *up, *down, *port;
@@ -2919,10 +2920,10 @@ static int tb_switch_asym_enable(struct tb_switch *sw, enum tb_link_width width)
 			return ret;
 	}
 
-	sw->link_width = width;
 	return 0;
 }
 
+/* Note updating sw->link_width done in tb_switch_update_link_attributes() */
 static int tb_switch_asym_disable(struct tb_switch *sw)
 {
 	struct tb_port *up, *down;
@@ -2957,7 +2958,6 @@ static int tb_switch_asym_disable(struct tb_switch *sw)
 			return ret;
 	}
 
-	sw->link_width = TB_LINK_WIDTH_DUAL;
 	return 0;
 }
 
diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index 5acdeb766860da..fd49f86e03532c 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -213,7 +213,17 @@ static void tb_add_dp_resources(struct tb_switch *sw)
 		if (!tb_switch_query_dp_resource(sw, port))
 			continue;
 
-		list_add(&port->list, &tcm->dp_resources);
+		/*
+		 * If DP IN on device router exist, position it at the
+		 * beginning of the DP resources list, so that it is used
+		 * before DP IN of the host router. This way external GPU(s)
+		 * will be prioritized when pairing DP IN to a DP OUT.
+		 */
+		if (tb_route(sw))
+			list_add(&port->list, &tcm->dp_resources);
+		else
+			list_add_tail(&port->list, &tcm->dp_resources);
+
 		tb_port_dbg(port, "DP IN resource available\n");
 	}
 }
diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c
index 4277733d0021bf..f8f0d24ff6e462 100644
--- a/drivers/thunderbolt/usb4.c
+++ b/drivers/thunderbolt/usb4.c
@@ -2311,13 +2311,13 @@ int usb4_usb3_port_release_bandwidth(struct tb_port *port, int *upstream_bw,
 		goto err_request;
 
 	/*
-	 * Always keep 1000 Mb/s to make sure xHCI has at least some
+	 * Always keep 900 Mb/s to make sure xHCI has at least some
 	 * bandwidth available for isochronous traffic.
 	 */
-	if (consumed_up < 1000)
-		consumed_up = 1000;
-	if (consumed_down < 1000)
-		consumed_down = 1000;
+	if (consumed_up < 900)
+		consumed_up = 900;
+	if (consumed_down < 900)
+		consumed_down = 900;
 
 	ret = usb4_usb3_port_write_allocated_bandwidth(port, consumed_up,
 						       consumed_down);
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index b94f567647cb65..e6218766d0c804 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -777,6 +777,7 @@ static const struct acpi_device_id dw8250_acpi_match[] = {
 	{ "INT33C5", (kernel_ulong_t)&dw8250_dw_apb },
 	{ "INT3434", (kernel_ulong_t)&dw8250_dw_apb },
 	{ "INT3435", (kernel_ulong_t)&dw8250_dw_apb },
+	{ "INTC10EE", (kernel_ulong_t)&dw8250_dw_apb },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, dw8250_acpi_match);
diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c
index 9837a27739fdf5..e3f482fd3de481 100644
--- a/drivers/tty/serial/8250/8250_early.c
+++ b/drivers/tty/serial/8250/8250_early.c
@@ -189,5 +189,6 @@ static int __init early_omap8250_setup(struct earlycon_device *device,
 OF_EARLYCON_DECLARE(omap8250, "ti,omap2-uart", early_omap8250_setup);
 OF_EARLYCON_DECLARE(omap8250, "ti,omap3-uart", early_omap8250_setup);
 OF_EARLYCON_DECLARE(omap8250, "ti,omap4-uart", early_omap8250_setup);
+OF_EARLYCON_DECLARE(omap8250, "ti,am654-uart", early_omap8250_setup);
 
 #endif
diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index 2d42f485c98766..578f35895b273f 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -933,7 +933,7 @@ static void __dma_rx_do_complete(struct uart_8250_port *p)
 	if (priv->habit & UART_HAS_RHR_IT_DIS) {
 		reg = serial_in(p, UART_OMAP_IER2);
 		reg &= ~UART_OMAP_IER2_RHR_IT_DIS;
-		serial_out(p, UART_OMAP_IER2, UART_OMAP_IER2_RHR_IT_DIS);
+		serial_out(p, UART_OMAP_IER2, reg);
 	}
 
 	dmaengine_tx_status(rxchan, cookie, &state);
@@ -1079,7 +1079,7 @@ static int omap_8250_rx_dma(struct uart_8250_port *p)
 	if (priv->habit & UART_HAS_RHR_IT_DIS) {
 		reg = serial_in(p, UART_OMAP_IER2);
 		reg |= UART_OMAP_IER2_RHR_IT_DIS;
-		serial_out(p, UART_OMAP_IER2, UART_OMAP_IER2_RHR_IT_DIS);
+		serial_out(p, UART_OMAP_IER2, reg);
 	}
 
 	dma_async_issue_pending(dma->rxchan);
@@ -1298,10 +1298,12 @@ static int omap_8250_dma_handle_irq(struct uart_port *port)
 
 	status = serial_port_in(port, UART_LSR);
 
-	if (priv->habit & UART_HAS_EFR2)
-		am654_8250_handle_rx_dma(up, iir, status);
-	else
-		status = omap_8250_handle_rx_dma(up, iir, status);
+	if ((iir & 0x3f) != UART_IIR_THRI) {
+		if (priv->habit & UART_HAS_EFR2)
+			am654_8250_handle_rx_dma(up, iir, status);
+		else
+			status = omap_8250_handle_rx_dma(up, iir, status);
+	}
 
 	serial8250_modem_status(up);
 	if (status & UART_LSR_THRE && up->dma->tx_err) {
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 925ee1d61afb20..8ca061d3bbb921 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -170,13 +170,6 @@ static const struct serial8250_config uart_config[] = {
 		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10,
 		.flags		= UART_CAP_FIFO,
 	},
-	[PORT_AR7] = {
-		.name		= "AR7",
-		.fifo_size	= 16,
-		.tx_loadsz	= 16,
-		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_00,
-		.flags		= UART_CAP_FIFO /* | UART_CAP_AFE */,
-	},
 	[PORT_U6_16550A] = {
 		.name		= "U6_16550A",
 		.fifo_size	= 64,
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 61cc24cd90e4bc..b7635363373e20 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -218,17 +218,18 @@ static struct vendor_data vendor_st = {
 
 /* Deals with DMA transactions */
 
-struct pl011_sgbuf {
-	struct scatterlist sg;
-	char *buf;
+struct pl011_dmabuf {
+	dma_addr_t		dma;
+	size_t			len;
+	char			*buf;
 };
 
 struct pl011_dmarx_data {
 	struct dma_chan		*chan;
 	struct completion	complete;
 	bool			use_buf_b;
-	struct pl011_sgbuf	sgbuf_a;
-	struct pl011_sgbuf	sgbuf_b;
+	struct pl011_dmabuf	dbuf_a;
+	struct pl011_dmabuf	dbuf_b;
 	dma_cookie_t		cookie;
 	bool			running;
 	struct timer_list	timer;
@@ -241,7 +242,8 @@ struct pl011_dmarx_data {
 
 struct pl011_dmatx_data {
 	struct dma_chan		*chan;
-	struct scatterlist	sg;
+	dma_addr_t		dma;
+	size_t			len;
 	char			*buf;
 	bool			queued;
 };
@@ -366,32 +368,24 @@ static int pl011_fifo_to_tty(struct uart_amba_port *uap)
 
 #define PL011_DMA_BUFFER_SIZE PAGE_SIZE
 
-static int pl011_sgbuf_init(struct dma_chan *chan, struct pl011_sgbuf *sg,
+static int pl011_dmabuf_init(struct dma_chan *chan, struct pl011_dmabuf *db,
 	enum dma_data_direction dir)
 {
-	dma_addr_t dma_addr;
-
-	sg->buf = dma_alloc_coherent(chan->device->dev,
-		PL011_DMA_BUFFER_SIZE, &dma_addr, GFP_KERNEL);
-	if (!sg->buf)
+	db->buf = dma_alloc_coherent(chan->device->dev, PL011_DMA_BUFFER_SIZE,
+				     &db->dma, GFP_KERNEL);
+	if (!db->buf)
 		return -ENOMEM;
-
-	sg_init_table(&sg->sg, 1);
-	sg_set_page(&sg->sg, phys_to_page(dma_addr),
-		PL011_DMA_BUFFER_SIZE, offset_in_page(dma_addr));
-	sg_dma_address(&sg->sg) = dma_addr;
-	sg_dma_len(&sg->sg) = PL011_DMA_BUFFER_SIZE;
+	db->len = PL011_DMA_BUFFER_SIZE;
 
 	return 0;
 }
 
-static void pl011_sgbuf_free(struct dma_chan *chan, struct pl011_sgbuf *sg,
+static void pl011_dmabuf_free(struct dma_chan *chan, struct pl011_dmabuf *db,
 	enum dma_data_direction dir)
 {
-	if (sg->buf) {
+	if (db->buf) {
 		dma_free_coherent(chan->device->dev,
-			PL011_DMA_BUFFER_SIZE, sg->buf,
-			sg_dma_address(&sg->sg));
+				  PL011_DMA_BUFFER_SIZE, db->buf, db->dma);
 	}
 }
 
@@ -552,8 +546,8 @@ static void pl011_dma_tx_callback(void *data)
 
 	uart_port_lock_irqsave(&uap->port, &flags);
 	if (uap->dmatx.queued)
-		dma_unmap_sg(dmatx->chan->device->dev, &dmatx->sg, 1,
-			     DMA_TO_DEVICE);
+		dma_unmap_single(dmatx->chan->device->dev, dmatx->dma,
+				dmatx->len, DMA_TO_DEVICE);
 
 	dmacr = uap->dmacr;
 	uap->dmacr = dmacr & ~UART011_TXDMAE;
@@ -639,18 +633,19 @@ static int pl011_dma_tx_refill(struct uart_amba_port *uap)
 			memcpy(&dmatx->buf[first], &xmit->buf[0], second);
 	}
 
-	dmatx->sg.length = count;
-
-	if (dma_map_sg(dma_dev->dev, &dmatx->sg, 1, DMA_TO_DEVICE) != 1) {
+	dmatx->len = count;
+	dmatx->dma = dma_map_single(dma_dev->dev, dmatx->buf, count,
+				    DMA_TO_DEVICE);
+	if (dmatx->dma == DMA_MAPPING_ERROR) {
 		uap->dmatx.queued = false;
 		dev_dbg(uap->port.dev, "unable to map TX DMA\n");
 		return -EBUSY;
 	}
 
-	desc = dmaengine_prep_slave_sg(chan, &dmatx->sg, 1, DMA_MEM_TO_DEV,
+	desc = dmaengine_prep_slave_single(chan, dmatx->dma, dmatx->len, DMA_MEM_TO_DEV,
 					     DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc) {
-		dma_unmap_sg(dma_dev->dev, &dmatx->sg, 1, DMA_TO_DEVICE);
+		dma_unmap_single(dma_dev->dev, dmatx->dma, dmatx->len, DMA_TO_DEVICE);
 		uap->dmatx.queued = false;
 		/*
 		 * If DMA cannot be used right now, we complete this
@@ -813,8 +808,8 @@ __acquires(&uap->port.lock)
 	dmaengine_terminate_async(uap->dmatx.chan);
 
 	if (uap->dmatx.queued) {
-		dma_unmap_sg(uap->dmatx.chan->device->dev, &uap->dmatx.sg, 1,
-			     DMA_TO_DEVICE);
+		dma_unmap_single(uap->dmatx.chan->device->dev, uap->dmatx.dma,
+				 uap->dmatx.len, DMA_TO_DEVICE);
 		uap->dmatx.queued = false;
 		uap->dmacr &= ~UART011_TXDMAE;
 		pl011_write(uap->dmacr, uap, REG_DMACR);
@@ -828,15 +823,15 @@ static int pl011_dma_rx_trigger_dma(struct uart_amba_port *uap)
 	struct dma_chan *rxchan = uap->dmarx.chan;
 	struct pl011_dmarx_data *dmarx = &uap->dmarx;
 	struct dma_async_tx_descriptor *desc;
-	struct pl011_sgbuf *sgbuf;
+	struct pl011_dmabuf *dbuf;
 
 	if (!rxchan)
 		return -EIO;
 
 	/* Start the RX DMA job */
-	sgbuf = uap->dmarx.use_buf_b ?
-		&uap->dmarx.sgbuf_b : &uap->dmarx.sgbuf_a;
-	desc = dmaengine_prep_slave_sg(rxchan, &sgbuf->sg, 1,
+	dbuf = uap->dmarx.use_buf_b ?
+		&uap->dmarx.dbuf_b : &uap->dmarx.dbuf_a;
+	desc = dmaengine_prep_slave_single(rxchan, dbuf->dma, dbuf->len,
 					DMA_DEV_TO_MEM,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	/*
@@ -876,8 +871,8 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap,
 			       bool readfifo)
 {
 	struct tty_port *port = &uap->port.state->port;
-	struct pl011_sgbuf *sgbuf = use_buf_b ?
-		&uap->dmarx.sgbuf_b : &uap->dmarx.sgbuf_a;
+	struct pl011_dmabuf *dbuf = use_buf_b ?
+		&uap->dmarx.dbuf_b : &uap->dmarx.dbuf_a;
 	int dma_count = 0;
 	u32 fifotaken = 0; /* only used for vdbg() */
 
@@ -886,7 +881,7 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap,
 
 	if (uap->dmarx.poll_rate) {
 		/* The data can be taken by polling */
-		dmataken = sgbuf->sg.length - dmarx->last_residue;
+		dmataken = dbuf->len - dmarx->last_residue;
 		/* Recalculate the pending size */
 		if (pending >= dmataken)
 			pending -= dmataken;
@@ -900,7 +895,7 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap,
 		 * Note that tty_insert_flip_buf() tries to take as many chars
 		 * as it can.
 		 */
-		dma_count = tty_insert_flip_string(port, sgbuf->buf + dmataken,
+		dma_count = tty_insert_flip_string(port, dbuf->buf + dmataken,
 				pending);
 
 		uap->port.icount.rx += dma_count;
@@ -911,7 +906,7 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap,
 
 	/* Reset the last_residue for Rx DMA poll */
 	if (uap->dmarx.poll_rate)
-		dmarx->last_residue = sgbuf->sg.length;
+		dmarx->last_residue = dbuf->len;
 
 	/*
 	 * Only continue with trying to read the FIFO if all DMA chars have
@@ -946,8 +941,8 @@ static void pl011_dma_rx_irq(struct uart_amba_port *uap)
 {
 	struct pl011_dmarx_data *dmarx = &uap->dmarx;
 	struct dma_chan *rxchan = dmarx->chan;
-	struct pl011_sgbuf *sgbuf = dmarx->use_buf_b ?
-		&dmarx->sgbuf_b : &dmarx->sgbuf_a;
+	struct pl011_dmabuf *dbuf = dmarx->use_buf_b ?
+		&dmarx->dbuf_b : &dmarx->dbuf_a;
 	size_t pending;
 	struct dma_tx_state state;
 	enum dma_status dmastat;
@@ -969,7 +964,7 @@ static void pl011_dma_rx_irq(struct uart_amba_port *uap)
 	pl011_write(uap->dmacr, uap, REG_DMACR);
 	uap->dmarx.running = false;
 
-	pending = sgbuf->sg.length - state.residue;
+	pending = dbuf->len - state.residue;
 	BUG_ON(pending > PL011_DMA_BUFFER_SIZE);
 	/* Then we terminate the transfer - we now know our residue */
 	dmaengine_terminate_all(rxchan);
@@ -996,8 +991,8 @@ static void pl011_dma_rx_callback(void *data)
 	struct pl011_dmarx_data *dmarx = &uap->dmarx;
 	struct dma_chan *rxchan = dmarx->chan;
 	bool lastbuf = dmarx->use_buf_b;
-	struct pl011_sgbuf *sgbuf = dmarx->use_buf_b ?
-		&dmarx->sgbuf_b : &dmarx->sgbuf_a;
+	struct pl011_dmabuf *dbuf = dmarx->use_buf_b ?
+		&dmarx->dbuf_b : &dmarx->dbuf_a;
 	size_t pending;
 	struct dma_tx_state state;
 	int ret;
@@ -1015,7 +1010,7 @@ static void pl011_dma_rx_callback(void *data)
 	 * the DMA irq handler. So we check the residue here.
 	 */
 	rxchan->device->device_tx_status(rxchan, dmarx->cookie, &state);
-	pending = sgbuf->sg.length - state.residue;
+	pending = dbuf->len - state.residue;
 	BUG_ON(pending > PL011_DMA_BUFFER_SIZE);
 	/* Then we terminate the transfer - we now know our residue */
 	dmaengine_terminate_all(rxchan);
@@ -1067,16 +1062,16 @@ static void pl011_dma_rx_poll(struct timer_list *t)
 	unsigned long flags;
 	unsigned int dmataken = 0;
 	unsigned int size = 0;
-	struct pl011_sgbuf *sgbuf;
+	struct pl011_dmabuf *dbuf;
 	int dma_count;
 	struct dma_tx_state state;
 
-	sgbuf = dmarx->use_buf_b ? &uap->dmarx.sgbuf_b : &uap->dmarx.sgbuf_a;
+	dbuf = dmarx->use_buf_b ? &uap->dmarx.dbuf_b : &uap->dmarx.dbuf_a;
 	rxchan->device->device_tx_status(rxchan, dmarx->cookie, &state);
 	if (likely(state.residue < dmarx->last_residue)) {
-		dmataken = sgbuf->sg.length - dmarx->last_residue;
+		dmataken = dbuf->len - dmarx->last_residue;
 		size = dmarx->last_residue - state.residue;
-		dma_count = tty_insert_flip_string(port, sgbuf->buf + dmataken,
+		dma_count = tty_insert_flip_string(port, dbuf->buf + dmataken,
 				size);
 		if (dma_count == size)
 			dmarx->last_residue =  state.residue;
@@ -1123,7 +1118,7 @@ static void pl011_dma_startup(struct uart_amba_port *uap)
 		return;
 	}
 
-	sg_init_one(&uap->dmatx.sg, uap->dmatx.buf, PL011_DMA_BUFFER_SIZE);
+	uap->dmatx.len = PL011_DMA_BUFFER_SIZE;
 
 	/* The DMA buffer is now the FIFO the TTY subsystem can use */
 	uap->port.fifosize = PL011_DMA_BUFFER_SIZE;
@@ -1133,7 +1128,7 @@ static void pl011_dma_startup(struct uart_amba_port *uap)
 		goto skip_rx;
 
 	/* Allocate and map DMA RX buffers */
-	ret = pl011_sgbuf_init(uap->dmarx.chan, &uap->dmarx.sgbuf_a,
+	ret = pl011_dmabuf_init(uap->dmarx.chan, &uap->dmarx.dbuf_a,
 			       DMA_FROM_DEVICE);
 	if (ret) {
 		dev_err(uap->port.dev, "failed to init DMA %s: %d\n",
@@ -1141,12 +1136,12 @@ static void pl011_dma_startup(struct uart_amba_port *uap)
 		goto skip_rx;
 	}
 
-	ret = pl011_sgbuf_init(uap->dmarx.chan, &uap->dmarx.sgbuf_b,
+	ret = pl011_dmabuf_init(uap->dmarx.chan, &uap->dmarx.dbuf_b,
 			       DMA_FROM_DEVICE);
 	if (ret) {
 		dev_err(uap->port.dev, "failed to init DMA %s: %d\n",
 			"RX buffer B", ret);
-		pl011_sgbuf_free(uap->dmarx.chan, &uap->dmarx.sgbuf_a,
+		pl011_dmabuf_free(uap->dmarx.chan, &uap->dmarx.dbuf_a,
 				 DMA_FROM_DEVICE);
 		goto skip_rx;
 	}
@@ -1200,8 +1195,9 @@ static void pl011_dma_shutdown(struct uart_amba_port *uap)
 		/* In theory, this should already be done by pl011_dma_flush_buffer */
 		dmaengine_terminate_all(uap->dmatx.chan);
 		if (uap->dmatx.queued) {
-			dma_unmap_sg(uap->dmatx.chan->device->dev, &uap->dmatx.sg, 1,
-				     DMA_TO_DEVICE);
+			dma_unmap_single(uap->dmatx.chan->device->dev,
+					 uap->dmatx.dma, uap->dmatx.len,
+					 DMA_TO_DEVICE);
 			uap->dmatx.queued = false;
 		}
 
@@ -1212,8 +1208,8 @@ static void pl011_dma_shutdown(struct uart_amba_port *uap)
 	if (uap->using_rx_dma) {
 		dmaengine_terminate_all(uap->dmarx.chan);
 		/* Clean up the RX DMA */
-		pl011_sgbuf_free(uap->dmarx.chan, &uap->dmarx.sgbuf_a, DMA_FROM_DEVICE);
-		pl011_sgbuf_free(uap->dmarx.chan, &uap->dmarx.sgbuf_b, DMA_FROM_DEVICE);
+		pl011_dmabuf_free(uap->dmarx.chan, &uap->dmarx.dbuf_a, DMA_FROM_DEVICE);
+		pl011_dmabuf_free(uap->dmarx.chan, &uap->dmarx.dbuf_b, DMA_FROM_DEVICE);
 		if (uap->dmarx.poll_rate)
 			del_timer_sync(&uap->dmarx.timer);
 		uap->using_rx_dma = false;
diff --git a/drivers/tty/serial/ma35d1_serial.c b/drivers/tty/serial/ma35d1_serial.c
index a6a7c405892e80..21b574f78b8615 100644
--- a/drivers/tty/serial/ma35d1_serial.c
+++ b/drivers/tty/serial/ma35d1_serial.c
@@ -552,11 +552,19 @@ static void ma35d1serial_console_putchar(struct uart_port *port, unsigned char c
  */
 static void ma35d1serial_console_write(struct console *co, const char *s, u32 count)
 {
-	struct uart_ma35d1_port *up = &ma35d1serial_ports[co->index];
+	struct uart_ma35d1_port *up;
 	unsigned long flags;
 	int locked = 1;
 	u32 ier;
 
+	if ((co->index < 0) || (co->index >= MA35_UART_NR)) {
+		pr_warn("Failed to write on ononsole port %x, out of range\n",
+			co->index);
+		return;
+	}
+
+	up = &ma35d1serial_ports[co->index];
+
 	if (up->port.sysrq)
 		locked = 0;
 	else if (oops_in_progress)
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index db2bb1c0d36c26..cf0c6120d30ede 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -766,6 +766,18 @@ static bool sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno)
 		case SC16IS7XX_IIR_RTOI_SRC:
 		case SC16IS7XX_IIR_XOFFI_SRC:
 			rxlen = sc16is7xx_port_read(port, SC16IS7XX_RXLVL_REG);
+
+			/*
+			 * There is a silicon bug that makes the chip report a
+			 * time-out interrupt but no data in the FIFO. This is
+			 * described in errata section 18.1.4.
+			 *
+			 * When this happens, read one byte from the FIFO to
+			 * clear the interrupt.
+			 */
+			if (iir == SC16IS7XX_IIR_RTOI_SRC && !rxlen)
+				rxlen = 1;
+
 			if (rxlen)
 				sc16is7xx_handle_rx(port, rxlen, iir);
 			break;
diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 2ba8ec254dceee..0787456c2b892f 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -436,7 +436,7 @@ int ufshcd_mcq_init(struct ufs_hba *hba)
 
 	for (i = 0; i < hba->nr_hw_queues; i++) {
 		hwq = &hba->uhq[i];
-		hwq->max_entries = hba->nutrs;
+		hwq->max_entries = hba->nutrs + 1;
 		spin_lock_init(&hwq->sq_lock);
 		spin_lock_init(&hwq->cq_lock);
 		mutex_init(&hwq->sq_mutex);
@@ -630,6 +630,7 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
 	int tag = scsi_cmd_to_rq(cmd)->tag;
 	struct ufshcd_lrb *lrbp = &hba->lrb[tag];
 	struct ufs_hw_queue *hwq;
+	unsigned long flags;
 	int err = FAILED;
 
 	if (!ufshcd_cmd_inflight(lrbp->cmd)) {
@@ -670,8 +671,10 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd)
 	}
 
 	err = SUCCESS;
+	spin_lock_irqsave(&hwq->cq_lock, flags);
 	if (ufshcd_cmd_inflight(lrbp->cmd))
 		ufshcd_release_scsi_cmd(hba, lrbp);
+	spin_unlock_irqrestore(&hwq->cq_lock, flags);
 
 out:
 	return err;
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 8b1031fb0a4400..16d76325039a5d 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -2274,9 +2274,10 @@ void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag,
 	if (is_mcq_enabled(hba)) {
 		int utrd_size = sizeof(struct utp_transfer_req_desc);
 		struct utp_transfer_req_desc *src = lrbp->utr_descriptor_ptr;
-		struct utp_transfer_req_desc *dest = hwq->sqe_base_addr + hwq->sq_tail_slot;
+		struct utp_transfer_req_desc *dest;
 
 		spin_lock(&hwq->sq_lock);
+		dest = hwq->sqe_base_addr + hwq->sq_tail_slot;
 		memcpy(dest, src, utrd_size);
 		ufshcd_inc_sq_tail(hwq);
 		spin_unlock(&hwq->sq_lock);
@@ -6444,11 +6445,24 @@ static bool ufshcd_abort_one(struct request *rq, void *priv)
 	struct scsi_device *sdev = cmd->device;
 	struct Scsi_Host *shost = sdev->host;
 	struct ufs_hba *hba = shost_priv(shost);
+	struct ufshcd_lrb *lrbp = &hba->lrb[tag];
+	struct ufs_hw_queue *hwq;
+	unsigned long flags;
 
 	*ret = ufshcd_try_to_abort_task(hba, tag);
 	dev_err(hba->dev, "Aborting tag %d / CDB %#02x %s\n", tag,
 		hba->lrb[tag].cmd ? hba->lrb[tag].cmd->cmnd[0] : -1,
 		*ret ? "failed" : "succeeded");
+
+	/* Release cmd in MCQ mode if abort succeeds */
+	if (is_mcq_enabled(hba) && (*ret == 0)) {
+		hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(lrbp->cmd));
+		spin_lock_irqsave(&hwq->cq_lock, flags);
+		if (ufshcd_cmd_inflight(lrbp->cmd))
+			ufshcd_release_scsi_cmd(hba, lrbp);
+		spin_unlock_irqrestore(&hwq->cq_lock, flags);
+	}
+
 	return *ret == 0;
 }
 
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 96cb8b5b4e66f5..17e24270477dd8 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -1516,9 +1516,11 @@ static int ufs_qcom_clk_scale_notify(struct ufs_hba *hba,
 			err = ufs_qcom_clk_scale_up_pre_change(hba);
 		else
 			err = ufs_qcom_clk_scale_down_pre_change(hba);
-		if (err)
-			ufshcd_uic_hibern8_exit(hba);
 
+		if (err) {
+			ufshcd_uic_hibern8_exit(hba);
+			return err;
+		}
 	} else {
 		if (scale_up)
 			err = ufs_qcom_clk_scale_up_post_change(hba);
diff --git a/drivers/ufs/host/ufshcd-pltfrm.c b/drivers/ufs/host/ufshcd-pltfrm.c
index da2558e274b473..db9d9365ff55dc 100644
--- a/drivers/ufs/host/ufshcd-pltfrm.c
+++ b/drivers/ufs/host/ufshcd-pltfrm.c
@@ -8,6 +8,7 @@
  *	Vinayak Holikatti <h.vinayak@samsung.com>
  */
 
+#include <linux/clk.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
@@ -213,6 +214,55 @@ static void ufshcd_init_lanes_per_dir(struct ufs_hba *hba)
 	}
 }
 
+/**
+ * ufshcd_parse_clock_min_max_freq  - Parse MIN and MAX clocks freq
+ * @hba: per adapter instance
+ *
+ * This function parses MIN and MAX frequencies of all clocks required
+ * by the host drivers.
+ *
+ * Returns 0 for success and non-zero for failure
+ */
+static int ufshcd_parse_clock_min_max_freq(struct ufs_hba *hba)
+{
+	struct list_head *head = &hba->clk_list_head;
+	struct ufs_clk_info *clki;
+	struct dev_pm_opp *opp;
+	unsigned long freq;
+	u8 idx = 0;
+
+	list_for_each_entry(clki, head, list) {
+		if (!clki->name)
+			continue;
+
+		clki->clk = devm_clk_get(hba->dev, clki->name);
+		if (IS_ERR(clki->clk))
+			continue;
+
+		/* Find Max Freq */
+		freq = ULONG_MAX;
+		opp = dev_pm_opp_find_freq_floor_indexed(hba->dev, &freq, idx);
+		if (IS_ERR(opp)) {
+			dev_err(hba->dev, "Failed to find OPP for MAX frequency\n");
+			return PTR_ERR(opp);
+		}
+		clki->max_freq = dev_pm_opp_get_freq_indexed(opp, idx);
+		dev_pm_opp_put(opp);
+
+		/* Find Min Freq */
+		freq = 0;
+		opp = dev_pm_opp_find_freq_ceil_indexed(hba->dev, &freq, idx);
+		if (IS_ERR(opp)) {
+			dev_err(hba->dev, "Failed to find OPP for MIN frequency\n");
+			return PTR_ERR(opp);
+		}
+		clki->min_freq = dev_pm_opp_get_freq_indexed(opp, idx++);
+		dev_pm_opp_put(opp);
+	}
+
+	return 0;
+}
+
 static int ufshcd_parse_operating_points(struct ufs_hba *hba)
 {
 	struct device *dev = hba->dev;
@@ -279,6 +329,10 @@ static int ufshcd_parse_operating_points(struct ufs_hba *hba)
 		return ret;
 	}
 
+	ret = ufshcd_parse_clock_min_max_freq(hba);
+	if (ret)
+		return ret;
+
 	hba->use_pm_opp = true;
 
 	return 0;
diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c
index af981778382df7..02f297f5637d75 100644
--- a/drivers/usb/cdns3/cdnsp-ring.c
+++ b/drivers/usb/cdns3/cdnsp-ring.c
@@ -1529,6 +1529,7 @@ irqreturn_t cdnsp_thread_irq_handler(int irq, void *data)
 	unsigned long flags;
 	int counter = 0;
 
+	local_bh_disable();
 	spin_lock_irqsave(&pdev->lock, flags);
 
 	if (pdev->cdnsp_state & (CDNSP_STATE_HALTED | CDNSP_STATE_DYING)) {
@@ -1541,6 +1542,7 @@ irqreturn_t cdnsp_thread_irq_handler(int irq, void *data)
 			cdnsp_died(pdev);
 
 		spin_unlock_irqrestore(&pdev->lock, flags);
+		local_bh_enable();
 		return IRQ_HANDLED;
 	}
 
@@ -1557,6 +1559,7 @@ irqreturn_t cdnsp_thread_irq_handler(int irq, void *data)
 	cdnsp_update_erst_dequeue(pdev, event_ring_deq, 1);
 
 	spin_unlock_irqrestore(&pdev->lock, flags);
+	local_bh_enable();
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index b19e38d5fd10c1..7f8d33f92ddb5f 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -1047,7 +1047,7 @@ int usb_get_bos_descriptor(struct usb_device *dev)
 
 		if (cap->bDescriptorType != USB_DT_DEVICE_CAPABILITY) {
 			dev_notice(ddev, "descriptor type invalid, skip\n");
-			continue;
+			goto skip_to_next_descriptor;
 		}
 
 		switch (cap_type) {
@@ -1078,6 +1078,7 @@ int usb_get_bos_descriptor(struct usb_device *dev)
 			break;
 		}
 
+skip_to_next_descriptor:
 		total_len -= length;
 		buffer += length;
 	}
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index b4584a0cd48456..87480a6e6d9348 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -622,29 +622,6 @@ static int hub_ext_port_status(struct usb_hub *hub, int port1, int type,
 		ret = 0;
 	}
 	mutex_unlock(&hub->status_mutex);
-
-	/*
-	 * There is no need to lock status_mutex here, because status_mutex
-	 * protects hub->status, and the phy driver only checks the port
-	 * status without changing the status.
-	 */
-	if (!ret) {
-		struct usb_device *hdev = hub->hdev;
-
-		/*
-		 * Only roothub will be notified of port state changes,
-		 * since the USB PHY only cares about changes at the next
-		 * level.
-		 */
-		if (is_root_hub(hdev)) {
-			struct usb_hcd *hcd = bus_to_hcd(hdev->bus);
-
-			if (hcd->usb_phy)
-				usb_phy_notify_port_status(hcd->usb_phy,
-							   port1 - 1, *status, *change);
-		}
-	}
-
 	return ret;
 }
 
diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c
index 0144ca8350c312..5c7538d498dd11 100644
--- a/drivers/usb/dwc2/hcd_intr.c
+++ b/drivers/usb/dwc2/hcd_intr.c
@@ -2015,15 +2015,17 @@ static void dwc2_hc_n_intr(struct dwc2_hsotg *hsotg, int chnum)
 {
 	struct dwc2_qtd *qtd;
 	struct dwc2_host_chan *chan;
-	u32 hcint, hcintmsk;
+	u32 hcint, hcintraw, hcintmsk;
 
 	chan = hsotg->hc_ptr_array[chnum];
 
-	hcint = dwc2_readl(hsotg, HCINT(chnum));
+	hcintraw = dwc2_readl(hsotg, HCINT(chnum));
 	hcintmsk = dwc2_readl(hsotg, HCINTMSK(chnum));
+	hcint = hcintraw & hcintmsk;
+	dwc2_writel(hsotg, hcint, HCINT(chnum));
+
 	if (!chan) {
 		dev_err(hsotg->dev, "## hc_ptr_array for channel is NULL ##\n");
-		dwc2_writel(hsotg, hcint, HCINT(chnum));
 		return;
 	}
 
@@ -2032,11 +2034,9 @@ static void dwc2_hc_n_intr(struct dwc2_hsotg *hsotg, int chnum)
 			 chnum);
 		dev_vdbg(hsotg->dev,
 			 "  hcint 0x%08x, hcintmsk 0x%08x, hcint&hcintmsk 0x%08x\n",
-			 hcint, hcintmsk, hcint & hcintmsk);
+			 hcintraw, hcintmsk, hcint);
 	}
 
-	dwc2_writel(hsotg, hcint, HCINT(chnum));
-
 	/*
 	 * If we got an interrupt after someone called
 	 * dwc2_hcd_endpoint_disable() we don't want to crash below
@@ -2046,8 +2046,7 @@ static void dwc2_hc_n_intr(struct dwc2_hsotg *hsotg, int chnum)
 		return;
 	}
 
-	chan->hcint = hcint;
-	hcint &= hcintmsk;
+	chan->hcint = hcintraw;
 
 	/*
 	 * If the channel was halted due to a dequeue, the qtd list might
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 0328c86ef80613..b101dbf8c5dcc7 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -2034,6 +2034,8 @@ static int dwc3_probe(struct platform_device *pdev)
 
 	pm_runtime_put(dev);
 
+	dma_set_max_seg_size(dev, UINT_MAX);
+
 	return 0;
 
 err_exit_debugfs:
diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c
index 039bf241769afb..57ddd2e43022eb 100644
--- a/drivers/usb/dwc3/drd.c
+++ b/drivers/usb/dwc3/drd.c
@@ -505,6 +505,7 @@ static int dwc3_setup_role_switch(struct dwc3 *dwc)
 		dwc->role_switch_default_mode = USB_DR_MODE_PERIPHERAL;
 		mode = DWC3_GCTL_PRTCAP_DEVICE;
 	}
+	dwc3_set_mode(dwc, mode);
 
 	dwc3_role_switch.fwnode = dev_fwnode(dwc->dev);
 	dwc3_role_switch.set = dwc3_usb_role_switch_set;
@@ -526,7 +527,6 @@ static int dwc3_setup_role_switch(struct dwc3 *dwc)
 		}
 	}
 
-	dwc3_set_mode(dwc, mode);
 	return 0;
 }
 #else
diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
index 3de43df6bbe814..fdf6d5d3c2ada4 100644
--- a/drivers/usb/dwc3/dwc3-qcom.c
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -546,10 +546,9 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev)
 				pdata ? pdata->hs_phy_irq_index : -1);
 	if (irq > 0) {
 		/* Keep wakeup interrupts disabled until suspend */
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
 					qcom_dwc3_resume_irq,
-					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					IRQF_ONESHOT | IRQF_NO_AUTOEN,
 					"qcom_dwc3 HS", qcom);
 		if (ret) {
 			dev_err(qcom->dev, "hs_phy_irq failed: %d\n", ret);
@@ -561,10 +560,9 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev)
 	irq = dwc3_qcom_get_irq(pdev, "dp_hs_phy_irq",
 				pdata ? pdata->dp_hs_phy_irq_index : -1);
 	if (irq > 0) {
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
 					qcom_dwc3_resume_irq,
-					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					IRQF_ONESHOT | IRQF_NO_AUTOEN,
 					"qcom_dwc3 DP_HS", qcom);
 		if (ret) {
 			dev_err(qcom->dev, "dp_hs_phy_irq failed: %d\n", ret);
@@ -576,10 +574,9 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev)
 	irq = dwc3_qcom_get_irq(pdev, "dm_hs_phy_irq",
 				pdata ? pdata->dm_hs_phy_irq_index : -1);
 	if (irq > 0) {
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
 					qcom_dwc3_resume_irq,
-					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					IRQF_ONESHOT | IRQF_NO_AUTOEN,
 					"qcom_dwc3 DM_HS", qcom);
 		if (ret) {
 			dev_err(qcom->dev, "dm_hs_phy_irq failed: %d\n", ret);
@@ -591,10 +588,9 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev)
 	irq = dwc3_qcom_get_irq(pdev, "ss_phy_irq",
 				pdata ? pdata->ss_phy_irq_index : -1);
 	if (irq > 0) {
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 		ret = devm_request_threaded_irq(qcom->dev, irq, NULL,
 					qcom_dwc3_resume_irq,
-					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					IRQF_ONESHOT | IRQF_NO_AUTOEN,
 					"qcom_dwc3 SS", qcom);
 		if (ret) {
 			dev_err(qcom->dev, "ss_phy_irq failed: %d\n", ret);
@@ -758,6 +754,7 @@ static int dwc3_qcom_of_register_core(struct platform_device *pdev)
 	if (!qcom->dwc3) {
 		ret = -ENODEV;
 		dev_err(dev, "failed to get dwc3 platform device\n");
+		of_platform_depopulate(dev);
 	}
 
 node_put:
@@ -766,9 +763,9 @@ node_put:
 	return ret;
 }
 
-static struct platform_device *
-dwc3_qcom_create_urs_usb_platdev(struct device *dev)
+static struct platform_device *dwc3_qcom_create_urs_usb_platdev(struct device *dev)
 {
+	struct platform_device *urs_usb = NULL;
 	struct fwnode_handle *fwh;
 	struct acpi_device *adev;
 	char name[8];
@@ -788,9 +785,26 @@ dwc3_qcom_create_urs_usb_platdev(struct device *dev)
 
 	adev = to_acpi_device_node(fwh);
 	if (!adev)
-		return NULL;
+		goto err_put_handle;
+
+	urs_usb = acpi_create_platform_device(adev, NULL);
+	if (IS_ERR_OR_NULL(urs_usb))
+		goto err_put_handle;
+
+	return urs_usb;
+
+err_put_handle:
+	fwnode_handle_put(fwh);
+
+	return urs_usb;
+}
 
-	return acpi_create_platform_device(adev, NULL);
+static void dwc3_qcom_destroy_urs_usb_platdev(struct platform_device *urs_usb)
+{
+	struct fwnode_handle *fwh = urs_usb->dev.fwnode;
+
+	platform_device_unregister(urs_usb);
+	fwnode_handle_put(fwh);
 }
 
 static int dwc3_qcom_probe(struct platform_device *pdev)
@@ -874,13 +888,13 @@ static int dwc3_qcom_probe(struct platform_device *pdev)
 	qcom->qscratch_base = devm_ioremap_resource(dev, parent_res);
 	if (IS_ERR(qcom->qscratch_base)) {
 		ret = PTR_ERR(qcom->qscratch_base);
-		goto clk_disable;
+		goto free_urs;
 	}
 
 	ret = dwc3_qcom_setup_irq(pdev);
 	if (ret) {
 		dev_err(dev, "failed to setup IRQs, err=%d\n", ret);
-		goto clk_disable;
+		goto free_urs;
 	}
 
 	/*
@@ -899,7 +913,7 @@ static int dwc3_qcom_probe(struct platform_device *pdev)
 
 	if (ret) {
 		dev_err(dev, "failed to register DWC3 Core, err=%d\n", ret);
-		goto depopulate;
+		goto free_urs;
 	}
 
 	ret = dwc3_qcom_interconnect_init(qcom);
@@ -931,10 +945,16 @@ static int dwc3_qcom_probe(struct platform_device *pdev)
 interconnect_exit:
 	dwc3_qcom_interconnect_exit(qcom);
 depopulate:
-	if (np)
+	if (np) {
 		of_platform_depopulate(&pdev->dev);
-	else
-		platform_device_put(pdev);
+	} else {
+		device_remove_software_node(&qcom->dwc3->dev);
+		platform_device_del(qcom->dwc3);
+	}
+	platform_device_put(qcom->dwc3);
+free_urs:
+	if (qcom->urs_usb)
+		dwc3_qcom_destroy_urs_usb_platdev(qcom->urs_usb);
 clk_disable:
 	for (i = qcom->num_clocks - 1; i >= 0; i--) {
 		clk_disable_unprepare(qcom->clks[i]);
@@ -953,11 +973,16 @@ static void dwc3_qcom_remove(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	int i;
 
-	device_remove_software_node(&qcom->dwc3->dev);
-	if (np)
+	if (np) {
 		of_platform_depopulate(&pdev->dev);
-	else
-		platform_device_put(pdev);
+	} else {
+		device_remove_software_node(&qcom->dwc3->dev);
+		platform_device_del(qcom->dwc3);
+	}
+	platform_device_put(qcom->dwc3);
+
+	if (qcom->urs_usb)
+		dwc3_qcom_destroy_urs_usb_platdev(qcom->urs_usb);
 
 	for (i = qcom->num_clocks - 1; i >= 0; i--) {
 		clk_disable_unprepare(qcom->clks[i]);
diff --git a/drivers/usb/dwc3/dwc3-rtk.c b/drivers/usb/dwc3/dwc3-rtk.c
index 590028e8fdcb23..3cd6b184551ce2 100644
--- a/drivers/usb/dwc3/dwc3-rtk.c
+++ b/drivers/usb/dwc3/dwc3-rtk.c
@@ -183,10 +183,13 @@ static enum usb_device_speed __get_dwc3_maximum_speed(struct device_node *np)
 
 	ret = of_property_read_string(dwc3_np, "maximum-speed", &maximum_speed);
 	if (ret < 0)
-		return USB_SPEED_UNKNOWN;
+		goto out;
 
 	ret = match_string(speed_names, ARRAY_SIZE(speed_names), maximum_speed);
 
+out:
+	of_node_put(dwc3_np);
+
 	return (ret < 0) ? USB_SPEED_UNKNOWN : ret;
 }
 
@@ -339,6 +342,9 @@ static int dwc3_rtk_probe_dwc3_core(struct dwc3_rtk *rtk)
 
 	switch_usb2_role(rtk, rtk->cur_role);
 
+	platform_device_put(dwc3_pdev);
+	of_node_put(dwc3_node);
+
 	return 0;
 
 err_pdev_put:
diff --git a/drivers/usb/fotg210/fotg210-hcd.c b/drivers/usb/fotg210/fotg210-hcd.c
index 929106c16b29b5..7bf810a0c98a93 100644
--- a/drivers/usb/fotg210/fotg210-hcd.c
+++ b/drivers/usb/fotg210/fotg210-hcd.c
@@ -428,8 +428,6 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh,
 			temp = size;
 		size -= temp;
 		next += temp;
-		if (temp == size)
-			goto done;
 	}
 
 	temp = snprintf(next, size, "\n");
@@ -439,7 +437,6 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh,
 	size -= temp;
 	next += temp;
 
-done:
 	*sizep = size;
 	*nextp = next;
 }
diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c
index ea85e2c701a15f..3c8a9dd585c09e 100644
--- a/drivers/usb/gadget/function/f_hid.c
+++ b/drivers/usb/gadget/function/f_hid.c
@@ -92,6 +92,7 @@ static void hidg_release(struct device *dev)
 {
 	struct f_hidg *hidg = container_of(dev, struct f_hidg, dev);
 
+	kfree(hidg->report_desc);
 	kfree(hidg->set_report_buf);
 	kfree(hidg);
 }
@@ -1287,9 +1288,9 @@ static struct usb_function *hidg_alloc(struct usb_function_instance *fi)
 	hidg->report_length = opts->report_length;
 	hidg->report_desc_length = opts->report_desc_length;
 	if (opts->report_desc) {
-		hidg->report_desc = devm_kmemdup(&hidg->dev, opts->report_desc,
-						 opts->report_desc_length,
-						 GFP_KERNEL);
+		hidg->report_desc = kmemdup(opts->report_desc,
+					    opts->report_desc_length,
+					    GFP_KERNEL);
 		if (!hidg->report_desc) {
 			ret = -ENOMEM;
 			goto err_put_device;
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index ded9531f141b1b..d59f94464b870b 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -1646,8 +1646,6 @@ static void gadget_unbind_driver(struct device *dev)
 
 	dev_dbg(&udc->dev, "unbinding gadget driver [%s]\n", driver->function);
 
-	kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
-
 	udc->allow_connect = false;
 	cancel_work_sync(&udc->vbus_work);
 	mutex_lock(&udc->connect_lock);
@@ -1667,6 +1665,8 @@ static void gadget_unbind_driver(struct device *dev)
 	driver->is_bound = false;
 	udc->driver = NULL;
 	mutex_unlock(&udc_lock);
+
+	kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
 }
 
 /* ------------------------------------------------------------------------- */
diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c
index 5b3cd455adecc2..61f3f8bbdcead3 100644
--- a/drivers/usb/host/xhci-mtk-sch.c
+++ b/drivers/usb/host/xhci-mtk-sch.c
@@ -650,9 +650,8 @@ static int check_isoc_ss_overlap(struct mu3h_sch_ep_info *sch_ep, u32 offset)
 
 		if (sch_ep->ep_type == ISOC_OUT_EP) {
 			for (j = 0; j < sch_ep->num_budget_microframes; j++) {
-				k = XHCI_MTK_BW_INDEX(base + j + CS_OFFSET);
-				/* use cs to indicate existence of in-ss @(base+j) */
-				if (tt->fs_bus_bw_in[k])
+				k = XHCI_MTK_BW_INDEX(base + j);
+				if (tt->in_ss_cnt[k])
 					return -ESCH_SS_OVERLAP;
 			}
 		} else if (sch_ep->ep_type == ISOC_IN_EP || sch_ep->ep_type == INT_IN_EP) {
@@ -769,6 +768,14 @@ static void update_sch_tt(struct mu3h_sch_ep_info *sch_ep, bool used)
 				tt->fs_frame_bw[f] -= (u16)sch_ep->bw_budget_table[j];
 			}
 		}
+
+		if (sch_ep->ep_type == ISOC_IN_EP || sch_ep->ep_type == INT_IN_EP) {
+			k = XHCI_MTK_BW_INDEX(base);
+			if (used)
+				tt->in_ss_cnt[k]++;
+			else
+				tt->in_ss_cnt[k]--;
+		}
 	}
 
 	if (used)
diff --git a/drivers/usb/host/xhci-mtk.h b/drivers/usb/host/xhci-mtk.h
index 865b55e23b1594..39f7ae7d30871d 100644
--- a/drivers/usb/host/xhci-mtk.h
+++ b/drivers/usb/host/xhci-mtk.h
@@ -38,6 +38,7 @@
  * @fs_bus_bw_in: save bandwidth used by FS/LS IN eps in each uframes
  * @ls_bus_bw: save bandwidth used by LS eps in each uframes
  * @fs_frame_bw: save bandwidth used by FS/LS eps in each FS frames
+ * @in_ss_cnt: the count of Start-Split for IN eps
  * @ep_list: Endpoints using this TT
  */
 struct mu3h_sch_tt {
@@ -45,6 +46,7 @@ struct mu3h_sch_tt {
 	u16 fs_bus_bw_in[XHCI_MTK_MAX_ESIT];
 	u8 ls_bus_bw[XHCI_MTK_MAX_ESIT];
 	u16 fs_frame_bw[XHCI_MTK_FRAMES_CNT];
+	u8 in_ss_cnt[XHCI_MTK_MAX_ESIT];
 	struct list_head ep_list;
 };
 
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 95ed9404f6f852..d6fc08e5db8fbd 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -535,8 +535,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	/* xHC spec requires PCI devices to support D3hot and D3cold */
 	if (xhci->hci_version >= 0x120)
 		xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW;
-	else if (pdev->vendor == PCI_VENDOR_ID_AMD && xhci->hci_version >= 0x110)
-		xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW;
 
 	if (xhci->quirks & XHCI_RESET_ON_RESUME)
 		xhci_dbg_trace(xhci, trace_xhci_dbg_quirks,
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index b93161374293b3..732cdeb739202e 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/usb/phy.h>
 #include <linux/slab.h>
@@ -148,7 +149,7 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s
 	int			ret;
 	int			irq;
 	struct xhci_plat_priv	*priv = NULL;
-
+	bool			of_match;
 
 	if (usb_disabled())
 		return -ENODEV;
@@ -253,16 +254,23 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s
 					 &xhci->imod_interval);
 	}
 
-	hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev, "usb-phy", 0);
-	if (IS_ERR(hcd->usb_phy)) {
-		ret = PTR_ERR(hcd->usb_phy);
-		if (ret == -EPROBE_DEFER)
-			goto disable_clk;
-		hcd->usb_phy = NULL;
-	} else {
-		ret = usb_phy_init(hcd->usb_phy);
-		if (ret)
-			goto disable_clk;
+	/*
+	 * Drivers such as dwc3 manages PHYs themself (and rely on driver name
+	 * matching for the xhci platform device).
+	 */
+	of_match = of_match_device(pdev->dev.driver->of_match_table, &pdev->dev);
+	if (of_match) {
+		hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev, "usb-phy", 0);
+		if (IS_ERR(hcd->usb_phy)) {
+			ret = PTR_ERR(hcd->usb_phy);
+			if (ret == -EPROBE_DEFER)
+				goto disable_clk;
+			hcd->usb_phy = NULL;
+		} else {
+			ret = usb_phy_init(hcd->usb_phy);
+			if (ret)
+				goto disable_clk;
+		}
 	}
 
 	hcd->tpl_support = of_usb_host_tpl_support(sysdev->of_node);
@@ -285,15 +293,17 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s
 			goto dealloc_usb2_hcd;
 		}
 
-		xhci->shared_hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev,
-			    "usb-phy", 1);
-		if (IS_ERR(xhci->shared_hcd->usb_phy)) {
-			xhci->shared_hcd->usb_phy = NULL;
-		} else {
-			ret = usb_phy_init(xhci->shared_hcd->usb_phy);
-			if (ret)
-				dev_err(sysdev, "%s init usb3phy fail (ret=%d)\n",
-					    __func__, ret);
+		if (of_match) {
+			xhci->shared_hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev,
+										"usb-phy", 1);
+			if (IS_ERR(xhci->shared_hcd->usb_phy)) {
+				xhci->shared_hcd->usb_phy = NULL;
+			} else {
+				ret = usb_phy_init(xhci->shared_hcd->usb_phy);
+				if (ret)
+					dev_err(sysdev, "%s init usb3phy fail (ret=%d)\n",
+						__func__, ret);
+			}
 		}
 
 		xhci->shared_hcd->tpl_support = hcd->tpl_support;
diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
index a341b2fbb7b44f..2b45404e9732ce 100644
--- a/drivers/usb/misc/onboard_usb_hub.c
+++ b/drivers/usb/misc/onboard_usb_hub.c
@@ -432,6 +432,8 @@ static const struct usb_device_id onboard_hub_id_table[] = {
 	{ USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2412) }, /* USB2412 USB 2.0 */
 	{ USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2514) }, /* USB2514B USB 2.0 */
 	{ USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2517) }, /* USB2517 USB 2.0 */
+	{ USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2744) }, /* USB5744 USB 2.0 */
+	{ USB_DEVICE(VENDOR_ID_MICROCHIP, 0x5744) }, /* USB5744 USB 3.0 */
 	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x0411) }, /* RTS5411 USB 3.1 */
 	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x5411) }, /* RTS5411 USB 2.1 */
 	{ USB_DEVICE(VENDOR_ID_REALTEK, 0x0414) }, /* RTS5414 USB 3.2 */
diff --git a/drivers/usb/misc/onboard_usb_hub.h b/drivers/usb/misc/onboard_usb_hub.h
index c4e24a7b92904c..292110e64a1d91 100644
--- a/drivers/usb/misc/onboard_usb_hub.h
+++ b/drivers/usb/misc/onboard_usb_hub.h
@@ -16,6 +16,11 @@ static const struct onboard_hub_pdata microchip_usb424_data = {
 	.num_supplies = 1,
 };
 
+static const struct onboard_hub_pdata microchip_usb5744_data = {
+	.reset_us = 0,
+	.num_supplies = 2,
+};
+
 static const struct onboard_hub_pdata realtek_rts5411_data = {
 	.reset_us = 0,
 	.num_supplies = 1,
@@ -50,6 +55,8 @@ static const struct of_device_id onboard_hub_match[] = {
 	{ .compatible = "usb424,2412", .data = &microchip_usb424_data, },
 	{ .compatible = "usb424,2514", .data = &microchip_usb424_data, },
 	{ .compatible = "usb424,2517", .data = &microchip_usb424_data, },
+	{ .compatible = "usb424,2744", .data = &microchip_usb5744_data, },
+	{ .compatible = "usb424,5744", .data = &microchip_usb5744_data, },
 	{ .compatible = "usb451,8140", .data = &ti_tusb8041_data, },
 	{ .compatible = "usb451,8142", .data = &ti_tusb8041_data, },
 	{ .compatible = "usb4b4,6504", .data = &cypress_hx3_data, },
diff --git a/drivers/usb/misc/usb-ljca.c b/drivers/usb/misc/usb-ljca.c
index c9decd0396d499..35770e608c6497 100644
--- a/drivers/usb/misc/usb-ljca.c
+++ b/drivers/usb/misc/usb-ljca.c
@@ -457,8 +457,8 @@ static void ljca_auxdev_acpi_bind(struct ljca_adapter *adap,
 				  u64 adr, u8 id)
 {
 	struct ljca_match_ids_walk_data wd = { 0 };
-	struct acpi_device *parent, *adev;
 	struct device *dev = adap->dev;
+	struct acpi_device *parent;
 	char uid[4];
 
 	parent = ACPI_COMPANION(dev);
@@ -466,17 +466,7 @@ static void ljca_auxdev_acpi_bind(struct ljca_adapter *adap,
 		return;
 
 	/*
-	 * get auxdev ACPI handle from the ACPI device directly
-	 * under the parent that matches _ADR.
-	 */
-	adev = acpi_find_child_device(parent, adr, false);
-	if (adev) {
-		ACPI_COMPANION_SET(&auxdev->dev, adev);
-		return;
-	}
-
-	/*
-	 * _ADR is a grey area in the ACPI specification, some
+	 * Currently LJCA hw doesn't use _ADR instead the shipped
 	 * platforms use _HID to distinguish children devices.
 	 */
 	switch (adr) {
@@ -656,10 +646,11 @@ static int ljca_enumerate_spi(struct ljca_adapter *adap)
 	unsigned int i;
 	int ret;
 
+	/* Not all LJCA chips implement SPI, a timeout reading the descriptors is normal */
 	ret = ljca_send(adap, LJCA_CLIENT_MNG, LJCA_MNG_ENUM_SPI, NULL, 0, buf,
 			sizeof(buf), true, LJCA_ENUM_CLIENT_TIMEOUT_MS);
 	if (ret < 0)
-		return ret;
+		return (ret == -ETIMEDOUT) ? 0 : ret;
 
 	/* check firmware response */
 	desc = (struct ljca_spi_descriptor *)buf;
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 1bf23611be1221..13a56783830df2 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1033,9 +1033,9 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, ACTISENSE_USG_PID) },
 	{ USB_DEVICE(FTDI_VID, ACTISENSE_NGT_PID) },
 	{ USB_DEVICE(FTDI_VID, ACTISENSE_NGW_PID) },
-	{ USB_DEVICE(FTDI_VID, ACTISENSE_D9AC_PID) },
-	{ USB_DEVICE(FTDI_VID, ACTISENSE_D9AD_PID) },
-	{ USB_DEVICE(FTDI_VID, ACTISENSE_D9AE_PID) },
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_UID_PID) },
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_USA_PID) },
+	{ USB_DEVICE(FTDI_VID, ACTISENSE_NGX_PID) },
 	{ USB_DEVICE(FTDI_VID, ACTISENSE_D9AF_PID) },
 	{ USB_DEVICE(FTDI_VID, CHETCO_SEAGAUGE_PID) },
 	{ USB_DEVICE(FTDI_VID, CHETCO_SEASWITCH_PID) },
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index e2099445db708f..21a2b5a25fc097 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -1568,9 +1568,9 @@
 #define ACTISENSE_USG_PID		0xD9A9 /* USG USB Serial Adapter */
 #define ACTISENSE_NGT_PID		0xD9AA /* NGT NMEA2000 Interface */
 #define ACTISENSE_NGW_PID		0xD9AB /* NGW NMEA2000 Gateway */
-#define ACTISENSE_D9AC_PID		0xD9AC /* Actisense Reserved */
-#define ACTISENSE_D9AD_PID		0xD9AD /* Actisense Reserved */
-#define ACTISENSE_D9AE_PID		0xD9AE /* Actisense Reserved */
+#define ACTISENSE_UID_PID		0xD9AC /* USB Isolating Device */
+#define ACTISENSE_USA_PID		0xD9AD /* USB to Serial Adapter */
+#define ACTISENSE_NGX_PID		0xD9AE /* NGX NMEA2000 Gateway */
 #define ACTISENSE_D9AF_PID		0xD9AF /* Actisense Reserved */
 #define CHETCO_SEAGAUGE_PID		0xA548 /* SeaGauge USB Adapter */
 #define CHETCO_SEASWITCH_PID		0xA549 /* SeaSwitch USB Adapter */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 45dcfaadaf98eb..72390dbf076928 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -203,8 +203,8 @@ static void option_instat_callback(struct urb *urb);
 #define DELL_PRODUCT_5829E_ESIM			0x81e4
 #define DELL_PRODUCT_5829E			0x81e6
 
-#define DELL_PRODUCT_FM101R			0x8213
-#define DELL_PRODUCT_FM101R_ESIM		0x8215
+#define DELL_PRODUCT_FM101R_ESIM		0x8213
+#define DELL_PRODUCT_FM101R			0x8215
 
 #define KYOCERA_VENDOR_ID			0x0c88
 #define KYOCERA_PRODUCT_KPC650			0x17da
@@ -272,6 +272,7 @@ static void option_instat_callback(struct urb *urb);
 #define QUECTEL_PRODUCT_RM500Q			0x0800
 #define QUECTEL_PRODUCT_RM520N			0x0801
 #define QUECTEL_PRODUCT_EC200U			0x0901
+#define QUECTEL_PRODUCT_EG912Y			0x6001
 #define QUECTEL_PRODUCT_EC200S_CN		0x6002
 #define QUECTEL_PRODUCT_EC200A			0x6005
 #define QUECTEL_PRODUCT_EM061K_LWW		0x6008
@@ -609,6 +610,8 @@ static void option_instat_callback(struct urb *urb);
 #define UNISOC_VENDOR_ID			0x1782
 /* TOZED LT70-C based on UNISOC SL8563 uses UNISOC's vendor ID */
 #define TOZED_PRODUCT_LT70C			0x4055
+/* Luat Air72*U series based on UNISOC UIS8910 uses UNISOC's vendor ID */
+#define LUAT_PRODUCT_AIR720U			0x4e00
 
 /* Device flags */
 
@@ -1230,6 +1233,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, 0x0700, 0xff), /* BG95 */
 	  .driver_info = RSVD(3) | ZLP },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x30) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x10),
 	  .driver_info = ZLP },
@@ -1242,6 +1246,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200U, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG912Y, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500K, 0xff, 0x00, 0x00) },
 
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
@@ -1546,7 +1551,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0165, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0167, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(4) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0189, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0189, 0xff, 0xff, 0xff),
+	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0191, 0xff, 0xff, 0xff), /* ZTE EuFi890 */
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0196, 0xff, 0xff, 0xff) },
@@ -2239,6 +2245,8 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(0) | RSVD(1) | RSVD(6) },
 	{ USB_DEVICE(0x0489, 0xe0b5),						/* Foxconn T77W968 ESIM */
 	  .driver_info = RSVD(0) | RSVD(1) | RSVD(6) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0da, 0xff),                     /* Foxconn T99W265 MBIM variant */
+	  .driver_info = RSVD(3) | RSVD(5) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0db, 0xff),			/* Foxconn T99W265 MBIM */
 	  .driver_info = RSVD(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0ee, 0xff),			/* Foxconn T99W368 MBIM */
@@ -2249,6 +2257,7 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(4) | RSVD(5) | RSVD(6) },
 	{ USB_DEVICE(0x1782, 0x4d10) },						/* Fibocom L610 (AT mode) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x1782, 0x4d11, 0xff) },			/* Fibocom L610 (ECM/RNDIS mode) */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x0001, 0xff, 0xff, 0xff) },	/* Fibocom L716-EU (ECM/RNDIS mode) */
 	{ USB_DEVICE(0x2cb7, 0x0104),						/* Fibocom NL678 series */
 	  .driver_info = RSVD(4) | RSVD(5) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0105, 0xff),			/* Fibocom NL678 series */
@@ -2271,6 +2280,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) },
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 20dcbccb290b36..fd68204374f2ce 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1306,6 +1306,17 @@ UNUSUAL_DEV(  0x090c, 0x6000, 0x0100, 0x0100,
 		US_FL_INITIAL_READ10 ),
 
 /*
+ * Patch by Tasos Sahanidis <tasos@tasossah.com>
+ * This flash drive always shows up with write protect enabled
+ * during the first mode sense.
+ */
+UNUSUAL_DEV(0x0951, 0x1697, 0x0100, 0x0100,
+		"Kingston",
+		"DT Ultimate G3",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_WP_DETECT),
+
+/*
  * This Pentax still camera is not conformant
  * to the USB storage specification: -
  * - It does not like the INQUIRY command. So we must handle this command
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 2e0451bd336e2b..16a670828dde19 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -267,7 +267,7 @@ static void typec_altmode_put_partner(struct altmode *altmode)
 	if (!partner)
 		return;
 
-	adev = &partner->adev;
+	adev = &altmode->adev;
 
 	if (is_typec_plug(adev->dev.parent)) {
 		struct typec_plug *plug = to_typec_plug(adev->dev.parent);
@@ -497,7 +497,8 @@ static void typec_altmode_release(struct device *dev)
 {
 	struct altmode *alt = to_altmode(to_typec_altmode(dev));
 
-	typec_altmode_put_partner(alt);
+	if (!is_typec_port(dev->parent))
+		typec_altmode_put_partner(alt);
 
 	altmode_id_remove(alt->adev.dev.parent, alt->id);
 	kfree(alt);
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 058d5b853b5749..bfb6f9481e87f7 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -4273,7 +4273,8 @@ static void run_state_machine(struct tcpm_port *port)
 				current_lim = PD_P_SNK_STDBY_MW / 5;
 			tcpm_set_current_limit(port, current_lim, 5000);
 			/* Not sink vbus if operational current is 0mA */
-			tcpm_set_charge(port, !!pdo_max_current(port->snk_pdo[0]));
+			tcpm_set_charge(port, !port->pd_supported ||
+					pdo_max_current(port->snk_pdo[0]));
 
 			if (!port->pd_supported)
 				tcpm_set_state(port, SNK_READY, 0);
@@ -5391,6 +5392,15 @@ static void _tcpm_pd_hard_reset(struct tcpm_port *port)
 	if (port->bist_request == BDO_MODE_TESTDATA && port->tcpc->set_bist_data)
 		port->tcpc->set_bist_data(port->tcpc, false);
 
+	switch (port->state) {
+	case ERROR_RECOVERY:
+	case PORT_RESET:
+	case PORT_RESET_WAIT_OFF:
+		return;
+	default:
+		break;
+	}
+
 	if (port->ams != NONE_AMS)
 		port->ams = NONE_AMS;
 	if (port->hard_reset_count < PD_N_HARD_RESET_COUNT)
diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c
index 0e867f531d344b..196535ad996d08 100644
--- a/drivers/usb/typec/tipd/core.c
+++ b/drivers/usb/typec/tipd/core.c
@@ -968,16 +968,17 @@ static int tps25750_start_patch_burst_mode(struct tps6598x *tps)
 	ret = of_property_match_string(np, "reg-names", "patch-address");
 	if (ret < 0) {
 		dev_err(tps->dev, "failed to get patch-address %d\n", ret);
-		return ret;
+		goto release_fw;
 	}
 
 	ret = of_property_read_u32_index(np, "reg", ret, &addr);
 	if (ret)
-		return ret;
+		goto release_fw;
 
 	if (addr == 0 || (addr >= 0x20 && addr <= 0x23)) {
 		dev_err(tps->dev, "wrong patch address %u\n", addr);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto release_fw;
 	}
 
 	bpms_data.addr = (u8)addr;
@@ -1226,7 +1227,10 @@ static int tps6598x_probe(struct i2c_client *client)
 			TPS_REG_INT_PLUG_EVENT;
 	}
 
-	tps->data = device_get_match_data(tps->dev);
+	if (dev_fwnode(tps->dev))
+		tps->data = device_get_match_data(tps->dev);
+	else
+		tps->data = i2c_get_match_data(client);
 	if (!tps->data)
 		return -EINVAL;
 
@@ -1425,7 +1429,7 @@ static const struct of_device_id tps6598x_of_match[] = {
 MODULE_DEVICE_TABLE(of, tps6598x_of_match);
 
 static const struct i2c_device_id tps6598x_id[] = {
-	{ "tps6598x" },
+	{ "tps6598x", (kernel_ulong_t)&tps6598x_data },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, tps6598x_id);
diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c
index db6e248f820831..4853141cd10c85 100644
--- a/drivers/usb/typec/ucsi/ucsi_glink.c
+++ b/drivers/usb/typec/ucsi/ucsi_glink.c
@@ -228,7 +228,7 @@ static void pmic_glink_ucsi_notify(struct work_struct *work)
 
 	con_num = UCSI_CCI_CONNECTOR(cci);
 	if (con_num) {
-		if (con_num < PMIC_GLINK_MAX_PORTS &&
+		if (con_num <= PMIC_GLINK_MAX_PORTS &&
 		    ucsi->port_orientation[con_num - 1]) {
 			int orientation = gpiod_get_value(ucsi->port_orientation[con_num - 1]);
 
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 12ac3397f39b81..26ba7da6b41062 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -2815,13 +2815,18 @@ static int setup_cvq_vring(struct mlx5_vdpa_dev *mvdev)
 	struct mlx5_control_vq *cvq = &mvdev->cvq;
 	int err = 0;
 
-	if (mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ))
+	if (mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ)) {
+		u16 idx = cvq->vring.last_avail_idx;
+
 		err = vringh_init_iotlb(&cvq->vring, mvdev->actual_features,
 					MLX5_CVQ_MAX_ENT, false,
 					(struct vring_desc *)(uintptr_t)cvq->desc_addr,
 					(struct vring_avail *)(uintptr_t)cvq->driver_addr,
 					(struct vring_used *)(uintptr_t)cvq->device_addr);
 
+		if (!err)
+			cvq->vring.last_avail_idx = cvq->vring.last_used_idx = idx;
+	}
 	return err;
 }
 
diff --git a/drivers/vdpa/pds/debugfs.c b/drivers/vdpa/pds/debugfs.c
index 9b04aad6ec35d7..c328e694f6e7f0 100644
--- a/drivers/vdpa/pds/debugfs.c
+++ b/drivers/vdpa/pds/debugfs.c
@@ -261,7 +261,7 @@ void pds_vdpa_debugfs_add_vdpadev(struct pds_vdpa_aux *vdpa_aux)
 	debugfs_create_file("config", 0400, vdpa_aux->dentry, vdpa_aux->pdsv, &config_fops);
 
 	for (i = 0; i < vdpa_aux->pdsv->num_vqs; i++) {
-		char name[8];
+		char name[16];
 
 		snprintf(name, sizeof(name), "vq%02d", i);
 		debugfs_create_file(name, 0400, vdpa_aux->dentry,
diff --git a/drivers/vdpa/pds/vdpa_dev.c b/drivers/vdpa/pds/vdpa_dev.c
index 52b2449182ad71..25c0fe5ec3d5df 100644
--- a/drivers/vdpa/pds/vdpa_dev.c
+++ b/drivers/vdpa/pds/vdpa_dev.c
@@ -318,9 +318,8 @@ static int pds_vdpa_set_driver_features(struct vdpa_device *vdpa_dev, u64 featur
 		return -EOPNOTSUPP;
 	}
 
-	pdsv->negotiated_features = nego_features;
-
 	driver_features = pds_vdpa_get_driver_features(vdpa_dev);
+	pdsv->negotiated_features = nego_features;
 	dev_dbg(dev, "%s: %#llx => %#llx\n",
 		__func__, driver_features, nego_features);
 
@@ -461,8 +460,10 @@ static void pds_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status)
 
 	pds_vdpa_cmd_set_status(pdsv, status);
 
-	/* Note: still working with FW on the need for this reset cmd */
 	if (status == 0) {
+		struct vdpa_callback null_cb = { };
+
+		pds_vdpa_set_config_cb(vdpa_dev, &null_cb);
 		pds_vdpa_cmd_reset(pdsv);
 
 		for (i = 0; i < pdsv->num_vqs; i++) {
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
index b3a3cb16579552..b137f367934393 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
@@ -437,7 +437,7 @@ static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
 	if (blk->shared_backend) {
 		blk->buffer = shared_buffer;
 	} else {
-		blk->buffer = kvmalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT,
+		blk->buffer = kvzalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT,
 				       GFP_KERNEL);
 		if (!blk->buffer) {
 			ret = -ENOMEM;
@@ -495,7 +495,7 @@ static int __init vdpasim_blk_init(void)
 		goto parent_err;
 
 	if (shared_backend) {
-		shared_buffer = kvmalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT,
+		shared_buffer = kvzalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT,
 					 GFP_KERNEL);
 		if (!shared_buffer) {
 			ret = -ENOMEM;
diff --git a/drivers/vfio/pci/pds/pci_drv.c b/drivers/vfio/pci/pds/pci_drv.c
index dd8c00c895a2ee..a34dda51662935 100644
--- a/drivers/vfio/pci/pds/pci_drv.c
+++ b/drivers/vfio/pci/pds/pci_drv.c
@@ -55,10 +55,10 @@ static void pds_vfio_recovery(struct pds_vfio_pci_device *pds_vfio)
 	 * VFIO_DEVICE_STATE_RUNNING.
 	 */
 	if (deferred_reset_needed) {
-		spin_lock(&pds_vfio->reset_lock);
+		mutex_lock(&pds_vfio->reset_mutex);
 		pds_vfio->deferred_reset = true;
 		pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_ERROR;
-		spin_unlock(&pds_vfio->reset_lock);
+		mutex_unlock(&pds_vfio->reset_mutex);
 	}
 }
 
diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c
index 649b18ee394bb7..4c351c59d05a93 100644
--- a/drivers/vfio/pci/pds/vfio_dev.c
+++ b/drivers/vfio/pci/pds/vfio_dev.c
@@ -29,7 +29,7 @@ struct pds_vfio_pci_device *pds_vfio_pci_drvdata(struct pci_dev *pdev)
 void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio)
 {
 again:
-	spin_lock(&pds_vfio->reset_lock);
+	mutex_lock(&pds_vfio->reset_mutex);
 	if (pds_vfio->deferred_reset) {
 		pds_vfio->deferred_reset = false;
 		if (pds_vfio->state == VFIO_DEVICE_STATE_ERROR) {
@@ -39,23 +39,23 @@ again:
 		}
 		pds_vfio->state = pds_vfio->deferred_reset_state;
 		pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
-		spin_unlock(&pds_vfio->reset_lock);
+		mutex_unlock(&pds_vfio->reset_mutex);
 		goto again;
 	}
 	mutex_unlock(&pds_vfio->state_mutex);
-	spin_unlock(&pds_vfio->reset_lock);
+	mutex_unlock(&pds_vfio->reset_mutex);
 }
 
 void pds_vfio_reset(struct pds_vfio_pci_device *pds_vfio)
 {
-	spin_lock(&pds_vfio->reset_lock);
+	mutex_lock(&pds_vfio->reset_mutex);
 	pds_vfio->deferred_reset = true;
 	pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
 	if (!mutex_trylock(&pds_vfio->state_mutex)) {
-		spin_unlock(&pds_vfio->reset_lock);
+		mutex_unlock(&pds_vfio->reset_mutex);
 		return;
 	}
-	spin_unlock(&pds_vfio->reset_lock);
+	mutex_unlock(&pds_vfio->reset_mutex);
 	pds_vfio_state_mutex_unlock(pds_vfio);
 }
 
@@ -155,6 +155,9 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
 
 	pds_vfio->vf_id = vf_id;
 
+	mutex_init(&pds_vfio->state_mutex);
+	mutex_init(&pds_vfio->reset_mutex);
+
 	vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P;
 	vdev->mig_ops = &pds_vfio_lm_ops;
 	vdev->log_ops = &pds_vfio_log_ops;
@@ -168,6 +171,17 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
 	return 0;
 }
 
+static void pds_vfio_release_device(struct vfio_device *vdev)
+{
+	struct pds_vfio_pci_device *pds_vfio =
+		container_of(vdev, struct pds_vfio_pci_device,
+			     vfio_coredev.vdev);
+
+	mutex_destroy(&pds_vfio->state_mutex);
+	mutex_destroy(&pds_vfio->reset_mutex);
+	vfio_pci_core_release_dev(vdev);
+}
+
 static int pds_vfio_open_device(struct vfio_device *vdev)
 {
 	struct pds_vfio_pci_device *pds_vfio =
@@ -179,7 +193,6 @@ static int pds_vfio_open_device(struct vfio_device *vdev)
 	if (err)
 		return err;
 
-	mutex_init(&pds_vfio->state_mutex);
 	pds_vfio->state = VFIO_DEVICE_STATE_RUNNING;
 	pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
 
@@ -199,14 +212,13 @@ static void pds_vfio_close_device(struct vfio_device *vdev)
 	pds_vfio_put_save_file(pds_vfio);
 	pds_vfio_dirty_disable(pds_vfio, true);
 	mutex_unlock(&pds_vfio->state_mutex);
-	mutex_destroy(&pds_vfio->state_mutex);
 	vfio_pci_core_close_device(vdev);
 }
 
 static const struct vfio_device_ops pds_vfio_ops = {
 	.name = "pds-vfio",
 	.init = pds_vfio_init_device,
-	.release = vfio_pci_core_release_dev,
+	.release = pds_vfio_release_device,
 	.open_device = pds_vfio_open_device,
 	.close_device = pds_vfio_close_device,
 	.ioctl = vfio_pci_core_ioctl,
diff --git a/drivers/vfio/pci/pds/vfio_dev.h b/drivers/vfio/pci/pds/vfio_dev.h
index b8f2d667608f3b..e7b01080a1ec3a 100644
--- a/drivers/vfio/pci/pds/vfio_dev.h
+++ b/drivers/vfio/pci/pds/vfio_dev.h
@@ -18,7 +18,7 @@ struct pds_vfio_pci_device {
 	struct pds_vfio_dirty dirty;
 	struct mutex state_mutex; /* protect migration state */
 	enum vfio_device_mig_state state;
-	spinlock_t reset_lock; /* protect reset_done flow */
+	struct mutex reset_mutex; /* protect reset_done flow */
 	u8 deferred_reset;
 	enum vfio_device_mig_state deferred_reset_state;
 	struct notifier_block nb;
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 30df5c58db73a8..da7ec77cdaff07 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -1582,7 +1582,6 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
 
 err:
 	put_device(&v->dev);
-	ida_simple_remove(&vhost_vdpa_ida, v->minor);
 	return r;
 }
 
diff --git a/drivers/video/fbdev/amifb.c b/drivers/video/fbdev/amifb.c
index b18c6b4f129a66..305f396c764c95 100644
--- a/drivers/video/fbdev/amifb.c
+++ b/drivers/video/fbdev/amifb.c
@@ -3752,7 +3752,7 @@ release:
 }
 
 
-static int __exit amifb_remove(struct platform_device *pdev)
+static void __exit amifb_remove(struct platform_device *pdev)
 {
 	struct fb_info *info = platform_get_drvdata(pdev);
 
@@ -3765,11 +3765,16 @@ static int __exit amifb_remove(struct platform_device *pdev)
 	chipfree();
 	framebuffer_release(info);
 	amifb_video_off();
-	return 0;
 }
 
-static struct platform_driver amifb_driver = {
-	.remove = __exit_p(amifb_remove),
+/*
+ * amifb_remove() lives in .exit.text. For drivers registered via
+ * module_platform_driver_probe() this ok because they cannot get unboud at
+ * runtime. The driver needs to be marked with __refdata, otherwise modpost
+ * triggers a section mismatch warning.
+ */
+static struct platform_driver amifb_driver __refdata = {
+	.remove_new = __exit_p(amifb_remove),
 	.driver   = {
 		.name	= "amiga-video",
 	},
diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c
index a908db23340986..9e391e5eaf9dae 100644
--- a/drivers/video/fbdev/atmel_lcdfb.c
+++ b/drivers/video/fbdev/atmel_lcdfb.c
@@ -220,7 +220,7 @@ static inline void atmel_lcdfb_power_control(struct atmel_lcdfb_info *sinfo, int
 	}
 }
 
-static const struct fb_fix_screeninfo atmel_lcdfb_fix __initconst = {
+static const struct fb_fix_screeninfo atmel_lcdfb_fix = {
 	.type		= FB_TYPE_PACKED_PIXELS,
 	.visual		= FB_VISUAL_TRUECOLOR,
 	.xpanstep	= 0,
@@ -841,7 +841,7 @@ static void atmel_lcdfb_task(struct work_struct *work)
 	atmel_lcdfb_reset(sinfo);
 }
 
-static int __init atmel_lcdfb_init_fbinfo(struct atmel_lcdfb_info *sinfo)
+static int atmel_lcdfb_init_fbinfo(struct atmel_lcdfb_info *sinfo)
 {
 	struct fb_info *info = sinfo->info;
 	int ret = 0;
@@ -1017,7 +1017,7 @@ put_display_node:
 	return ret;
 }
 
-static int __init atmel_lcdfb_probe(struct platform_device *pdev)
+static int atmel_lcdfb_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct fb_info *info;
@@ -1223,14 +1223,14 @@ out:
 	return ret;
 }
 
-static int __exit atmel_lcdfb_remove(struct platform_device *pdev)
+static void atmel_lcdfb_remove(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct fb_info *info = dev_get_drvdata(dev);
 	struct atmel_lcdfb_info *sinfo;
 
 	if (!info || !info->par)
-		return 0;
+		return;
 	sinfo = info->par;
 
 	cancel_work_sync(&sinfo->task);
@@ -1252,8 +1252,6 @@ static int __exit atmel_lcdfb_remove(struct platform_device *pdev)
 	}
 
 	framebuffer_release(info);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -1301,7 +1299,8 @@ static int atmel_lcdfb_resume(struct platform_device *pdev)
 #endif
 
 static struct platform_driver atmel_lcdfb_driver = {
-	.remove		= __exit_p(atmel_lcdfb_remove),
+	.probe		= atmel_lcdfb_probe,
+	.remove_new	= atmel_lcdfb_remove,
 	.suspend	= atmel_lcdfb_suspend,
 	.resume		= atmel_lcdfb_resume,
 	.driver		= {
@@ -1309,8 +1308,7 @@ static struct platform_driver atmel_lcdfb_driver = {
 		.of_match_table	= atmel_lcdfb_dt_ids,
 	},
 };
-
-module_platform_driver_probe(atmel_lcdfb_driver, atmel_lcdfb_probe);
+module_platform_driver(atmel_lcdfb_driver);
 
 MODULE_DESCRIPTION("AT91 LCD Controller framebuffer driver");
 MODULE_AUTHOR("Nicolas Ferre <nicolas.ferre@atmel.com>");
diff --git a/drivers/video/fbdev/fsl-diu-fb.c b/drivers/video/fbdev/fsl-diu-fb.c
index 7fbd9f069ac2ed..0bced82fa4940d 100644
--- a/drivers/video/fbdev/fsl-diu-fb.c
+++ b/drivers/video/fbdev/fsl-diu-fb.c
@@ -490,7 +490,7 @@ static enum fsl_diu_monitor_port fsl_diu_name_to_port(const char *s)
  * Workaround for failed writing desc register of planes.
  * Needed with MPC5121 DIU rev 2.0 silicon.
  */
-void wr_reg_wa(u32 *reg, u32 val)
+static void wr_reg_wa(u32 *reg, u32 val)
 {
 	do {
 		out_be32(reg, val);
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index bf59daf862fc71..a80939fe2ee6d1 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -1013,6 +1013,8 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 	} else if (IS_ENABLED(CONFIG_SYSFB)) {
 		base = screen_info.lfb_base;
 		size = screen_info.lfb_size;
+	} else {
+		goto err1;
 	}
 
 	/*
diff --git a/drivers/video/fbdev/imsttfb.c b/drivers/video/fbdev/imsttfb.c
index e7e03e920729dc..660499260f4651 100644
--- a/drivers/video/fbdev/imsttfb.c
+++ b/drivers/video/fbdev/imsttfb.c
@@ -1421,7 +1421,6 @@ static int init_imstt(struct fb_info *info)
 	if ((info->var.xres * info->var.yres) * (info->var.bits_per_pixel >> 3) > info->fix.smem_len
 	    || !(compute_imstt_regvals(par, info->var.xres, info->var.yres))) {
 		printk("imsttfb: %ux%ux%u not supported\n", info->var.xres, info->var.yres, info->var.bits_per_pixel);
-		framebuffer_release(info);
 		return -ENODEV;
 	}
 
@@ -1453,14 +1452,11 @@ static int init_imstt(struct fb_info *info)
 	              FBINFO_HWACCEL_FILLRECT |
 	              FBINFO_HWACCEL_YPAN;
 
-	if (fb_alloc_cmap(&info->cmap, 0, 0)) {
-		framebuffer_release(info);
+	if (fb_alloc_cmap(&info->cmap, 0, 0))
 		return -ENODEV;
-	}
 
 	if (register_framebuffer(info) < 0) {
 		fb_dealloc_cmap(&info->cmap);
-		framebuffer_release(info);
 		return -ENODEV;
 	}
 
@@ -1500,8 +1496,8 @@ static int imsttfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	if (!request_mem_region(addr, size, "imsttfb")) {
 		printk(KERN_ERR "imsttfb: Can't reserve memory region\n");
-		framebuffer_release(info);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto release_info;
 	}
 
 	switch (pdev->device) {
@@ -1518,36 +1514,39 @@ static int imsttfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			printk(KERN_INFO "imsttfb: Device 0x%x unknown, "
 					 "contact maintainer.\n", pdev->device);
 			ret = -ENODEV;
-			goto error;
+			goto release_mem_region;
 	}
 
 	info->fix.smem_start = addr;
 	info->screen_base = (__u8 *)ioremap(addr, par->ramdac == IBM ?
 					    0x400000 : 0x800000);
 	if (!info->screen_base)
-		goto error;
+		goto release_mem_region;
 	info->fix.mmio_start = addr + 0x800000;
 	par->dc_regs = ioremap(addr + 0x800000, 0x1000);
 	if (!par->dc_regs)
-		goto error;
+		goto unmap_screen_base;
 	par->cmap_regs_phys = addr + 0x840000;
 	par->cmap_regs = (__u8 *)ioremap(addr + 0x840000, 0x1000);
 	if (!par->cmap_regs)
-		goto error;
+		goto unmap_dc_regs;
 	info->pseudo_palette = par->palette;
 	ret = init_imstt(info);
 	if (ret)
-		goto error;
+		goto unmap_cmap_regs;
 
 	pci_set_drvdata(pdev, info);
-	return ret;
+	return 0;
 
-error:
-	if (par->dc_regs)
-		iounmap(par->dc_regs);
-	if (info->screen_base)
-		iounmap(info->screen_base);
+unmap_cmap_regs:
+	iounmap(par->cmap_regs);
+unmap_dc_regs:
+	iounmap(par->dc_regs);
+unmap_screen_base:
+	iounmap(info->screen_base);
+release_mem_region:
 	release_mem_region(addr, size);
+release_info:
 	framebuffer_release(info);
 	return ret;
 }
diff --git a/drivers/video/fbdev/offb.c b/drivers/video/fbdev/offb.c
index dcb1b81d35db57..b421b46d88efca 100644
--- a/drivers/video/fbdev/offb.c
+++ b/drivers/video/fbdev/offb.c
@@ -423,11 +423,9 @@ static void offb_init_fb(struct platform_device *parent, const char *name,
 	fix = &info->fix;
 	var = &info->var;
 
-	if (name) {
-		strcpy(fix->id, "OFfb ");
-		strncat(fix->id, name, sizeof(fix->id) - sizeof("OFfb "));
-		fix->id[sizeof(fix->id) - 1] = '\0';
-	} else
+	if (name)
+		snprintf(fix->id, sizeof(fix->id), "OFfb %s", name);
+	else
 		snprintf(fix->id, sizeof(fix->id), "OFfb %pOFn", dp);
 
 
diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c
index 42c96f1cfc93c4..694cf6318782bc 100644
--- a/drivers/video/fbdev/omap/omapfb_main.c
+++ b/drivers/video/fbdev/omap/omapfb_main.c
@@ -1643,17 +1643,16 @@ static int omapfb_do_probe(struct platform_device *pdev,
 		r = -ENOMEM;
 		goto cleanup;
 	}
-	fbdev->int_irq = platform_get_irq(pdev, 0);
-	if (fbdev->int_irq < 0) {
-		r = -ENXIO;
+
+	r = platform_get_irq(pdev, 0);
+	if (r < 0)
 		goto cleanup;
-	}
+	fbdev->int_irq = r;
 
-	fbdev->ext_irq = platform_get_irq(pdev, 1);
-	if (fbdev->ext_irq < 0) {
-		r = -ENXIO;
+	r = platform_get_irq(pdev, 1);
+	if (r < 0)
 		goto cleanup;
-	}
+	fbdev->ext_irq = r;
 
 	init_state++;
 
@@ -1857,20 +1856,13 @@ static int __init omapfb_setup(char *options)
 		if (!strncmp(this_opt, "accel", 5))
 			def_accel = 1;
 		else if (!strncmp(this_opt, "vram:", 5)) {
+			unsigned long long vram;
 			char *suffix;
-			unsigned long vram;
-			vram = (simple_strtoul(this_opt + 5, &suffix, 0));
+
+			vram = memparse(this_opt + 5, &suffix);
 			switch (suffix[0]) {
 			case '\0':
 				break;
-			case 'm':
-			case 'M':
-				vram *= 1024;
-				fallthrough;
-			case 'k':
-			case 'K':
-				vram *= 1024;
-				break;
 			default:
 				pr_debug("omapfb: invalid vram suffix %c\n",
 					 suffix[0]);
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/connector-analog-tv.c b/drivers/video/fbdev/omap2/omapfb/displays/connector-analog-tv.c
index 0daaf9f89bab5c..c6786726a1af1d 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/connector-analog-tv.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/connector-analog-tv.c
@@ -221,7 +221,7 @@ err_reg:
 	return r;
 }
 
-static int __exit tvc_remove(struct platform_device *pdev)
+static void tvc_remove(struct platform_device *pdev)
 {
 	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
 	struct omap_dss_device *dssdev = &ddata->dssdev;
@@ -233,8 +233,6 @@ static int __exit tvc_remove(struct platform_device *pdev)
 	tvc_disconnect(dssdev);
 
 	omap_dss_put_device(in);
-
-	return 0;
 }
 
 static const struct of_device_id tvc_of_match[] = {
@@ -247,11 +245,10 @@ MODULE_DEVICE_TABLE(of, tvc_of_match);
 
 static struct platform_driver tvc_connector_driver = {
 	.probe	= tvc_probe,
-	.remove	= __exit_p(tvc_remove),
+	.remove_new = tvc_remove,
 	.driver	= {
 		.name	= "connector-analog-tv",
 		.of_match_table = tvc_of_match,
-		.suppress_bind_attrs = true,
 	},
 };
 
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/connector-dvi.c b/drivers/video/fbdev/omap2/omapfb/displays/connector-dvi.c
index c8ad3ef42bd319..0cc9294f89b497 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/connector-dvi.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/connector-dvi.c
@@ -303,7 +303,7 @@ err_reg:
 	return r;
 }
 
-static int __exit dvic_remove(struct platform_device *pdev)
+static void dvic_remove(struct platform_device *pdev)
 {
 	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
 	struct omap_dss_device *dssdev = &ddata->dssdev;
@@ -317,8 +317,6 @@ static int __exit dvic_remove(struct platform_device *pdev)
 	omap_dss_put_device(in);
 
 	i2c_put_adapter(ddata->i2c_adapter);
-
-	return 0;
 }
 
 static const struct of_device_id dvic_of_match[] = {
@@ -330,11 +328,10 @@ MODULE_DEVICE_TABLE(of, dvic_of_match);
 
 static struct platform_driver dvi_connector_driver = {
 	.probe	= dvic_probe,
-	.remove	= __exit_p(dvic_remove),
+	.remove_new = dvic_remove,
 	.driver	= {
 		.name	= "connector-dvi",
 		.of_match_table = dvic_of_match,
-		.suppress_bind_attrs = true,
 	},
 };
 
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/connector-hdmi.c b/drivers/video/fbdev/omap2/omapfb/displays/connector-hdmi.c
index 8f9ff9fb4ca4c3..b862a32670aeff 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/connector-hdmi.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/connector-hdmi.c
@@ -249,7 +249,7 @@ err_reg:
 	return r;
 }
 
-static int __exit hdmic_remove(struct platform_device *pdev)
+static void hdmic_remove(struct platform_device *pdev)
 {
 	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
 	struct omap_dss_device *dssdev = &ddata->dssdev;
@@ -261,8 +261,6 @@ static int __exit hdmic_remove(struct platform_device *pdev)
 	hdmic_disconnect(dssdev);
 
 	omap_dss_put_device(in);
-
-	return 0;
 }
 
 static const struct of_device_id hdmic_of_match[] = {
@@ -274,11 +272,10 @@ MODULE_DEVICE_TABLE(of, hdmic_of_match);
 
 static struct platform_driver hdmi_connector_driver = {
 	.probe	= hdmic_probe,
-	.remove	= __exit_p(hdmic_remove),
+	.remove_new = hdmic_remove,
 	.driver	= {
 		.name	= "connector-hdmi",
 		.of_match_table = hdmic_of_match,
-		.suppress_bind_attrs = true,
 	},
 };
 
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/encoder-opa362.c b/drivers/video/fbdev/omap2/omapfb/displays/encoder-opa362.c
index dd29dc5c77ec8f..f0d3eb581166bd 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/encoder-opa362.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/encoder-opa362.c
@@ -231,7 +231,7 @@ err_reg:
 	return r;
 }
 
-static int __exit opa362_remove(struct platform_device *pdev)
+static void opa362_remove(struct platform_device *pdev)
 {
 	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
 	struct omap_dss_device *dssdev = &ddata->dssdev;
@@ -248,8 +248,6 @@ static int __exit opa362_remove(struct platform_device *pdev)
 		opa362_disconnect(dssdev, dssdev->dst);
 
 	omap_dss_put_device(in);
-
-	return 0;
 }
 
 static const struct of_device_id opa362_of_match[] = {
@@ -260,11 +258,10 @@ MODULE_DEVICE_TABLE(of, opa362_of_match);
 
 static struct platform_driver opa362_driver = {
 	.probe	= opa362_probe,
-	.remove	= __exit_p(opa362_remove),
+	.remove_new = opa362_remove,
 	.driver	= {
 		.name	= "amplifier-opa362",
 		.of_match_table = opa362_of_match,
-		.suppress_bind_attrs = true,
 	},
 };
 
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/encoder-tfp410.c b/drivers/video/fbdev/omap2/omapfb/displays/encoder-tfp410.c
index 7bac420169a69f..c8aca4592949cb 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/encoder-tfp410.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/encoder-tfp410.c
@@ -217,7 +217,7 @@ err_reg:
 	return r;
 }
 
-static int __exit tfp410_remove(struct platform_device *pdev)
+static void tfp410_remove(struct platform_device *pdev)
 {
 	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
 	struct omap_dss_device *dssdev = &ddata->dssdev;
@@ -234,8 +234,6 @@ static int __exit tfp410_remove(struct platform_device *pdev)
 		tfp410_disconnect(dssdev, dssdev->dst);
 
 	omap_dss_put_device(in);
-
-	return 0;
 }
 
 static const struct of_device_id tfp410_of_match[] = {
@@ -247,11 +245,10 @@ MODULE_DEVICE_TABLE(of, tfp410_of_match);
 
 static struct platform_driver tfp410_driver = {
 	.probe	= tfp410_probe,
-	.remove	= __exit_p(tfp410_remove),
+	.remove_new = tfp410_remove,
 	.driver	= {
 		.name	= "tfp410",
 		.of_match_table = tfp410_of_match,
-		.suppress_bind_attrs = true,
 	},
 };
 
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/encoder-tpd12s015.c b/drivers/video/fbdev/omap2/omapfb/displays/encoder-tpd12s015.c
index 67f0c9250e9e4c..eb3926d0361b9e 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/encoder-tpd12s015.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/encoder-tpd12s015.c
@@ -283,7 +283,7 @@ err_gpio:
 	return r;
 }
 
-static int __exit tpd_remove(struct platform_device *pdev)
+static void tpd_remove(struct platform_device *pdev)
 {
 	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
 	struct omap_dss_device *dssdev = &ddata->dssdev;
@@ -300,8 +300,6 @@ static int __exit tpd_remove(struct platform_device *pdev)
 		tpd_disconnect(dssdev, dssdev->dst);
 
 	omap_dss_put_device(in);
-
-	return 0;
 }
 
 static const struct of_device_id tpd_of_match[] = {
@@ -313,11 +311,10 @@ MODULE_DEVICE_TABLE(of, tpd_of_match);
 
 static struct platform_driver tpd_driver = {
 	.probe	= tpd_probe,
-	.remove	= __exit_p(tpd_remove),
+	.remove_new = tpd_remove,
 	.driver	= {
 		.name	= "tpd12s015",
 		.of_match_table = tpd_of_match,
-		.suppress_bind_attrs = true,
 	},
 };
 
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-dpi.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-dpi.c
index 9790053c5877c0..937f9091274f03 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/panel-dpi.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-dpi.c
@@ -211,7 +211,7 @@ err_reg:
 	return r;
 }
 
-static int __exit panel_dpi_remove(struct platform_device *pdev)
+static void panel_dpi_remove(struct platform_device *pdev)
 {
 	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
 	struct omap_dss_device *dssdev = &ddata->dssdev;
@@ -223,8 +223,6 @@ static int __exit panel_dpi_remove(struct platform_device *pdev)
 	panel_dpi_disconnect(dssdev);
 
 	omap_dss_put_device(in);
-
-	return 0;
 }
 
 static const struct of_device_id panel_dpi_of_match[] = {
@@ -236,11 +234,10 @@ MODULE_DEVICE_TABLE(of, panel_dpi_of_match);
 
 static struct platform_driver panel_dpi_driver = {
 	.probe = panel_dpi_probe,
-	.remove = __exit_p(panel_dpi_remove),
+	.remove_new = panel_dpi_remove,
 	.driver = {
 		.name = "panel-dpi",
 		.of_match_table = panel_dpi_of_match,
-		.suppress_bind_attrs = true,
 	},
 };
 
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c
index 77fce1223a6400..adb8881bac285c 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c
@@ -1241,7 +1241,7 @@ err_reg:
 	return r;
 }
 
-static int __exit dsicm_remove(struct platform_device *pdev)
+static void dsicm_remove(struct platform_device *pdev)
 {
 	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
 	struct omap_dss_device *dssdev = &ddata->dssdev;
@@ -1269,8 +1269,6 @@ static int __exit dsicm_remove(struct platform_device *pdev)
 
 	/* reset, to be sure that the panel is in a valid state */
 	dsicm_hw_reset(ddata);
-
-	return 0;
 }
 
 static const struct of_device_id dsicm_of_match[] = {
@@ -1282,11 +1280,10 @@ MODULE_DEVICE_TABLE(of, dsicm_of_match);
 
 static struct platform_driver dsicm_driver = {
 	.probe = dsicm_probe,
-	.remove = __exit_p(dsicm_remove),
+	.remove_new = dsicm_remove,
 	.driver = {
 		.name = "panel-dsi-cm",
 		.of_match_table = dsicm_of_match,
-		.suppress_bind_attrs = true,
 	},
 };
 
diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-sharp-ls037v7dw01.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-sharp-ls037v7dw01.c
index cc30758300e25b..e37268cf8dcaec 100644
--- a/drivers/video/fbdev/omap2/omapfb/displays/panel-sharp-ls037v7dw01.c
+++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-sharp-ls037v7dw01.c
@@ -292,7 +292,7 @@ err_reg:
 	return r;
 }
 
-static int __exit sharp_ls_remove(struct platform_device *pdev)
+static void sharp_ls_remove(struct platform_device *pdev)
 {
 	struct panel_drv_data *ddata = platform_get_drvdata(pdev);
 	struct omap_dss_device *dssdev = &ddata->dssdev;
@@ -304,8 +304,6 @@ static int __exit sharp_ls_remove(struct platform_device *pdev)
 	sharp_ls_disconnect(dssdev);
 
 	omap_dss_put_device(in);
-
-	return 0;
 }
 
 static const struct of_device_id sharp_ls_of_match[] = {
@@ -317,11 +315,10 @@ MODULE_DEVICE_TABLE(of, sharp_ls_of_match);
 
 static struct platform_driver sharp_ls_driver = {
 	.probe = sharp_ls_probe,
-	.remove = __exit_p(sharp_ls_remove),
+	.remove_new = sharp_ls_remove,
 	.driver = {
 		.name = "panel-sharp-ls037v7dw01",
 		.of_match_table = sharp_ls_of_match,
-		.suppress_bind_attrs = true,
 	},
 };
 
diff --git a/drivers/video/fbdev/omap2/omapfb/vrfb.c b/drivers/video/fbdev/omap2/omapfb/vrfb.c
index ee0dd4c6a6466a..568e6e1eca628e 100644
--- a/drivers/video/fbdev/omap2/omapfb/vrfb.c
+++ b/drivers/video/fbdev/omap2/omapfb/vrfb.c
@@ -368,17 +368,10 @@ static int __init vrfb_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static void __exit vrfb_remove(struct platform_device *pdev)
-{
-	vrfb_loaded = false;
-}
-
 static struct platform_driver vrfb_driver = {
 	.driver.name	= "omapvrfb",
-	.remove		= __exit_p(vrfb_remove),
 };
-
-module_platform_driver_probe(vrfb_driver, vrfb_probe);
+builtin_platform_driver_probe(vrfb_driver, vrfb_probe);
 
 MODULE_AUTHOR("Tomi Valkeinen <tomi.valkeinen@ti.com>");
 MODULE_DESCRIPTION("OMAP VRFB");
diff --git a/drivers/video/fbdev/via/viafbdev.c b/drivers/video/fbdev/via/viafbdev.c
index 58868f8880d655..a52b1ba43a4874 100644
--- a/drivers/video/fbdev/via/viafbdev.c
+++ b/drivers/video/fbdev/via/viafbdev.c
@@ -574,7 +574,7 @@ static int viafb_ioctl(struct fb_info *info, u_int cmd, u_long arg)
 		break;
 
 	case VIAFB_SET_GAMMA_LUT:
-		viafb_gamma_table = memdup_user(argp, 256 * sizeof(u32));
+		viafb_gamma_table = memdup_array_user(argp, 256, sizeof(u32));
 		if (IS_ERR(viafb_gamma_table))
 			return PTR_ERR(viafb_gamma_table);
 		viafb_set_gamma_table(viafb_bpp, viafb_gamma_table);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index c2524a7207cfae..7a5593997e0efe 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -242,7 +242,7 @@ void vp_del_vqs(struct virtio_device *vdev)
 			if (v != VIRTIO_MSI_NO_VECTOR) {
 				int irq = pci_irq_vector(vp_dev->pci_dev, v);
 
-				irq_set_affinity_hint(irq, NULL);
+				irq_update_affinity_hint(irq, NULL);
 				free_irq(irq, vq);
 			}
 		}
@@ -443,10 +443,10 @@ int vp_set_vq_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask)
 		mask = vp_dev->msix_affinity_masks[info->msix_vector];
 		irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector);
 		if (!cpu_mask)
-			irq_set_affinity_hint(irq, NULL);
+			irq_update_affinity_hint(irq, NULL);
 		else {
 			cpumask_copy(mask, cpu_mask);
-			irq_set_affinity_hint(irq, mask);
+			irq_set_affinity_and_hint(irq, mask);
 		}
 	}
 	return 0;
diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
index e2a1fe7bb66cc9..7de8b1ebabac42 100644
--- a/drivers/virtio/virtio_pci_modern_dev.c
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -294,9 +294,10 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 
 	err = -EINVAL;
 	mdev->common = vp_modern_map_capability(mdev, common,
-				      sizeof(struct virtio_pci_common_cfg), 4,
-				      0, sizeof(struct virtio_pci_modern_common_cfg),
-				      &mdev->common_len, NULL);
+			      sizeof(struct virtio_pci_common_cfg), 4, 0,
+			      offsetofend(struct virtio_pci_modern_common_cfg,
+					  queue_reset),
+			      &mdev->common_len, NULL);
 	if (!mdev->common)
 		goto err_map_common;
 	mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1,
diff --git a/drivers/vlynq/Kconfig b/drivers/vlynq/Kconfig
deleted file mode 100644
index e7f9492a0b048c..00000000000000
--- a/drivers/vlynq/Kconfig
+++ /dev/null
@@ -1,21 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-menu "TI VLYNQ"
-	depends on AR7
-
-config VLYNQ
-	bool "TI VLYNQ bus support"
-	help
-	  Support for Texas Instruments(R) VLYNQ bus.
-	  The VLYNQ bus is a high-speed, serial and packetized
-	  data bus which allows external peripherals of a SoC
-	  to appear into the system's main memory.
-
-	  If unsure, say N
-
-config VLYNQ_DEBUG
-	bool "VLYNQ bus debug"
-	depends on VLYNQ && DEBUG_KERNEL
-	help
-	  Turn on VLYNQ bus debugging.
-
-endmenu
diff --git a/drivers/vlynq/Makefile b/drivers/vlynq/Makefile
deleted file mode 100644
index d9ce5b2b5ce0fa..00000000000000
--- a/drivers/vlynq/Makefile
+++ /dev/null
@@ -1,6 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile for kernel vlynq drivers
-#
-
-obj-$(CONFIG_VLYNQ) += vlynq.o
diff --git a/drivers/vlynq/vlynq.c b/drivers/vlynq/vlynq.c
deleted file mode 100644
index 4af6615808cc51..00000000000000
--- a/drivers/vlynq/vlynq.c
+++ /dev/null
@@ -1,799 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2006, 2007 Eugene Konev <ejka@openwrt.org>
- *
- * Parts of the VLYNQ specification can be found here:
- * http://www.ti.com/litv/pdf/sprue36a
- */
-
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/device.h>
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/platform_device.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <linux/slab.h>
-#include <linux/irq.h>
-
-#include <linux/vlynq.h>
-
-#define VLYNQ_CTRL_PM_ENABLE		0x80000000
-#define VLYNQ_CTRL_CLOCK_INT		0x00008000
-#define VLYNQ_CTRL_CLOCK_DIV(x)		(((x) & 7) << 16)
-#define VLYNQ_CTRL_INT_LOCAL		0x00004000
-#define VLYNQ_CTRL_INT_ENABLE		0x00002000
-#define VLYNQ_CTRL_INT_VECTOR(x)	(((x) & 0x1f) << 8)
-#define VLYNQ_CTRL_INT2CFG		0x00000080
-#define VLYNQ_CTRL_RESET		0x00000001
-
-#define VLYNQ_CTRL_CLOCK_MASK          (0x7 << 16)
-
-#define VLYNQ_INT_OFFSET		0x00000014
-#define VLYNQ_REMOTE_OFFSET		0x00000080
-
-#define VLYNQ_STATUS_LINK		0x00000001
-#define VLYNQ_STATUS_LERROR		0x00000080
-#define VLYNQ_STATUS_RERROR		0x00000100
-
-#define VINT_ENABLE			0x00000100
-#define VINT_TYPE_EDGE			0x00000080
-#define VINT_LEVEL_LOW			0x00000040
-#define VINT_VECTOR(x)			((x) & 0x1f)
-#define VINT_OFFSET(irq)		(8 * ((irq) % 4))
-
-#define VLYNQ_AUTONEGO_V2		0x00010000
-
-struct vlynq_regs {
-	u32 revision;
-	u32 control;
-	u32 status;
-	u32 int_prio;
-	u32 int_status;
-	u32 int_pending;
-	u32 int_ptr;
-	u32 tx_offset;
-	struct vlynq_mapping rx_mapping[4];
-	u32 chip;
-	u32 autonego;
-	u32 unused[6];
-	u32 int_device[8];
-};
-
-#ifdef CONFIG_VLYNQ_DEBUG
-static void vlynq_dump_regs(struct vlynq_device *dev)
-{
-	int i;
-
-	printk(KERN_DEBUG "VLYNQ local=%p remote=%p\n",
-			dev->local, dev->remote);
-	for (i = 0; i < 32; i++) {
-		printk(KERN_DEBUG "VLYNQ: local %d: %08x\n",
-			i + 1, ((u32 *)dev->local)[i]);
-		printk(KERN_DEBUG "VLYNQ: remote %d: %08x\n",
-			i + 1, ((u32 *)dev->remote)[i]);
-	}
-}
-
-static void vlynq_dump_mem(u32 *base, int count)
-{
-	int i;
-
-	for (i = 0; i < (count + 3) / 4; i++) {
-		if (i % 4 == 0)
-			printk(KERN_DEBUG "\nMEM[0x%04x]:", i * 4);
-		printk(KERN_DEBUG " 0x%08x", *(base + i));
-	}
-	printk(KERN_DEBUG "\n");
-}
-#endif
-
-/* Check the VLYNQ link status with a given device */
-static int vlynq_linked(struct vlynq_device *dev)
-{
-	int i;
-
-	for (i = 0; i < 100; i++)
-		if (readl(&dev->local->status) & VLYNQ_STATUS_LINK)
-			return 1;
-		else
-			cpu_relax();
-
-	return 0;
-}
-
-static void vlynq_reset(struct vlynq_device *dev)
-{
-	writel(readl(&dev->local->control) | VLYNQ_CTRL_RESET,
-			&dev->local->control);
-
-	/* Wait for the devices to finish resetting */
-	msleep(5);
-
-	/* Remove reset bit */
-	writel(readl(&dev->local->control) & ~VLYNQ_CTRL_RESET,
-			&dev->local->control);
-
-	/* Give some time for the devices to settle */
-	msleep(5);
-}
-
-static void vlynq_irq_unmask(struct irq_data *d)
-{
-	struct vlynq_device *dev = irq_data_get_irq_chip_data(d);
-	int virq;
-	u32 val;
-
-	BUG_ON(!dev);
-	virq = d->irq - dev->irq_start;
-	val = readl(&dev->remote->int_device[virq >> 2]);
-	val |= (VINT_ENABLE | virq) << VINT_OFFSET(virq);
-	writel(val, &dev->remote->int_device[virq >> 2]);
-}
-
-static void vlynq_irq_mask(struct irq_data *d)
-{
-	struct vlynq_device *dev = irq_data_get_irq_chip_data(d);
-	int virq;
-	u32 val;
-
-	BUG_ON(!dev);
-	virq = d->irq - dev->irq_start;
-	val = readl(&dev->remote->int_device[virq >> 2]);
-	val &= ~(VINT_ENABLE << VINT_OFFSET(virq));
-	writel(val, &dev->remote->int_device[virq >> 2]);
-}
-
-static int vlynq_irq_type(struct irq_data *d, unsigned int flow_type)
-{
-	struct vlynq_device *dev = irq_data_get_irq_chip_data(d);
-	int virq;
-	u32 val;
-
-	BUG_ON(!dev);
-	virq = d->irq - dev->irq_start;
-	val = readl(&dev->remote->int_device[virq >> 2]);
-	switch (flow_type & IRQ_TYPE_SENSE_MASK) {
-	case IRQ_TYPE_EDGE_RISING:
-	case IRQ_TYPE_EDGE_FALLING:
-	case IRQ_TYPE_EDGE_BOTH:
-		val |= VINT_TYPE_EDGE << VINT_OFFSET(virq);
-		val &= ~(VINT_LEVEL_LOW << VINT_OFFSET(virq));
-		break;
-	case IRQ_TYPE_LEVEL_HIGH:
-		val &= ~(VINT_TYPE_EDGE << VINT_OFFSET(virq));
-		val &= ~(VINT_LEVEL_LOW << VINT_OFFSET(virq));
-		break;
-	case IRQ_TYPE_LEVEL_LOW:
-		val &= ~(VINT_TYPE_EDGE << VINT_OFFSET(virq));
-		val |= VINT_LEVEL_LOW << VINT_OFFSET(virq);
-		break;
-	default:
-		return -EINVAL;
-	}
-	writel(val, &dev->remote->int_device[virq >> 2]);
-	return 0;
-}
-
-static void vlynq_local_ack(struct irq_data *d)
-{
-	struct vlynq_device *dev = irq_data_get_irq_chip_data(d);
-	u32 status = readl(&dev->local->status);
-
-	pr_debug("%s: local status: 0x%08x\n",
-		       dev_name(&dev->dev), status);
-	writel(status, &dev->local->status);
-}
-
-static void vlynq_remote_ack(struct irq_data *d)
-{
-	struct vlynq_device *dev = irq_data_get_irq_chip_data(d);
-	u32 status = readl(&dev->remote->status);
-
-	pr_debug("%s: remote status: 0x%08x\n",
-		       dev_name(&dev->dev), status);
-	writel(status, &dev->remote->status);
-}
-
-static irqreturn_t vlynq_irq(int irq, void *dev_id)
-{
-	struct vlynq_device *dev = dev_id;
-	u32 status;
-	int virq = 0;
-
-	status = readl(&dev->local->int_status);
-	writel(status, &dev->local->int_status);
-
-	if (unlikely(!status))
-		spurious_interrupt();
-
-	while (status) {
-		if (status & 1)
-			do_IRQ(dev->irq_start + virq);
-		status >>= 1;
-		virq++;
-	}
-
-	return IRQ_HANDLED;
-}
-
-static struct irq_chip vlynq_irq_chip = {
-	.name = "vlynq",
-	.irq_unmask = vlynq_irq_unmask,
-	.irq_mask = vlynq_irq_mask,
-	.irq_set_type = vlynq_irq_type,
-};
-
-static struct irq_chip vlynq_local_chip = {
-	.name = "vlynq local error",
-	.irq_unmask = vlynq_irq_unmask,
-	.irq_mask = vlynq_irq_mask,
-	.irq_ack = vlynq_local_ack,
-};
-
-static struct irq_chip vlynq_remote_chip = {
-	.name = "vlynq local error",
-	.irq_unmask = vlynq_irq_unmask,
-	.irq_mask = vlynq_irq_mask,
-	.irq_ack = vlynq_remote_ack,
-};
-
-static int vlynq_setup_irq(struct vlynq_device *dev)
-{
-	u32 val;
-	int i, virq;
-
-	if (dev->local_irq == dev->remote_irq) {
-		printk(KERN_ERR
-		       "%s: local vlynq irq should be different from remote\n",
-		       dev_name(&dev->dev));
-		return -EINVAL;
-	}
-
-	/* Clear local and remote error bits */
-	writel(readl(&dev->local->status), &dev->local->status);
-	writel(readl(&dev->remote->status), &dev->remote->status);
-
-	/* Now setup interrupts */
-	val = VLYNQ_CTRL_INT_VECTOR(dev->local_irq);
-	val |= VLYNQ_CTRL_INT_ENABLE | VLYNQ_CTRL_INT_LOCAL |
-		VLYNQ_CTRL_INT2CFG;
-	val |= readl(&dev->local->control);
-	writel(VLYNQ_INT_OFFSET, &dev->local->int_ptr);
-	writel(val, &dev->local->control);
-
-	val = VLYNQ_CTRL_INT_VECTOR(dev->remote_irq);
-	val |= VLYNQ_CTRL_INT_ENABLE;
-	val |= readl(&dev->remote->control);
-	writel(VLYNQ_INT_OFFSET, &dev->remote->int_ptr);
-	writel(val, &dev->remote->int_ptr);
-	writel(val, &dev->remote->control);
-
-	for (i = dev->irq_start; i <= dev->irq_end; i++) {
-		virq = i - dev->irq_start;
-		if (virq == dev->local_irq) {
-			irq_set_chip_and_handler(i, &vlynq_local_chip,
-						 handle_level_irq);
-			irq_set_chip_data(i, dev);
-		} else if (virq == dev->remote_irq) {
-			irq_set_chip_and_handler(i, &vlynq_remote_chip,
-						 handle_level_irq);
-			irq_set_chip_data(i, dev);
-		} else {
-			irq_set_chip_and_handler(i, &vlynq_irq_chip,
-						 handle_simple_irq);
-			irq_set_chip_data(i, dev);
-			writel(0, &dev->remote->int_device[virq >> 2]);
-		}
-	}
-
-	if (request_irq(dev->irq, vlynq_irq, IRQF_SHARED, "vlynq", dev)) {
-		printk(KERN_ERR "%s: request_irq failed\n",
-					dev_name(&dev->dev));
-		return -EAGAIN;
-	}
-
-	return 0;
-}
-
-static void vlynq_device_release(struct device *dev)
-{
-	struct vlynq_device *vdev = to_vlynq_device(dev);
-	kfree(vdev);
-}
-
-static int vlynq_device_match(struct device *dev,
-			      struct device_driver *drv)
-{
-	struct vlynq_device *vdev = to_vlynq_device(dev);
-	struct vlynq_driver *vdrv = to_vlynq_driver(drv);
-	struct vlynq_device_id *ids = vdrv->id_table;
-
-	while (ids->id) {
-		if (ids->id == vdev->dev_id) {
-			vdev->divisor = ids->divisor;
-			vlynq_set_drvdata(vdev, ids);
-			printk(KERN_INFO "Driver found for VLYNQ "
-				"device: %08x\n", vdev->dev_id);
-			return 1;
-		}
-		printk(KERN_DEBUG "Not using the %08x VLYNQ device's driver"
-			" for VLYNQ device: %08x\n", ids->id, vdev->dev_id);
-		ids++;
-	}
-	return 0;
-}
-
-static int vlynq_device_probe(struct device *dev)
-{
-	struct vlynq_device *vdev = to_vlynq_device(dev);
-	struct vlynq_driver *drv = to_vlynq_driver(dev->driver);
-	struct vlynq_device_id *id = vlynq_get_drvdata(vdev);
-	int result = -ENODEV;
-
-	if (drv->probe)
-		result = drv->probe(vdev, id);
-	if (result)
-		put_device(dev);
-	return result;
-}
-
-static void vlynq_device_remove(struct device *dev)
-{
-	struct vlynq_driver *drv = to_vlynq_driver(dev->driver);
-
-	if (drv->remove)
-		drv->remove(to_vlynq_device(dev));
-}
-
-int __vlynq_register_driver(struct vlynq_driver *driver, struct module *owner)
-{
-	driver->driver.name = driver->name;
-	driver->driver.bus = &vlynq_bus_type;
-	return driver_register(&driver->driver);
-}
-EXPORT_SYMBOL(__vlynq_register_driver);
-
-void vlynq_unregister_driver(struct vlynq_driver *driver)
-{
-	driver_unregister(&driver->driver);
-}
-EXPORT_SYMBOL(vlynq_unregister_driver);
-
-/*
- * A VLYNQ remote device can clock the VLYNQ bus master
- * using a dedicated clock line. In that case, both the
- * remove device and the bus master should have the same
- * serial clock dividers configured. Iterate through the
- * 8 possible dividers until we actually link with the
- * device.
- */
-static int __vlynq_try_remote(struct vlynq_device *dev)
-{
-	int i;
-
-	vlynq_reset(dev);
-	for (i = dev->dev_id ? vlynq_rdiv2 : vlynq_rdiv8; dev->dev_id ?
-			i <= vlynq_rdiv8 : i >= vlynq_rdiv2;
-		dev->dev_id ? i++ : i--) {
-
-		if (!vlynq_linked(dev))
-			break;
-
-		writel((readl(&dev->remote->control) &
-				~VLYNQ_CTRL_CLOCK_MASK) |
-				VLYNQ_CTRL_CLOCK_INT |
-				VLYNQ_CTRL_CLOCK_DIV(i - vlynq_rdiv1),
-				&dev->remote->control);
-		writel((readl(&dev->local->control)
-				& ~(VLYNQ_CTRL_CLOCK_INT |
-				VLYNQ_CTRL_CLOCK_MASK)) |
-				VLYNQ_CTRL_CLOCK_DIV(i - vlynq_rdiv1),
-				&dev->local->control);
-
-		if (vlynq_linked(dev)) {
-			printk(KERN_DEBUG
-				"%s: using remote clock divisor %d\n",
-				dev_name(&dev->dev), i - vlynq_rdiv1 + 1);
-			dev->divisor = i;
-			return 0;
-		} else {
-			vlynq_reset(dev);
-		}
-	}
-
-	return -ENODEV;
-}
-
-/*
- * A VLYNQ remote device can be clocked by the VLYNQ bus
- * master using a dedicated clock line. In that case, only
- * the bus master configures the serial clock divider.
- * Iterate through the 8 possible dividers until we
- * actually get a link with the device.
- */
-static int __vlynq_try_local(struct vlynq_device *dev)
-{
-	int i;
-
-	vlynq_reset(dev);
-
-	for (i = dev->dev_id ? vlynq_ldiv2 : vlynq_ldiv8; dev->dev_id ?
-			i <= vlynq_ldiv8 : i >= vlynq_ldiv2;
-		dev->dev_id ? i++ : i--) {
-
-		writel((readl(&dev->local->control) &
-				~VLYNQ_CTRL_CLOCK_MASK) |
-				VLYNQ_CTRL_CLOCK_INT |
-				VLYNQ_CTRL_CLOCK_DIV(i - vlynq_ldiv1),
-				&dev->local->control);
-
-		if (vlynq_linked(dev)) {
-			printk(KERN_DEBUG
-				"%s: using local clock divisor %d\n",
-				dev_name(&dev->dev), i - vlynq_ldiv1 + 1);
-			dev->divisor = i;
-			return 0;
-		} else {
-			vlynq_reset(dev);
-		}
-	}
-
-	return -ENODEV;
-}
-
-/*
- * When using external clocking method, serial clock
- * is supplied by an external oscillator, therefore we
- * should mask the local clock bit in the clock control
- * register for both the bus master and the remote device.
- */
-static int __vlynq_try_external(struct vlynq_device *dev)
-{
-	vlynq_reset(dev);
-	if (!vlynq_linked(dev))
-		return -ENODEV;
-
-	writel((readl(&dev->remote->control) &
-			~VLYNQ_CTRL_CLOCK_INT),
-			&dev->remote->control);
-
-	writel((readl(&dev->local->control) &
-			~VLYNQ_CTRL_CLOCK_INT),
-			&dev->local->control);
-
-	if (vlynq_linked(dev)) {
-		printk(KERN_DEBUG "%s: using external clock\n",
-			dev_name(&dev->dev));
-			dev->divisor = vlynq_div_external;
-		return 0;
-	}
-
-	return -ENODEV;
-}
-
-static int __vlynq_enable_device(struct vlynq_device *dev)
-{
-	int result;
-	struct plat_vlynq_ops *ops = dev->dev.platform_data;
-
-	result = ops->on(dev);
-	if (result)
-		return result;
-
-	switch (dev->divisor) {
-	case vlynq_div_external:
-	case vlynq_div_auto:
-		/* When the device is brought from reset it should have clock
-		 * generation negotiated by hardware.
-		 * Check which device is generating clocks and perform setup
-		 * accordingly */
-		if (vlynq_linked(dev) && readl(&dev->remote->control) &
-		   VLYNQ_CTRL_CLOCK_INT) {
-			if (!__vlynq_try_remote(dev) ||
-				!__vlynq_try_local(dev)  ||
-				!__vlynq_try_external(dev))
-				return 0;
-		} else {
-			if (!__vlynq_try_external(dev) ||
-				!__vlynq_try_local(dev)    ||
-				!__vlynq_try_remote(dev))
-				return 0;
-		}
-		break;
-	case vlynq_ldiv1:
-	case vlynq_ldiv2:
-	case vlynq_ldiv3:
-	case vlynq_ldiv4:
-	case vlynq_ldiv5:
-	case vlynq_ldiv6:
-	case vlynq_ldiv7:
-	case vlynq_ldiv8:
-		writel(VLYNQ_CTRL_CLOCK_INT |
-			VLYNQ_CTRL_CLOCK_DIV(dev->divisor -
-			vlynq_ldiv1), &dev->local->control);
-		writel(0, &dev->remote->control);
-		if (vlynq_linked(dev)) {
-			printk(KERN_DEBUG
-				"%s: using local clock divisor %d\n",
-				dev_name(&dev->dev),
-				dev->divisor - vlynq_ldiv1 + 1);
-			return 0;
-		}
-		break;
-	case vlynq_rdiv1:
-	case vlynq_rdiv2:
-	case vlynq_rdiv3:
-	case vlynq_rdiv4:
-	case vlynq_rdiv5:
-	case vlynq_rdiv6:
-	case vlynq_rdiv7:
-	case vlynq_rdiv8:
-		writel(0, &dev->local->control);
-		writel(VLYNQ_CTRL_CLOCK_INT |
-			VLYNQ_CTRL_CLOCK_DIV(dev->divisor -
-			vlynq_rdiv1), &dev->remote->control);
-		if (vlynq_linked(dev)) {
-			printk(KERN_DEBUG
-				"%s: using remote clock divisor %d\n",
-				dev_name(&dev->dev),
-				dev->divisor - vlynq_rdiv1 + 1);
-			return 0;
-		}
-		break;
-	}
-
-	ops->off(dev);
-	return -ENODEV;
-}
-
-int vlynq_enable_device(struct vlynq_device *dev)
-{
-	struct plat_vlynq_ops *ops = dev->dev.platform_data;
-	int result = -ENODEV;
-
-	result = __vlynq_enable_device(dev);
-	if (result)
-		return result;
-
-	result = vlynq_setup_irq(dev);
-	if (result)
-		ops->off(dev);
-
-	dev->enabled = !result;
-	return result;
-}
-EXPORT_SYMBOL(vlynq_enable_device);
-
-
-void vlynq_disable_device(struct vlynq_device *dev)
-{
-	struct plat_vlynq_ops *ops = dev->dev.platform_data;
-
-	dev->enabled = 0;
-	free_irq(dev->irq, dev);
-	ops->off(dev);
-}
-EXPORT_SYMBOL(vlynq_disable_device);
-
-int vlynq_set_local_mapping(struct vlynq_device *dev, u32 tx_offset,
-			    struct vlynq_mapping *mapping)
-{
-	int i;
-
-	if (!dev->enabled)
-		return -ENXIO;
-
-	writel(tx_offset, &dev->local->tx_offset);
-	for (i = 0; i < 4; i++) {
-		writel(mapping[i].offset, &dev->local->rx_mapping[i].offset);
-		writel(mapping[i].size, &dev->local->rx_mapping[i].size);
-	}
-	return 0;
-}
-EXPORT_SYMBOL(vlynq_set_local_mapping);
-
-int vlynq_set_remote_mapping(struct vlynq_device *dev, u32 tx_offset,
-			     struct vlynq_mapping *mapping)
-{
-	int i;
-
-	if (!dev->enabled)
-		return -ENXIO;
-
-	writel(tx_offset, &dev->remote->tx_offset);
-	for (i = 0; i < 4; i++) {
-		writel(mapping[i].offset, &dev->remote->rx_mapping[i].offset);
-		writel(mapping[i].size, &dev->remote->rx_mapping[i].size);
-	}
-	return 0;
-}
-EXPORT_SYMBOL(vlynq_set_remote_mapping);
-
-int vlynq_set_local_irq(struct vlynq_device *dev, int virq)
-{
-	int irq = dev->irq_start + virq;
-	if (dev->enabled)
-		return -EBUSY;
-
-	if ((irq < dev->irq_start) || (irq > dev->irq_end))
-		return -EINVAL;
-
-	if (virq == dev->remote_irq)
-		return -EINVAL;
-
-	dev->local_irq = virq;
-
-	return 0;
-}
-EXPORT_SYMBOL(vlynq_set_local_irq);
-
-int vlynq_set_remote_irq(struct vlynq_device *dev, int virq)
-{
-	int irq = dev->irq_start + virq;
-	if (dev->enabled)
-		return -EBUSY;
-
-	if ((irq < dev->irq_start) || (irq > dev->irq_end))
-		return -EINVAL;
-
-	if (virq == dev->local_irq)
-		return -EINVAL;
-
-	dev->remote_irq = virq;
-
-	return 0;
-}
-EXPORT_SYMBOL(vlynq_set_remote_irq);
-
-static int vlynq_probe(struct platform_device *pdev)
-{
-	struct vlynq_device *dev;
-	struct resource *regs_res, *mem_res, *irq_res;
-	int len, result;
-
-	regs_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
-	if (!regs_res)
-		return -ENODEV;
-
-	mem_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mem");
-	if (!mem_res)
-		return -ENODEV;
-
-	irq_res = platform_get_resource_byname(pdev, IORESOURCE_IRQ, "devirq");
-	if (!irq_res)
-		return -ENODEV;
-
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-	if (!dev) {
-		printk(KERN_ERR
-		       "vlynq: failed to allocate device structure\n");
-		return -ENOMEM;
-	}
-
-	dev->id = pdev->id;
-	dev->dev.bus = &vlynq_bus_type;
-	dev->dev.parent = &pdev->dev;
-	dev_set_name(&dev->dev, "vlynq%d", dev->id);
-	dev->dev.platform_data = pdev->dev.platform_data;
-	dev->dev.release = vlynq_device_release;
-
-	dev->regs_start = regs_res->start;
-	dev->regs_end = regs_res->end;
-	dev->mem_start = mem_res->start;
-	dev->mem_end = mem_res->end;
-
-	len = resource_size(regs_res);
-	if (!request_mem_region(regs_res->start, len, dev_name(&dev->dev))) {
-		printk(KERN_ERR "%s: Can't request vlynq registers\n",
-		       dev_name(&dev->dev));
-		result = -ENXIO;
-		goto fail_request;
-	}
-
-	dev->local = ioremap(regs_res->start, len);
-	if (!dev->local) {
-		printk(KERN_ERR "%s: Can't remap vlynq registers\n",
-		       dev_name(&dev->dev));
-		result = -ENXIO;
-		goto fail_remap;
-	}
-
-	dev->remote = (struct vlynq_regs *)((void *)dev->local +
-					    VLYNQ_REMOTE_OFFSET);
-
-	dev->irq = platform_get_irq_byname(pdev, "irq");
-	dev->irq_start = irq_res->start;
-	dev->irq_end = irq_res->end;
-	dev->local_irq = dev->irq_end - dev->irq_start;
-	dev->remote_irq = dev->local_irq - 1;
-
-	if (device_register(&dev->dev))
-		goto fail_register;
-	platform_set_drvdata(pdev, dev);
-
-	printk(KERN_INFO "%s: regs 0x%p, irq %d, mem 0x%p\n",
-	       dev_name(&dev->dev), (void *)dev->regs_start, dev->irq,
-	       (void *)dev->mem_start);
-
-	dev->dev_id = 0;
-	dev->divisor = vlynq_div_auto;
-	result = __vlynq_enable_device(dev);
-	if (result == 0) {
-		dev->dev_id = readl(&dev->remote->chip);
-		((struct plat_vlynq_ops *)(dev->dev.platform_data))->off(dev);
-	}
-	if (dev->dev_id)
-		printk(KERN_INFO "Found a VLYNQ device: %08x\n", dev->dev_id);
-
-	return 0;
-
-fail_register:
-	iounmap(dev->local);
-fail_remap:
-fail_request:
-	release_mem_region(regs_res->start, len);
-	kfree(dev);
-	return result;
-}
-
-static int vlynq_remove(struct platform_device *pdev)
-{
-	struct vlynq_device *dev = platform_get_drvdata(pdev);
-
-	device_unregister(&dev->dev);
-	iounmap(dev->local);
-	release_mem_region(dev->regs_start,
-			   dev->regs_end - dev->regs_start + 1);
-
-	kfree(dev);
-
-	return 0;
-}
-
-static struct platform_driver vlynq_platform_driver = {
-	.driver.name = "vlynq",
-	.probe = vlynq_probe,
-	.remove = vlynq_remove,
-};
-
-struct bus_type vlynq_bus_type = {
-	.name = "vlynq",
-	.match = vlynq_device_match,
-	.probe = vlynq_device_probe,
-	.remove = vlynq_device_remove,
-};
-EXPORT_SYMBOL(vlynq_bus_type);
-
-static int vlynq_init(void)
-{
-	int res = 0;
-
-	res = bus_register(&vlynq_bus_type);
-	if (res)
-		goto fail_bus;
-
-	res = platform_driver_register(&vlynq_platform_driver);
-	if (res)
-		goto fail_platform;
-
-	return 0;
-
-fail_platform:
-	bus_unregister(&vlynq_bus_type);
-fail_bus:
-	return res;
-}
-
-static void vlynq_exit(void)
-{
-	platform_driver_unregister(&vlynq_platform_driver);
-	bus_unregister(&vlynq_bus_type);
-}
-
-module_init(vlynq_init);
-module_exit(vlynq_exit);
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 8cb6fa45d599a2..7d22051b15a299 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -1768,12 +1768,6 @@ config SIBYTE_WDOG
 	  To compile this driver as a loadable module, choose M here.
 	  The module will be called sb_wdog.
 
-config AR7_WDT
-	tristate "TI AR7 Watchdog Timer"
-	depends on AR7 || (MIPS && 32BIT && COMPILE_TEST)
-	help
-	  Hardware driver for the TI AR7 Watchdog Timer.
-
 config TXX9_WDT
 	tristate "Toshiba TXx9 Watchdog Timer"
 	depends on CPU_TX49XX || (MIPS && COMPILE_TEST)
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index 7eab9de311cb93..7cbc34514ec115 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -168,7 +168,6 @@ obj-$(CONFIG_INDYDOG) += indydog.o
 obj-$(CONFIG_JZ4740_WDT) += jz4740_wdt.o
 obj-$(CONFIG_WDT_MTX1) += mtx-1_wdt.o
 obj-$(CONFIG_SIBYTE_WDOG) += sb_wdog.o
-obj-$(CONFIG_AR7_WDT) += ar7_wdt.o
 obj-$(CONFIG_TXX9_WDT) += txx9wdt.o
 obj-$(CONFIG_OCTEON_WDT) += octeon-wdt.o
 octeon-wdt-y := octeon-wdt-main.o octeon-wdt-nmi.o
diff --git a/drivers/watchdog/ar7_wdt.c b/drivers/watchdog/ar7_wdt.c
deleted file mode 100644
index cdcaeb0961ac94..00000000000000
--- a/drivers/watchdog/ar7_wdt.c
+++ /dev/null
@@ -1,315 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * drivers/watchdog/ar7_wdt.c
- *
- * Copyright (C) 2007 Nicolas Thill <nico@openwrt.org>
- * Copyright (c) 2005 Enrik Berkhan <Enrik.Berkhan@akk.org>
- *
- * Some code taken from:
- * National Semiconductor SCx200 Watchdog support
- * Copyright (c) 2001,2002 Christer Weinigel <wingel@nano-system.com>
- *
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/errno.h>
-#include <linux/miscdevice.h>
-#include <linux/platform_device.h>
-#include <linux/watchdog.h>
-#include <linux/fs.h>
-#include <linux/ioport.h>
-#include <linux/io.h>
-#include <linux/uaccess.h>
-#include <linux/clk.h>
-
-#include <asm/addrspace.h>
-#include <asm/mach-ar7/ar7.h>
-
-#define LONGNAME "TI AR7 Watchdog Timer"
-
-MODULE_AUTHOR("Nicolas Thill <nico@openwrt.org>");
-MODULE_DESCRIPTION(LONGNAME);
-MODULE_LICENSE("GPL");
-
-static int margin = 60;
-module_param(margin, int, 0);
-MODULE_PARM_DESC(margin, "Watchdog margin in seconds");
-
-static bool nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, bool, 0);
-MODULE_PARM_DESC(nowayout, "Disable watchdog shutdown on close");
-
-#define READ_REG(x) readl((void __iomem *)&(x))
-#define WRITE_REG(x, v) writel((v), (void __iomem *)&(x))
-
-struct ar7_wdt {
-	u32 kick_lock;
-	u32 kick;
-	u32 change_lock;
-	u32 change;
-	u32 disable_lock;
-	u32 disable;
-	u32 prescale_lock;
-	u32 prescale;
-};
-
-static unsigned long wdt_is_open;
-static unsigned expect_close;
-static DEFINE_SPINLOCK(wdt_lock);
-
-/* XXX currently fixed, allows max margin ~68.72 secs */
-#define prescale_value 0xffff
-
-/* Pointer to the remapped WDT IO space */
-static struct ar7_wdt *ar7_wdt;
-
-static struct clk *vbus_clk;
-
-static void ar7_wdt_kick(u32 value)
-{
-	WRITE_REG(ar7_wdt->kick_lock, 0x5555);
-	if ((READ_REG(ar7_wdt->kick_lock) & 3) == 1) {
-		WRITE_REG(ar7_wdt->kick_lock, 0xaaaa);
-		if ((READ_REG(ar7_wdt->kick_lock) & 3) == 3) {
-			WRITE_REG(ar7_wdt->kick, value);
-			return;
-		}
-	}
-	pr_err("failed to unlock WDT kick reg\n");
-}
-
-static void ar7_wdt_prescale(u32 value)
-{
-	WRITE_REG(ar7_wdt->prescale_lock, 0x5a5a);
-	if ((READ_REG(ar7_wdt->prescale_lock) & 3) == 1) {
-		WRITE_REG(ar7_wdt->prescale_lock, 0xa5a5);
-		if ((READ_REG(ar7_wdt->prescale_lock) & 3) == 3) {
-			WRITE_REG(ar7_wdt->prescale, value);
-			return;
-		}
-	}
-	pr_err("failed to unlock WDT prescale reg\n");
-}
-
-static void ar7_wdt_change(u32 value)
-{
-	WRITE_REG(ar7_wdt->change_lock, 0x6666);
-	if ((READ_REG(ar7_wdt->change_lock) & 3) == 1) {
-		WRITE_REG(ar7_wdt->change_lock, 0xbbbb);
-		if ((READ_REG(ar7_wdt->change_lock) & 3) == 3) {
-			WRITE_REG(ar7_wdt->change, value);
-			return;
-		}
-	}
-	pr_err("failed to unlock WDT change reg\n");
-}
-
-static void ar7_wdt_disable(u32 value)
-{
-	WRITE_REG(ar7_wdt->disable_lock, 0x7777);
-	if ((READ_REG(ar7_wdt->disable_lock) & 3) == 1) {
-		WRITE_REG(ar7_wdt->disable_lock, 0xcccc);
-		if ((READ_REG(ar7_wdt->disable_lock) & 3) == 2) {
-			WRITE_REG(ar7_wdt->disable_lock, 0xdddd);
-			if ((READ_REG(ar7_wdt->disable_lock) & 3) == 3) {
-				WRITE_REG(ar7_wdt->disable, value);
-				return;
-			}
-		}
-	}
-	pr_err("failed to unlock WDT disable reg\n");
-}
-
-static void ar7_wdt_update_margin(int new_margin)
-{
-	u32 change;
-	u32 vbus_rate;
-
-	vbus_rate = clk_get_rate(vbus_clk);
-	change = new_margin * (vbus_rate / prescale_value);
-	if (change < 1)
-		change = 1;
-	if (change > 0xffff)
-		change = 0xffff;
-	ar7_wdt_change(change);
-	margin = change * prescale_value / vbus_rate;
-	pr_info("timer margin %d seconds (prescale %d, change %d, freq %d)\n",
-		margin, prescale_value, change, vbus_rate);
-}
-
-static void ar7_wdt_enable_wdt(void)
-{
-	pr_debug("enabling watchdog timer\n");
-	ar7_wdt_disable(1);
-	ar7_wdt_kick(1);
-}
-
-static void ar7_wdt_disable_wdt(void)
-{
-	pr_debug("disabling watchdog timer\n");
-	ar7_wdt_disable(0);
-}
-
-static int ar7_wdt_open(struct inode *inode, struct file *file)
-{
-	/* only allow one at a time */
-	if (test_and_set_bit(0, &wdt_is_open))
-		return -EBUSY;
-	ar7_wdt_enable_wdt();
-	expect_close = 0;
-
-	return stream_open(inode, file);
-}
-
-static int ar7_wdt_release(struct inode *inode, struct file *file)
-{
-	if (!expect_close)
-		pr_warn("watchdog device closed unexpectedly, will not disable the watchdog timer\n");
-	else if (!nowayout)
-		ar7_wdt_disable_wdt();
-	clear_bit(0, &wdt_is_open);
-	return 0;
-}
-
-static ssize_t ar7_wdt_write(struct file *file, const char *data,
-			     size_t len, loff_t *ppos)
-{
-	/* check for a magic close character */
-	if (len) {
-		size_t i;
-
-		spin_lock(&wdt_lock);
-		ar7_wdt_kick(1);
-		spin_unlock(&wdt_lock);
-
-		expect_close = 0;
-		for (i = 0; i < len; ++i) {
-			char c;
-			if (get_user(c, data + i))
-				return -EFAULT;
-			if (c == 'V')
-				expect_close = 1;
-		}
-
-	}
-	return len;
-}
-
-static long ar7_wdt_ioctl(struct file *file,
-					unsigned int cmd, unsigned long arg)
-{
-	static const struct watchdog_info ident = {
-		.identity = LONGNAME,
-		.firmware_version = 1,
-		.options = (WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING |
-						WDIOF_MAGICCLOSE),
-	};
-	int new_margin;
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		if (copy_to_user((struct watchdog_info *)arg, &ident,
-				sizeof(ident)))
-			return -EFAULT;
-		return 0;
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		if (put_user(0, (int *)arg))
-			return -EFAULT;
-		return 0;
-	case WDIOC_KEEPALIVE:
-		ar7_wdt_kick(1);
-		return 0;
-	case WDIOC_SETTIMEOUT:
-		if (get_user(new_margin, (int *)arg))
-			return -EFAULT;
-		if (new_margin < 1)
-			return -EINVAL;
-
-		spin_lock(&wdt_lock);
-		ar7_wdt_update_margin(new_margin);
-		ar7_wdt_kick(1);
-		spin_unlock(&wdt_lock);
-		fallthrough;
-	case WDIOC_GETTIMEOUT:
-		if (put_user(margin, (int *)arg))
-			return -EFAULT;
-		return 0;
-	default:
-		return -ENOTTY;
-	}
-}
-
-static const struct file_operations ar7_wdt_fops = {
-	.owner		= THIS_MODULE,
-	.write		= ar7_wdt_write,
-	.unlocked_ioctl	= ar7_wdt_ioctl,
-	.compat_ioctl	= compat_ptr_ioctl,
-	.open		= ar7_wdt_open,
-	.release	= ar7_wdt_release,
-	.llseek		= no_llseek,
-};
-
-static struct miscdevice ar7_wdt_miscdev = {
-	.minor		= WATCHDOG_MINOR,
-	.name		= "watchdog",
-	.fops		= &ar7_wdt_fops,
-};
-
-static int ar7_wdt_probe(struct platform_device *pdev)
-{
-	int rc;
-
-	ar7_wdt = devm_platform_ioremap_resource_byname(pdev, "regs");
-	if (IS_ERR(ar7_wdt))
-		return PTR_ERR(ar7_wdt);
-
-	vbus_clk = clk_get(NULL, "vbus");
-	if (IS_ERR(vbus_clk)) {
-		pr_err("could not get vbus clock\n");
-		return PTR_ERR(vbus_clk);
-	}
-
-	ar7_wdt_disable_wdt();
-	ar7_wdt_prescale(prescale_value);
-	ar7_wdt_update_margin(margin);
-
-	rc = misc_register(&ar7_wdt_miscdev);
-	if (rc) {
-		pr_err("unable to register misc device\n");
-		goto out;
-	}
-	return 0;
-
-out:
-	clk_put(vbus_clk);
-	vbus_clk = NULL;
-	return rc;
-}
-
-static void ar7_wdt_remove(struct platform_device *pdev)
-{
-	misc_deregister(&ar7_wdt_miscdev);
-	clk_put(vbus_clk);
-	vbus_clk = NULL;
-}
-
-static void ar7_wdt_shutdown(struct platform_device *pdev)
-{
-	if (!nowayout)
-		ar7_wdt_disable_wdt();
-}
-
-static struct platform_driver ar7_wdt_driver = {
-	.probe = ar7_wdt_probe,
-	.remove_new = ar7_wdt_remove,
-	.shutdown = ar7_wdt_shutdown,
-	.driver = {
-		.name = "ar7_wdt",
-	},
-};
-
-module_platform_driver(ar7_wdt_driver);
diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c
index b8f2f971c2f0fc..e3585330cf98b1 100644
--- a/drivers/xen/events/events_2l.c
+++ b/drivers/xen/events/events_2l.c
@@ -171,11 +171,11 @@ static void evtchn_2l_handle_events(unsigned cpu, struct evtchn_loop_ctrl *ctrl)
 	int i;
 	struct shared_info *s = HYPERVISOR_shared_info;
 	struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu);
+	evtchn_port_t evtchn;
 
 	/* Timer interrupt has highest priority. */
-	irq = irq_from_virq(cpu, VIRQ_TIMER);
+	irq = irq_evtchn_from_virq(cpu, VIRQ_TIMER, &evtchn);
 	if (irq != -1) {
-		evtchn_port_t evtchn = evtchn_from_irq(irq);
 		word_idx = evtchn / BITS_PER_LONG;
 		bit_idx = evtchn % BITS_PER_LONG;
 		if (active_evtchns(cpu, s, word_idx) & (1ULL << bit_idx))
@@ -328,9 +328,9 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
 	for (i = 0; i < EVTCHN_2L_NR_CHANNELS; i++) {
 		if (sync_test_bit(i, BM(sh->evtchn_pending))) {
 			int word_idx = i / BITS_PER_EVTCHN_WORD;
-			printk("  %d: event %d -> irq %d%s%s%s\n",
+			printk("  %d: event %d -> irq %u%s%s%s\n",
 			       cpu_from_evtchn(i), i,
-			       get_evtchn_to_irq(i),
+			       irq_from_evtchn(i),
 			       sync_test_bit(word_idx, BM(&v->evtchn_pending_sel))
 			       ? "" : " l2-clear",
 			       !sync_test_bit(i, BM(sh->evtchn_mask))
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 6de6b084ea60d5..b8cfea7812d6b6 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -164,6 +164,8 @@ static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};
 
 /* IRQ <-> IPI mapping */
 static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};
+/* Cache for IPI event channels - needed for hot cpu unplug (avoid RCU usage). */
+static DEFINE_PER_CPU(evtchn_port_t [XEN_NR_IPIS], ipi_to_evtchn) = {[0 ... XEN_NR_IPIS-1] = 0};
 
 /* Event channel distribution data */
 static atomic_t channels_on_cpu[NR_CPUS];
@@ -172,7 +174,7 @@ static int **evtchn_to_irq;
 #ifdef CONFIG_X86
 static unsigned long *pirq_eoi_map;
 #endif
-static bool (*pirq_needs_eoi)(unsigned irq);
+static bool (*pirq_needs_eoi)(struct irq_info *info);
 
 #define EVTCHN_ROW(e)  (e / (PAGE_SIZE/sizeof(**evtchn_to_irq)))
 #define EVTCHN_COL(e)  (e % (PAGE_SIZE/sizeof(**evtchn_to_irq)))
@@ -188,7 +190,6 @@ static struct irq_chip xen_lateeoi_chip;
 static struct irq_chip xen_percpu_chip;
 static struct irq_chip xen_pirq_chip;
 static void enable_dynirq(struct irq_data *data);
-static void disable_dynirq(struct irq_data *data);
 
 static DEFINE_PER_CPU(unsigned int, irq_epoch);
 
@@ -246,15 +247,6 @@ static int set_evtchn_to_irq(evtchn_port_t evtchn, unsigned int irq)
 	return 0;
 }
 
-int get_evtchn_to_irq(evtchn_port_t evtchn)
-{
-	if (evtchn >= xen_evtchn_max_channels())
-		return -1;
-	if (evtchn_to_irq[EVTCHN_ROW(evtchn)] == NULL)
-		return -1;
-	return READ_ONCE(evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)]);
-}
-
 /* Get info for IRQ */
 static struct irq_info *info_for_irq(unsigned irq)
 {
@@ -272,6 +264,19 @@ static void set_info_for_irq(unsigned int irq, struct irq_info *info)
 		irq_set_chip_data(irq, info);
 }
 
+static struct irq_info *evtchn_to_info(evtchn_port_t evtchn)
+{
+	int irq;
+
+	if (evtchn >= xen_evtchn_max_channels())
+		return NULL;
+	if (evtchn_to_irq[EVTCHN_ROW(evtchn)] == NULL)
+		return NULL;
+	irq = READ_ONCE(evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)]);
+
+	return (irq < 0) ? NULL : info_for_irq(irq);
+}
+
 /* Per CPU channel accounting */
 static void channels_on_cpu_dec(struct irq_info *info)
 {
@@ -298,6 +303,13 @@ static void channels_on_cpu_inc(struct irq_info *info)
 	info->is_accounted = 1;
 }
 
+static void xen_irq_free_desc(unsigned int irq)
+{
+	/* Legacy IRQ descriptors are managed by the arch. */
+	if (irq >= nr_legacy_irqs())
+		irq_free_desc(irq);
+}
+
 static void delayed_free_irq(struct work_struct *work)
 {
 	struct irq_info *info = container_of(to_rcu_work(work), struct irq_info,
@@ -309,14 +321,11 @@ static void delayed_free_irq(struct work_struct *work)
 
 	kfree(info);
 
-	/* Legacy IRQ descriptors are managed by the arch. */
-	if (irq >= nr_legacy_irqs())
-		irq_free_desc(irq);
+	xen_irq_free_desc(irq);
 }
 
 /* Constructors for packed IRQ information. */
 static int xen_irq_info_common_setup(struct irq_info *info,
-				     unsigned irq,
 				     enum xen_irq_type type,
 				     evtchn_port_t evtchn,
 				     unsigned short cpu)
@@ -326,29 +335,27 @@ static int xen_irq_info_common_setup(struct irq_info *info,
 	BUG_ON(info->type != IRQT_UNBOUND && info->type != type);
 
 	info->type = type;
-	info->irq = irq;
 	info->evtchn = evtchn;
 	info->cpu = cpu;
 	info->mask_reason = EVT_MASK_REASON_EXPLICIT;
 	raw_spin_lock_init(&info->lock);
 
-	ret = set_evtchn_to_irq(evtchn, irq);
+	ret = set_evtchn_to_irq(evtchn, info->irq);
 	if (ret < 0)
 		return ret;
 
-	irq_clear_status_flags(irq, IRQ_NOREQUEST|IRQ_NOAUTOEN);
+	irq_clear_status_flags(info->irq, IRQ_NOREQUEST | IRQ_NOAUTOEN);
 
 	return xen_evtchn_port_setup(evtchn);
 }
 
-static int xen_irq_info_evtchn_setup(unsigned irq,
+static int xen_irq_info_evtchn_setup(struct irq_info *info,
 				     evtchn_port_t evtchn,
 				     struct xenbus_device *dev)
 {
-	struct irq_info *info = info_for_irq(irq);
 	int ret;
 
-	ret = xen_irq_info_common_setup(info, irq, IRQT_EVTCHN, evtchn, 0);
+	ret = xen_irq_info_common_setup(info, IRQT_EVTCHN, evtchn, 0);
 	info->u.interdomain = dev;
 	if (dev)
 		atomic_inc(&dev->event_channels);
@@ -356,49 +363,37 @@ static int xen_irq_info_evtchn_setup(unsigned irq,
 	return ret;
 }
 
-static int xen_irq_info_ipi_setup(unsigned cpu,
-				  unsigned irq,
-				  evtchn_port_t evtchn,
-				  enum ipi_vector ipi)
+static int xen_irq_info_ipi_setup(struct irq_info *info, unsigned int cpu,
+				  evtchn_port_t evtchn, enum ipi_vector ipi)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	info->u.ipi = ipi;
 
-	per_cpu(ipi_to_irq, cpu)[ipi] = irq;
+	per_cpu(ipi_to_irq, cpu)[ipi] = info->irq;
+	per_cpu(ipi_to_evtchn, cpu)[ipi] = evtchn;
 
-	return xen_irq_info_common_setup(info, irq, IRQT_IPI, evtchn, 0);
+	return xen_irq_info_common_setup(info, IRQT_IPI, evtchn, 0);
 }
 
-static int xen_irq_info_virq_setup(unsigned cpu,
-				   unsigned irq,
-				   evtchn_port_t evtchn,
-				   unsigned virq)
+static int xen_irq_info_virq_setup(struct irq_info *info, unsigned int cpu,
+				   evtchn_port_t evtchn, unsigned int virq)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	info->u.virq = virq;
 
-	per_cpu(virq_to_irq, cpu)[virq] = irq;
+	per_cpu(virq_to_irq, cpu)[virq] = info->irq;
 
-	return xen_irq_info_common_setup(info, irq, IRQT_VIRQ, evtchn, 0);
+	return xen_irq_info_common_setup(info, IRQT_VIRQ, evtchn, 0);
 }
 
-static int xen_irq_info_pirq_setup(unsigned irq,
-				   evtchn_port_t evtchn,
-				   unsigned pirq,
-				   unsigned gsi,
-				   uint16_t domid,
-				   unsigned char flags)
+static int xen_irq_info_pirq_setup(struct irq_info *info, evtchn_port_t evtchn,
+				   unsigned int pirq, unsigned int gsi,
+				   uint16_t domid, unsigned char flags)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	info->u.pirq.pirq = pirq;
 	info->u.pirq.gsi = gsi;
 	info->u.pirq.domid = domid;
 	info->u.pirq.flags = flags;
 
-	return xen_irq_info_common_setup(info, irq, IRQT_PIRQ, evtchn, 0);
+	return xen_irq_info_common_setup(info, IRQT_PIRQ, evtchn, 0);
 }
 
 static void xen_irq_info_cleanup(struct irq_info *info)
@@ -412,7 +407,7 @@ static void xen_irq_info_cleanup(struct irq_info *info)
 /*
  * Accessors for packed IRQ information.
  */
-evtchn_port_t evtchn_from_irq(unsigned irq)
+static evtchn_port_t evtchn_from_irq(unsigned int irq)
 {
 	const struct irq_info *info = NULL;
 
@@ -426,64 +421,51 @@ evtchn_port_t evtchn_from_irq(unsigned irq)
 
 unsigned int irq_from_evtchn(evtchn_port_t evtchn)
 {
-	return get_evtchn_to_irq(evtchn);
+	struct irq_info *info = evtchn_to_info(evtchn);
+
+	return info ? info->irq : -1;
 }
 EXPORT_SYMBOL_GPL(irq_from_evtchn);
 
-int irq_from_virq(unsigned int cpu, unsigned int virq)
+int irq_evtchn_from_virq(unsigned int cpu, unsigned int virq,
+			 evtchn_port_t *evtchn)
 {
-	return per_cpu(virq_to_irq, cpu)[virq];
+	int irq = per_cpu(virq_to_irq, cpu)[virq];
+
+	*evtchn = evtchn_from_irq(irq);
+
+	return irq;
 }
 
-static enum ipi_vector ipi_from_irq(unsigned irq)
+static enum ipi_vector ipi_from_irq(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	BUG_ON(info == NULL);
 	BUG_ON(info->type != IRQT_IPI);
 
 	return info->u.ipi;
 }
 
-static unsigned virq_from_irq(unsigned irq)
+static unsigned int virq_from_irq(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	BUG_ON(info == NULL);
 	BUG_ON(info->type != IRQT_VIRQ);
 
 	return info->u.virq;
 }
 
-static unsigned pirq_from_irq(unsigned irq)
+static unsigned int pirq_from_irq(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	BUG_ON(info == NULL);
 	BUG_ON(info->type != IRQT_PIRQ);
 
 	return info->u.pirq.pirq;
 }
 
-static enum xen_irq_type type_from_irq(unsigned irq)
-{
-	return info_for_irq(irq)->type;
-}
-
-static unsigned cpu_from_irq(unsigned irq)
-{
-	return info_for_irq(irq)->cpu;
-}
-
 unsigned int cpu_from_evtchn(evtchn_port_t evtchn)
 {
-	int irq = get_evtchn_to_irq(evtchn);
-	unsigned ret = 0;
-
-	if (irq != -1)
-		ret = cpu_from_irq(irq);
+	struct irq_info *info = evtchn_to_info(evtchn);
 
-	return ret;
+	return info ? info->cpu : 0;
 }
 
 static void do_mask(struct irq_info *info, u8 reason)
@@ -515,36 +497,30 @@ static void do_unmask(struct irq_info *info, u8 reason)
 }
 
 #ifdef CONFIG_X86
-static bool pirq_check_eoi_map(unsigned irq)
+static bool pirq_check_eoi_map(struct irq_info *info)
 {
-	return test_bit(pirq_from_irq(irq), pirq_eoi_map);
+	return test_bit(pirq_from_irq(info), pirq_eoi_map);
 }
 #endif
 
-static bool pirq_needs_eoi_flag(unsigned irq)
+static bool pirq_needs_eoi_flag(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(irq);
 	BUG_ON(info->type != IRQT_PIRQ);
 
 	return info->u.pirq.flags & PIRQ_NEEDS_EOI;
 }
 
-static void bind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int cpu,
+static void bind_evtchn_to_cpu(struct irq_info *info, unsigned int cpu,
 			       bool force_affinity)
 {
-	int irq = get_evtchn_to_irq(evtchn);
-	struct irq_info *info = info_for_irq(irq);
-
-	BUG_ON(irq == -1);
-
 	if (IS_ENABLED(CONFIG_SMP) && force_affinity) {
-		struct irq_data *data = irq_get_irq_data(irq);
+		struct irq_data *data = irq_get_irq_data(info->irq);
 
 		irq_data_update_affinity(data, cpumask_of(cpu));
 		irq_data_update_effective_affinity(data, cpumask_of(cpu));
 	}
 
-	xen_evtchn_port_bind_to_cpu(evtchn, cpu, info->cpu);
+	xen_evtchn_port_bind_to_cpu(info->evtchn, cpu, info->cpu);
 
 	channels_on_cpu_dec(info);
 	info->cpu = cpu;
@@ -601,7 +577,9 @@ static void lateeoi_list_add(struct irq_info *info)
 
 	spin_lock_irqsave(&eoi->eoi_list_lock, flags);
 
-	if (list_empty(&eoi->eoi_list)) {
+	elem = list_first_entry_or_null(&eoi->eoi_list, struct irq_info,
+					eoi_list);
+	if (!elem || info->eoi_time < elem->eoi_time) {
 		list_add(&info->eoi_list, &eoi->eoi_list);
 		mod_delayed_work_on(info->eoi_cpu, system_wq,
 				    &eoi->delayed, delay);
@@ -732,50 +710,49 @@ void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags)
 }
 EXPORT_SYMBOL_GPL(xen_irq_lateeoi);
 
-static void xen_irq_init(unsigned irq)
+static struct irq_info *xen_irq_init(unsigned int irq)
 {
 	struct irq_info *info;
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
-	if (info == NULL)
-		panic("Unable to allocate metadata for IRQ%d\n", irq);
+	if (info) {
+		info->irq = irq;
+		info->type = IRQT_UNBOUND;
+		info->refcnt = -1;
+		INIT_RCU_WORK(&info->rwork, delayed_free_irq);
 
-	info->type = IRQT_UNBOUND;
-	info->refcnt = -1;
-	INIT_RCU_WORK(&info->rwork, delayed_free_irq);
+		set_info_for_irq(irq, info);
+		/*
+		 * Interrupt affinity setting can be immediate. No point
+		 * in delaying it until an interrupt is handled.
+		 */
+		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 
-	set_info_for_irq(irq, info);
-	/*
-	 * Interrupt affinity setting can be immediate. No point
-	 * in delaying it until an interrupt is handled.
-	 */
-	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
+		INIT_LIST_HEAD(&info->eoi_list);
+		list_add_tail(&info->list, &xen_irq_list_head);
+	}
 
-	INIT_LIST_HEAD(&info->eoi_list);
-	list_add_tail(&info->list, &xen_irq_list_head);
+	return info;
 }
 
-static int __must_check xen_allocate_irqs_dynamic(int nvec)
+static struct irq_info *xen_allocate_irq_dynamic(void)
 {
-	int i, irq = irq_alloc_descs(-1, 0, nvec, -1);
+	int irq = irq_alloc_desc_from(0, -1);
+	struct irq_info *info = NULL;
 
 	if (irq >= 0) {
-		for (i = 0; i < nvec; i++)
-			xen_irq_init(irq + i);
+		info = xen_irq_init(irq);
+		if (!info)
+			xen_irq_free_desc(irq);
 	}
 
-	return irq;
-}
-
-static inline int __must_check xen_allocate_irq_dynamic(void)
-{
-
-	return xen_allocate_irqs_dynamic(1);
+	return info;
 }
 
-static int __must_check xen_allocate_irq_gsi(unsigned gsi)
+static struct irq_info *xen_allocate_irq_gsi(unsigned int gsi)
 {
 	int irq;
+	struct irq_info *info;
 
 	/*
 	 * A PV guest has no concept of a GSI (since it has no ACPI
@@ -792,15 +769,15 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi)
 	else
 		irq = irq_alloc_desc_at(gsi, -1);
 
-	xen_irq_init(irq);
+	info = xen_irq_init(irq);
+	if (!info)
+		xen_irq_free_desc(irq);
 
-	return irq;
+	return info;
 }
 
-static void xen_free_irq(unsigned irq)
+static void xen_free_irq(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(irq);
-
 	if (WARN_ON(!info))
 		return;
 
@@ -821,14 +798,11 @@ static void event_handler_exit(struct irq_info *info)
 	clear_evtchn(info->evtchn);
 }
 
-static void pirq_query_unmask(int irq)
+static void pirq_query_unmask(struct irq_info *info)
 {
 	struct physdev_irq_status_query irq_status;
-	struct irq_info *info = info_for_irq(irq);
-
-	BUG_ON(info->type != IRQT_PIRQ);
 
-	irq_status.irq = pirq_from_irq(irq);
+	irq_status.irq = pirq_from_irq(info);
 	if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
 		irq_status.flags = 0;
 
@@ -837,61 +811,81 @@ static void pirq_query_unmask(int irq)
 		info->u.pirq.flags |= PIRQ_NEEDS_EOI;
 }
 
-static void eoi_pirq(struct irq_data *data)
+static void do_eoi_pirq(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(data->irq);
-	evtchn_port_t evtchn = info ? info->evtchn : 0;
-	struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
+	struct physdev_eoi eoi = { .irq = pirq_from_irq(info) };
 	int rc = 0;
 
-	if (!VALID_EVTCHN(evtchn))
+	if (!VALID_EVTCHN(info->evtchn))
 		return;
 
 	event_handler_exit(info);
 
-	if (pirq_needs_eoi(data->irq)) {
+	if (pirq_needs_eoi(info)) {
 		rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
 		WARN_ON(rc);
 	}
 }
 
+static void eoi_pirq(struct irq_data *data)
+{
+	struct irq_info *info = info_for_irq(data->irq);
+
+	do_eoi_pirq(info);
+}
+
+static void do_disable_dynirq(struct irq_info *info)
+{
+	if (VALID_EVTCHN(info->evtchn))
+		do_mask(info, EVT_MASK_REASON_EXPLICIT);
+}
+
+static void disable_dynirq(struct irq_data *data)
+{
+	struct irq_info *info = info_for_irq(data->irq);
+
+	if (info)
+		do_disable_dynirq(info);
+}
+
 static void mask_ack_pirq(struct irq_data *data)
 {
-	disable_dynirq(data);
-	eoi_pirq(data);
+	struct irq_info *info = info_for_irq(data->irq);
+
+	if (info) {
+		do_disable_dynirq(info);
+		do_eoi_pirq(info);
+	}
 }
 
-static unsigned int __startup_pirq(unsigned int irq)
+static unsigned int __startup_pirq(struct irq_info *info)
 {
 	struct evtchn_bind_pirq bind_pirq;
-	struct irq_info *info = info_for_irq(irq);
-	evtchn_port_t evtchn = evtchn_from_irq(irq);
+	evtchn_port_t evtchn = info->evtchn;
 	int rc;
 
-	BUG_ON(info->type != IRQT_PIRQ);
-
 	if (VALID_EVTCHN(evtchn))
 		goto out;
 
-	bind_pirq.pirq = pirq_from_irq(irq);
+	bind_pirq.pirq = pirq_from_irq(info);
 	/* NB. We are happy to share unless we are probing. */
 	bind_pirq.flags = info->u.pirq.flags & PIRQ_SHAREABLE ?
 					BIND_PIRQ__WILL_SHARE : 0;
 	rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_pirq, &bind_pirq);
 	if (rc != 0) {
-		pr_warn("Failed to obtain physical IRQ %d\n", irq);
+		pr_warn("Failed to obtain physical IRQ %d\n", info->irq);
 		return 0;
 	}
 	evtchn = bind_pirq.port;
 
-	pirq_query_unmask(irq);
+	pirq_query_unmask(info);
 
-	rc = set_evtchn_to_irq(evtchn, irq);
+	rc = set_evtchn_to_irq(evtchn, info->irq);
 	if (rc)
 		goto err;
 
 	info->evtchn = evtchn;
-	bind_evtchn_to_cpu(evtchn, 0, false);
+	bind_evtchn_to_cpu(info, 0, false);
 
 	rc = xen_evtchn_port_setup(evtchn);
 	if (rc)
@@ -900,26 +894,28 @@ static unsigned int __startup_pirq(unsigned int irq)
 out:
 	do_unmask(info, EVT_MASK_REASON_EXPLICIT);
 
-	eoi_pirq(irq_get_irq_data(irq));
+	do_eoi_pirq(info);
 
 	return 0;
 
 err:
-	pr_err("irq%d: Failed to set port to irq mapping (%d)\n", irq, rc);
+	pr_err("irq%d: Failed to set port to irq mapping (%d)\n", info->irq,
+	       rc);
 	xen_evtchn_close(evtchn);
 	return 0;
 }
 
 static unsigned int startup_pirq(struct irq_data *data)
 {
-	return __startup_pirq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+
+	return __startup_pirq(info);
 }
 
 static void shutdown_pirq(struct irq_data *data)
 {
-	unsigned int irq = data->irq;
-	struct irq_info *info = info_for_irq(irq);
-	evtchn_port_t evtchn = evtchn_from_irq(irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info->evtchn;
 
 	BUG_ON(info->type != IRQT_PIRQ);
 
@@ -957,10 +953,14 @@ int xen_irq_from_gsi(unsigned gsi)
 }
 EXPORT_SYMBOL_GPL(xen_irq_from_gsi);
 
-static void __unbind_from_irq(unsigned int irq)
+static void __unbind_from_irq(struct irq_info *info, unsigned int irq)
 {
-	evtchn_port_t evtchn = evtchn_from_irq(irq);
-	struct irq_info *info = info_for_irq(irq);
+	evtchn_port_t evtchn;
+
+	if (!info) {
+		xen_irq_free_desc(irq);
+		return;
+	}
 
 	if (info->refcnt > 0) {
 		info->refcnt--;
@@ -968,19 +968,22 @@ static void __unbind_from_irq(unsigned int irq)
 			return;
 	}
 
+	evtchn = info->evtchn;
+
 	if (VALID_EVTCHN(evtchn)) {
-		unsigned int cpu = cpu_from_irq(irq);
+		unsigned int cpu = info->cpu;
 		struct xenbus_device *dev;
 
 		if (!info->is_static)
 			xen_evtchn_close(evtchn);
 
-		switch (type_from_irq(irq)) {
+		switch (info->type) {
 		case IRQT_VIRQ:
-			per_cpu(virq_to_irq, cpu)[virq_from_irq(irq)] = -1;
+			per_cpu(virq_to_irq, cpu)[virq_from_irq(info)] = -1;
 			break;
 		case IRQT_IPI:
-			per_cpu(ipi_to_irq, cpu)[ipi_from_irq(irq)] = -1;
+			per_cpu(ipi_to_irq, cpu)[ipi_from_irq(info)] = -1;
+			per_cpu(ipi_to_evtchn, cpu)[ipi_from_irq(info)] = 0;
 			break;
 		case IRQT_EVTCHN:
 			dev = info->u.interdomain;
@@ -994,7 +997,7 @@ static void __unbind_from_irq(unsigned int irq)
 		xen_irq_info_cleanup(info);
 	}
 
-	xen_free_irq(irq);
+	xen_free_irq(info);
 }
 
 /*
@@ -1010,24 +1013,24 @@ static void __unbind_from_irq(unsigned int irq)
 int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 			     unsigned pirq, int shareable, char *name)
 {
-	int irq;
+	struct irq_info *info;
 	struct physdev_irq irq_op;
 	int ret;
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = xen_irq_from_gsi(gsi);
-	if (irq != -1) {
+	ret = xen_irq_from_gsi(gsi);
+	if (ret != -1) {
 		pr_info("%s: returning irq %d for gsi %u\n",
-			__func__, irq, gsi);
+			__func__, ret, gsi);
 		goto out;
 	}
 
-	irq = xen_allocate_irq_gsi(gsi);
-	if (irq < 0)
+	info = xen_allocate_irq_gsi(gsi);
+	if (!info)
 		goto out;
 
-	irq_op.irq = irq;
+	irq_op.irq = info->irq;
 	irq_op.vector = 0;
 
 	/* Only the privileged domain can do this. For non-priv, the pcifront
@@ -1035,20 +1038,19 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 	 * this in the priv domain. */
 	if (xen_initial_domain() &&
 	    HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
-		xen_free_irq(irq);
-		irq = -ENOSPC;
+		xen_free_irq(info);
+		ret = -ENOSPC;
 		goto out;
 	}
 
-	ret = xen_irq_info_pirq_setup(irq, 0, pirq, gsi, DOMID_SELF,
+	ret = xen_irq_info_pirq_setup(info, 0, pirq, gsi, DOMID_SELF,
 			       shareable ? PIRQ_SHAREABLE : 0);
 	if (ret < 0) {
-		__unbind_from_irq(irq);
-		irq = ret;
+		__unbind_from_irq(info, info->irq);
 		goto out;
 	}
 
-	pirq_query_unmask(irq);
+	pirq_query_unmask(info);
 	/* We try to use the handler with the appropriate semantic for the
 	 * type of interrupt: if the interrupt is an edge triggered
 	 * interrupt we use handle_edge_irq.
@@ -1065,16 +1067,18 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 	 * is the right choice either way.
 	 */
 	if (shareable)
-		irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+		irq_set_chip_and_handler_name(info->irq, &xen_pirq_chip,
 				handle_fasteoi_irq, name);
 	else
-		irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+		irq_set_chip_and_handler_name(info->irq, &xen_pirq_chip,
 				handle_edge_irq, name);
 
+	ret = info->irq;
+
 out:
 	mutex_unlock(&irq_mapping_update_lock);
 
-	return irq;
+	return ret;
 }
 
 #ifdef CONFIG_PCI_MSI
@@ -1096,17 +1100,24 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 			     int pirq, int nvec, const char *name, domid_t domid)
 {
 	int i, irq, ret;
+	struct irq_info *info;
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = xen_allocate_irqs_dynamic(nvec);
+	irq = irq_alloc_descs(-1, 0, nvec, -1);
 	if (irq < 0)
 		goto out;
 
 	for (i = 0; i < nvec; i++) {
+		info = xen_irq_init(irq + i);
+		if (!info) {
+			ret = -ENOMEM;
+			goto error_irq;
+		}
+
 		irq_set_chip_and_handler_name(irq + i, &xen_pirq_chip, handle_edge_irq, name);
 
-		ret = xen_irq_info_pirq_setup(irq + i, 0, pirq + i, 0, domid,
+		ret = xen_irq_info_pirq_setup(info, 0, pirq + i, 0, domid,
 					      i == 0 ? 0 : PIRQ_MSI_GROUP);
 		if (ret < 0)
 			goto error_irq;
@@ -1118,9 +1129,12 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 out:
 	mutex_unlock(&irq_mapping_update_lock);
 	return irq;
+
 error_irq:
-	while (nvec--)
-		__unbind_from_irq(irq + nvec);
+	while (nvec--) {
+		info = info_for_irq(irq + nvec);
+		__unbind_from_irq(info, irq + nvec);
+	}
 	mutex_unlock(&irq_mapping_update_lock);
 	return ret;
 }
@@ -1156,67 +1170,45 @@ int xen_destroy_irq(int irq)
 		}
 	}
 
-	xen_free_irq(irq);
+	xen_free_irq(info);
 
 out:
 	mutex_unlock(&irq_mapping_update_lock);
 	return rc;
 }
 
-int xen_irq_from_pirq(unsigned pirq)
-{
-	int irq;
-
-	struct irq_info *info;
-
-	mutex_lock(&irq_mapping_update_lock);
-
-	list_for_each_entry(info, &xen_irq_list_head, list) {
-		if (info->type != IRQT_PIRQ)
-			continue;
-		irq = info->irq;
-		if (info->u.pirq.pirq == pirq)
-			goto out;
-	}
-	irq = -1;
-out:
-	mutex_unlock(&irq_mapping_update_lock);
-
-	return irq;
-}
-
-
 int xen_pirq_from_irq(unsigned irq)
 {
-	return pirq_from_irq(irq);
+	struct irq_info *info = info_for_irq(irq);
+
+	return pirq_from_irq(info);
 }
 EXPORT_SYMBOL_GPL(xen_pirq_from_irq);
 
 static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip,
 				   struct xenbus_device *dev)
 {
-	int irq;
-	int ret;
+	int ret = -ENOMEM;
+	struct irq_info *info;
 
 	if (evtchn >= xen_evtchn_max_channels())
 		return -ENOMEM;
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = get_evtchn_to_irq(evtchn);
+	info = evtchn_to_info(evtchn);
 
-	if (irq == -1) {
-		irq = xen_allocate_irq_dynamic();
-		if (irq < 0)
+	if (!info) {
+		info = xen_allocate_irq_dynamic();
+		if (!info)
 			goto out;
 
-		irq_set_chip_and_handler_name(irq, chip,
+		irq_set_chip_and_handler_name(info->irq, chip,
 					      handle_edge_irq, "event");
 
-		ret = xen_irq_info_evtchn_setup(irq, evtchn, dev);
+		ret = xen_irq_info_evtchn_setup(info, evtchn, dev);
 		if (ret < 0) {
-			__unbind_from_irq(irq);
-			irq = ret;
+			__unbind_from_irq(info, info->irq);
 			goto out;
 		}
 		/*
@@ -1226,17 +1218,17 @@ static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip,
 		 * affinity setting is not invoked on them so nothing would
 		 * bind the channel.
 		 */
-		bind_evtchn_to_cpu(evtchn, 0, false);
-	} else {
-		struct irq_info *info = info_for_irq(irq);
-		if (!WARN_ON(!info || info->type != IRQT_EVTCHN))
-			info->refcnt++;
+		bind_evtchn_to_cpu(info, 0, false);
+	} else if (!WARN_ON(info->type != IRQT_EVTCHN)) {
+		info->refcnt++;
 	}
 
+	ret = info->irq;
+
 out:
 	mutex_unlock(&irq_mapping_update_lock);
 
-	return irq;
+	return ret;
 }
 
 int bind_evtchn_to_irq(evtchn_port_t evtchn)
@@ -1255,18 +1247,19 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 {
 	struct evtchn_bind_ipi bind_ipi;
 	evtchn_port_t evtchn;
-	int ret, irq;
+	struct irq_info *info;
+	int ret;
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = per_cpu(ipi_to_irq, cpu)[ipi];
+	ret = per_cpu(ipi_to_irq, cpu)[ipi];
 
-	if (irq == -1) {
-		irq = xen_allocate_irq_dynamic();
-		if (irq < 0)
+	if (ret == -1) {
+		info = xen_allocate_irq_dynamic();
+		if (!info)
 			goto out;
 
-		irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
+		irq_set_chip_and_handler_name(info->irq, &xen_percpu_chip,
 					      handle_percpu_irq, "ipi");
 
 		bind_ipi.vcpu = xen_vcpu_nr(cpu);
@@ -1275,25 +1268,25 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 			BUG();
 		evtchn = bind_ipi.port;
 
-		ret = xen_irq_info_ipi_setup(cpu, irq, evtchn, ipi);
+		ret = xen_irq_info_ipi_setup(info, cpu, evtchn, ipi);
 		if (ret < 0) {
-			__unbind_from_irq(irq);
-			irq = ret;
+			__unbind_from_irq(info, info->irq);
 			goto out;
 		}
 		/*
 		 * Force the affinity mask to the target CPU so proc shows
 		 * the correct target.
 		 */
-		bind_evtchn_to_cpu(evtchn, cpu, true);
+		bind_evtchn_to_cpu(info, cpu, true);
+		ret = info->irq;
 	} else {
-		struct irq_info *info = info_for_irq(irq);
+		info = info_for_irq(ret);
 		WARN_ON(info == NULL || info->type != IRQT_IPI);
 	}
 
  out:
 	mutex_unlock(&irq_mapping_update_lock);
-	return irq;
+	return ret;
 }
 
 static int bind_interdomain_evtchn_to_irq_chip(struct xenbus_device *dev,
@@ -1361,22 +1354,23 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu)
 {
 	struct evtchn_bind_virq bind_virq;
 	evtchn_port_t evtchn = 0;
-	int irq, ret;
+	struct irq_info *info;
+	int ret;
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = per_cpu(virq_to_irq, cpu)[virq];
+	ret = per_cpu(virq_to_irq, cpu)[virq];
 
-	if (irq == -1) {
-		irq = xen_allocate_irq_dynamic();
-		if (irq < 0)
+	if (ret == -1) {
+		info = xen_allocate_irq_dynamic();
+		if (!info)
 			goto out;
 
 		if (percpu)
-			irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
+			irq_set_chip_and_handler_name(info->irq, &xen_percpu_chip,
 						      handle_percpu_irq, "virq");
 		else
-			irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
+			irq_set_chip_and_handler_name(info->irq, &xen_dynamic_chip,
 						      handle_edge_irq, "virq");
 
 		bind_virq.virq = virq;
@@ -1391,10 +1385,9 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu)
 			BUG_ON(ret < 0);
 		}
 
-		ret = xen_irq_info_virq_setup(cpu, irq, evtchn, virq);
+		ret = xen_irq_info_virq_setup(info, cpu, evtchn, virq);
 		if (ret < 0) {
-			__unbind_from_irq(irq);
-			irq = ret;
+			__unbind_from_irq(info, info->irq);
 			goto out;
 		}
 
@@ -1402,22 +1395,26 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu)
 		 * Force the affinity mask for percpu interrupts so proc
 		 * shows the correct target.
 		 */
-		bind_evtchn_to_cpu(evtchn, cpu, percpu);
+		bind_evtchn_to_cpu(info, cpu, percpu);
+		ret = info->irq;
 	} else {
-		struct irq_info *info = info_for_irq(irq);
+		info = info_for_irq(ret);
 		WARN_ON(info == NULL || info->type != IRQT_VIRQ);
 	}
 
 out:
 	mutex_unlock(&irq_mapping_update_lock);
 
-	return irq;
+	return ret;
 }
 
 static void unbind_from_irq(unsigned int irq)
 {
+	struct irq_info *info;
+
 	mutex_lock(&irq_mapping_update_lock);
-	__unbind_from_irq(irq);
+	info = info_for_irq(irq);
+	__unbind_from_irq(info, irq);
 	mutex_unlock(&irq_mapping_update_lock);
 }
 
@@ -1568,13 +1565,7 @@ EXPORT_SYMBOL_GPL(xen_set_irq_priority);
 
 int evtchn_make_refcounted(evtchn_port_t evtchn, bool is_static)
 {
-	int irq = get_evtchn_to_irq(evtchn);
-	struct irq_info *info;
-
-	if (irq == -1)
-		return -ENOENT;
-
-	info = info_for_irq(irq);
+	struct irq_info *info = evtchn_to_info(evtchn);
 
 	if (!info)
 		return -ENOENT;
@@ -1590,7 +1581,6 @@ EXPORT_SYMBOL_GPL(evtchn_make_refcounted);
 
 int evtchn_get(evtchn_port_t evtchn)
 {
-	int irq;
 	struct irq_info *info;
 	int err = -ENOENT;
 
@@ -1599,11 +1589,7 @@ int evtchn_get(evtchn_port_t evtchn)
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = get_evtchn_to_irq(evtchn);
-	if (irq == -1)
-		goto done;
-
-	info = info_for_irq(irq);
+	info = evtchn_to_info(evtchn);
 
 	if (!info)
 		goto done;
@@ -1623,16 +1609,17 @@ EXPORT_SYMBOL_GPL(evtchn_get);
 
 void evtchn_put(evtchn_port_t evtchn)
 {
-	int irq = get_evtchn_to_irq(evtchn);
-	if (WARN_ON(irq == -1))
+	struct irq_info *info = evtchn_to_info(evtchn);
+
+	if (WARN_ON(!info))
 		return;
-	unbind_from_irq(irq);
+	unbind_from_irq(info->irq);
 }
 EXPORT_SYMBOL_GPL(evtchn_put);
 
 void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector)
 {
-	int irq;
+	evtchn_port_t evtchn;
 
 #ifdef CONFIG_X86
 	if (unlikely(vector == XEN_NMI_VECTOR)) {
@@ -1643,9 +1630,9 @@ void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector)
 		return;
 	}
 #endif
-	irq = per_cpu(ipi_to_irq, cpu)[vector];
-	BUG_ON(irq < 0);
-	notify_remote_via_irq(irq);
+	evtchn = per_cpu(ipi_to_evtchn, cpu)[vector];
+	BUG_ON(evtchn == 0);
+	notify_remote_via_evtchn(evtchn);
 }
 
 struct evtchn_loop_ctrl {
@@ -1656,12 +1643,10 @@ struct evtchn_loop_ctrl {
 
 void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl)
 {
-	int irq;
-	struct irq_info *info;
+	struct irq_info *info = evtchn_to_info(port);
 	struct xenbus_device *dev;
 
-	irq = get_evtchn_to_irq(port);
-	if (irq == -1)
+	if (!info)
 		return;
 
 	/*
@@ -1686,7 +1671,6 @@ void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl)
 		}
 	}
 
-	info = info_for_irq(irq);
 	if (xchg_acquire(&info->is_active, 1))
 		return;
 
@@ -1700,7 +1684,7 @@ void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl)
 		info->eoi_time = get_jiffies_64() + event_eoi_delay;
 	}
 
-	generic_handle_irq(irq);
+	generic_handle_irq(info->irq);
 }
 
 int xen_evtchn_do_upcall(void)
@@ -1758,16 +1742,17 @@ void rebind_evtchn_irq(evtchn_port_t evtchn, int irq)
 	mutex_lock(&irq_mapping_update_lock);
 
 	/* After resume the irq<->evtchn mappings are all cleared out */
-	BUG_ON(get_evtchn_to_irq(evtchn) != -1);
+	BUG_ON(evtchn_to_info(evtchn));
 	/* Expect irq to have been bound before,
 	   so there should be a proper type */
 	BUG_ON(info->type == IRQT_UNBOUND);
 
-	(void)xen_irq_info_evtchn_setup(irq, evtchn, NULL);
+	info->irq = irq;
+	(void)xen_irq_info_evtchn_setup(info, evtchn, NULL);
 
 	mutex_unlock(&irq_mapping_update_lock);
 
-	bind_evtchn_to_cpu(evtchn, info->cpu, false);
+	bind_evtchn_to_cpu(info, info->cpu, false);
 
 	/* Unmask the event channel. */
 	enable_irq(irq);
@@ -1801,7 +1786,7 @@ static int xen_rebind_evtchn_to_cpu(struct irq_info *info, unsigned int tcpu)
 	 * it, but don't do the xenlinux-level rebind in that case.
 	 */
 	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
-		bind_evtchn_to_cpu(evtchn, tcpu, false);
+		bind_evtchn_to_cpu(info, tcpu, false);
 
 	do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 
@@ -1858,28 +1843,30 @@ static void enable_dynirq(struct irq_data *data)
 		do_unmask(info, EVT_MASK_REASON_EXPLICIT);
 }
 
-static void disable_dynirq(struct irq_data *data)
+static void do_ack_dynirq(struct irq_info *info)
 {
-	struct irq_info *info = info_for_irq(data->irq);
-	evtchn_port_t evtchn = info ? info->evtchn : 0;
+	evtchn_port_t evtchn = info->evtchn;
 
 	if (VALID_EVTCHN(evtchn))
-		do_mask(info, EVT_MASK_REASON_EXPLICIT);
+		event_handler_exit(info);
 }
 
 static void ack_dynirq(struct irq_data *data)
 {
 	struct irq_info *info = info_for_irq(data->irq);
-	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
-	if (VALID_EVTCHN(evtchn))
-		event_handler_exit(info);
+	if (info)
+		do_ack_dynirq(info);
 }
 
 static void mask_ack_dynirq(struct irq_data *data)
 {
-	disable_dynirq(data);
-	ack_dynirq(data);
+	struct irq_info *info = info_for_irq(data->irq);
+
+	if (info) {
+		do_disable_dynirq(info);
+		do_ack_dynirq(info);
+	}
 }
 
 static void lateeoi_ack_dynirq(struct irq_data *data)
@@ -1952,13 +1939,13 @@ static void restore_pirqs(void)
 		if (rc) {
 			pr_warn("xen map irq failed gsi=%d irq=%d pirq=%d rc=%d\n",
 				gsi, irq, pirq, rc);
-			xen_free_irq(irq);
+			xen_free_irq(info);
 			continue;
 		}
 
 		printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq);
 
-		__startup_pirq(irq);
+		__startup_pirq(info);
 	}
 }
 
@@ -1966,13 +1953,15 @@ static void restore_cpu_virqs(unsigned int cpu)
 {
 	struct evtchn_bind_virq bind_virq;
 	evtchn_port_t evtchn;
+	struct irq_info *info;
 	int virq, irq;
 
 	for (virq = 0; virq < NR_VIRQS; virq++) {
 		if ((irq = per_cpu(virq_to_irq, cpu)[virq]) == -1)
 			continue;
+		info = info_for_irq(irq);
 
-		BUG_ON(virq_from_irq(irq) != virq);
+		BUG_ON(virq_from_irq(info) != virq);
 
 		/* Get a new binding from Xen. */
 		bind_virq.virq = virq;
@@ -1983,9 +1972,9 @@ static void restore_cpu_virqs(unsigned int cpu)
 		evtchn = bind_virq.port;
 
 		/* Record the new mapping. */
-		(void)xen_irq_info_virq_setup(cpu, irq, evtchn, virq);
+		xen_irq_info_virq_setup(info, cpu, evtchn, virq);
 		/* The affinity mask is still valid */
-		bind_evtchn_to_cpu(evtchn, cpu, false);
+		bind_evtchn_to_cpu(info, cpu, false);
 	}
 }
 
@@ -1993,13 +1982,15 @@ static void restore_cpu_ipis(unsigned int cpu)
 {
 	struct evtchn_bind_ipi bind_ipi;
 	evtchn_port_t evtchn;
+	struct irq_info *info;
 	int ipi, irq;
 
 	for (ipi = 0; ipi < XEN_NR_IPIS; ipi++) {
 		if ((irq = per_cpu(ipi_to_irq, cpu)[ipi]) == -1)
 			continue;
+		info = info_for_irq(irq);
 
-		BUG_ON(ipi_from_irq(irq) != ipi);
+		BUG_ON(ipi_from_irq(info) != ipi);
 
 		/* Get a new binding from Xen. */
 		bind_ipi.vcpu = xen_vcpu_nr(cpu);
@@ -2009,9 +2000,9 @@ static void restore_cpu_ipis(unsigned int cpu)
 		evtchn = bind_ipi.port;
 
 		/* Record the new mapping. */
-		(void)xen_irq_info_ipi_setup(cpu, irq, evtchn, ipi);
+		xen_irq_info_ipi_setup(info, cpu, evtchn, ipi);
 		/* The affinity mask is still valid */
-		bind_evtchn_to_cpu(evtchn, cpu, false);
+		bind_evtchn_to_cpu(info, cpu, false);
 	}
 }
 
@@ -2025,13 +2016,6 @@ void xen_clear_irq_pending(int irq)
 		event_handler_exit(info);
 }
 EXPORT_SYMBOL(xen_clear_irq_pending);
-void xen_set_irq_pending(int irq)
-{
-	evtchn_port_t evtchn = evtchn_from_irq(irq);
-
-	if (VALID_EVTCHN(evtchn))
-		set_evtchn(evtchn);
-}
 
 bool xen_test_irq_pending(int irq)
 {
diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h
index 4d3398eff9cdf1..19ae31695edcf1 100644
--- a/drivers/xen/events/events_internal.h
+++ b/drivers/xen/events/events_internal.h
@@ -33,7 +33,6 @@ struct evtchn_ops {
 
 extern const struct evtchn_ops *evtchn_ops;
 
-int get_evtchn_to_irq(evtchn_port_t evtchn);
 void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl);
 
 unsigned int cpu_from_evtchn(evtchn_port_t evtchn);
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index b3e3d1bb37f3e3..50865527314538 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -47,6 +47,9 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
+#ifdef CONFIG_ACPI
+#include <acpi/processor.h>
+#endif
 
 /*
  * @cpu_id: Xen physical cpu logic number
@@ -400,4 +403,23 @@ bool __init xen_processor_present(uint32_t acpi_id)
 
 	return online;
 }
+
+void xen_sanitize_proc_cap_bits(uint32_t *cap)
+{
+	struct xen_platform_op op = {
+		.cmd			= XENPF_set_processor_pminfo,
+		.u.set_pminfo.id	= -1,
+		.u.set_pminfo.type	= XEN_PM_PDC,
+	};
+	u32 buf[3] = { ACPI_PDC_REVISION_ID, 1, *cap };
+	int ret;
+
+	set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
+	ret = HYPERVISOR_platform_op(&op);
+	if (ret)
+		pr_err("sanitize of _PDC buffer bits from Xen failed: %d\n",
+		       ret);
+	else
+		*cap = buf[2];
+}
 #endif
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 1ce7f3c7a95093..0eb337a8ec0fa2 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -1115,7 +1115,7 @@ struct privcmd_kernel_ioreq {
 	spinlock_t lock; /* Protects ioeventfds list */
 	struct list_head ioeventfds;
 	struct list_head list;
-	struct ioreq_port ports[0];
+	struct ioreq_port ports[] __counted_by(vcpus);
 };
 
 static irqreturn_t ioeventfd_interrupt(int irq, void *dev_id)
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 946bd56f0ac53e..0e6c6c25d154f5 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -405,4 +405,5 @@ const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.get_sgtable = dma_common_get_sgtable,
 	.alloc_pages = dma_common_alloc_pages,
 	.free_pages = dma_common_free_pages,
+	.max_mapping_size = swiotlb_max_mapping_size,
 };
diff --git a/drivers/xen/xen-front-pgdir-shbuf.c b/drivers/xen/xen-front-pgdir-shbuf.c
index b52e0fa595a992..223870a0111b27 100644
--- a/drivers/xen/xen-front-pgdir-shbuf.c
+++ b/drivers/xen/xen-front-pgdir-shbuf.c
@@ -21,7 +21,7 @@
 
 #include <xen/xen-front-pgdir-shbuf.h>
 
-/**
+/*
  * This structure represents the structure of a shared page
  * that contains grant references to the pages of the shared
  * buffer. This structure is common to many Xen para-virtualized
@@ -33,7 +33,7 @@ struct xen_page_directory {
 	grant_ref_t gref[]; /* Variable length */
 };
 
-/**
+/*
  * Shared buffer ops which are differently implemented
  * depending on the allocation mode, e.g. if the buffer
  * is allocated by the corresponding backend or frontend.
@@ -61,7 +61,7 @@ struct xen_front_pgdir_shbuf_ops {
 	int (*unmap)(struct xen_front_pgdir_shbuf *buf);
 };
 
-/**
+/*
  * Get granted reference to the very first page of the
  * page directory. Usually this is passed to the backend,
  * so it can find/fill the grant references to the buffer's
@@ -81,7 +81,7 @@ xen_front_pgdir_shbuf_get_dir_start(struct xen_front_pgdir_shbuf *buf)
 }
 EXPORT_SYMBOL_GPL(xen_front_pgdir_shbuf_get_dir_start);
 
-/**
+/*
  * Map granted references of the shared buffer.
  *
  * Depending on the shared buffer mode of allocation
@@ -102,7 +102,7 @@ int xen_front_pgdir_shbuf_map(struct xen_front_pgdir_shbuf *buf)
 }
 EXPORT_SYMBOL_GPL(xen_front_pgdir_shbuf_map);
 
-/**
+/*
  * Unmap granted references of the shared buffer.
  *
  * Depending on the shared buffer mode of allocation
@@ -123,7 +123,7 @@ int xen_front_pgdir_shbuf_unmap(struct xen_front_pgdir_shbuf *buf)
 }
 EXPORT_SYMBOL_GPL(xen_front_pgdir_shbuf_unmap);
 
-/**
+/*
  * Free all the resources of the shared buffer.
  *
  * \param buf shared buffer which resources to be freed.
@@ -150,7 +150,7 @@ EXPORT_SYMBOL_GPL(xen_front_pgdir_shbuf_free);
 				 offsetof(struct xen_page_directory, \
 					  gref)) / sizeof(grant_ref_t))
 
-/**
+/*
  * Get the number of pages the page directory consumes itself.
  *
  * \param buf shared buffer.
@@ -160,7 +160,7 @@ static int get_num_pages_dir(struct xen_front_pgdir_shbuf *buf)
 	return DIV_ROUND_UP(buf->num_pages, XEN_NUM_GREFS_PER_PAGE);
 }
 
-/**
+/*
  * Calculate the number of grant references needed to share the buffer
  * and its pages when backend allocates the buffer.
  *
@@ -172,7 +172,7 @@ static void backend_calc_num_grefs(struct xen_front_pgdir_shbuf *buf)
 	buf->num_grefs = get_num_pages_dir(buf);
 }
 
-/**
+/*
  * Calculate the number of grant references needed to share the buffer
  * and its pages when frontend allocates the buffer.
  *
@@ -190,7 +190,7 @@ static void guest_calc_num_grefs(struct xen_front_pgdir_shbuf *buf)
 #define xen_page_to_vaddr(page) \
 	((uintptr_t)pfn_to_kaddr(page_to_xen_pfn(page)))
 
-/**
+/*
  * Unmap the buffer previously mapped with grant references
  * provided by the backend.
  *
@@ -238,7 +238,7 @@ static int backend_unmap(struct xen_front_pgdir_shbuf *buf)
 	return ret;
 }
 
-/**
+/*
  * Map the buffer with grant references provided by the backend.
  *
  * \param buf shared buffer.
@@ -320,7 +320,7 @@ static int backend_map(struct xen_front_pgdir_shbuf *buf)
 	return ret;
 }
 
-/**
+/*
  * Fill page directory with grant references to the pages of the
  * page directory itself.
  *
@@ -350,7 +350,7 @@ static void backend_fill_page_dir(struct xen_front_pgdir_shbuf *buf)
 	page_dir->gref_dir_next_page = XEN_GREF_LIST_END;
 }
 
-/**
+/*
  * Fill page directory with grant references to the pages of the
  * page directory and the buffer we share with the backend.
  *
@@ -389,7 +389,7 @@ static void guest_fill_page_dir(struct xen_front_pgdir_shbuf *buf)
 	}
 }
 
-/**
+/*
  * Grant references to the frontend's buffer pages.
  *
  * These will be shared with the backend, so it can
@@ -418,7 +418,7 @@ static int guest_grant_refs_for_buffer(struct xen_front_pgdir_shbuf *buf,
 	return 0;
 }
 
-/**
+/*
  * Grant all the references needed to share the buffer.
  *
  * Grant references to the page directory pages and, if
@@ -466,7 +466,7 @@ static int grant_references(struct xen_front_pgdir_shbuf *buf)
 	return 0;
 }
 
-/**
+/*
  * Allocate all required structures to mange shared buffer.
  *
  * \param buf shared buffer.
@@ -506,7 +506,7 @@ static const struct xen_front_pgdir_shbuf_ops local_ops = {
 	.grant_refs_for_buffer = guest_grant_refs_for_buffer,
 };
 
-/**
+/*
  * Allocate a new instance of a shared buffer.
  *
  * \param cfg configuration to be used while allocating a new shared buffer.
diff --git a/fs/Kconfig b/fs/Kconfig
index fd1f655b4f1ff3..42837617a55b54 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -268,6 +268,7 @@ config HUGETLBFS
 
 config HUGETLB_PAGE
 	def_bool HUGETLBFS
+	select XARRAY_MULTI
 
 config HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	def_bool HUGETLB_PAGE
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index 988c2ac7cececd..926cb1188eba6c 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -409,10 +409,12 @@ static int afs_update_cell(struct afs_cell *cell)
 		if (ret == -ENOMEM)
 			goto out_wake;
 
-		ret = -ENOMEM;
 		vllist = afs_alloc_vlserver_list(0);
-		if (!vllist)
+		if (!vllist) {
+			if (ret >= 0)
+				ret = -ENOMEM;
 			goto out_wake;
+		}
 
 		switch (ret) {
 		case -ENODATA:
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 4d04ef2d3ae7bb..1f656005018ea0 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -114,6 +114,7 @@ static int afs_probe_cell_name(struct dentry *dentry)
 	struct afs_net *net = afs_d2net(dentry);
 	const char *name = dentry->d_name.name;
 	size_t len = dentry->d_name.len;
+	char *result = NULL;
 	int ret;
 
 	/* Names prefixed with a dot are R/W mounts. */
@@ -131,9 +132,22 @@ static int afs_probe_cell_name(struct dentry *dentry)
 	}
 
 	ret = dns_query(net->net, "afsdb", name, len, "srv=1",
-			NULL, NULL, false);
-	if (ret == -ENODATA)
-		ret = -EDESTADDRREQ;
+			&result, NULL, false);
+	if (ret == -ENODATA || ret == -ENOKEY || ret == 0)
+		ret = -ENOENT;
+	if (ret > 0 && ret >= sizeof(struct dns_server_list_v1_header)) {
+		struct dns_server_list_v1_header *v1 = (void *)result;
+
+		if (v1->hdr.zero == 0 &&
+		    v1->hdr.content == DNS_PAYLOAD_IS_SERVER_LIST &&
+		    v1->hdr.version == 1 &&
+		    (v1->status != DNS_LOOKUP_GOOD &&
+		     v1->status != DNS_LOOKUP_GOOD_WITH_BAD))
+			return -ENOENT;
+
+	}
+
+	kfree(result);
 	return ret;
 }
 
@@ -252,20 +266,9 @@ static int afs_dynroot_d_revalidate(struct dentry *dentry, unsigned int flags)
 	return 1;
 }
 
-/*
- * Allow the VFS to enquire as to whether a dentry should be unhashed (mustn't
- * sleep)
- * - called from dput() when d_count is going to 0.
- * - return 1 to request dentry be unhashed, 0 otherwise
- */
-static int afs_dynroot_d_delete(const struct dentry *dentry)
-{
-	return d_really_is_positive(dentry);
-}
-
 const struct dentry_operations afs_dynroot_dentry_operations = {
 	.d_revalidate	= afs_dynroot_d_revalidate,
-	.d_delete	= afs_dynroot_d_delete,
+	.d_delete	= always_delete_dentry,
 	.d_release	= afs_d_release,
 	.d_automount	= afs_d_automount,
 };
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index c9cef3782b4ae4..7385d62c8cf503 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -553,6 +553,7 @@ struct afs_server_entry {
 };
 
 struct afs_server_list {
+	struct rcu_head		rcu;
 	afs_volid_t		vids[AFS_MAXTYPES]; /* Volume IDs */
 	refcount_t		usage;
 	unsigned char		nr_servers;
@@ -585,6 +586,7 @@ struct afs_volume {
 #define AFS_VOLUME_OFFLINE	4	/* - T if volume offline notice given */
 #define AFS_VOLUME_BUSY		5	/* - T if volume busy notice given */
 #define AFS_VOLUME_MAYBE_NO_IBULK 6	/* - T if some servers don't have InlineBulkStatus */
+#define AFS_VOLUME_RM_TREE	7	/* - Set if volume removed from cell->volumes */
 #ifdef CONFIG_AFS_FSCACHE
 	struct fscache_volume	*cache;		/* Caching cookie */
 #endif
@@ -1512,6 +1514,7 @@ extern struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *,
 extern struct afs_volume *afs_create_volume(struct afs_fs_context *);
 extern int afs_activate_volume(struct afs_volume *);
 extern void afs_deactivate_volume(struct afs_volume *);
+bool afs_try_get_volume(struct afs_volume *volume, enum afs_volume_trace reason);
 extern struct afs_volume *afs_get_volume(struct afs_volume *, enum afs_volume_trace);
 extern void afs_put_volume(struct afs_net *, struct afs_volume *, enum afs_volume_trace);
 extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *);
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index ed1644e7683f47..d642d06a453be7 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -424,7 +424,7 @@ error_kill_call:
 	if (call->async) {
 		if (cancel_work_sync(&call->async_work))
 			afs_put_call(call);
-		afs_put_call(call);
+		afs_set_call_complete(call, ret, 0);
 	}
 
 	ac->error = ret;
diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c
index ed9056703505fe..b59896b1de0af2 100644
--- a/fs/afs/server_list.c
+++ b/fs/afs/server_list.c
@@ -17,7 +17,7 @@ void afs_put_serverlist(struct afs_net *net, struct afs_server_list *slist)
 		for (i = 0; i < slist->nr_servers; i++)
 			afs_unuse_server(net, slist->servers[i].server,
 					 afs_server_trace_put_slist);
-		kfree(slist);
+		kfree_rcu(slist, rcu);
 	}
 }
 
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 95d713074dc813..a01a0fb2cdbb5c 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -407,6 +407,10 @@ static int afs_validate_fc(struct fs_context *fc)
 			return PTR_ERR(volume);
 
 		ctx->volume = volume;
+		if (volume->type != AFSVL_RWVOL) {
+			ctx->flock_mode = afs_flock_mode_local;
+			fc->sb_flags |= SB_RDONLY;
+		}
 	}
 
 	return 0;
diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c
index 488e58490b16e7..eb415ce563600e 100644
--- a/fs/afs/vl_rotate.c
+++ b/fs/afs/vl_rotate.c
@@ -58,6 +58,12 @@ static bool afs_start_vl_iteration(struct afs_vl_cursor *vc)
 		}
 
 		/* Status load is ordered after lookup counter load */
+		if (cell->dns_status == DNS_LOOKUP_GOT_NOT_FOUND) {
+			pr_warn("No record of cell %s\n", cell->name);
+			vc->error = -ENOENT;
+			return false;
+		}
+
 		if (cell->dns_source == DNS_RECORD_UNAVAILABLE) {
 			vc->error = -EDESTADDRREQ;
 			return false;
@@ -285,6 +291,7 @@ failed:
  */
 static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc)
 {
+	struct afs_cell *cell = vc->cell;
 	static int count;
 	int i;
 
@@ -294,6 +301,9 @@ static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc)
 
 	rcu_read_lock();
 	pr_notice("EDESTADDR occurred\n");
+	pr_notice("CELL: %s err=%d\n", cell->name, cell->error);
+	pr_notice("DNS: src=%u st=%u lc=%x\n",
+		  cell->dns_source, cell->dns_status, cell->dns_lookup_count);
 	pr_notice("VC: ut=%lx ix=%u ni=%hu fl=%hx err=%hd\n",
 		  vc->untried, vc->index, vc->nr_iterations, vc->flags, vc->error);
 
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 29d483c8028130..115c081a8e2ce5 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -32,8 +32,13 @@ static struct afs_volume *afs_insert_volume_into_cell(struct afs_cell *cell,
 		} else if (p->vid > volume->vid) {
 			pp = &(*pp)->rb_right;
 		} else {
-			volume = afs_get_volume(p, afs_volume_trace_get_cell_insert);
-			goto found;
+			if (afs_try_get_volume(p, afs_volume_trace_get_cell_insert)) {
+				volume = p;
+				goto found;
+			}
+
+			set_bit(AFS_VOLUME_RM_TREE, &volume->flags);
+			rb_replace_node_rcu(&p->cell_node, &volume->cell_node, &cell->volumes);
 		}
 	}
 
@@ -56,7 +61,8 @@ static void afs_remove_volume_from_cell(struct afs_volume *volume)
 				 afs_volume_trace_remove);
 		write_seqlock(&cell->volume_lock);
 		hlist_del_rcu(&volume->proc_link);
-		rb_erase(&volume->cell_node, &cell->volumes);
+		if (!test_and_set_bit(AFS_VOLUME_RM_TREE, &volume->flags))
+			rb_erase(&volume->cell_node, &cell->volumes);
 		write_sequnlock(&cell->volume_lock);
 	}
 }
@@ -232,6 +238,20 @@ static void afs_destroy_volume(struct afs_net *net, struct afs_volume *volume)
 }
 
 /*
+ * Try to get a reference on a volume record.
+ */
+bool afs_try_get_volume(struct afs_volume *volume, enum afs_volume_trace reason)
+{
+	int r;
+
+	if (__refcount_inc_not_zero(&volume->ref, &r)) {
+		trace_afs_volume(volume->vid, r + 1, reason);
+		return true;
+	}
+	return false;
+}
+
+/*
  * Get a reference on a volume record.
  */
 struct afs_volume *afs_get_volume(struct afs_volume *volume,
diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c
index a5083d447a62f1..1f5db686366316 100644
--- a/fs/autofs/inode.c
+++ b/fs/autofs/inode.c
@@ -309,9 +309,7 @@ static int autofs_fill_super(struct super_block *s, struct fs_context *fc)
 	struct autofs_fs_context *ctx = fc->fs_private;
 	struct autofs_sb_info *sbi = s->s_fs_info;
 	struct inode *root_inode;
-	struct dentry *root;
 	struct autofs_info *ino;
-	int ret = -ENOMEM;
 
 	pr_debug("starting up, sbi = %p\n", sbi);
 
@@ -328,56 +326,44 @@ static int autofs_fill_super(struct super_block *s, struct fs_context *fc)
 	 */
 	ino = autofs_new_ino(sbi);
 	if (!ino)
-		goto fail;
+		return -ENOMEM;
 
 	root_inode = autofs_get_inode(s, S_IFDIR | 0755);
+	if (!root_inode)
+		return -ENOMEM;
+
 	root_inode->i_uid = ctx->uid;
 	root_inode->i_gid = ctx->gid;
+	root_inode->i_fop = &autofs_root_operations;
+	root_inode->i_op = &autofs_dir_inode_operations;
 
-	root = d_make_root(root_inode);
-	if (!root)
-		goto fail_ino;
-
-	root->d_fsdata = ino;
+	s->s_root = d_make_root(root_inode);
+	if (unlikely(!s->s_root)) {
+		autofs_free_ino(ino);
+		return -ENOMEM;
+	}
+	s->s_root->d_fsdata = ino;
 
 	if (ctx->pgrp_set) {
 		sbi->oz_pgrp = find_get_pid(ctx->pgrp);
-		if (!sbi->oz_pgrp) {
-			ret = invalf(fc, "Could not find process group %d",
-				     ctx->pgrp);
-			goto fail_dput;
-		}
-	} else {
+		if (!sbi->oz_pgrp)
+			return invalf(fc, "Could not find process group %d",
+				      ctx->pgrp);
+	} else
 		sbi->oz_pgrp = get_task_pid(current, PIDTYPE_PGID);
-	}
 
 	if (autofs_type_trigger(sbi->type))
-		__managed_dentry_set_managed(root);
-
-	root_inode->i_fop = &autofs_root_operations;
-	root_inode->i_op = &autofs_dir_inode_operations;
+		/* s->s_root won't be contended so there's little to
+		 * be gained by not taking the d_lock when setting
+		 * d_flags, even when a lot mounts are being done.
+		 */
+		managed_dentry_set_managed(s->s_root);
 
 	pr_debug("pipe fd = %d, pgrp = %u\n",
 		 sbi->pipefd, pid_nr(sbi->oz_pgrp));
 
 	sbi->flags &= ~AUTOFS_SBI_CATATONIC;
-
-	/*
-	 * Success! Install the root dentry now to indicate completion.
-	 */
-	s->s_root = root;
 	return 0;
-
-	/*
-	 * Failure ... clean up.
-	 */
-fail_dput:
-	dput(root);
-	goto fail;
-fail_ino:
-	autofs_free_ino(ino);
-fail:
-	return ret;
 }
 
 /*
diff --git a/fs/bcachefs/Kconfig b/fs/bcachefs/Kconfig
index c08c2c7d6fbbab..fddc7be580223a 100644
--- a/fs/bcachefs/Kconfig
+++ b/fs/bcachefs/Kconfig
@@ -33,6 +33,18 @@ config BCACHEFS_QUOTA
 	depends on BCACHEFS_FS
 	select QUOTACTL
 
+config BCACHEFS_ERASURE_CODING
+	bool "bcachefs erasure coding (RAID5/6) support (EXPERIMENTAL)"
+	depends on BCACHEFS_FS
+	select QUOTACTL
+	help
+	This enables the "erasure_code" filesysystem and inode option, which
+	organizes data into reed-solomon stripes instead of ordinary
+	replication.
+
+	WARNING: this feature is still undergoing on disk format changes, and
+	should only be enabled for testing purposes.
+
 config BCACHEFS_POSIX_ACL
 	bool "bcachefs POSIX ACL support"
 	depends on BCACHEFS_FS
diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index b85c7765272f6e..0e615798260721 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -1297,6 +1297,30 @@ out:
 	return wp;
 }
 
+static noinline void
+deallocate_extra_replicas(struct bch_fs *c,
+			  struct open_buckets *ptrs,
+			  struct open_buckets *ptrs_no_use,
+			  unsigned extra_replicas)
+{
+	struct open_buckets ptrs2 = { 0 };
+	struct open_bucket *ob;
+	unsigned i;
+
+	open_bucket_for_each(c, ptrs, ob, i) {
+		unsigned d = bch_dev_bkey_exists(c, ob->dev)->mi.durability;
+
+		if (d && d <= extra_replicas) {
+			extra_replicas -= d;
+			ob_push(c, ptrs_no_use, ob);
+		} else {
+			ob_push(c, &ptrs2, ob);
+		}
+	}
+
+	*ptrs = ptrs2;
+}
+
 /*
  * Get us an open_bucket we can allocate from, return with it locked:
  */
@@ -1321,6 +1345,9 @@ int bch2_alloc_sectors_start_trans(struct btree_trans *trans,
 	int ret;
 	int i;
 
+	if (!IS_ENABLED(CONFIG_BCACHEFS_ERASURE_CODING))
+		erasure_code = false;
+
 	BUG_ON(flags & BCH_WRITE_ONLY_SPECIFIED_DEVS);
 
 	BUG_ON(!nr_replicas || !nr_replicas_required);
@@ -1347,8 +1374,17 @@ retry:
 			goto alloc_done;
 
 		/* Don't retry from all devices if we're out of open buckets: */
-		if (bch2_err_matches(ret, BCH_ERR_open_buckets_empty))
-			goto allocate_blocking;
+		if (bch2_err_matches(ret, BCH_ERR_open_buckets_empty)) {
+			int ret = open_bucket_add_buckets(trans, &ptrs, wp, devs_have,
+					      target, erasure_code,
+					      nr_replicas, &nr_effective,
+					      &have_cache, watermark,
+					      flags, cl);
+			if (!ret ||
+			    bch2_err_matches(ret, BCH_ERR_transaction_restart) ||
+			    bch2_err_matches(ret, BCH_ERR_open_buckets_empty))
+				goto alloc_done;
+		}
 
 		/*
 		 * Only try to allocate cache (durability = 0 devices) from the
@@ -1362,7 +1398,6 @@ retry:
 					      &have_cache, watermark,
 					      flags, cl);
 	} else {
-allocate_blocking:
 		ret = open_bucket_add_buckets(trans, &ptrs, wp, devs_have,
 					      target, erasure_code,
 					      nr_replicas, &nr_effective,
@@ -1382,6 +1417,9 @@ alloc_done:
 	if (ret)
 		goto err;
 
+	if (nr_effective > nr_replicas)
+		deallocate_extra_replicas(c, &ptrs, &wp->ptrs, nr_effective - nr_replicas);
+
 	/* Free buckets we didn't use: */
 	open_bucket_for_each(c, &wp->ptrs, ob, i)
 		open_bucket_free_unused(c, ob);
diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index ef02c9bb035417..23c0834a97a4ac 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -313,17 +313,17 @@ struct btree *bch2_backpointer_get_node(struct btree_trans *trans,
 				  bp.level - 1,
 				  0);
 	b = bch2_btree_iter_peek_node(iter);
-	if (IS_ERR(b))
+	if (IS_ERR_OR_NULL(b))
 		goto err;
 
 	BUG_ON(b->c.level != bp.level - 1);
 
-	if (b && extent_matches_bp(c, bp.btree_id, bp.level,
-				   bkey_i_to_s_c(&b->key),
-				   bucket, bp))
+	if (extent_matches_bp(c, bp.btree_id, bp.level,
+			      bkey_i_to_s_c(&b->key),
+			      bucket, bp))
 		return b;
 
-	if (b && btree_node_will_make_reachable(b)) {
+	if (btree_node_will_make_reachable(b)) {
 		b = ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node);
 	} else {
 		backpointer_not_found(trans, bp_pos, bp, bkey_i_to_s_c(&b->key));
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 9cb8684959ee17..dfa22f9d9a1d34 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -617,7 +617,7 @@ struct journal_seq_blacklist_table {
 		u64		start;
 		u64		end;
 		bool		dirty;
-	}			entries[0];
+	}			entries[];
 };
 
 struct journal_keys {
@@ -638,6 +638,8 @@ struct journal_keys {
 	size_t			gap;
 	size_t			nr;
 	size_t			size;
+	atomic_t		ref;
+	bool			initial_ref_held;
 };
 
 struct btree_trans_buf {
@@ -929,7 +931,7 @@ struct bch_fs {
 	mempool_t		compression_bounce[2];
 	mempool_t		compress_workspace[BCH_COMPRESSION_TYPE_NR];
 	mempool_t		decompress_workspace;
-	ZSTD_parameters		zstd_params;
+	size_t			zstd_workspace_size;
 
 	struct crypto_shash	*sha256;
 	struct crypto_sync_skcipher *chacha20;
diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 0a750953ff921b..1ab1f08d763b02 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -151,7 +151,11 @@ struct bpos {
 #else
 #error edit for your odd byteorder.
 #endif
-} __packed __aligned(4);
+} __packed
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+__aligned(4)
+#endif
+;
 
 #define KEY_INODE_MAX			((__u64)~0ULL)
 #define KEY_OFFSET_MAX			((__u64)~0ULL)
@@ -1528,7 +1532,7 @@ struct bch_sb_field_disk_groups {
 	x(move_extent_write,				36)	\
 	x(move_extent_finish,				37)	\
 	x(move_extent_fail,				38)	\
-	x(move_extent_alloc_mem_fail,			39)	\
+	x(move_extent_start_fail,			39)	\
 	x(copygc,					40)	\
 	x(copygc_wait,					41)	\
 	x(gc_gens_end,					42)	\
diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index 47e7770d058317..79495cd7a79499 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -9,6 +9,7 @@
 #include "debug.h"
 #include "errcode.h"
 #include "error.h"
+#include "journal.h"
 #include "trace.h"
 
 #include <linux/prefetch.h>
@@ -424,14 +425,11 @@ void bch2_fs_btree_cache_exit(struct bch_fs *c)
 		BUG_ON(btree_node_read_in_flight(b) ||
 		       btree_node_write_in_flight(b));
 
-		if (btree_node_dirty(b))
-			bch2_btree_complete_write(c, b, btree_current_write(b));
-		clear_btree_node_dirty_acct(c, b);
-
 		btree_node_data_free(c, b);
 	}
 
-	BUG_ON(atomic_read(&c->btree_cache.dirty));
+	BUG_ON(!bch2_journal_error(&c->journal) &&
+	       atomic_read(&c->btree_cache.dirty));
 
 	list_splice(&bc->freed_pcpu, &bc->freed_nonpcpu);
 
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 0b5d09c8475d00..30ab78a2451740 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -1541,8 +1541,8 @@ static int bch2_gc_alloc_start(struct bch_fs *c, bool metadata_only)
 		rcu_assign_pointer(ca->buckets_gc, buckets);
 	}
 
-	for_each_btree_key(trans, iter, BTREE_ID_alloc, POS_MIN,
-			   BTREE_ITER_PREFETCH, k, ret) {
+	ret = for_each_btree_key2(trans, iter, BTREE_ID_alloc, POS_MIN,
+				  BTREE_ITER_PREFETCH, k, ({
 		ca = bch_dev_bkey_exists(c, k.k->p.inode);
 		g = gc_bucket(ca, k.k->p.offset);
 
@@ -1561,8 +1561,9 @@ static int bch2_gc_alloc_start(struct bch_fs *c, bool metadata_only)
 			g->stripe		= a->stripe;
 			g->stripe_redundancy	= a->stripe_redundancy;
 		}
-	}
-	bch2_trans_iter_exit(trans, &iter);
+
+		0;
+	}));
 err:
 	bch2_trans_put(trans);
 	if (ret)
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 37d896edb06e04..5a720f0cd5a653 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -1358,10 +1358,9 @@ static bool btree_node_has_extra_bsets(struct bch_fs *c, unsigned offset, void *
 	return offset;
 }
 
-static void btree_node_read_all_replicas_done(struct closure *cl)
+static CLOSURE_CALLBACK(btree_node_read_all_replicas_done)
 {
-	struct btree_node_read_all *ra =
-		container_of(cl, struct btree_node_read_all, cl);
+	closure_type(ra, struct btree_node_read_all, cl);
 	struct bch_fs *c = ra->c;
 	struct btree *b = ra->b;
 	struct printbuf buf = PRINTBUF;
@@ -1567,7 +1566,7 @@ static int btree_node_read_all_replicas(struct bch_fs *c, struct btree *b, bool
 
 	if (sync) {
 		closure_sync(&ra->cl);
-		btree_node_read_all_replicas_done(&ra->cl);
+		btree_node_read_all_replicas_done(&ra->cl.work);
 	} else {
 		continue_at(&ra->cl, btree_node_read_all_replicas_done,
 			    c->io_complete_wq);
@@ -1705,8 +1704,8 @@ int bch2_btree_root_read(struct bch_fs *c, enum btree_id id,
 	return bch2_trans_run(c, __bch2_btree_root_read(trans, id, k, level));
 }
 
-void bch2_btree_complete_write(struct bch_fs *c, struct btree *b,
-			      struct btree_write *w)
+static void bch2_btree_complete_write(struct bch_fs *c, struct btree *b,
+				      struct btree_write *w)
 {
 	unsigned long old, new, v = READ_ONCE(b->will_make_reachable);
 
diff --git a/fs/bcachefs/btree_io.h b/fs/bcachefs/btree_io.h
index 7e03dd76fb3804..e0d7fa5b1dfb9a 100644
--- a/fs/bcachefs/btree_io.h
+++ b/fs/bcachefs/btree_io.h
@@ -134,9 +134,6 @@ void bch2_btree_node_read(struct bch_fs *, struct btree *, bool);
 int bch2_btree_root_read(struct bch_fs *, enum btree_id,
 			 const struct bkey_i *, unsigned);
 
-void bch2_btree_complete_write(struct bch_fs *, struct btree *,
-			      struct btree_write *);
-
 bool bch2_btree_post_write_cleanup(struct bch_fs *, struct btree *);
 
 enum btree_write_flags {
diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index c2adf3fbb0b3ab..6be79129738d0f 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -2981,7 +2981,8 @@ struct btree_trans *__bch2_trans_get(struct bch_fs *c, unsigned fn_idx)
 	trans->fn_idx		= fn_idx;
 	trans->locking_wait.task = current;
 	trans->journal_replay_not_finished =
-		!test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags);
+		unlikely(!test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags)) &&
+		atomic_inc_not_zero(&c->journal_keys.ref);
 	closure_init_stack(&trans->ref);
 
 	s = btree_trans_stats(trans);
@@ -3087,8 +3088,6 @@ void bch2_trans_put(struct btree_trans *trans)
 		srcu_read_unlock(&c->btree_trans_barrier, trans->srcu_idx);
 	}
 
-	bch2_journal_preres_put(&c->journal, &trans->journal_preres);
-
 	kfree(trans->extra_journal_entries.data);
 
 	if (trans->fs_usage_deltas) {
@@ -3100,6 +3099,9 @@ void bch2_trans_put(struct btree_trans *trans)
 			kfree(trans->fs_usage_deltas);
 	}
 
+	if (unlikely(trans->journal_replay_not_finished))
+		bch2_journal_keys_put(c);
+
 	if (trans->mem_bytes == BTREE_TRANS_MEM_MAX)
 		mempool_free(trans->mem, &c->btree_trans_mem_pool);
 	else
@@ -3212,10 +3214,9 @@ void bch2_fs_btree_iter_exit(struct bch_fs *c)
 	mempool_exit(&c->btree_trans_pool);
 }
 
-int bch2_fs_btree_iter_init(struct bch_fs *c)
+void bch2_fs_btree_iter_init_early(struct bch_fs *c)
 {
 	struct btree_transaction_stats *s;
-	int ret;
 
 	for (s = c->btree_transaction_stats;
 	     s < c->btree_transaction_stats + ARRAY_SIZE(c->btree_transaction_stats);
@@ -3226,6 +3227,11 @@ int bch2_fs_btree_iter_init(struct bch_fs *c)
 
 	INIT_LIST_HEAD(&c->btree_trans_list);
 	seqmutex_init(&c->btree_trans_lock);
+}
+
+int bch2_fs_btree_iter_init(struct bch_fs *c)
+{
+	int ret;
 
 	c->btree_trans_bufs = alloc_percpu(struct btree_trans_buf);
 	if (!c->btree_trans_bufs)
diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h
index 85e7cb52f6b6c4..eaffced4c132b5 100644
--- a/fs/bcachefs/btree_iter.h
+++ b/fs/bcachefs/btree_iter.h
@@ -938,6 +938,7 @@ unsigned bch2_trans_get_fn_idx(const char *);
 void bch2_btree_trans_to_text(struct printbuf *, struct btree_trans *);
 
 void bch2_fs_btree_iter_exit(struct bch_fs *);
+void bch2_fs_btree_iter_init_early(struct bch_fs *);
 int bch2_fs_btree_iter_init(struct bch_fs *);
 
 #endif /* _BCACHEFS_BTREE_ITER_H */
diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c
index 58a981bcf3aa8c..ec52f50d249d07 100644
--- a/fs/bcachefs/btree_journal_iter.c
+++ b/fs/bcachefs/btree_journal_iter.c
@@ -80,6 +80,8 @@ struct bkey_i *bch2_journal_keys_peek_upto(struct bch_fs *c, enum btree_id btree
 	struct journal_keys *keys = &c->journal_keys;
 	unsigned iters = 0;
 	struct journal_key *k;
+
+	BUG_ON(*idx > keys->nr);
 search:
 	if (!*idx)
 		*idx = __bch2_journal_key_search(keys, btree_id, level, pos);
@@ -189,10 +191,12 @@ int bch2_journal_key_insert_take(struct bch_fs *c, enum btree_id id,
 		/* Since @keys was full, there was no gap: */
 		memcpy(new_keys.d, keys->d, sizeof(keys->d[0]) * keys->nr);
 		kvfree(keys->d);
-		*keys = new_keys;
+		keys->d		= new_keys.d;
+		keys->nr	= new_keys.nr;
+		keys->size	= new_keys.size;
 
 		/* And now the gap is at the end: */
-		keys->gap = keys->nr;
+		keys->gap	= keys->nr;
 	}
 
 	journal_iters_move_gap(c, keys->gap, idx);
@@ -415,10 +419,16 @@ static int journal_sort_key_cmp(const void *_l, const void *_r)
 		cmp_int(l->journal_offset, r->journal_offset);
 }
 
-void bch2_journal_keys_free(struct journal_keys *keys)
+void bch2_journal_keys_put(struct bch_fs *c)
 {
+	struct journal_keys *keys = &c->journal_keys;
 	struct journal_key *i;
 
+	BUG_ON(atomic_read(&keys->ref) <= 0);
+
+	if (!atomic_dec_and_test(&keys->ref))
+		return;
+
 	move_gap(keys->d, keys->nr, keys->size, keys->gap, keys->nr);
 	keys->gap = keys->nr;
 
@@ -429,6 +439,8 @@ void bch2_journal_keys_free(struct journal_keys *keys)
 	kvfree(keys->d);
 	keys->d = NULL;
 	keys->nr = keys->gap = keys->size = 0;
+
+	bch2_journal_entries_free(c);
 }
 
 static void __journal_keys_sort(struct journal_keys *keys)
diff --git a/fs/bcachefs/btree_journal_iter.h b/fs/bcachefs/btree_journal_iter.h
index 5d64e7e22f262d..8ca4c100b2e3e4 100644
--- a/fs/bcachefs/btree_journal_iter.h
+++ b/fs/bcachefs/btree_journal_iter.h
@@ -49,7 +49,15 @@ void bch2_btree_and_journal_iter_init_node_iter(struct btree_and_journal_iter *,
 						struct bch_fs *,
 						struct btree *);
 
-void bch2_journal_keys_free(struct journal_keys *);
+void bch2_journal_keys_put(struct bch_fs *);
+
+static inline void bch2_journal_keys_put_initial(struct bch_fs *c)
+{
+	if (c->journal_keys.initial_ref_held)
+		bch2_journal_keys_put(c);
+	c->journal_keys.initial_ref_held = false;
+}
+
 void bch2_journal_entries_free(struct bch_fs *);
 
 int bch2_journal_keys_sort(struct bch_fs *);
diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c
index 9b78f78a75b59c..1b7a5668df7cc4 100644
--- a/fs/bcachefs/btree_key_cache.c
+++ b/fs/bcachefs/btree_key_cache.c
@@ -89,10 +89,13 @@ static void bkey_cached_free(struct btree_key_cache *bc,
 	ck->btree_trans_barrier_seq =
 		start_poll_synchronize_srcu(&c->btree_trans_barrier);
 
-	if (ck->c.lock.readers)
+	if (ck->c.lock.readers) {
 		list_move_tail(&ck->list, &bc->freed_pcpu);
-	else
+		bc->nr_freed_pcpu++;
+	} else {
 		list_move_tail(&ck->list, &bc->freed_nonpcpu);
+		bc->nr_freed_nonpcpu++;
+	}
 	atomic_long_inc(&bc->nr_freed);
 
 	kfree(ck->k);
@@ -109,6 +112,8 @@ static void __bkey_cached_move_to_freelist_ordered(struct btree_key_cache *bc,
 {
 	struct bkey_cached *pos;
 
+	bc->nr_freed_nonpcpu++;
+
 	list_for_each_entry_reverse(pos, &bc->freed_nonpcpu, list) {
 		if (ULONG_CMP_GE(ck->btree_trans_barrier_seq,
 				 pos->btree_trans_barrier_seq)) {
@@ -158,6 +163,7 @@ static void bkey_cached_move_to_freelist(struct btree_key_cache *bc,
 #else
 		mutex_lock(&bc->lock);
 		list_move_tail(&ck->list, &bc->freed_nonpcpu);
+		bc->nr_freed_nonpcpu++;
 		mutex_unlock(&bc->lock);
 #endif
 	} else {
@@ -217,6 +223,7 @@ bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path,
 			       f->nr < ARRAY_SIZE(f->objs) / 2) {
 				ck = list_last_entry(&bc->freed_nonpcpu, struct bkey_cached, list);
 				list_del_init(&ck->list);
+				bc->nr_freed_nonpcpu--;
 				f->objs[f->nr++] = ck;
 			}
 
@@ -229,6 +236,7 @@ bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path,
 		if (!list_empty(&bc->freed_nonpcpu)) {
 			ck = list_last_entry(&bc->freed_nonpcpu, struct bkey_cached, list);
 			list_del_init(&ck->list);
+			bc->nr_freed_nonpcpu--;
 		}
 		mutex_unlock(&bc->lock);
 #endif
@@ -664,7 +672,6 @@ static int btree_key_cache_flush_pos(struct btree_trans *trans,
 		goto out;
 
 	bch2_journal_pin_drop(j, &ck->journal);
-	bch2_journal_preres_put(j, &ck->res);
 
 	BUG_ON(!btree_node_locked(c_iter.path, 0));
 
@@ -762,18 +769,6 @@ bool bch2_btree_insert_key_cached(struct btree_trans *trans,
 
 	BUG_ON(insert->k.u64s > ck->u64s);
 
-	if (likely(!(flags & BTREE_INSERT_JOURNAL_REPLAY))) {
-		int difference;
-
-		BUG_ON(jset_u64s(insert->k.u64s) > trans->journal_preres.u64s);
-
-		difference = jset_u64s(insert->k.u64s) - ck->res.u64s;
-		if (difference > 0) {
-			trans->journal_preres.u64s	-= difference;
-			ck->res.u64s			+= difference;
-		}
-	}
-
 	bkey_copy(ck->k, insert);
 	ck->valid = true;
 
@@ -850,6 +845,8 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink,
 	 * Newest freed entries are at the end of the list - once we hit one
 	 * that's too new to be freed, we can bail out:
 	 */
+	scanned += bc->nr_freed_nonpcpu;
+
 	list_for_each_entry_safe(ck, t, &bc->freed_nonpcpu, list) {
 		if (!poll_state_synchronize_srcu(&c->btree_trans_barrier,
 						 ck->btree_trans_barrier_seq))
@@ -859,13 +856,15 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink,
 		six_lock_exit(&ck->c.lock);
 		kmem_cache_free(bch2_key_cache, ck);
 		atomic_long_dec(&bc->nr_freed);
-		scanned++;
 		freed++;
+		bc->nr_freed_nonpcpu--;
 	}
 
 	if (scanned >= nr)
 		goto out;
 
+	scanned += bc->nr_freed_pcpu;
+
 	list_for_each_entry_safe(ck, t, &bc->freed_pcpu, list) {
 		if (!poll_state_synchronize_srcu(&c->btree_trans_barrier,
 						 ck->btree_trans_barrier_seq))
@@ -875,8 +874,8 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink,
 		six_lock_exit(&ck->c.lock);
 		kmem_cache_free(bch2_key_cache, ck);
 		atomic_long_dec(&bc->nr_freed);
-		scanned++;
 		freed++;
+		bc->nr_freed_pcpu--;
 	}
 
 	if (scanned >= nr)
@@ -982,6 +981,9 @@ void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc)
 	}
 #endif
 
+	BUG_ON(list_count_nodes(&bc->freed_pcpu) != bc->nr_freed_pcpu);
+	BUG_ON(list_count_nodes(&bc->freed_nonpcpu) != bc->nr_freed_nonpcpu);
+
 	list_splice(&bc->freed_pcpu,	&items);
 	list_splice(&bc->freed_nonpcpu,	&items);
 
@@ -990,9 +992,6 @@ void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc)
 	list_for_each_entry_safe(ck, n, &items, list) {
 		cond_resched();
 
-		bch2_journal_pin_drop(&c->journal, &ck->journal);
-		bch2_journal_preres_put(&c->journal, &ck->res);
-
 		list_del(&ck->list);
 		kfree(ck->k);
 		six_lock_exit(&ck->c.lock);
diff --git a/fs/bcachefs/btree_key_cache_types.h b/fs/bcachefs/btree_key_cache_types.h
new file mode 100644
index 00000000000000..290e4e57df5bbc
--- /dev/null
+++ b/fs/bcachefs/btree_key_cache_types.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BCACHEFS_BTREE_KEY_CACHE_TYPES_H
+#define _BCACHEFS_BTREE_KEY_CACHE_TYPES_H
+
+struct btree_key_cache_freelist {
+	struct bkey_cached	*objs[16];
+	unsigned		nr;
+};
+
+struct btree_key_cache {
+	struct mutex		lock;
+	struct rhashtable	table;
+	bool			table_init_done;
+
+	struct list_head	freed_pcpu;
+	size_t			nr_freed_pcpu;
+	struct list_head	freed_nonpcpu;
+	size_t			nr_freed_nonpcpu;
+
+	struct shrinker		*shrink;
+	unsigned		shrink_iter;
+	struct btree_key_cache_freelist __percpu *pcpu_freed;
+
+	atomic_long_t		nr_freed;
+	atomic_long_t		nr_keys;
+	atomic_long_t		nr_dirty;
+};
+
+struct bkey_cached_key {
+	u32			btree_id;
+	struct bpos		pos;
+} __packed __aligned(4);
+
+#endif /* _BCACHEFS_BTREE_KEY_CACHE_TYPES_H */
diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index decad7b66c59c1..12907beda98c2b 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -78,6 +78,53 @@ inline void bch2_btree_node_prep_for_write(struct btree_trans *trans,
 		bch2_btree_init_next(trans, b);
 }
 
+static noinline int trans_lock_write_fail(struct btree_trans *trans, struct btree_insert_entry *i)
+{
+	while (--i >= trans->updates) {
+		if (same_leaf_as_prev(trans, i))
+			continue;
+
+		bch2_btree_node_unlock_write(trans, i->path, insert_l(i)->b);
+	}
+
+	trace_and_count(trans->c, trans_restart_would_deadlock_write, trans);
+	return btree_trans_restart(trans, BCH_ERR_transaction_restart_would_deadlock_write);
+}
+
+static inline int bch2_trans_lock_write(struct btree_trans *trans)
+{
+	struct btree_insert_entry *i;
+
+	EBUG_ON(trans->write_locked);
+
+	trans_for_each_update(trans, i) {
+		if (same_leaf_as_prev(trans, i))
+			continue;
+
+		if (bch2_btree_node_lock_write(trans, i->path, &insert_l(i)->b->c))
+			return trans_lock_write_fail(trans, i);
+
+		if (!i->cached)
+			bch2_btree_node_prep_for_write(trans, i->path, insert_l(i)->b);
+	}
+
+	trans->write_locked = true;
+	return 0;
+}
+
+static inline void bch2_trans_unlock_write(struct btree_trans *trans)
+{
+	if (likely(trans->write_locked)) {
+		struct btree_insert_entry *i;
+
+		trans_for_each_update(trans, i)
+			if (!same_leaf_as_prev(trans, i))
+				bch2_btree_node_unlock_write_inlined(trans, i->path,
+								     insert_l(i)->b);
+		trans->write_locked = false;
+	}
+}
+
 /* Inserting into a given leaf node (last stage of insert): */
 
 /* Handle overwrites and do insert, for non extents: */
@@ -276,17 +323,6 @@ static inline void btree_insert_entry_checks(struct btree_trans *trans,
 		bch2_snapshot_is_internal_node(trans->c, i->k->k.p.snapshot));
 }
 
-static noinline int
-bch2_trans_journal_preres_get_cold(struct btree_trans *trans, unsigned flags,
-				   unsigned long trace_ip)
-{
-	return drop_locks_do(trans,
-		bch2_journal_preres_get(&trans->c->journal,
-			&trans->journal_preres,
-			trans->journal_preres_u64s,
-			(flags & BCH_WATERMARK_MASK)));
-}
-
 static __always_inline int bch2_trans_journal_res_get(struct btree_trans *trans,
 						      unsigned flags)
 {
@@ -321,6 +357,45 @@ static inline int btree_key_can_insert(struct btree_trans *trans,
 	return 0;
 }
 
+noinline static int
+btree_key_can_insert_cached_slowpath(struct btree_trans *trans, unsigned flags,
+				     struct btree_path *path, unsigned new_u64s)
+{
+	struct bch_fs *c = trans->c;
+	struct btree_insert_entry *i;
+	struct bkey_cached *ck = (void *) path->l[0].b;
+	struct bkey_i *new_k;
+	int ret;
+
+	bch2_trans_unlock_write(trans);
+	bch2_trans_unlock(trans);
+
+	new_k = kmalloc(new_u64s * sizeof(u64), GFP_KERNEL);
+	if (!new_k) {
+		bch_err(c, "error allocating memory for key cache key, btree %s u64s %u",
+			bch2_btree_id_str(path->btree_id), new_u64s);
+		return -BCH_ERR_ENOMEM_btree_key_cache_insert;
+	}
+
+	ret =   bch2_trans_relock(trans) ?:
+		bch2_trans_lock_write(trans);
+	if (unlikely(ret)) {
+		kfree(new_k);
+		return ret;
+	}
+
+	memcpy(new_k, ck->k, ck->u64s * sizeof(u64));
+
+	trans_for_each_update(trans, i)
+		if (i->old_v == &ck->k->v)
+			i->old_v = &new_k->v;
+
+	kfree(ck->k);
+	ck->u64s	= new_u64s;
+	ck->k		= new_k;
+	return 0;
+}
+
 static int btree_key_can_insert_cached(struct btree_trans *trans, unsigned flags,
 				       struct btree_path *path, unsigned u64s)
 {
@@ -347,12 +422,9 @@ static int btree_key_can_insert_cached(struct btree_trans *trans, unsigned flags
 		return 0;
 
 	new_u64s	= roundup_pow_of_two(u64s);
-	new_k		= krealloc(ck->k, new_u64s * sizeof(u64), GFP_NOFS);
-	if (!new_k) {
-		bch_err(c, "error allocating memory for key cache key, btree %s u64s %u",
-			bch2_btree_id_str(path->btree_id), new_u64s);
-		return -BCH_ERR_ENOMEM_btree_key_cache_insert;
-	}
+	new_k		= krealloc(ck->k, new_u64s * sizeof(u64), GFP_NOWAIT);
+	if (unlikely(!new_k))
+		return btree_key_can_insert_cached_slowpath(trans, flags, path, new_u64s);
 
 	trans_for_each_update(trans, i)
 		if (i->old_v == &ck->k->v)
@@ -732,37 +804,6 @@ revert_fs_usage:
 	return ret;
 }
 
-static noinline int trans_lock_write_fail(struct btree_trans *trans, struct btree_insert_entry *i)
-{
-	while (--i >= trans->updates) {
-		if (same_leaf_as_prev(trans, i))
-			continue;
-
-		bch2_btree_node_unlock_write(trans, i->path, insert_l(i)->b);
-	}
-
-	trace_and_count(trans->c, trans_restart_would_deadlock_write, trans);
-	return btree_trans_restart(trans, BCH_ERR_transaction_restart_would_deadlock_write);
-}
-
-static inline int trans_lock_write(struct btree_trans *trans)
-{
-	struct btree_insert_entry *i;
-
-	trans_for_each_update(trans, i) {
-		if (same_leaf_as_prev(trans, i))
-			continue;
-
-		if (bch2_btree_node_lock_write(trans, i->path, &insert_l(i)->b->c))
-			return trans_lock_write_fail(trans, i);
-
-		if (!i->cached)
-			bch2_btree_node_prep_for_write(trans, i->path, insert_l(i)->b);
-	}
-
-	return 0;
-}
-
 static noinline void bch2_drop_overwrites_from_journal(struct btree_trans *trans)
 {
 	struct btree_insert_entry *i;
@@ -830,15 +871,7 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags
 		}
 	}
 
-	ret = bch2_journal_preres_get(&c->journal,
-			&trans->journal_preres, trans->journal_preres_u64s,
-			(flags & BCH_WATERMARK_MASK)|JOURNAL_RES_GET_NONBLOCK);
-	if (unlikely(ret == -BCH_ERR_journal_preres_get_blocked))
-		ret = bch2_trans_journal_preres_get_cold(trans, flags, trace_ip);
-	if (unlikely(ret))
-		return ret;
-
-	ret = trans_lock_write(trans);
+	ret = bch2_trans_lock_write(trans);
 	if (unlikely(ret))
 		return ret;
 
@@ -847,10 +880,7 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags
 	if (!ret && unlikely(trans->journal_replay_not_finished))
 		bch2_drop_overwrites_from_journal(trans);
 
-	trans_for_each_update(trans, i)
-		if (!same_leaf_as_prev(trans, i))
-			bch2_btree_node_unlock_write_inlined(trans, i->path,
-							insert_l(i)->b);
+	bch2_trans_unlock_write(trans);
 
 	if (!ret && trans->journal_pin)
 		bch2_journal_pin_add(&c->journal, trans->journal_res.seq,
@@ -1003,7 +1033,6 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 	struct bch_fs *c = trans->c;
 	struct btree_insert_entry *i = NULL;
 	struct btree_write_buffered_key *wb;
-	unsigned u64s;
 	int ret = 0;
 
 	if (!trans->nr_updates &&
@@ -1063,13 +1092,8 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 
 	EBUG_ON(test_bit(BCH_FS_CLEAN_SHUTDOWN, &c->flags));
 
-	memset(&trans->journal_preres, 0, sizeof(trans->journal_preres));
-
 	trans->journal_u64s		= trans->extra_journal_entries.nr;
-	trans->journal_preres_u64s	= 0;
-
 	trans->journal_transaction_names = READ_ONCE(c->opts.journal_transaction_names);
-
 	if (trans->journal_transaction_names)
 		trans->journal_u64s += jset_u64s(JSET_ENTRY_LOG_U64s);
 
@@ -1085,16 +1109,11 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 		if (i->key_cache_already_flushed)
 			continue;
 
-		/* we're going to journal the key being updated: */
-		u64s = jset_u64s(i->k->k.u64s);
-		if (i->cached &&
-		    likely(!(flags & BTREE_INSERT_JOURNAL_REPLAY)))
-			trans->journal_preres_u64s += u64s;
-
 		if (i->flags & BTREE_UPDATE_NOJOURNAL)
 			continue;
 
-		trans->journal_u64s += u64s;
+		/* we're going to journal the key being updated: */
+		trans->journal_u64s += jset_u64s(i->k->k.u64s);
 
 		/* and we're also going to log the overwrite: */
 		if (trans->journal_transaction_names)
@@ -1126,8 +1145,6 @@ retry:
 
 	trace_and_count(c, transaction_commit, trans, _RET_IP_);
 out:
-	bch2_journal_preres_put(&c->journal, &trans->journal_preres);
-
 	if (likely(!(flags & BTREE_INSERT_NOCHECK_RW)))
 		bch2_write_ref_put(c, BCH_WRITE_REF_trans);
 out_reset:
diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h
index 941841a0c5bf68..60453ba86c4b96 100644
--- a/fs/bcachefs/btree_types.h
+++ b/fs/bcachefs/btree_types.h
@@ -5,7 +5,7 @@
 #include <linux/list.h>
 #include <linux/rhashtable.h>
 
-//#include "bkey_methods.h"
+#include "btree_key_cache_types.h"
 #include "buckets_types.h"
 #include "darray.h"
 #include "errcode.h"
@@ -312,31 +312,6 @@ struct btree_iter {
 #endif
 };
 
-struct btree_key_cache_freelist {
-	struct bkey_cached	*objs[16];
-	unsigned		nr;
-};
-
-struct btree_key_cache {
-	struct mutex		lock;
-	struct rhashtable	table;
-	bool			table_init_done;
-	struct list_head	freed_pcpu;
-	struct list_head	freed_nonpcpu;
-	struct shrinker		*shrink;
-	unsigned		shrink_iter;
-	struct btree_key_cache_freelist __percpu *pcpu_freed;
-
-	atomic_long_t		nr_freed;
-	atomic_long_t		nr_keys;
-	atomic_long_t		nr_dirty;
-};
-
-struct bkey_cached_key {
-	u32			btree_id;
-	struct bpos		pos;
-} __packed __aligned(4);
-
 #define BKEY_CACHED_ACCESSED		0
 #define BKEY_CACHED_DIRTY		1
 
@@ -352,7 +327,6 @@ struct bkey_cached {
 	struct rhash_head	hash;
 	struct list_head	list;
 
-	struct journal_preres	res;
 	struct journal_entry_pin journal;
 	u64			seq;
 
@@ -389,11 +363,7 @@ struct btree_insert_entry {
 	unsigned long		ip_allocated;
 };
 
-#ifndef CONFIG_LOCKDEP
 #define BTREE_ITER_MAX		64
-#else
-#define BTREE_ITER_MAX		32
-#endif
 
 struct btree_trans_commit_hook;
 typedef int (btree_trans_commit_hook_fn)(struct btree_trans *, struct btree_trans_commit_hook *);
@@ -434,6 +404,7 @@ struct btree_trans {
 	bool			journal_transaction_names:1;
 	bool			journal_replay_not_finished:1;
 	bool			notrace_relock_fail:1;
+	bool			write_locked:1;
 	enum bch_errcode	restarted:16;
 	u32			restart_count;
 	unsigned long		last_begin_ip;
@@ -465,11 +436,9 @@ struct btree_trans {
 	struct journal_entry_pin *journal_pin;
 
 	struct journal_res	journal_res;
-	struct journal_preres	journal_preres;
 	u64			*journal_seq;
 	struct disk_reservation *disk_res;
 	unsigned		journal_u64s;
-	unsigned		journal_preres_u64s;
 	struct replicas_delta_list *fs_usage_deltas;
 };
 
diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c
index 324767c0ddccd7..25fdca00bf7bde 100644
--- a/fs/bcachefs/btree_update.c
+++ b/fs/bcachefs/btree_update.c
@@ -554,6 +554,19 @@ int __must_check bch2_trans_update_seq(struct btree_trans *trans, u64 seq,
 						 BTREE_UPDATE_PREJOURNAL);
 }
 
+static noinline int bch2_btree_insert_clone_trans(struct btree_trans *trans,
+						  enum btree_id btree,
+						  struct bkey_i *k)
+{
+	struct bkey_i *n = bch2_trans_kmalloc(trans, bkey_bytes(&k->k));
+	int ret = PTR_ERR_OR_ZERO(n);
+	if (ret)
+		return ret;
+
+	bkey_copy(n, k);
+	return bch2_btree_insert_trans(trans, btree, n, 0);
+}
+
 int __must_check bch2_trans_update_buffered(struct btree_trans *trans,
 					    enum btree_id btree,
 					    struct bkey_i *k)
@@ -564,6 +577,9 @@ int __must_check bch2_trans_update_buffered(struct btree_trans *trans,
 	EBUG_ON(trans->nr_wb_updates > trans->wb_updates_size);
 	EBUG_ON(k->k.u64s > BTREE_WRITE_BUFERED_U64s_MAX);
 
+	if (unlikely(trans->journal_replay_not_finished))
+		return bch2_btree_insert_clone_trans(trans, btree, k);
+
 	trans_for_each_wb_update(trans, i) {
 		if (i->btree == btree && bpos_eq(i->k.k.p, k->k.p)) {
 			bkey_copy(&i->k, k);
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 39c2db68123bd1..239fcc3c7c996c 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -99,7 +99,7 @@ static void btree_node_interior_verify(struct bch_fs *c, struct btree *b)
 
 /* Calculate ideal packed bkey format for new btree nodes: */
 
-void __bch2_btree_calc_format(struct bkey_format_state *s, struct btree *b)
+static void __bch2_btree_calc_format(struct bkey_format_state *s, struct btree *b)
 {
 	struct bkey_packed *k;
 	struct bset_tree *t;
@@ -125,21 +125,20 @@ static struct bkey_format bch2_btree_calc_format(struct btree *b)
 	return bch2_bkey_format_done(&s);
 }
 
-static size_t btree_node_u64s_with_format(struct btree *b,
+static size_t btree_node_u64s_with_format(struct btree_nr_keys nr,
+					  struct bkey_format *old_f,
 					  struct bkey_format *new_f)
 {
-	struct bkey_format *old_f = &b->format;
-
 	/* stupid integer promotion rules */
 	ssize_t delta =
 	    (((int) new_f->key_u64s - old_f->key_u64s) *
-	     (int) b->nr.packed_keys) +
+	     (int) nr.packed_keys) +
 	    (((int) new_f->key_u64s - BKEY_U64s) *
-	     (int) b->nr.unpacked_keys);
+	     (int) nr.unpacked_keys);
 
-	BUG_ON(delta + b->nr.live_u64s < 0);
+	BUG_ON(delta + nr.live_u64s < 0);
 
-	return b->nr.live_u64s + delta;
+	return nr.live_u64s + delta;
 }
 
 /**
@@ -147,16 +146,18 @@ static size_t btree_node_u64s_with_format(struct btree *b,
  *
  * @c:		filesystem handle
  * @b:		btree node to rewrite
+ * @nr:		number of keys for new node (i.e. b->nr)
  * @new_f:	bkey format to translate keys to
  *
  * Returns: true if all re-packed keys will be able to fit in a new node.
  *
  * Assumes all keys will successfully pack with the new format.
  */
-bool bch2_btree_node_format_fits(struct bch_fs *c, struct btree *b,
+static bool bch2_btree_node_format_fits(struct bch_fs *c, struct btree *b,
+				 struct btree_nr_keys nr,
 				 struct bkey_format *new_f)
 {
-	size_t u64s = btree_node_u64s_with_format(b, new_f);
+	size_t u64s = btree_node_u64s_with_format(nr, &b->format, new_f);
 
 	return __vstruct_bytes(struct btree_node, u64s) < btree_bytes(c);
 }
@@ -391,7 +392,7 @@ static struct btree *bch2_btree_node_alloc_replacement(struct btree_update *as,
 	 * The keys might expand with the new format - if they wouldn't fit in
 	 * the btree node anymore, use the old format for now:
 	 */
-	if (!bch2_btree_node_format_fits(as->c, b, &format))
+	if (!bch2_btree_node_format_fits(as->c, b, b->nr, &format))
 		format = b->format;
 
 	SET_BTREE_NODE_SEQ(n->data, BTREE_NODE_SEQ(b->data) + 1);
@@ -513,8 +514,6 @@ static void bch2_btree_update_free(struct btree_update *as, struct btree_trans *
 		up_read(&c->gc_lock);
 	as->took_gc_lock = false;
 
-	bch2_journal_preres_put(&c->journal, &as->journal_preres);
-
 	bch2_journal_pin_drop(&c->journal, &as->journal);
 	bch2_journal_pin_flush(&c->journal, &as->journal);
 	bch2_disk_reservation_put(c, &as->disk_res);
@@ -734,8 +733,6 @@ err:
 
 	bch2_journal_pin_drop(&c->journal, &as->journal);
 
-	bch2_journal_preres_put(&c->journal, &as->journal_preres);
-
 	mutex_lock(&c->btree_interior_update_lock);
 	for (i = 0; i < as->nr_new_nodes; i++) {
 		b = as->new_nodes[i];
@@ -782,9 +779,9 @@ static void btree_interior_update_work(struct work_struct *work)
 	}
 }
 
-static void btree_update_set_nodes_written(struct closure *cl)
+static CLOSURE_CALLBACK(btree_update_set_nodes_written)
 {
-	struct btree_update *as = container_of(cl, struct btree_update, cl);
+	closure_type(as, struct btree_update, cl);
 	struct bch_fs *c = as->c;
 
 	mutex_lock(&c->btree_interior_update_lock);
@@ -1047,7 +1044,6 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 	unsigned nr_nodes[2] = { 0, 0 };
 	unsigned update_level = level;
 	enum bch_watermark watermark = flags & BCH_WATERMARK_MASK;
-	unsigned journal_flags = 0;
 	int ret = 0;
 	u32 restart_count = trans->restart_count;
 
@@ -1061,9 +1057,16 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 	flags &= ~BCH_WATERMARK_MASK;
 	flags |= watermark;
 
-	if (flags & BTREE_INSERT_JOURNAL_RECLAIM)
-		journal_flags |= JOURNAL_RES_GET_NONBLOCK;
-	journal_flags |= watermark;
+	if (!(flags & BTREE_INSERT_JOURNAL_RECLAIM) &&
+	    watermark < c->journal.watermark) {
+		struct journal_res res = { 0 };
+
+		ret = drop_locks_do(trans,
+			bch2_journal_res_get(&c->journal, &res, 1,
+					     watermark|JOURNAL_RES_GET_CHECK));
+		if (ret)
+			return ERR_PTR(ret);
+	}
 
 	while (1) {
 		nr_nodes[!!update_level] += 1 + split;
@@ -1080,8 +1083,12 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 			break;
 		}
 
+		/*
+		 * Always check for space for two keys, even if we won't have to
+		 * split at prior level - it might have been a merge instead:
+		 */
 		if (bch2_btree_node_insert_fits(c, path->l[update_level].b,
-					BKEY_BTREE_PTR_U64s_MAX * (1 + split)))
+						BKEY_BTREE_PTR_U64s_MAX * 2))
 			break;
 
 		split = path->l[update_level].b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c);
@@ -1129,27 +1136,6 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 	if (ret)
 		goto err;
 
-	ret = bch2_journal_preres_get(&c->journal, &as->journal_preres,
-				      BTREE_UPDATE_JOURNAL_RES,
-				      journal_flags|JOURNAL_RES_GET_NONBLOCK);
-	if (ret) {
-		if (flags & BTREE_INSERT_JOURNAL_RECLAIM) {
-			ret = -BCH_ERR_journal_reclaim_would_deadlock;
-			goto err;
-		}
-
-		ret = drop_locks_do(trans,
-			bch2_journal_preres_get(&c->journal, &as->journal_preres,
-					      BTREE_UPDATE_JOURNAL_RES,
-					      journal_flags));
-		if (ret == -BCH_ERR_journal_preres_get_blocked) {
-			trace_and_count(c, trans_restart_journal_preres_get, trans, _RET_IP_, journal_flags);
-			ret = btree_trans_restart(trans, BCH_ERR_transaction_restart_journal_preres_get);
-		}
-		if (ret)
-			goto err;
-	}
-
 	ret = bch2_disk_reservation_get(c, &as->disk_res,
 			(nr_nodes[0] + nr_nodes[1]) * btree_sectors(c),
 			c->opts.metadata_replicas,
@@ -1360,8 +1346,11 @@ static void __btree_split_node(struct btree_update *as,
 	struct bkey_packed *out[2];
 	struct bkey uk;
 	unsigned u64s, n1_u64s = (b->nr.live_u64s * 3) / 5;
+	struct { unsigned nr_keys, val_u64s; } nr_keys[2];
 	int i;
 
+	memset(&nr_keys, 0, sizeof(nr_keys));
+
 	for (i = 0; i < 2; i++) {
 		BUG_ON(n[i]->nsets != 1);
 
@@ -1383,6 +1372,9 @@ static void __btree_split_node(struct btree_update *as,
 		if (!i)
 			n1_pos = uk.p;
 		bch2_bkey_format_add_key(&format[i], &uk);
+
+		nr_keys[i].nr_keys++;
+		nr_keys[i].val_u64s += bkeyp_val_u64s(&b->format, k);
 	}
 
 	btree_set_min(n[0], b->data->min_key);
@@ -1395,6 +1387,12 @@ static void __btree_split_node(struct btree_update *as,
 		bch2_bkey_format_add_pos(&format[i], n[i]->data->max_key);
 
 		n[i]->data->format = bch2_bkey_format_done(&format[i]);
+
+		unsigned u64s = nr_keys[i].nr_keys * n[i]->data->format.key_u64s +
+			nr_keys[i].val_u64s;
+		if (__vstruct_bytes(struct btree_node, u64s) > btree_bytes(as->c))
+			n[i]->data->format = b->format;
+
 		btree_node_set_format(n[i], n[i]->data->format);
 	}
 
@@ -1837,8 +1835,8 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans,
 	bch2_bkey_format_add_pos(&new_s, next->data->max_key);
 	new_f = bch2_bkey_format_done(&new_s);
 
-	sib_u64s = btree_node_u64s_with_format(b, &new_f) +
-		btree_node_u64s_with_format(m, &new_f);
+	sib_u64s = btree_node_u64s_with_format(b->nr, &b->format, &new_f) +
+		btree_node_u64s_with_format(m->nr, &m->format, &new_f);
 
 	if (sib_u64s > BTREE_FOREGROUND_MERGE_HYSTERESIS(c)) {
 		sib_u64s -= BTREE_FOREGROUND_MERGE_HYSTERESIS(c);
@@ -2296,6 +2294,10 @@ int bch2_btree_node_update_key_get_iter(struct btree_trans *trans,
 
 	BUG_ON(!btree_node_hashed(b));
 
+	struct bch_extent_ptr *ptr;
+	bch2_bkey_drop_ptrs(bkey_i_to_s(new_key), ptr,
+			    !bch2_bkey_has_device(bkey_i_to_s(&b->key), ptr->dev));
+
 	ret = bch2_btree_node_update_key(trans, &iter, b, new_key,
 					 commit_flags, skip_triggers);
 out:
diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h
index 4df21512d640da..a6668992a272ba 100644
--- a/fs/bcachefs/btree_update_interior.h
+++ b/fs/bcachefs/btree_update_interior.h
@@ -6,10 +6,6 @@
 #include "btree_locking.h"
 #include "btree_update.h"
 
-void __bch2_btree_calc_format(struct bkey_format_state *, struct btree *);
-bool bch2_btree_node_format_fits(struct bch_fs *c, struct btree *,
-				struct bkey_format *);
-
 #define BTREE_UPDATE_NODES_MAX		((BTREE_MAX_DEPTH - 2) * 2 + GC_MERGE_NODES)
 
 #define BTREE_UPDATE_JOURNAL_RES	(BTREE_UPDATE_NODES_MAX * (BKEY_BTREE_PTR_U64s_MAX + 1))
@@ -55,7 +51,6 @@ struct btree_update {
 	unsigned			update_level;
 
 	struct disk_reservation		disk_res;
-	struct journal_preres		journal_preres;
 
 	/*
 	 * BTREE_INTERIOR_UPDATING_NODE:
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index 58d8c6ffd95542..5a91d3189fcf7e 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -854,8 +854,12 @@ static int __mark_pointer(struct btree_trans *trans,
 		return ret;
 
 	*dst_sectors += sectors;
-	*bucket_data_type = *dirty_sectors || *cached_sectors
-		? ptr_data_type : 0;
+
+	if (!*dirty_sectors && !*cached_sectors)
+		*bucket_data_type = 0;
+	else if (*bucket_data_type != BCH_DATA_stripe)
+		*bucket_data_type = ptr_data_type;
+
 	return 0;
 }
 
@@ -2091,8 +2095,6 @@ int bch2_dev_buckets_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets)
 	bucket_gens->first_bucket = ca->mi.first_bucket;
 	bucket_gens->nbuckets	= nbuckets;
 
-	bch2_copygc_stop(c);
-
 	if (resize) {
 		down_write(&c->gc_lock);
 		down_write(&ca->bucket_lock);
diff --git a/fs/bcachefs/compress.c b/fs/bcachefs/compress.c
index a8b148ec2a2b6b..51af8ea230edbf 100644
--- a/fs/bcachefs/compress.c
+++ b/fs/bcachefs/compress.c
@@ -354,8 +354,7 @@ static int attempt_compress(struct bch_fs *c,
 		 */
 		unsigned level = min((compression.level * 3) / 2, zstd_max_clevel());
 		ZSTD_parameters params = zstd_get_params(level, c->opts.encoded_extent_max);
-		ZSTD_CCtx *ctx = zstd_init_cctx(workspace,
-			zstd_cctx_workspace_bound(&params.cParams));
+		ZSTD_CCtx *ctx = zstd_init_cctx(workspace, c->zstd_workspace_size);
 
 		/*
 		 * ZSTD requires that when we decompress we pass in the exact
@@ -371,7 +370,7 @@ static int attempt_compress(struct bch_fs *c,
 		size_t len = zstd_compress_cctx(ctx,
 				dst + 4,	dst_len - 4 - 7,
 				src,		src_len,
-				&c->zstd_params);
+				&params);
 		if (zstd_is_error(len))
 			return 0;
 
@@ -572,6 +571,13 @@ static int __bch2_fs_compress_init(struct bch_fs *c, u64 features)
 	size_t decompress_workspace_size = 0;
 	ZSTD_parameters params = zstd_get_params(zstd_max_clevel(),
 						 c->opts.encoded_extent_max);
+
+	/*
+	 * ZSTD is lying: if we allocate the size of the workspace it says it
+	 * requires, it returns memory allocation errors
+	 */
+	c->zstd_workspace_size = zstd_cctx_workspace_bound(&params.cParams);
+
 	struct {
 		unsigned			feature;
 		enum bch_compression_type	type;
@@ -585,13 +591,11 @@ static int __bch2_fs_compress_init(struct bch_fs *c, u64 features)
 			zlib_deflate_workspacesize(MAX_WBITS, DEF_MEM_LEVEL),
 			zlib_inflate_workspacesize(), },
 		{ BCH_FEATURE_zstd, BCH_COMPRESSION_TYPE_zstd,
-			zstd_cctx_workspace_bound(&params.cParams),
+			c->zstd_workspace_size,
 			zstd_dctx_workspace_bound() },
 	}, *i;
 	bool have_compressed = false;
 
-	c->zstd_params = params;
-
 	for (i = compression_types;
 	     i < compression_types + ARRAY_SIZE(compression_types);
 	     i++)
diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index 0771a6d880bf5e..b05457d284a600 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -239,6 +239,34 @@ restart_drop_extra_replicas:
 
 		next_pos = insert->k.p;
 
+		/*
+		 * Check for nonce offset inconsistency:
+		 * This is debug code - we've been seeing this bug rarely, and
+		 * it's been hard to reproduce, so this should give us some more
+		 * information when it does occur:
+		 */
+		struct printbuf err = PRINTBUF;
+		int invalid = bch2_bkey_invalid(c, bkey_i_to_s_c(insert), __btree_node_type(0, m->btree_id), 0, &err);
+		printbuf_exit(&err);
+
+		if (invalid) {
+			struct printbuf buf = PRINTBUF;
+
+			prt_str(&buf, "about to insert invalid key in data update path");
+			prt_str(&buf, "\nold: ");
+			bch2_bkey_val_to_text(&buf, c, old);
+			prt_str(&buf, "\nk:   ");
+			bch2_bkey_val_to_text(&buf, c, k);
+			prt_str(&buf, "\nnew: ");
+			bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(insert));
+
+			bch2_print_string_as_lines(KERN_ERR, buf.buf);
+			printbuf_exit(&buf);
+
+			bch2_fatal_error(c);
+			goto out;
+		}
+
 		ret =   bch2_insert_snapshot_whiteouts(trans, m->btree_id,
 						k.k->p, bkey_start_pos(&insert->k)) ?:
 			bch2_insert_snapshot_whiteouts(trans, m->btree_id,
@@ -328,7 +356,7 @@ void bch2_data_update_exit(struct data_update *update)
 	bch2_bio_free_pages_pool(c, &update->op.wbio.bio);
 }
 
-void bch2_update_unwritten_extent(struct btree_trans *trans,
+static void bch2_update_unwritten_extent(struct btree_trans *trans,
 				  struct data_update *update)
 {
 	struct bch_fs *c = update->op.c;
@@ -408,7 +436,51 @@ void bch2_update_unwritten_extent(struct btree_trans *trans,
 	}
 }
 
+int bch2_extent_drop_ptrs(struct btree_trans *trans,
+			  struct btree_iter *iter,
+			  struct bkey_s_c k,
+			  struct data_update_opts data_opts)
+{
+	struct bch_fs *c = trans->c;
+	struct bkey_i *n;
+	int ret;
+
+	n = bch2_bkey_make_mut_noupdate(trans, k);
+	ret = PTR_ERR_OR_ZERO(n);
+	if (ret)
+		return ret;
+
+	while (data_opts.kill_ptrs) {
+		unsigned i = 0, drop = __fls(data_opts.kill_ptrs);
+		struct bch_extent_ptr *ptr;
+
+		bch2_bkey_drop_ptrs(bkey_i_to_s(n), ptr, i++ == drop);
+		data_opts.kill_ptrs ^= 1U << drop;
+	}
+
+	/*
+	 * If the new extent no longer has any pointers, bch2_extent_normalize()
+	 * will do the appropriate thing with it (turning it into a
+	 * KEY_TYPE_error key, or just a discard if it was a cached extent)
+	 */
+	bch2_extent_normalize(c, bkey_i_to_s(n));
+
+	/*
+	 * Since we're not inserting through an extent iterator
+	 * (BTREE_ITER_ALL_SNAPSHOTS iterators aren't extent iterators),
+	 * we aren't using the extent overwrite path to delete, we're
+	 * just using the normal key deletion path:
+	 */
+	if (bkey_deleted(&n->k) && !(iter->flags & BTREE_ITER_IS_EXTENTS))
+		n->k.size = 0;
+
+	return bch2_trans_relock(trans) ?:
+		bch2_trans_update(trans, iter, n, BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) ?:
+		bch2_trans_commit(trans, NULL, NULL, BTREE_INSERT_NOFAIL);
+}
+
 int bch2_data_update_init(struct btree_trans *trans,
+			  struct btree_iter *iter,
 			  struct moving_context *ctxt,
 			  struct data_update *m,
 			  struct write_point_specifier wp,
@@ -424,7 +496,7 @@ int bch2_data_update_init(struct btree_trans *trans,
 	const struct bch_extent_ptr *ptr;
 	unsigned i, reserve_sectors = k.k->size * data_opts.extra_replicas;
 	unsigned ptrs_locked = 0;
-	int ret;
+	int ret = 0;
 
 	bch2_bkey_buf_init(&m->k);
 	bch2_bkey_buf_reassemble(&m->k, c, k);
@@ -450,6 +522,8 @@ int bch2_data_update_init(struct btree_trans *trans,
 	bkey_for_each_ptr(ptrs, ptr)
 		percpu_ref_get(&bch_dev_bkey_exists(c, ptr->dev)->ref);
 
+	unsigned durability_have = 0, durability_removing = 0;
+
 	i = 0;
 	bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
 		bool locked;
@@ -461,8 +535,11 @@ int bch2_data_update_init(struct btree_trans *trans,
 				reserve_sectors += k.k->size;
 
 			m->op.nr_replicas += bch2_extent_ptr_desired_durability(c, &p);
-		} else if (!p.ptr.cached) {
+			durability_removing += bch2_extent_ptr_desired_durability(c, &p);
+		} else if (!p.ptr.cached &&
+			   !((1U << i) & m->data_opts.kill_ptrs)) {
 			bch2_dev_list_add_dev(&m->op.devs_have, p.ptr.dev);
+			durability_have += bch2_extent_ptr_durability(c, &p);
 		}
 
 		/*
@@ -483,7 +560,8 @@ int bch2_data_update_init(struct btree_trans *trans,
 				move_ctxt_wait_event(ctxt,
 						(locked = bch2_bucket_nocow_trylock(&c->nocow_locks,
 									  PTR_BUCKET_POS(c, &p.ptr), 0)) ||
-						!atomic_read(&ctxt->read_sectors));
+						(!atomic_read(&ctxt->read_sectors) &&
+						 !atomic_read(&ctxt->write_sectors)));
 
 				if (!locked)
 					bch2_bucket_nocow_lock(&c->nocow_locks,
@@ -501,6 +579,29 @@ int bch2_data_update_init(struct btree_trans *trans,
 		i++;
 	}
 
+	/*
+	 * If current extent durability is less than io_opts.data_replicas,
+	 * we're not trying to rereplicate the extent up to data_replicas here -
+	 * unless extra_replicas was specified
+	 *
+	 * Increasing replication is an explicit operation triggered by
+	 * rereplicate, currently, so that users don't get an unexpected -ENOSPC
+	 */
+	if (durability_have >= io_opts.data_replicas) {
+		m->data_opts.kill_ptrs |= m->data_opts.rewrite_ptrs;
+		m->data_opts.rewrite_ptrs = 0;
+		/* if iter == NULL, it's just a promote */
+		if (iter)
+			ret = bch2_extent_drop_ptrs(trans, iter, k, m->data_opts);
+		goto done;
+	}
+
+	m->op.nr_replicas = min(durability_removing, io_opts.data_replicas - durability_have) +
+		m->data_opts.extra_replicas;
+	m->op.nr_replicas_required = m->op.nr_replicas;
+
+	BUG_ON(!m->op.nr_replicas);
+
 	if (reserve_sectors) {
 		ret = bch2_disk_reservation_add(c, &m->op.res, reserve_sectors,
 				m->data_opts.extra_replicas
@@ -510,14 +611,11 @@ int bch2_data_update_init(struct btree_trans *trans,
 			goto err;
 	}
 
-	m->op.nr_replicas += m->data_opts.extra_replicas;
-	m->op.nr_replicas_required = m->op.nr_replicas;
-
-	BUG_ON(!m->op.nr_replicas);
+	if (bkey_extent_is_unwritten(k)) {
+		bch2_update_unwritten_extent(trans, m);
+		goto done;
+	}
 
-	/* Special handling required: */
-	if (bkey_extent_is_unwritten(k))
-		return -BCH_ERR_unwritten_extent_update;
 	return 0;
 err:
 	i = 0;
@@ -532,6 +630,9 @@ err:
 	bch2_bkey_buf_exit(&m->k, c);
 	bch2_bio_free_pages_pool(c, &m->op.wbio.bio);
 	return ret;
+done:
+	bch2_data_update_exit(m);
+	return ret ?: -BCH_ERR_data_update_done;
 }
 
 void bch2_data_update_opts_normalize(struct bkey_s_c k, struct data_update_opts *opts)
diff --git a/fs/bcachefs/data_update.h b/fs/bcachefs/data_update.h
index 9dc17b9d837951..991095bbd469ba 100644
--- a/fs/bcachefs/data_update.h
+++ b/fs/bcachefs/data_update.h
@@ -32,9 +32,14 @@ int bch2_data_update_index_update(struct bch_write_op *);
 void bch2_data_update_read_done(struct data_update *,
 				struct bch_extent_crc_unpacked);
 
+int bch2_extent_drop_ptrs(struct btree_trans *,
+			  struct btree_iter *,
+			  struct bkey_s_c,
+			  struct data_update_opts);
+
 void bch2_data_update_exit(struct data_update *);
-void bch2_update_unwritten_extent(struct btree_trans *, struct data_update *);
-int bch2_data_update_init(struct btree_trans *, struct moving_context *,
+int bch2_data_update_init(struct btree_trans *, struct btree_iter *,
+			  struct moving_context *,
 			  struct data_update *,
 			  struct write_point_specifier,
 			  struct bch_io_opts, struct data_update_opts,
diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c
index 1a0f2d5715692b..2bfff0da7000b3 100644
--- a/fs/bcachefs/dirent.c
+++ b/fs/bcachefs/dirent.c
@@ -485,20 +485,15 @@ retry:
 	return ret;
 }
 
-int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir)
+int bch2_empty_dir_snapshot(struct btree_trans *trans, u64 dir, u32 snapshot)
 {
 	struct btree_iter iter;
 	struct bkey_s_c k;
-	u32 snapshot;
 	int ret;
 
-	ret = bch2_subvolume_get_snapshot(trans, dir.subvol, &snapshot);
-	if (ret)
-		return ret;
-
 	for_each_btree_key_upto_norestart(trans, iter, BTREE_ID_dirents,
-			   SPOS(dir.inum, 0, snapshot),
-			   POS(dir.inum, U64_MAX), 0, k, ret)
+			   SPOS(dir, 0, snapshot),
+			   POS(dir, U64_MAX), 0, k, ret)
 		if (k.k->type == KEY_TYPE_dirent) {
 			ret = -ENOTEMPTY;
 			break;
@@ -508,6 +503,14 @@ int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir)
 	return ret;
 }
 
+int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir)
+{
+	u32 snapshot;
+
+	return bch2_subvolume_get_snapshot(trans, dir.subvol, &snapshot) ?:
+		bch2_empty_dir_snapshot(trans, dir.inum, snapshot);
+}
+
 int bch2_readdir(struct bch_fs *c, subvol_inum inum, struct dir_context *ctx)
 {
 	struct btree_trans *trans = bch2_trans_get(c);
diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h
index cd262bf4d9c536..1e3431990abd35 100644
--- a/fs/bcachefs/dirent.h
+++ b/fs/bcachefs/dirent.h
@@ -64,6 +64,7 @@ u64 bch2_dirent_lookup(struct bch_fs *, subvol_inum,
 		       const struct bch_hash_info *,
 		       const struct qstr *, subvol_inum *);
 
+int bch2_empty_dir_snapshot(struct btree_trans *, u64, u32);
 int bch2_empty_dir_trans(struct btree_trans *, subvol_inum);
 int bch2_readdir(struct bch_fs *, subvol_inum, struct dir_context *);
 
diff --git a/fs/bcachefs/disk_groups.c b/fs/bcachefs/disk_groups.c
index d613695abf9f67..4d0cb0ccff32f2 100644
--- a/fs/bcachefs/disk_groups.c
+++ b/fs/bcachefs/disk_groups.c
@@ -555,6 +555,7 @@ void bch2_target_to_text(struct printbuf *out, struct bch_fs *c, unsigned v)
 	case TARGET_DEV: {
 		struct bch_dev *ca;
 
+		out->atomic++;
 		rcu_read_lock();
 		ca = t.dev < c->sb.nr_devices
 			? rcu_dereference(c->devs[t.dev])
@@ -570,6 +571,7 @@ void bch2_target_to_text(struct printbuf *out, struct bch_fs *c, unsigned v)
 		}
 
 		rcu_read_unlock();
+		out->atomic--;
 		break;
 	}
 	case TARGET_GROUP:
@@ -580,7 +582,7 @@ void bch2_target_to_text(struct printbuf *out, struct bch_fs *c, unsigned v)
 	}
 }
 
-void bch2_target_to_text_sb(struct printbuf *out, struct bch_sb *sb, unsigned v)
+static void bch2_target_to_text_sb(struct printbuf *out, struct bch_sb *sb, unsigned v)
 {
 	struct target t = target_decode(v);
 
diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index 875f7c5a6fca63..2a77de18c004e7 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -1373,6 +1373,15 @@ ec_new_stripe_head_alloc(struct bch_fs *c, unsigned target,
 			h->nr_active_devs++;
 
 	rcu_read_unlock();
+
+	/*
+	 * If we only have redundancy + 1 devices, we're better off with just
+	 * replication:
+	 */
+	if (h->nr_active_devs < h->redundancy + 2)
+		bch_err(c, "insufficient devices available to create stripe (have %u, need %u) - mismatched bucket sizes?",
+			h->nr_active_devs, h->redundancy + 2);
+
 	list_add(&h->list, &c->ec_stripe_head_list);
 	return h;
 }
@@ -1424,6 +1433,11 @@ __bch2_ec_stripe_head_get(struct btree_trans *trans,
 
 	h = ec_new_stripe_head_alloc(c, target, algo, redundancy, watermark);
 found:
+	if (!IS_ERR_OR_NULL(h) &&
+	    h->nr_active_devs < h->redundancy + 2) {
+		mutex_unlock(&h->lock);
+		h = NULL;
+	}
 	mutex_unlock(&c->ec_stripe_head_lock);
 	return h;
 }
@@ -1681,8 +1695,6 @@ struct ec_stripe_head *bch2_ec_stripe_head_get(struct btree_trans *trans,
 	int ret;
 
 	h = __bch2_ec_stripe_head_get(trans, target, algo, redundancy, watermark);
-	if (!h)
-		bch_err(c, "no stripe head");
 	if (IS_ERR_OR_NULL(h))
 		return h;
 
diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h
index 68a1a96bb7caf5..ae7910bf2228c4 100644
--- a/fs/bcachefs/errcode.h
+++ b/fs/bcachefs/errcode.h
@@ -162,7 +162,7 @@
 	x(BCH_ERR_fsck,			fsck_repair_unimplemented)		\
 	x(BCH_ERR_fsck,			fsck_repair_impossible)			\
 	x(0,				restart_recovery)			\
-	x(0,				unwritten_extent_update)		\
+	x(0,				data_update_done)			\
 	x(EINVAL,			device_state_not_allowed)		\
 	x(EINVAL,			member_info_missing)			\
 	x(EINVAL,			mismatched_block_size)			\
@@ -210,6 +210,7 @@
 	x(BCH_ERR_invalid_sb,		invalid_sb_members)			\
 	x(BCH_ERR_invalid_sb,		invalid_sb_disk_groups)			\
 	x(BCH_ERR_invalid_sb,		invalid_sb_replicas)			\
+	x(BCH_ERR_invalid_sb,		invalid_replicas_entry)			\
 	x(BCH_ERR_invalid_sb,		invalid_sb_journal)			\
 	x(BCH_ERR_invalid_sb,		invalid_sb_journal_seq_blacklist)	\
 	x(BCH_ERR_invalid_sb,		invalid_sb_crypt)			\
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index a864de231b69e2..9d8afcb5979a12 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -649,37 +649,31 @@ unsigned bch2_bkey_replicas(struct bch_fs *c, struct bkey_s_c k)
 	return replicas;
 }
 
-unsigned bch2_extent_ptr_desired_durability(struct bch_fs *c, struct extent_ptr_decoded *p)
+static inline unsigned __extent_ptr_durability(struct bch_dev *ca, struct extent_ptr_decoded *p)
 {
-	struct bch_dev *ca;
-
 	if (p->ptr.cached)
 		return 0;
 
-	ca = bch_dev_bkey_exists(c, p->ptr.dev);
-
-	return ca->mi.durability +
-		(p->has_ec
-		 ? p->ec.redundancy
-		 : 0);
+	return p->has_ec
+		? p->ec.redundancy + 1
+		: ca->mi.durability;
 }
 
-unsigned bch2_extent_ptr_durability(struct bch_fs *c, struct extent_ptr_decoded *p)
+unsigned bch2_extent_ptr_desired_durability(struct bch_fs *c, struct extent_ptr_decoded *p)
 {
-	struct bch_dev *ca;
+	struct bch_dev *ca = bch_dev_bkey_exists(c, p->ptr.dev);
 
-	if (p->ptr.cached)
-		return 0;
+	return __extent_ptr_durability(ca, p);
+}
 
-	ca = bch_dev_bkey_exists(c, p->ptr.dev);
+unsigned bch2_extent_ptr_durability(struct bch_fs *c, struct extent_ptr_decoded *p)
+{
+	struct bch_dev *ca = bch_dev_bkey_exists(c, p->ptr.dev);
 
 	if (ca->mi.state == BCH_MEMBER_STATE_failed)
 		return 0;
 
-	return ca->mi.durability +
-		(p->has_ec
-		 ? p->ec.redundancy
-		 : 0);
+	return __extent_ptr_durability(ca, p);
 }
 
 unsigned bch2_bkey_durability(struct bch_fs *c, struct bkey_s_c k)
@@ -1300,7 +1294,8 @@ unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *c, struct bkey_s_c k,
 		unsigned i = 0;
 
 		bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
-			if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible) {
+			if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible ||
+			    p.ptr.unwritten) {
 				rewrite_ptrs = 0;
 				goto incompressible;
 			}
diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c
index 5b42a76c4796f9..9a479e4de6b36a 100644
--- a/fs/bcachefs/fs-io-direct.c
+++ b/fs/bcachefs/fs-io-direct.c
@@ -35,9 +35,9 @@ static void bio_check_or_release(struct bio *bio, bool check_dirty)
 	}
 }
 
-static void bch2_dio_read_complete(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_dio_read_complete)
 {
-	struct dio_read *dio = container_of(cl, struct dio_read, cl);
+	closure_type(dio, struct dio_read, cl);
 
 	dio->req->ki_complete(dio->req, dio->ret);
 	bio_check_or_release(&dio->rbio.bio, dio->should_dirty);
@@ -325,9 +325,9 @@ static noinline int bch2_dio_write_copy_iov(struct dio_write *dio)
 	return 0;
 }
 
-static void bch2_dio_write_flush_done(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_dio_write_flush_done)
 {
-	struct dio_write *dio = container_of(cl, struct dio_write, op.cl);
+	closure_type(dio, struct dio_write, op.cl);
 	struct bch_fs *c = dio->op.c;
 
 	closure_debug_destroy(cl);
diff --git a/fs/bcachefs/fs-io-pagecache.c b/fs/bcachefs/fs-io-pagecache.c
index 8bd9bcdd27f738..ff664fd0d8ef80 100644
--- a/fs/bcachefs/fs-io-pagecache.c
+++ b/fs/bcachefs/fs-io-pagecache.c
@@ -13,7 +13,7 @@
 
 int bch2_filemap_get_contig_folios_d(struct address_space *mapping,
 				     loff_t start, u64 end,
-				     int fgp_flags, gfp_t gfp,
+				     fgf_t fgp_flags, gfp_t gfp,
 				     folios *fs)
 {
 	struct folio *f;
diff --git a/fs/bcachefs/fs-io-pagecache.h b/fs/bcachefs/fs-io-pagecache.h
index a2222ad586e9e7..27f712ae37a682 100644
--- a/fs/bcachefs/fs-io-pagecache.h
+++ b/fs/bcachefs/fs-io-pagecache.h
@@ -7,7 +7,7 @@
 typedef DARRAY(struct folio *) folios;
 
 int bch2_filemap_get_contig_folios_d(struct address_space *, loff_t,
-				     u64, int, gfp_t, folios *);
+				     u64, fgf_t, gfp_t, folios *);
 int bch2_write_invalidate_inode_pages_range(struct address_space *, loff_t, loff_t);
 
 /*
diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index 5a39bcb597a33d..a70b7a03057d7f 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -413,7 +413,7 @@ retry:
 
 	if ((arg.flags & BCH_SUBVOL_SNAPSHOT_CREATE) &&
 	    !arg.src_ptr)
-		snapshot_src.subvol = to_bch_ei(dir)->ei_inode.bi_subvol;
+		snapshot_src.subvol = inode_inum(to_bch_ei(dir)).subvol;
 
 	inode = __bch2_create(file_mnt_idmap(filp), to_bch_ei(dir),
 			      dst_dentry, arg.mode|S_IFDIR,
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 166d8d8abe683f..ba93e32d7708e6 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -1143,24 +1143,33 @@ static int bch2_encode_fh(struct inode *vinode, u32 *fh, int *len,
 {
 	struct bch_inode_info *inode	= to_bch_ei(vinode);
 	struct bch_inode_info *dir	= to_bch_ei(vdir);
-
-	if (*len < sizeof(struct bcachefs_fid_with_parent) / sizeof(u32))
-		return FILEID_INVALID;
+	int min_len;
 
 	if (!S_ISDIR(inode->v.i_mode) && dir) {
 		struct bcachefs_fid_with_parent *fid = (void *) fh;
 
+		min_len = sizeof(*fid) / sizeof(u32);
+		if (*len < min_len) {
+			*len = min_len;
+			return FILEID_INVALID;
+		}
+
 		fid->fid = bch2_inode_to_fid(inode);
 		fid->dir = bch2_inode_to_fid(dir);
 
-		*len = sizeof(*fid) / sizeof(u32);
+		*len = min_len;
 		return FILEID_BCACHEFS_WITH_PARENT;
 	} else {
 		struct bcachefs_fid *fid = (void *) fh;
 
+		min_len = sizeof(*fid) / sizeof(u32);
+		if (*len < min_len) {
+			*len = min_len;
+			return FILEID_INVALID;
+		}
 		*fid = bch2_inode_to_fid(inode);
 
-		*len = sizeof(*fid) / sizeof(u32);
+		*len = min_len;
 		return FILEID_BCACHEFS_WITHOUT_PARENT;
 	}
 }
@@ -1667,8 +1676,7 @@ static int bch2_show_devname(struct seq_file *seq, struct dentry *root)
 		if (!first)
 			seq_putc(seq, ':');
 		first = false;
-		seq_puts(seq, "/dev/");
-		seq_puts(seq, ca->name);
+		seq_puts(seq, ca->disk_sb.sb_name);
 	}
 
 	return 0;
@@ -1734,6 +1742,9 @@ static int bch2_unfreeze(struct super_block *sb)
 	struct bch_fs *c = sb->s_fs_info;
 	int ret;
 
+	if (test_bit(BCH_FS_EMERGENCY_RO, &c->flags))
+		return 0;
+
 	down_write(&c->state_lock);
 	ret = bch2_fs_read_write(c);
 	up_write(&c->state_lock);
@@ -1922,10 +1933,7 @@ out:
 	return dget(sb->s_root);
 
 err_put_super:
-	sb->s_fs_info = NULL;
-	c->vfs_sb = NULL;
 	deactivate_locked_super(sb);
-	bch2_fs_stop(c);
 	return ERR_PTR(bch2_err_class(ret));
 }
 
@@ -1933,11 +1941,8 @@ static void bch2_kill_sb(struct super_block *sb)
 {
 	struct bch_fs *c = sb->s_fs_info;
 
-	if (c)
-		c->vfs_sb = NULL;
 	generic_shutdown_super(sb);
-	if (c)
-		bch2_fs_free(c);
+	bch2_fs_free(c);
 }
 
 static struct file_system_type bcache_fs_type = {
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 9f3e9bd3d767a7..e0c5cd119acc93 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -2220,7 +2220,7 @@ static int nlink_cmp(const void *_l, const void *_r)
 	const struct nlink *l = _l;
 	const struct nlink *r = _r;
 
-	return cmp_int(l->inum, r->inum) ?: cmp_int(l->snapshot, r->snapshot);
+	return cmp_int(l->inum, r->inum);
 }
 
 static void inc_link(struct bch_fs *c, struct snapshots_seen *s,
diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index def77f2d88024b..9309cfeecd8d61 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -7,6 +7,7 @@
 #include "btree_update.h"
 #include "buckets.h"
 #include "compress.h"
+#include "dirent.h"
 #include "error.h"
 #include "extents.h"
 #include "extent_update.h"
@@ -1093,11 +1094,15 @@ static int may_delete_deleted_inode(struct btree_trans *trans,
 	if (ret)
 		goto out;
 
-	if (fsck_err_on(S_ISDIR(inode.bi_mode), c,
-			deleted_inode_is_dir,
-			"directory %llu:%u in deleted_inodes btree",
-			pos.offset, pos.snapshot))
-		goto delete;
+	if (S_ISDIR(inode.bi_mode)) {
+		ret = bch2_empty_dir_snapshot(trans, pos.offset, pos.snapshot);
+		if (fsck_err_on(ret == -ENOTEMPTY, c, deleted_inode_is_dir,
+				"non empty directory %llu:%u in deleted_inodes btree",
+				pos.offset, pos.snapshot))
+			goto delete;
+		if (ret)
+			goto out;
+	}
 
 	if (fsck_err_on(!(inode.bi_flags & BCH_INODE_unlinked), c,
 			deleted_inode_not_unlinked,
@@ -1134,7 +1139,7 @@ static int may_delete_deleted_inode(struct btree_trans *trans,
 		 * unlinked inodes in the snapshot leaves:
 		 */
 		*need_another_pass = true;
-		return 0;
+		goto out;
 	}
 
 	ret = 1;
@@ -1169,8 +1174,10 @@ again:
 	 */
 	for_each_btree_key(trans, iter, BTREE_ID_deleted_inodes, POS_MIN,
 			   BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k, ret) {
-		ret = lockrestart_do(trans, may_delete_deleted_inode(trans, &iter, k.k->p,
-								     &need_another_pass));
+		ret = commit_do(trans, NULL, NULL,
+				BTREE_INSERT_NOFAIL|
+				BTREE_INSERT_LAZY_RW,
+			may_delete_deleted_inode(trans, &iter, k.k->p, &need_another_pass));
 		if (ret < 0)
 			break;
 
diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c
index a56ed553dc15e6..36763865facd46 100644
--- a/fs/bcachefs/io_read.c
+++ b/fs/bcachefs/io_read.c
@@ -209,7 +209,7 @@ static struct promote_op *__promote_alloc(struct btree_trans *trans,
 	bio = &op->write.op.wbio.bio;
 	bio_init(bio, NULL, bio->bi_inline_vecs, pages, 0);
 
-	ret = bch2_data_update_init(trans, NULL, &op->write,
+	ret = bch2_data_update_init(trans, NULL, NULL, &op->write,
 			writepoint_hashed((unsigned long) current),
 			opts,
 			(struct data_update_opts) {
diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index f02b3f7d26a016..8ede46b1e35463 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -580,9 +580,9 @@ static inline void wp_update_state(struct write_point *wp, bool running)
 	__wp_update_state(wp, state);
 }
 
-static void bch2_write_index(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_write_index)
 {
-	struct bch_write_op *op = container_of(cl, struct bch_write_op, cl);
+	closure_type(op, struct bch_write_op, cl);
 	struct write_point *wp = op->wp;
 	struct workqueue_struct *wq = index_update_wq(op);
 	unsigned long flags;
@@ -795,7 +795,7 @@ static int bch2_write_decrypt(struct bch_write_op *op)
 	 * checksum:
 	 */
 	csum = bch2_checksum_bio(c, op->crc.csum_type, nonce, &op->wbio.bio);
-	if (bch2_crc_cmp(op->crc.csum, csum))
+	if (bch2_crc_cmp(op->crc.csum, csum) && !c->opts.no_data_io)
 		return -EIO;
 
 	ret = bch2_encrypt_bio(c, op->crc.csum_type, nonce, &op->wbio.bio);
@@ -1208,9 +1208,9 @@ static void __bch2_nocow_write_done(struct bch_write_op *op)
 		bch2_nocow_write_convert_unwritten(op);
 }
 
-static void bch2_nocow_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_nocow_write_done)
 {
-	struct bch_write_op *op = container_of(cl, struct bch_write_op, cl);
+	closure_type(op, struct bch_write_op, cl);
 
 	__bch2_nocow_write_done(op);
 	bch2_write_done(cl);
@@ -1363,7 +1363,7 @@ err:
 		op->insert_keys.top = op->insert_keys.keys;
 	} else if (op->flags & BCH_WRITE_SYNC) {
 		closure_sync(&op->cl);
-		bch2_nocow_write_done(&op->cl);
+		bch2_nocow_write_done(&op->cl.work);
 	} else {
 		/*
 		 * XXX
@@ -1566,9 +1566,9 @@ err:
  * If op->discard is true, instead of inserting the data it invalidates the
  * region of the cache represented by op->bio and op->inode.
  */
-void bch2_write(struct closure *cl)
+CLOSURE_CALLBACK(bch2_write)
 {
-	struct bch_write_op *op = container_of(cl, struct bch_write_op, cl);
+	closure_type(op, struct bch_write_op, cl);
 	struct bio *bio = &op->wbio.bio;
 	struct bch_fs *c = op->c;
 	unsigned data_len;
diff --git a/fs/bcachefs/io_write.h b/fs/bcachefs/io_write.h
index 9323167229eeae..6c276a48f95dc2 100644
--- a/fs/bcachefs/io_write.h
+++ b/fs/bcachefs/io_write.h
@@ -90,8 +90,7 @@ static inline void bch2_write_op_init(struct bch_write_op *op, struct bch_fs *c,
 	op->devs_need_flush	= NULL;
 }
 
-void bch2_write(struct closure *);
-
+CLOSURE_CALLBACK(bch2_write);
 void bch2_write_point_do_index_updates(struct work_struct *);
 
 static inline struct bch_write_bio *wbio_init(struct bio *bio)
diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index 5b5d69f2316b21..8cf238be6213ec 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -249,7 +249,7 @@ static bool journal_entry_want_write(struct journal *j)
 	return ret;
 }
 
-static bool journal_entry_close(struct journal *j)
+bool bch2_journal_entry_close(struct journal *j)
 {
 	bool ret;
 
@@ -321,6 +321,8 @@ static int journal_entry_open(struct journal *j)
 	atomic64_inc(&j->seq);
 	journal_pin_list_init(fifo_push_ref(&j->pin), 1);
 
+	BUG_ON(j->pin.back - 1 != atomic64_read(&j->seq));
+
 	BUG_ON(j->buf + (journal_cur_seq(j) & JOURNAL_BUF_MASK) != buf);
 
 	bkey_extent_init(&buf->key);
@@ -381,7 +383,7 @@ static bool journal_quiesced(struct journal *j)
 	bool ret = atomic64_read(&j->seq) == j->seq_ondisk;
 
 	if (!ret)
-		journal_entry_close(j);
+		bch2_journal_entry_close(j);
 	return ret;
 }
 
@@ -434,7 +436,7 @@ retry:
 
 	/*
 	 * Recheck after taking the lock, so we don't race with another thread
-	 * that just did journal_entry_open() and call journal_entry_close()
+	 * that just did journal_entry_open() and call bch2_journal_entry_close()
 	 * unnecessarily
 	 */
 	if (journal_res_get_fast(j, res, flags)) {
@@ -526,36 +528,6 @@ int bch2_journal_res_get_slowpath(struct journal *j, struct journal_res *res,
 	return ret;
 }
 
-/* journal_preres: */
-
-static bool journal_preres_available(struct journal *j,
-				     struct journal_preres *res,
-				     unsigned new_u64s,
-				     unsigned flags)
-{
-	bool ret = bch2_journal_preres_get_fast(j, res, new_u64s, flags, true);
-
-	if (!ret && mutex_trylock(&j->reclaim_lock)) {
-		bch2_journal_reclaim(j);
-		mutex_unlock(&j->reclaim_lock);
-	}
-
-	return ret;
-}
-
-int __bch2_journal_preres_get(struct journal *j,
-			      struct journal_preres *res,
-			      unsigned new_u64s,
-			      unsigned flags)
-{
-	int ret;
-
-	closure_wait_event(&j->preres_wait,
-		   (ret = bch2_journal_error(j)) ||
-		   journal_preres_available(j, res, new_u64s, flags));
-	return ret;
-}
-
 /* journal_entry_res: */
 
 void bch2_journal_entry_res_resize(struct journal *j,
@@ -1069,7 +1041,7 @@ void bch2_fs_journal_stop(struct journal *j)
 	bch2_journal_reclaim_stop(j);
 	bch2_journal_flush_all_pins(j);
 
-	wait_event(j->wait, journal_entry_close(j));
+	wait_event(j->wait, bch2_journal_entry_close(j));
 
 	/*
 	 * Always write a new journal entry, to make sure the clock hands are up
@@ -1306,7 +1278,6 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j)
 	prt_printf(out, "last_seq:\t\t%llu\n",		journal_last_seq(j));
 	prt_printf(out, "last_seq_ondisk:\t%llu\n",		j->last_seq_ondisk);
 	prt_printf(out, "flushed_seq_ondisk:\t%llu\n",	j->flushed_seq_ondisk);
-	prt_printf(out, "prereserved:\t\t%u/%u\n",		j->prereserved.reserved, j->prereserved.remaining);
 	prt_printf(out, "watermark:\t\t%s\n",		bch2_watermarks[j->watermark]);
 	prt_printf(out, "each entry reserved:\t%u\n",	j->entry_u64s_reserved);
 	prt_printf(out, "nr flush writes:\t%llu\n",		j->nr_flush_writes);
diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h
index 011711e99c8d82..2f768e11aec9a9 100644
--- a/fs/bcachefs/journal.h
+++ b/fs/bcachefs/journal.h
@@ -136,9 +136,7 @@ static inline u64 journal_last_seq(struct journal *j)
 
 static inline u64 journal_cur_seq(struct journal *j)
 {
-	EBUG_ON(j->pin.back - 1 != atomic64_read(&j->seq));
-
-	return j->pin.back - 1;
+	return atomic64_read(&j->seq);
 }
 
 static inline u64 journal_last_unwritten_seq(struct journal *j)
@@ -268,6 +266,7 @@ static inline union journal_res_state journal_state_buf_put(struct journal *j, u
 	return s;
 }
 
+bool bch2_journal_entry_close(struct journal *);
 void bch2_journal_buf_put_final(struct journal *, u64, bool);
 
 static inline void __bch2_journal_buf_put(struct journal *j, unsigned idx, u64 seq)
@@ -395,104 +394,6 @@ out:
 	return 0;
 }
 
-/* journal_preres: */
-
-static inline void journal_set_watermark(struct journal *j)
-{
-	union journal_preres_state s = READ_ONCE(j->prereserved);
-	unsigned watermark = BCH_WATERMARK_stripe;
-
-	if (fifo_free(&j->pin) < j->pin.size / 4)
-		watermark = max_t(unsigned, watermark, BCH_WATERMARK_copygc);
-	if (fifo_free(&j->pin) < j->pin.size / 8)
-		watermark = max_t(unsigned, watermark, BCH_WATERMARK_reclaim);
-
-	if (s.reserved > s.remaining)
-		watermark = max_t(unsigned, watermark, BCH_WATERMARK_copygc);
-	if (!s.remaining)
-		watermark = max_t(unsigned, watermark, BCH_WATERMARK_reclaim);
-
-	if (watermark == j->watermark)
-		return;
-
-	swap(watermark, j->watermark);
-	if (watermark > j->watermark)
-		journal_wake(j);
-}
-
-static inline void bch2_journal_preres_put(struct journal *j,
-					   struct journal_preres *res)
-{
-	union journal_preres_state s = { .reserved = res->u64s };
-
-	if (!res->u64s)
-		return;
-
-	s.v = atomic64_sub_return(s.v, &j->prereserved.counter);
-	res->u64s = 0;
-
-	if (unlikely(s.waiting)) {
-		clear_bit(ilog2((((union journal_preres_state) { .waiting = 1 }).v)),
-			  (unsigned long *) &j->prereserved.v);
-		closure_wake_up(&j->preres_wait);
-	}
-
-	if (s.reserved <= s.remaining && j->watermark)
-		journal_set_watermark(j);
-}
-
-int __bch2_journal_preres_get(struct journal *,
-			struct journal_preres *, unsigned, unsigned);
-
-static inline int bch2_journal_preres_get_fast(struct journal *j,
-					       struct journal_preres *res,
-					       unsigned new_u64s,
-					       unsigned flags,
-					       bool set_waiting)
-{
-	int d = new_u64s - res->u64s;
-	union journal_preres_state old, new;
-	u64 v = atomic64_read(&j->prereserved.counter);
-	enum bch_watermark watermark = flags & BCH_WATERMARK_MASK;
-	int ret;
-
-	do {
-		old.v = new.v = v;
-		ret = 0;
-
-		if (watermark == BCH_WATERMARK_reclaim ||
-		    new.reserved + d < new.remaining) {
-			new.reserved += d;
-			ret = 1;
-		} else if (set_waiting && !new.waiting)
-			new.waiting = true;
-		else
-			return 0;
-	} while ((v = atomic64_cmpxchg(&j->prereserved.counter,
-				       old.v, new.v)) != old.v);
-
-	if (ret)
-		res->u64s += d;
-	return ret;
-}
-
-static inline int bch2_journal_preres_get(struct journal *j,
-					  struct journal_preres *res,
-					  unsigned new_u64s,
-					  unsigned flags)
-{
-	if (new_u64s <= res->u64s)
-		return 0;
-
-	if (bch2_journal_preres_get_fast(j, res, new_u64s, flags, false))
-		return 0;
-
-	if (flags & JOURNAL_RES_GET_NONBLOCK)
-		return -BCH_ERR_journal_preres_get_blocked;
-
-	return __bch2_journal_preres_get(j, res, new_u64s, flags);
-}
-
 /* journal_entry_res: */
 
 void bch2_journal_entry_res_resize(struct journal *,
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index f4bc2cdbfdd792..5de1b68fb8afc8 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -547,6 +547,7 @@ static int journal_entry_data_usage_validate(struct bch_fs *c,
 	struct jset_entry_data_usage *u =
 		container_of(entry, struct jset_entry_data_usage, entry);
 	unsigned bytes = jset_u64s(le16_to_cpu(entry->u64s)) * sizeof(u64);
+	struct printbuf err = PRINTBUF;
 	int ret = 0;
 
 	if (journal_entry_err_on(bytes < sizeof(*u) ||
@@ -555,10 +556,19 @@ static int journal_entry_data_usage_validate(struct bch_fs *c,
 				 journal_entry_data_usage_bad_size,
 				 "invalid journal entry usage: bad size")) {
 		journal_entry_null_range(entry, vstruct_next(entry));
-		return ret;
+		goto out;
 	}
 
+	if (journal_entry_err_on(bch2_replicas_entry_validate(&u->r, c->disk_sb.sb, &err),
+				 c, version, jset, entry,
+				 journal_entry_data_usage_bad_size,
+				 "invalid journal entry usage: %s", err.buf)) {
+		journal_entry_null_range(entry, vstruct_next(entry));
+		goto out;
+	}
+out:
 fsck_err:
+	printbuf_exit(&err);
 	return ret;
 }
 
@@ -1025,10 +1035,9 @@ next_block:
 	return 0;
 }
 
-static void bch2_journal_read_device(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_journal_read_device)
 {
-	struct journal_device *ja =
-		container_of(cl, struct journal_device, read);
+	closure_type(ja, struct journal_device, read);
 	struct bch_dev *ca = container_of(ja, struct bch_dev, journal);
 	struct bch_fs *c = ca->fs;
 	struct journal_list *jlist =
@@ -1079,6 +1088,12 @@ found:
 
 	if (ja->bucket_seq[ja->cur_idx] &&
 	    ja->sectors_free == ca->mi.bucket_size) {
+#if 0
+		/*
+		 * Debug code for ZNS support, where we (probably) want to be
+		 * correlated where we stopped in the journal to the zone write
+		 * points:
+		 */
 		bch_err(c, "ja->sectors_free == ca->mi.bucket_size");
 		bch_err(c, "cur_idx %u/%u", ja->cur_idx, ja->nr);
 		for (i = 0; i < 3; i++) {
@@ -1086,6 +1101,7 @@ found:
 
 			bch_err(c, "bucket_seq[%u] = %llu", idx, ja->bucket_seq[idx]);
 		}
+#endif
 		ja->sectors_free = 0;
 	}
 
@@ -1513,9 +1529,9 @@ static inline struct journal_buf *journal_last_unwritten_buf(struct journal *j)
 	return j->buf + (journal_last_unwritten_seq(j) & JOURNAL_BUF_MASK);
 }
 
-static void journal_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_done)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct journal_buf *w = journal_last_unwritten_buf(j);
 	struct bch_replicas_padded replicas;
@@ -1583,6 +1599,7 @@ static void journal_write_done(struct closure *cl)
 	} while ((v = atomic64_cmpxchg(&j->reservations.counter,
 				       old.v, new.v)) != old.v);
 
+	bch2_journal_reclaim_fast(j);
 	bch2_journal_space_available(j);
 
 	closure_wake_up(&w->wait);
@@ -1631,9 +1648,9 @@ static void journal_write_endio(struct bio *bio)
 	percpu_ref_put(&ca->io_ref);
 }
 
-static void do_journal_write(struct closure *cl)
+static CLOSURE_CALLBACK(do_journal_write)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct bch_dev *ca;
 	struct journal_buf *w = journal_last_unwritten_buf(j);
@@ -1843,9 +1860,9 @@ static int bch2_journal_write_pick_flush(struct journal *j, struct journal_buf *
 	return 0;
 }
 
-void bch2_journal_write(struct closure *cl)
+CLOSURE_CALLBACK(bch2_journal_write)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct bch_dev *ca;
 	struct journal_buf *w = journal_last_unwritten_buf(j);
diff --git a/fs/bcachefs/journal_io.h b/fs/bcachefs/journal_io.h
index a88d097b13f129..c035e7c108e190 100644
--- a/fs/bcachefs/journal_io.h
+++ b/fs/bcachefs/journal_io.h
@@ -60,6 +60,6 @@ void bch2_journal_ptrs_to_text(struct printbuf *, struct bch_fs *,
 
 int bch2_journal_read(struct bch_fs *, u64 *, u64 *, u64 *);
 
-void bch2_journal_write(struct closure *);
+CLOSURE_CALLBACK(bch2_journal_write);
 
 #endif /* _BCACHEFS_JOURNAL_IO_H */
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index 9a584aaaa2eba9..ec712104addb32 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -50,16 +50,21 @@ unsigned bch2_journal_dev_buckets_available(struct journal *j,
 	return available;
 }
 
-static void journal_set_remaining(struct journal *j, unsigned u64s_remaining)
+static inline void journal_set_watermark(struct journal *j, bool low_on_space)
 {
-	union journal_preres_state old, new;
-	u64 v = atomic64_read(&j->prereserved.counter);
+	unsigned watermark = BCH_WATERMARK_stripe;
 
-	do {
-		old.v = new.v = v;
-		new.remaining = u64s_remaining;
-	} while ((v = atomic64_cmpxchg(&j->prereserved.counter,
-				       old.v, new.v)) != old.v);
+	if (low_on_space)
+		watermark = max_t(unsigned, watermark, BCH_WATERMARK_reclaim);
+	if (fifo_free(&j->pin) < j->pin.size / 4)
+		watermark = max_t(unsigned, watermark, BCH_WATERMARK_reclaim);
+
+	if (watermark == j->watermark)
+		return;
+
+	swap(watermark, j->watermark);
+	if (watermark > j->watermark)
+		journal_wake(j);
 }
 
 static struct journal_space
@@ -162,7 +167,6 @@ void bch2_journal_space_available(struct journal *j)
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct bch_dev *ca;
 	unsigned clean, clean_ondisk, total;
-	s64 u64s_remaining = 0;
 	unsigned max_entry_size	 = min(j->buf[0].buf_size >> 9,
 				       j->buf[1].buf_size >> 9);
 	unsigned i, nr_online = 0, nr_devs_want;
@@ -222,16 +226,10 @@ void bch2_journal_space_available(struct journal *j)
 	else
 		clear_bit(JOURNAL_MAY_SKIP_FLUSH, &j->flags);
 
-	u64s_remaining  = (u64) clean << 6;
-	u64s_remaining -= (u64) total << 3;
-	u64s_remaining = max(0LL, u64s_remaining);
-	u64s_remaining /= 4;
-	u64s_remaining = min_t(u64, u64s_remaining, U32_MAX);
+	journal_set_watermark(j, clean * 4 <= total);
 out:
 	j->cur_entry_sectors	= !ret ? j->space[journal_space_discarded].next_entry : 0;
 	j->cur_entry_error	= ret;
-	journal_set_remaining(j, u64s_remaining);
-	journal_set_watermark(j);
 
 	if (!ret)
 		journal_wake(j);
@@ -555,11 +553,6 @@ static u64 journal_seq_to_flush(struct journal *j)
 		/* Try to keep the journal at most half full: */
 		nr_buckets = ja->nr / 2;
 
-		/* And include pre-reservations: */
-		nr_buckets += DIV_ROUND_UP(j->prereserved.reserved,
-					   (ca->mi.bucket_size << 6) -
-					   journal_entry_overhead(j));
-
 		nr_buckets = min(nr_buckets, ja->nr);
 
 		bucket_to_flush = (ja->cur_idx + nr_buckets) % ja->nr;
@@ -638,10 +631,7 @@ static int __bch2_journal_reclaim(struct journal *j, bool direct, bool kicked)
 			       msecs_to_jiffies(c->opts.journal_reclaim_delay)))
 			min_nr = 1;
 
-		if (j->prereserved.reserved * 4 > j->prereserved.remaining)
-			min_nr = 1;
-
-		if (fifo_free(&j->pin) <= 32)
+		if (j->watermark != BCH_WATERMARK_stripe)
 			min_nr = 1;
 
 		if (atomic_read(&c->btree_cache.dirty) * 2 > c->btree_cache.used)
@@ -652,8 +642,6 @@ static int __bch2_journal_reclaim(struct journal *j, bool direct, bool kicked)
 		trace_and_count(c, journal_reclaim_start, c,
 				direct, kicked,
 				min_nr, min_key_cache,
-				j->prereserved.reserved,
-				j->prereserved.remaining,
 				atomic_read(&c->btree_cache.dirty),
 				c->btree_cache.used,
 				atomic_long_read(&c->btree_key_cache.nr_dirty),
@@ -788,6 +776,9 @@ static int journal_flush_done(struct journal *j, u64 seq_to_flush,
 			       (1U << JOURNAL_PIN_btree), 0, 0, 0))
 		*did_work = true;
 
+	if (seq_to_flush > journal_cur_seq(j))
+		bch2_journal_entry_close(j);
+
 	spin_lock(&j->lock);
 	/*
 	 * If journal replay hasn't completed, the unreplayed journal entries
diff --git a/fs/bcachefs/journal_types.h b/fs/bcachefs/journal_types.h
index 42504e16acb6cc..a756b69582e349 100644
--- a/fs/bcachefs/journal_types.h
+++ b/fs/bcachefs/journal_types.h
@@ -76,14 +76,6 @@ struct journal_res {
 	u64			seq;
 };
 
-/*
- * For reserving space in the journal prior to getting a reservation on a
- * particular journal entry:
- */
-struct journal_preres {
-	unsigned		u64s;
-};
-
 union journal_res_state {
 	struct {
 		atomic64_t	counter;
@@ -104,22 +96,6 @@ union journal_res_state {
 	};
 };
 
-union journal_preres_state {
-	struct {
-		atomic64_t	counter;
-	};
-
-	struct {
-		u64		v;
-	};
-
-	struct {
-		u64		waiting:1,
-				reserved:31,
-				remaining:32;
-	};
-};
-
 /* bytes: */
 #define JOURNAL_ENTRY_SIZE_MIN		(64U << 10) /* 64k */
 #define JOURNAL_ENTRY_SIZE_MAX		(4U  << 20) /* 4M */
@@ -180,8 +156,6 @@ struct journal {
 	union journal_res_state reservations;
 	enum bch_watermark	watermark;
 
-	union journal_preres_state prereserved;
-
 	} __aligned(SMP_CACHE_BYTES);
 
 	unsigned long		flags;
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index ab749bf2fcbc55..54830ee0ed8867 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -49,17 +49,6 @@ static void trace_move_extent_read2(struct bch_fs *c, struct bkey_s_c k)
 	}
 }
 
-static void trace_move_extent_alloc_mem_fail2(struct bch_fs *c, struct bkey_s_c k)
-{
-	if (trace_move_extent_alloc_mem_fail_enabled()) {
-		struct printbuf buf = PRINTBUF;
-
-		bch2_bkey_val_to_text(&buf, c, k);
-		trace_move_extent_alloc_mem_fail(c, buf.buf);
-		printbuf_exit(&buf);
-	}
-}
-
 struct moving_io {
 	struct list_head		read_list;
 	struct list_head		io_list;
@@ -163,12 +152,18 @@ void bch2_move_ctxt_wait_for_io(struct moving_context *ctxt)
 		atomic_read(&ctxt->write_sectors) != sectors_pending);
 }
 
+static void bch2_moving_ctxt_flush_all(struct moving_context *ctxt)
+{
+	move_ctxt_wait_event(ctxt, list_empty(&ctxt->reads));
+	bch2_trans_unlock_long(ctxt->trans);
+	closure_sync(&ctxt->cl);
+}
+
 void bch2_moving_ctxt_exit(struct moving_context *ctxt)
 {
 	struct bch_fs *c = ctxt->trans->c;
 
-	move_ctxt_wait_event(ctxt, list_empty(&ctxt->reads));
-	closure_sync(&ctxt->cl);
+	bch2_moving_ctxt_flush_all(ctxt);
 
 	EBUG_ON(atomic_read(&ctxt->write_sectors));
 	EBUG_ON(atomic_read(&ctxt->write_ios));
@@ -223,49 +218,6 @@ void bch2_move_stats_init(struct bch_move_stats *stats, char *name)
 	scnprintf(stats->name, sizeof(stats->name), "%s", name);
 }
 
-static int bch2_extent_drop_ptrs(struct btree_trans *trans,
-				 struct btree_iter *iter,
-				 struct bkey_s_c k,
-				 struct data_update_opts data_opts)
-{
-	struct bch_fs *c = trans->c;
-	struct bkey_i *n;
-	int ret;
-
-	n = bch2_bkey_make_mut_noupdate(trans, k);
-	ret = PTR_ERR_OR_ZERO(n);
-	if (ret)
-		return ret;
-
-	while (data_opts.kill_ptrs) {
-		unsigned i = 0, drop = __fls(data_opts.kill_ptrs);
-		struct bch_extent_ptr *ptr;
-
-		bch2_bkey_drop_ptrs(bkey_i_to_s(n), ptr, i++ == drop);
-		data_opts.kill_ptrs ^= 1U << drop;
-	}
-
-	/*
-	 * If the new extent no longer has any pointers, bch2_extent_normalize()
-	 * will do the appropriate thing with it (turning it into a
-	 * KEY_TYPE_error key, or just a discard if it was a cached extent)
-	 */
-	bch2_extent_normalize(c, bkey_i_to_s(n));
-
-	/*
-	 * Since we're not inserting through an extent iterator
-	 * (BTREE_ITER_ALL_SNAPSHOTS iterators aren't extent iterators),
-	 * we aren't using the extent overwrite path to delete, we're
-	 * just using the normal key deletion path:
-	 */
-	if (bkey_deleted(&n->k))
-		n->k.size = 0;
-
-	return bch2_trans_relock(trans) ?:
-		bch2_trans_update(trans, iter, n, BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) ?:
-		bch2_trans_commit(trans, NULL, NULL, BTREE_INSERT_NOFAIL);
-}
-
 int bch2_move_extent(struct moving_context *ctxt,
 		     struct move_bucket_in_flight *bucket_in_flight,
 		     struct btree_iter *iter,
@@ -335,19 +287,11 @@ int bch2_move_extent(struct moving_context *ctxt,
 	io->rbio.bio.bi_iter.bi_sector	= bkey_start_offset(k.k);
 	io->rbio.bio.bi_end_io		= move_read_endio;
 
-	ret = bch2_data_update_init(trans, ctxt, &io->write, ctxt->wp,
+	ret = bch2_data_update_init(trans, iter, ctxt, &io->write, ctxt->wp,
 				    io_opts, data_opts, iter->btree_id, k);
-	if (ret && ret != -BCH_ERR_unwritten_extent_update)
+	if (ret)
 		goto err_free_pages;
 
-	if (ret == -BCH_ERR_unwritten_extent_update) {
-		bch2_update_unwritten_extent(trans, &io->write);
-		move_free(io);
-		return 0;
-	}
-
-	BUG_ON(ret);
-
 	io->write.op.end_io = move_write_done;
 
 	if (ctxt->rate)
@@ -391,8 +335,23 @@ err_free_pages:
 err_free:
 	kfree(io);
 err:
-	this_cpu_inc(c->counters[BCH_COUNTER_move_extent_alloc_mem_fail]);
-	trace_move_extent_alloc_mem_fail2(c, k);
+	if (ret == -BCH_ERR_data_update_done)
+		return 0;
+
+	if (bch2_err_matches(ret, EROFS) ||
+	    bch2_err_matches(ret, BCH_ERR_transaction_restart))
+		return ret;
+
+	this_cpu_inc(c->counters[BCH_COUNTER_move_extent_start_fail]);
+	if (trace_move_extent_start_fail_enabled()) {
+		struct printbuf buf = PRINTBUF;
+
+		bch2_bkey_val_to_text(&buf, c, k);
+		prt_str(&buf, ": ");
+		prt_str(&buf, bch2_err_str(ret));
+		trace_move_extent_start_fail(c, buf.buf);
+		printbuf_exit(&buf);
+	}
 	return ret;
 }
 
@@ -482,37 +441,30 @@ int bch2_move_get_io_opts_one(struct btree_trans *trans,
 int bch2_move_ratelimit(struct moving_context *ctxt)
 {
 	struct bch_fs *c = ctxt->trans->c;
+	bool is_kthread = current->flags & PF_KTHREAD;
 	u64 delay;
 
-	if (ctxt->wait_on_copygc && !c->copygc_running) {
-		bch2_trans_unlock_long(ctxt->trans);
+	if (ctxt->wait_on_copygc && c->copygc_running) {
+		bch2_moving_ctxt_flush_all(ctxt);
 		wait_event_killable(c->copygc_running_wq,
 				    !c->copygc_running ||
-				    kthread_should_stop());
+				    (is_kthread && kthread_should_stop()));
 	}
 
 	do {
 		delay = ctxt->rate ? bch2_ratelimit_delay(ctxt->rate) : 0;
 
-
-		if (delay) {
-			if (delay > HZ / 10)
-				bch2_trans_unlock_long(ctxt->trans);
-			else
-				bch2_trans_unlock(ctxt->trans);
-			set_current_state(TASK_INTERRUPTIBLE);
-		}
-
-		if ((current->flags & PF_KTHREAD) && kthread_should_stop()) {
-			__set_current_state(TASK_RUNNING);
+		if (is_kthread && kthread_should_stop())
 			return 1;
-		}
 
 		if (delay)
-			schedule_timeout(delay);
+			move_ctxt_wait_event_timeout(ctxt,
+					freezing(current) ||
+					(is_kthread && kthread_should_stop()),
+					delay);
 
 		if (unlikely(freezing(current))) {
-			move_ctxt_wait_event(ctxt, list_empty(&ctxt->reads));
+			bch2_moving_ctxt_flush_all(ctxt);
 			try_to_freeze();
 		}
 	} while (delay);
@@ -683,6 +635,7 @@ int __bch2_evacuate_bucket(struct moving_context *ctxt,
 {
 	struct btree_trans *trans = ctxt->trans;
 	struct bch_fs *c = trans->c;
+	bool is_kthread = current->flags & PF_KTHREAD;
 	struct bch_io_opts io_opts = bch2_opts_to_inode_opts(c->opts);
 	struct btree_iter iter;
 	struct bkey_buf sk;
@@ -728,6 +681,9 @@ int __bch2_evacuate_bucket(struct moving_context *ctxt,
 	}
 
 	while (!(ret = bch2_move_ratelimit(ctxt))) {
+		if (is_kthread && kthread_should_stop())
+			break;
+
 		bch2_trans_begin(trans);
 
 		ret = bch2_get_next_backpointer(trans, bucket, gen,
diff --git a/fs/bcachefs/move.h b/fs/bcachefs/move.h
index 07cf9d42643b4f..0906aa2d1de29c 100644
--- a/fs/bcachefs/move.h
+++ b/fs/bcachefs/move.h
@@ -38,6 +38,25 @@ struct moving_context {
 	wait_queue_head_t	wait;
 };
 
+#define move_ctxt_wait_event_timeout(_ctxt, _cond, _timeout)			\
+({										\
+	int _ret = 0;								\
+	while (true) {								\
+		bool cond_finished = false;					\
+		bch2_moving_ctxt_do_pending_writes(_ctxt);			\
+										\
+		if (_cond)							\
+			break;							\
+		bch2_trans_unlock_long((_ctxt)->trans);				\
+		_ret = __wait_event_timeout((_ctxt)->wait,			\
+			     bch2_moving_ctxt_next_pending_write(_ctxt) ||	\
+			     (cond_finished = (_cond)), _timeout);		\
+		if (_ret || ( cond_finished))					\
+			break;							\
+	}									\
+	_ret;									\
+})
+
 #define move_ctxt_wait_event(_ctxt, _cond)				\
 do {									\
 	bool cond_finished = false;					\
diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c
index 0a0576326c5b2d..a84e79f79e5ec5 100644
--- a/fs/bcachefs/movinggc.c
+++ b/fs/bcachefs/movinggc.c
@@ -207,7 +207,7 @@ static int bch2_copygc(struct moving_context *ctxt,
 		goto err;
 
 	darray_for_each(buckets, i) {
-		if (unlikely(freezing(current)))
+		if (kthread_should_stop() || freezing(current))
 			break;
 
 		f = move_bucket_in_flight_add(buckets_in_flight, *i);
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 9c30500ce9200a..c7d9074c82d97b 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -144,7 +144,7 @@ static int bch2_journal_replay(struct bch_fs *c)
 	u64 start_seq	= c->journal_replay_seq_start;
 	u64 end_seq	= c->journal_replay_seq_start;
 	size_t i;
-	int ret;
+	int ret = 0;
 
 	move_gap(keys->d, keys->nr, keys->size, keys->gap, keys->nr);
 	keys->gap = keys->nr;
@@ -167,6 +167,8 @@ static int bch2_journal_replay(struct bch_fs *c)
 			goto err;
 	}
 
+	BUG_ON(!atomic_read(&keys->ref));
+
 	for (i = 0; i < keys->nr; i++) {
 		k = keys_sorted[i];
 
@@ -188,6 +190,9 @@ static int bch2_journal_replay(struct bch_fs *c)
 		}
 	}
 
+	if (!c->opts.keep_journal)
+		bch2_journal_keys_put_initial(c);
+
 	replay_now_at(j, j->replay_journal_seq_end);
 	j->replay_journal_seq = 0;
 
@@ -909,10 +914,8 @@ out:
 	bch2_flush_fsck_errs(c);
 
 	if (!c->opts.keep_journal &&
-	    test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags)) {
-		bch2_journal_keys_free(&c->journal_keys);
-		bch2_journal_entries_free(c);
-	}
+	    test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags))
+		bch2_journal_keys_put_initial(c);
 	kfree(clean);
 
 	if (!ret && test_bit(BCH_FS_NEED_DELETE_DEAD_SNAPSHOTS, &c->flags)) {
diff --git a/fs/bcachefs/recovery.h b/fs/bcachefs/recovery.h
index 852d30567da9c4..d266aae90200e5 100644
--- a/fs/bcachefs/recovery.h
+++ b/fs/bcachefs/recovery.h
@@ -10,6 +10,9 @@ extern const char * const bch2_recovery_passes[];
 static inline int bch2_run_explicit_recovery_pass(struct bch_fs *c,
 						  enum bch_recovery_pass pass)
 {
+	if (c->recovery_passes_explicit & BIT_ULL(pass))
+		return 0;
+
 	bch_info(c, "running explicit recovery pass %s (%u), currently at %s (%u)",
 		 bch2_recovery_passes[pass], pass,
 		 bch2_recovery_passes[c->curr_recovery_pass], c->curr_recovery_pass);
diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c
index 6e1bfe9feb59e4..37d16e04e6715a 100644
--- a/fs/bcachefs/reflink.c
+++ b/fs/bcachefs/reflink.c
@@ -121,6 +121,14 @@ int bch2_trans_mark_reflink_v(struct btree_trans *trans,
 {
 	check_indirect_extent_deleting(new, &flags);
 
+	if (old.k->type == KEY_TYPE_reflink_v &&
+	    new->k.type == KEY_TYPE_reflink_v &&
+	    old.k->u64s == new->k.u64s &&
+	    !memcmp(bkey_s_c_to_reflink_v(old).v->start,
+		    bkey_i_to_reflink_v(new)->v.start,
+		    bkey_val_bytes(&new->k) - 8))
+		return 0;
+
 	return bch2_trans_mark_extent(trans, btree_id, level, old, new, flags);
 }
 
diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c
index 1c3ae13bfced1d..2008fe8bf7060d 100644
--- a/fs/bcachefs/replicas.c
+++ b/fs/bcachefs/replicas.c
@@ -68,6 +68,33 @@ void bch2_replicas_entry_to_text(struct printbuf *out,
 	prt_printf(out, "]");
 }
 
+int bch2_replicas_entry_validate(struct bch_replicas_entry *r,
+				 struct bch_sb *sb,
+				 struct printbuf *err)
+{
+	if (!r->nr_devs) {
+		prt_printf(err, "no devices in entry ");
+		goto bad;
+	}
+
+	if (r->nr_required > 1 &&
+	    r->nr_required >= r->nr_devs) {
+		prt_printf(err, "bad nr_required in entry ");
+		goto bad;
+	}
+
+	for (unsigned i = 0; i < r->nr_devs; i++)
+		if (!bch2_dev_exists(sb, r->devs[i])) {
+			prt_printf(err, "invalid device %u in entry ", r->devs[i]);
+			goto bad;
+		}
+
+	return 0;
+bad:
+	bch2_replicas_entry_to_text(err, r);
+	return -BCH_ERR_invalid_replicas_entry;
+}
+
 void bch2_cpu_replicas_to_text(struct printbuf *out,
 			       struct bch_replicas_cpu *r)
 {
@@ -163,7 +190,8 @@ void bch2_devlist_to_replicas(struct bch_replicas_entry *e,
 }
 
 static struct bch_replicas_cpu
-cpu_replicas_add_entry(struct bch_replicas_cpu *old,
+cpu_replicas_add_entry(struct bch_fs *c,
+		       struct bch_replicas_cpu *old,
 		       struct bch_replicas_entry *new_entry)
 {
 	unsigned i;
@@ -173,6 +201,9 @@ cpu_replicas_add_entry(struct bch_replicas_cpu *old,
 					replicas_entry_bytes(new_entry)),
 	};
 
+	for (i = 0; i < new_entry->nr_devs; i++)
+		BUG_ON(!bch2_dev_exists2(c, new_entry->devs[i]));
+
 	BUG_ON(!new_entry->data_type);
 	verify_replicas_entry(new_entry);
 
@@ -382,7 +413,7 @@ static int bch2_mark_replicas_slowpath(struct bch_fs *c,
 
 	if (c->replicas_gc.entries &&
 	    !__replicas_has_entry(&c->replicas_gc, new_entry)) {
-		new_gc = cpu_replicas_add_entry(&c->replicas_gc, new_entry);
+		new_gc = cpu_replicas_add_entry(c, &c->replicas_gc, new_entry);
 		if (!new_gc.entries) {
 			ret = -BCH_ERR_ENOMEM_cpu_replicas;
 			goto err;
@@ -390,7 +421,7 @@ static int bch2_mark_replicas_slowpath(struct bch_fs *c,
 	}
 
 	if (!__replicas_has_entry(&c->replicas, new_entry)) {
-		new_r = cpu_replicas_add_entry(&c->replicas, new_entry);
+		new_r = cpu_replicas_add_entry(c, &c->replicas, new_entry);
 		if (!new_r.entries) {
 			ret = -BCH_ERR_ENOMEM_cpu_replicas;
 			goto err;
@@ -598,7 +629,7 @@ int bch2_replicas_set_usage(struct bch_fs *c,
 	if (idx < 0) {
 		struct bch_replicas_cpu n;
 
-		n = cpu_replicas_add_entry(&c->replicas, r);
+		n = cpu_replicas_add_entry(c, &c->replicas, r);
 		if (!n.entries)
 			return -BCH_ERR_ENOMEM_cpu_replicas;
 
@@ -797,7 +828,7 @@ static int bch2_cpu_replicas_validate(struct bch_replicas_cpu *cpu_r,
 				      struct bch_sb *sb,
 				      struct printbuf *err)
 {
-	unsigned i, j;
+	unsigned i;
 
 	sort_cmp_size(cpu_r->entries,
 		      cpu_r->nr,
@@ -808,31 +839,9 @@ static int bch2_cpu_replicas_validate(struct bch_replicas_cpu *cpu_r,
 		struct bch_replicas_entry *e =
 			cpu_replicas_entry(cpu_r, i);
 
-		if (e->data_type >= BCH_DATA_NR) {
-			prt_printf(err, "invalid data type in entry ");
-			bch2_replicas_entry_to_text(err, e);
-			return -BCH_ERR_invalid_sb_replicas;
-		}
-
-		if (!e->nr_devs) {
-			prt_printf(err, "no devices in entry ");
-			bch2_replicas_entry_to_text(err, e);
-			return -BCH_ERR_invalid_sb_replicas;
-		}
-
-		if (e->nr_required > 1 &&
-		    e->nr_required >= e->nr_devs) {
-			prt_printf(err, "bad nr_required in entry ");
-			bch2_replicas_entry_to_text(err, e);
-			return -BCH_ERR_invalid_sb_replicas;
-		}
-
-		for (j = 0; j < e->nr_devs; j++)
-			if (!bch2_dev_exists(sb, e->devs[j])) {
-				prt_printf(err, "invalid device %u in entry ", e->devs[j]);
-				bch2_replicas_entry_to_text(err, e);
-				return -BCH_ERR_invalid_sb_replicas;
-			}
+		int ret = bch2_replicas_entry_validate(e, sb, err);
+		if (ret)
+			return ret;
 
 		if (i + 1 < cpu_r->nr) {
 			struct bch_replicas_entry *n =
diff --git a/fs/bcachefs/replicas.h b/fs/bcachefs/replicas.h
index 4887675a86f09c..f70a642775d1b2 100644
--- a/fs/bcachefs/replicas.h
+++ b/fs/bcachefs/replicas.h
@@ -9,6 +9,8 @@
 void bch2_replicas_entry_sort(struct bch_replicas_entry *);
 void bch2_replicas_entry_to_text(struct printbuf *,
 				 struct bch_replicas_entry *);
+int bch2_replicas_entry_validate(struct bch_replicas_entry *,
+				 struct bch_sb *, struct printbuf *);
 void bch2_cpu_replicas_to_text(struct printbuf *, struct bch_replicas_cpu *);
 
 static inline struct bch_replicas_entry *
diff --git a/fs/bcachefs/six.c b/fs/bcachefs/six.c
index b775cf0fb7cbf2..97790445e67ad2 100644
--- a/fs/bcachefs/six.c
+++ b/fs/bcachefs/six.c
@@ -163,8 +163,11 @@ static int __do_six_trylock(struct six_lock *lock, enum six_lock_type type,
 		this_cpu_sub(*lock->readers, !ret);
 		preempt_enable();
 
-		if (!ret && (old & SIX_LOCK_WAITING_write))
-			ret = -1 - SIX_LOCK_write;
+		if (!ret) {
+			smp_mb();
+			if (atomic_read(&lock->state) & SIX_LOCK_WAITING_write)
+				ret = -1 - SIX_LOCK_write;
+		}
 	} else if (type == SIX_LOCK_write && lock->readers) {
 		if (try) {
 			atomic_add(SIX_LOCK_HELD_write, &lock->state);
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index e9af77b384c76c..5dac038f085195 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -959,7 +959,7 @@ static int bch2_snapshot_node_delete(struct btree_trans *trans, u32 id)
 					parent_id, id))
 			goto err;
 
-		parent->v.children[i] = le32_to_cpu(child_id);
+		parent->v.children[i] = cpu_to_le32(child_id);
 
 		normalize_snapshot_child_pointers(&parent->v);
 	}
diff --git a/fs/bcachefs/subvolume_types.h b/fs/bcachefs/subvolume_types.h
index 86833445af2056..2d2e66a4e4681e 100644
--- a/fs/bcachefs/subvolume_types.h
+++ b/fs/bcachefs/subvolume_types.h
@@ -20,7 +20,7 @@ struct snapshot_t {
 };
 
 struct snapshot_table {
-	struct snapshot_t	s[0];
+	DECLARE_FLEX_ARRAY(struct snapshot_t, s);
 };
 
 typedef struct {
diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index f4cad903f4d69d..f3e12f7979d5ea 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -166,6 +166,7 @@ void bch2_free_super(struct bch_sb_handle *sb)
 	if (!IS_ERR_OR_NULL(sb->bdev))
 		blkdev_put(sb->bdev, sb->holder);
 	kfree(sb->holder);
+	kfree(sb->sb_name);
 
 	kfree(sb->sb);
 	memset(sb, 0, sizeof(*sb));
@@ -675,6 +676,10 @@ retry:
 	if (!sb->holder)
 		return -ENOMEM;
 
+	sb->sb_name = kstrdup(path, GFP_KERNEL);
+	if (!sb->sb_name)
+		return -ENOMEM;
+
 #ifndef __KERNEL__
 	if (opt_get(*opts, direct_io) == false)
 		sb->mode |= BLK_OPEN_BUFFERED;
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 24672bb31cbe9c..818ec467a06b96 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -72,6 +72,12 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Kent Overstreet <kent.overstreet@gmail.com>");
 MODULE_DESCRIPTION("bcachefs filesystem");
+MODULE_SOFTDEP("pre: crc32c");
+MODULE_SOFTDEP("pre: crc64");
+MODULE_SOFTDEP("pre: sha256");
+MODULE_SOFTDEP("pre: chacha20");
+MODULE_SOFTDEP("pre: poly1305");
+MODULE_SOFTDEP("pre: xxhash");
 
 #define KTYPE(type)							\
 static const struct attribute_group type ## _group = {			\
@@ -423,6 +429,18 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early)
 		bch2_dev_allocator_add(c, ca);
 	bch2_recalc_capacity(c);
 
+	set_bit(BCH_FS_RW, &c->flags);
+	set_bit(BCH_FS_WAS_RW, &c->flags);
+
+#ifndef BCH_WRITE_REF_DEBUG
+	percpu_ref_reinit(&c->writes);
+#else
+	for (i = 0; i < BCH_WRITE_REF_NR; i++) {
+		BUG_ON(atomic_long_read(&c->writes[i]));
+		atomic_long_inc(&c->writes[i]);
+	}
+#endif
+
 	ret = bch2_gc_thread_start(c);
 	if (ret) {
 		bch_err(c, "error starting gc thread");
@@ -439,24 +457,16 @@ static int __bch2_fs_read_write(struct bch_fs *c, bool early)
 			goto err;
 	}
 
-#ifndef BCH_WRITE_REF_DEBUG
-	percpu_ref_reinit(&c->writes);
-#else
-	for (i = 0; i < BCH_WRITE_REF_NR; i++) {
-		BUG_ON(atomic_long_read(&c->writes[i]));
-		atomic_long_inc(&c->writes[i]);
-	}
-#endif
-	set_bit(BCH_FS_RW, &c->flags);
-	set_bit(BCH_FS_WAS_RW, &c->flags);
-
 	bch2_do_discards(c);
 	bch2_do_invalidates(c);
 	bch2_do_stripe_deletes(c);
 	bch2_do_pending_node_rewrites(c);
 	return 0;
 err:
-	__bch2_fs_read_only(c);
+	if (test_bit(BCH_FS_RW, &c->flags))
+		bch2_fs_read_only(c);
+	else
+		__bch2_fs_read_only(c);
 	return ret;
 }
 
@@ -504,8 +514,8 @@ static void __bch2_fs_free(struct bch_fs *c)
 	bch2_io_clock_exit(&c->io_clock[WRITE]);
 	bch2_io_clock_exit(&c->io_clock[READ]);
 	bch2_fs_compress_exit(c);
-	bch2_journal_keys_free(&c->journal_keys);
-	bch2_journal_entries_free(c);
+	bch2_journal_keys_put_initial(c);
+	BUG_ON(atomic_read(&c->journal_keys.ref));
 	bch2_fs_btree_write_buffer_exit(c);
 	percpu_free_rwsem(&c->mark_lock);
 	free_percpu(c->online_reserved);
@@ -702,12 +712,15 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 
 	init_rwsem(&c->gc_lock);
 	mutex_init(&c->gc_gens_lock);
+	atomic_set(&c->journal_keys.ref, 1);
+	c->journal_keys.initial_ref_held = true;
 
 	for (i = 0; i < BCH_TIME_STAT_NR; i++)
 		bch2_time_stats_init(&c->times[i]);
 
 	bch2_fs_copygc_init(c);
 	bch2_fs_btree_key_cache_init_early(&c->btree_key_cache);
+	bch2_fs_btree_iter_init_early(c);
 	bch2_fs_btree_interior_update_init_early(c);
 	bch2_fs_allocator_background_init(c);
 	bch2_fs_allocator_foreground_init(c);
diff --git a/fs/bcachefs/super_types.h b/fs/bcachefs/super_types.h
index 7dda4985b99fe6..9c1fd4ca2b1034 100644
--- a/fs/bcachefs/super_types.h
+++ b/fs/bcachefs/super_types.h
@@ -5,6 +5,7 @@
 struct bch_sb_handle {
 	struct bch_sb		*sb;
 	struct block_device	*bdev;
+	char			*sb_name;
 	struct bio		*bio;
 	void			*holder;
 	size_t			buffer_size;
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index ab743115f169e5..f3cb7115b530bb 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -276,8 +276,8 @@ static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c
 		if (!btree_type_has_ptrs(id))
 			continue;
 
-		for_each_btree_key(trans, iter, id, POS_MIN,
-				   BTREE_ITER_ALL_SNAPSHOTS, k, ret) {
+		ret = for_each_btree_key2(trans, iter, id, POS_MIN,
+					  BTREE_ITER_ALL_SNAPSHOTS, k, ({
 			struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
 			const union bch_extent_entry *entry;
 			struct extent_ptr_decoded p;
@@ -309,8 +309,8 @@ static int bch2_compression_stats_to_text(struct printbuf *out, struct bch_fs *c
 				nr_uncompressed_extents++;
 			else if (compressed)
 				nr_compressed_extents++;
-		}
-		bch2_trans_iter_exit(trans, &iter);
+			0;
+		}));
 	}
 
 	bch2_trans_put(trans);
diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index 893304a1f06e6e..fd49b63562c36c 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -196,10 +196,9 @@ DEFINE_EVENT(bio, journal_write,
 TRACE_EVENT(journal_reclaim_start,
 	TP_PROTO(struct bch_fs *c, bool direct, bool kicked,
 		 u64 min_nr, u64 min_key_cache,
-		 u64 prereserved, u64 prereserved_total,
 		 u64 btree_cache_dirty, u64 btree_cache_total,
 		 u64 btree_key_cache_dirty, u64 btree_key_cache_total),
-	TP_ARGS(c, direct, kicked, min_nr, min_key_cache, prereserved, prereserved_total,
+	TP_ARGS(c, direct, kicked, min_nr, min_key_cache,
 		btree_cache_dirty, btree_cache_total,
 		btree_key_cache_dirty, btree_key_cache_total),
 
@@ -209,8 +208,6 @@ TRACE_EVENT(journal_reclaim_start,
 		__field(bool,		kicked			)
 		__field(u64,		min_nr			)
 		__field(u64,		min_key_cache		)
-		__field(u64,		prereserved		)
-		__field(u64,		prereserved_total	)
 		__field(u64,		btree_cache_dirty	)
 		__field(u64,		btree_cache_total	)
 		__field(u64,		btree_key_cache_dirty	)
@@ -223,22 +220,18 @@ TRACE_EVENT(journal_reclaim_start,
 		__entry->kicked			= kicked;
 		__entry->min_nr			= min_nr;
 		__entry->min_key_cache		= min_key_cache;
-		__entry->prereserved		= prereserved;
-		__entry->prereserved_total	= prereserved_total;
 		__entry->btree_cache_dirty	= btree_cache_dirty;
 		__entry->btree_cache_total	= btree_cache_total;
 		__entry->btree_key_cache_dirty	= btree_key_cache_dirty;
 		__entry->btree_key_cache_total	= btree_key_cache_total;
 	),
 
-	TP_printk("%d,%d direct %u kicked %u min %llu key cache %llu prereserved %llu/%llu btree cache %llu/%llu key cache %llu/%llu",
+	TP_printk("%d,%d direct %u kicked %u min %llu key cache %llu btree cache %llu/%llu key cache %llu/%llu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->direct,
 		  __entry->kicked,
 		  __entry->min_nr,
 		  __entry->min_key_cache,
-		  __entry->prereserved,
-		  __entry->prereserved_total,
 		  __entry->btree_cache_dirty,
 		  __entry->btree_cache_total,
 		  __entry->btree_key_cache_dirty,
@@ -761,9 +754,9 @@ TRACE_EVENT(move_extent_fail,
 	TP_printk("%d:%d %s", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(msg))
 );
 
-DEFINE_EVENT(bkey, move_extent_alloc_mem_fail,
-	TP_PROTO(struct bch_fs *c, const char *k),
-	TP_ARGS(c, k)
+DEFINE_EVENT(bkey, move_extent_start_fail,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
 );
 
 TRACE_EVENT(move_data,
diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c
index a39ff0c296ecfb..79d982674c1803 100644
--- a/fs/bcachefs/xattr.c
+++ b/fs/bcachefs/xattr.c
@@ -552,6 +552,14 @@ static int bch2_xattr_bcachefs_set(const struct xattr_handler *handler,
 		s.v = v + 1;
 		s.defined = true;
 	} else {
+		/*
+		 * Check if this option was set on the parent - if so, switched
+		 * back to inheriting from the parent:
+		 *
+		 * rename() also has to deal with keeping inherited options up
+		 * to date - see bch2_reinherit_attrs()
+		 */
+		spin_lock(&dentry->d_lock);
 		if (!IS_ROOT(dentry)) {
 			struct bch_inode_info *dir =
 				to_bch_ei(d_inode(dentry->d_parent));
@@ -560,6 +568,7 @@ static int bch2_xattr_bcachefs_set(const struct xattr_handler *handler,
 		} else {
 			s.v = 0;
 		}
+		spin_unlock(&dentry->d_lock);
 
 		s.defined = false;
 	}
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 2a9344a3fcee92..35c1d24d4a7842 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -432,7 +432,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 	if (btrfs_block_can_be_shared(trans, root, buf)) {
 		ret = btrfs_lookup_extent_info(trans, fs_info, buf->start,
 					       btrfs_header_level(buf), 1,
-					       &refs, &flags);
+					       &refs, &flags, NULL);
 		if (ret)
 			return ret;
 		if (unlikely(refs == 0)) {
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index 51453d4928fa40..2833e8ef4c098f 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -199,7 +199,7 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode,
 	start = round_down(start, fs_info->sectorsize);
 
 	btrfs_free_reserved_data_space_noquota(fs_info, len);
-	btrfs_qgroup_free_data(inode, reserved, start, len);
+	btrfs_qgroup_free_data(inode, reserved, start, len, NULL);
 }
 
 /*
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 9223934d95f472..891ea2fa263c93 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -1041,7 +1041,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 	}
 
-	if (btrfs_qgroup_enabled(fs_info) && !generic_ref->skip_qgroup) {
+	if (btrfs_qgroup_full_accounting(fs_info) && !generic_ref->skip_qgroup) {
 		record = kzalloc(sizeof(*record), GFP_NOFS);
 		if (!record) {
 			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
@@ -1144,7 +1144,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 	}
 
-	if (btrfs_qgroup_enabled(fs_info) && !generic_ref->skip_qgroup) {
+	if (btrfs_qgroup_full_accounting(fs_info) && !generic_ref->skip_qgroup) {
 		record = kzalloc(sizeof(*record), GFP_NOFS);
 		if (!record) {
 			kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 401ea09ae4b8ce..62cb97f7c94fa2 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3213,6 +3213,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_alloc;
 	}
 
+	btrfs_info(fs_info, "first mount of filesystem %pU", disk_super->fsid);
 	/*
 	 * Verify the type first, if that or the checksum value are
 	 * corrupted, we'll find out
@@ -4798,6 +4799,32 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
 	}
 }
 
+static void btrfs_free_all_qgroup_pertrans(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_root *gang[8];
+	int i;
+	int ret;
+
+	spin_lock(&fs_info->fs_roots_radix_lock);
+	while (1) {
+		ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix,
+						 (void **)gang, 0,
+						 ARRAY_SIZE(gang),
+						 BTRFS_ROOT_TRANS_TAG);
+		if (ret == 0)
+			break;
+		for (i = 0; i < ret; i++) {
+			struct btrfs_root *root = gang[i];
+
+			btrfs_qgroup_free_meta_all_pertrans(root);
+			radix_tree_tag_clear(&fs_info->fs_roots_radix,
+					(unsigned long)root->root_key.objectid,
+					BTRFS_ROOT_TRANS_TAG);
+		}
+	}
+	spin_unlock(&fs_info->fs_roots_radix_lock);
+}
+
 void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 				   struct btrfs_fs_info *fs_info)
 {
@@ -4826,6 +4853,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 				     EXTENT_DIRTY);
 	btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents);
 
+	btrfs_free_all_qgroup_pertrans(fs_info);
+
 	cur_trans->state =TRANS_STATE_COMPLETED;
 	wake_up(&cur_trans->commit_wait);
 }
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c8e5b4715b495c..01423670bc8a2b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -102,7 +102,8 @@ int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len)
  */
 int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info, u64 bytenr,
-			     u64 offset, int metadata, u64 *refs, u64 *flags)
+			     u64 offset, int metadata, u64 *refs, u64 *flags,
+			     u64 *owning_root)
 {
 	struct btrfs_root *extent_root;
 	struct btrfs_delayed_ref_head *head;
@@ -114,6 +115,7 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 	u32 item_size;
 	u64 num_refs;
 	u64 extent_flags;
+	u64 owner = 0;
 	int ret;
 
 	/*
@@ -167,6 +169,8 @@ search_again:
 					    struct btrfs_extent_item);
 			num_refs = btrfs_extent_refs(leaf, ei);
 			extent_flags = btrfs_extent_flags(leaf, ei);
+			owner = btrfs_get_extent_owner_root(fs_info, leaf,
+							    path->slots[0]);
 		} else {
 			ret = -EUCLEAN;
 			btrfs_err(fs_info,
@@ -226,6 +230,8 @@ out:
 		*refs = num_refs;
 	if (flags)
 		*flags = extent_flags;
+	if (owning_root)
+		*owning_root = owner;
 out_free:
 	btrfs_free_path(path);
 	return ret;
@@ -1541,6 +1547,23 @@ out:
 	return ret;
 }
 
+static void free_head_ref_squota_rsv(struct btrfs_fs_info *fs_info,
+				     struct btrfs_delayed_ref_head *href)
+{
+	u64 root = href->owning_root;
+
+	/*
+	 * Don't check must_insert_reserved, as this is called from contexts
+	 * where it has already been unset.
+	 */
+	if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE ||
+	    !href->is_data || !is_fstree(root))
+		return;
+
+	btrfs_qgroup_free_refroot(fs_info, root, href->reserved_bytes,
+				  BTRFS_QGROUP_RSV_DATA);
+}
+
 static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 				struct btrfs_delayed_ref_head *href,
 				struct btrfs_delayed_ref_node *node,
@@ -1563,7 +1586,6 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 		struct btrfs_squota_delta delta = {
 			.root = href->owning_root,
 			.num_bytes = node->num_bytes,
-			.rsv_bytes = href->reserved_bytes,
 			.is_data = true,
 			.is_inc	= true,
 			.generation = trans->transid,
@@ -1580,11 +1602,9 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 						 flags, ref->objectid,
 						 ref->offset, &key,
 						 node->ref_mod, href->owning_root);
+		free_head_ref_squota_rsv(trans->fs_info, href);
 		if (!ret)
 			ret = btrfs_record_squota_delta(trans->fs_info, &delta);
-		else
-			btrfs_qgroup_free_refroot(trans->fs_info, delta.root,
-						  delta.rsv_bytes, BTRFS_QGROUP_RSV_DATA);
 	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
 		ret = __btrfs_inc_extent_ref(trans, node, parent, ref->root,
 					     ref->objectid, ref->offset,
@@ -1736,7 +1756,6 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 		struct btrfs_squota_delta delta = {
 			.root = href->owning_root,
 			.num_bytes = fs_info->nodesize,
-			.rsv_bytes = 0,
 			.is_data = false,
 			.is_inc = true,
 			.generation = trans->transid,
@@ -1768,8 +1787,10 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 	int ret = 0;
 
 	if (TRANS_ABORTED(trans)) {
-		if (insert_reserved)
+		if (insert_reserved) {
 			btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1);
+			free_head_ref_squota_rsv(trans->fs_info, href);
+		}
 		return 0;
 	}
 
@@ -1865,6 +1886,8 @@ u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
 				  struct btrfs_delayed_ref_root *delayed_refs,
 				  struct btrfs_delayed_ref_head *head)
 {
+	u64 ret = 0;
+
 	/*
 	 * We had csum deletions accounted for in our delayed refs rsv, we need
 	 * to drop the csum leaves for this update from our delayed_refs_rsv.
@@ -1879,14 +1902,13 @@ u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
 
 		btrfs_delayed_refs_rsv_release(fs_info, 0, nr_csums);
 
-		return btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums);
+		ret = btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums);
 	}
-	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE &&
-	    head->must_insert_reserved && head->is_data)
-		btrfs_qgroup_free_refroot(fs_info, head->owning_root,
-					  head->reserved_bytes, BTRFS_QGROUP_RSV_DATA);
+	/* must_insert_reserved can be set only if we didn't run the head ref. */
+	if (head->must_insert_reserved)
+		free_head_ref_squota_rsv(fs_info, head);
 
-	return 0;
+	return ret;
 }
 
 static int cleanup_ref_head(struct btrfs_trans_handle *trans,
@@ -2027,6 +2049,12 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans,
 		 * spin lock.
 		 */
 		must_insert_reserved = locked_ref->must_insert_reserved;
+		/*
+		 * Unsetting this on the head ref relinquishes ownership of
+		 * the rsv_bytes, so it is critical that every possible code
+		 * path from here forward frees all reserves including qgroup
+		 * reserve.
+		 */
 		locked_ref->must_insert_reserved = false;
 
 		extent_op = locked_ref->extent_op;
@@ -3286,7 +3314,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 		struct btrfs_squota_delta delta = {
 			.root = delayed_ref_root,
 			.num_bytes = num_bytes,
-			.rsv_bytes = 0,
 			.is_data = is_data,
 			.is_inc = false,
 			.generation = btrfs_extent_generation(leaf, ei),
@@ -4931,7 +4958,6 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 		.root = root_objectid,
 		.num_bytes = ins->offset,
 		.generation = trans->transid,
-		.rsv_bytes = 0,
 		.is_data = true,
 		.is_inc = true,
 	};
@@ -5234,7 +5260,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
 		/* We don't lock the tree block, it's OK to be racy here */
 		ret = btrfs_lookup_extent_info(trans, fs_info, bytenr,
 					       wc->level - 1, 1, &refs,
-					       &flags);
+					       &flags, NULL);
 		/* We don't care about errors in readahead. */
 		if (ret < 0)
 			continue;
@@ -5301,7 +5327,8 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
 		ret = btrfs_lookup_extent_info(trans, fs_info,
 					       eb->start, level, 1,
 					       &wc->refs[level],
-					       &wc->flags[level]);
+					       &wc->flags[level],
+					       NULL);
 		BUG_ON(ret == -ENOMEM);
 		if (ret)
 			return ret;
@@ -5391,6 +5418,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	u64 bytenr;
 	u64 generation;
 	u64 parent;
+	u64 owner_root = 0;
 	struct btrfs_tree_parent_check check = { 0 };
 	struct btrfs_key key;
 	struct btrfs_ref ref = { 0 };
@@ -5434,7 +5462,8 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_lookup_extent_info(trans, fs_info, bytenr, level - 1, 1,
 				       &wc->refs[level - 1],
-				       &wc->flags[level - 1]);
+				       &wc->flags[level - 1],
+				       &owner_root);
 	if (ret < 0)
 		goto out_unlock;
 
@@ -5567,8 +5596,7 @@ skip:
 		find_next_key(path, level, &wc->drop_progress);
 
 		btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr,
-				       fs_info->nodesize, parent,
-				       btrfs_header_owner(next));
+				       fs_info->nodesize, parent, owner_root);
 		btrfs_init_tree_ref(&ref, level - 1, root->root_key.objectid,
 				    0, false);
 		ret = btrfs_free_extent(trans, &ref);
@@ -5635,7 +5663,8 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 			ret = btrfs_lookup_extent_info(trans, fs_info,
 						       eb->start, level, 1,
 						       &wc->refs[level],
-						       &wc->flags[level]);
+						       &wc->flags[level],
+						       NULL);
 			if (ret < 0) {
 				btrfs_tree_unlock_rw(eb, path->locks[level]);
 				path->locks[level] = 0;
@@ -5880,7 +5909,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 			ret = btrfs_lookup_extent_info(trans, fs_info,
 						path->nodes[level]->start,
 						level, 1, &wc->refs[level],
-						&wc->flags[level]);
+						&wc->flags[level], NULL);
 			if (ret < 0) {
 				err = ret;
 				goto out_end_trans;
diff --git a/fs/btrfs/extent-tree.h b/fs/btrfs/extent-tree.h
index 0716f65d9753bb..2e066035cceeea 100644
--- a/fs/btrfs/extent-tree.h
+++ b/fs/btrfs/extent-tree.h
@@ -99,7 +99,8 @@ u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
 int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len);
 int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info, u64 bytenr,
-			     u64 offset, int metadata, u64 *refs, u64 *flags);
+			     u64 offset, int metadata, u64 *refs, u64 *flags,
+			     u64 *owner_root);
 int btrfs_pin_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num,
 		     int reserved);
 int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 03cef28d9e3789..8f724c54fc8e9c 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -674,8 +674,8 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
  * 		the array will be skipped
  *
  * Return: 0        if all pages were able to be allocated;
- *         -ENOMEM  otherwise, and the caller is responsible for freeing all
- *                  non-null page pointers in the array.
+ *         -ENOMEM  otherwise, the partially allocated pages would be freed and
+ *                  the array slots zeroed
  */
 int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array)
 {
@@ -694,8 +694,13 @@ int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array)
 		 * though alloc_pages_bulk_array() falls back to alloc_page()
 		 * if  it could not bulk-allocate. So we must be out of memory.
 		 */
-		if (allocated == last)
+		if (allocated == last) {
+			for (int i = 0; i < allocated; i++) {
+				__free_page(page_array[i]);
+				page_array[i] = NULL;
+			}
 			return -ENOMEM;
+		}
 
 		memalloc_retry_wait(GFP_NOFS);
 	}
@@ -2297,7 +2302,8 @@ static int try_release_extent_state(struct extent_io_tree *tree,
 		ret = 0;
 	} else {
 		u32 clear_bits = ~(EXTENT_LOCKED | EXTENT_NODATASUM |
-				   EXTENT_DELALLOC_NEW | EXTENT_CTLBITS);
+				   EXTENT_DELALLOC_NEW | EXTENT_CTLBITS |
+				   EXTENT_QGROUP_RESERVED);
 
 		/*
 		 * At this point we can safely clear everything except the
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f47731c45bb504..32611a4edd6b23 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -3192,7 +3192,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 			qgroup_reserved -= range->len;
 		} else if (qgroup_reserved > 0) {
 			btrfs_qgroup_free_data(BTRFS_I(inode), data_reserved,
-					       range->start, range->len);
+					       range->start, range->len, NULL);
 			qgroup_reserved -= range->len;
 		}
 		list_del(&range->list);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5e3fccddde0c61..fb3c3f43c3fa40 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -688,7 +688,7 @@ out:
 	 * And at reserve time, it's always aligned to page size, so
 	 * just free one page here.
 	 */
-	btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE);
+	btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE, NULL);
 	btrfs_free_path(path);
 	btrfs_end_transaction(trans);
 	return ret;
@@ -5132,7 +5132,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
 		 */
 		if (state_flags & EXTENT_DELALLOC)
 			btrfs_qgroup_free_data(BTRFS_I(inode), NULL, start,
-					       end - start + 1);
+					       end - start + 1, NULL);
 
 		clear_extent_bit(io_tree, start, end,
 				 EXTENT_CLEAR_ALL_BITS | EXTENT_DO_ACCOUNTING,
@@ -6983,8 +6983,15 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode,
 	int ret;
 
 	alloc_hint = get_extent_allocation_hint(inode, start, len);
+again:
 	ret = btrfs_reserve_extent(root, len, len, fs_info->sectorsize,
 				   0, alloc_hint, &ins, 1, 1);
+	if (ret == -EAGAIN) {
+		ASSERT(btrfs_is_zoned(fs_info));
+		wait_on_bit_io(&inode->root->fs_info->flags, BTRFS_FS_NEED_ZONE_FINISH,
+			       TASK_UNINTERRUPTIBLE);
+		goto again;
+	}
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -8052,7 +8059,7 @@ next:
 		 *    reserved data space.
 		 *    Since the IO will never happen for this page.
 		 */
-		btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur);
+		btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur, NULL);
 		if (!inode_evicting) {
 			clear_extent_bit(tree, cur, range_end, EXTENT_LOCKED |
 				 EXTENT_DELALLOC | EXTENT_UPTODATE |
@@ -9484,7 +9491,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
 	struct btrfs_path *path;
 	u64 start = ins->objectid;
 	u64 len = ins->offset;
-	int qgroup_released;
+	u64 qgroup_released = 0;
 	int ret;
 
 	memset(&stack_fi, 0, sizeof(stack_fi));
@@ -9497,9 +9504,9 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
 	btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE);
 	/* Encryption and other encoding is reserved and all 0 */
 
-	qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len);
-	if (qgroup_released < 0)
-		return ERR_PTR(qgroup_released);
+	ret = btrfs_qgroup_release_data(inode, file_offset, len, &qgroup_released);
+	if (ret < 0)
+		return ERR_PTR(ret);
 
 	if (trans) {
 		ret = insert_reserved_file_extent(trans, inode,
@@ -10394,7 +10401,7 @@ out_delalloc_release:
 	btrfs_delalloc_release_metadata(inode, disk_num_bytes, ret < 0);
 out_qgroup_free_data:
 	if (ret < 0)
-		btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes);
+		btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes, NULL);
 out_free_data_space:
 	/*
 	 * If btrfs_reserve_extent() succeeded, then we already decremented
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 752acff2c73436..a1743904202b78 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1290,6 +1290,15 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file,
 			 * are limited to own subvolumes only
 			 */
 			ret = -EPERM;
+		} else if (btrfs_ino(BTRFS_I(src_inode)) != BTRFS_FIRST_FREE_OBJECTID) {
+			/*
+			 * Snapshots must be made with the src_inode referring
+			 * to the subvolume inode, otherwise the permission
+			 * checking above is useless because we may have
+			 * permission on a lower directory but not the subvol
+			 * itself.
+			 */
+			ret = -EINVAL;
 		} else {
 			ret = btrfs_mksnapshot(&file->f_path, idmap,
 					       name, namelen,
@@ -1528,7 +1537,7 @@ static noinline int key_in_sk(struct btrfs_key *key,
 static noinline int copy_to_sk(struct btrfs_path *path,
 			       struct btrfs_key *key,
 			       struct btrfs_ioctl_search_key *sk,
-			       size_t *buf_size,
+			       u64 *buf_size,
 			       char __user *ubuf,
 			       unsigned long *sk_offset,
 			       int *num_found)
@@ -1660,7 +1669,7 @@ out:
 
 static noinline int search_ioctl(struct inode *inode,
 				 struct btrfs_ioctl_search_key *sk,
-				 size_t *buf_size,
+				 u64 *buf_size,
 				 char __user *ubuf)
 {
 	struct btrfs_fs_info *info = btrfs_sb(inode->i_sb);
@@ -1733,7 +1742,7 @@ static noinline int btrfs_ioctl_tree_search(struct inode *inode,
 	struct btrfs_ioctl_search_args __user *uargs = argp;
 	struct btrfs_ioctl_search_key sk;
 	int ret;
-	size_t buf_size;
+	u64 buf_size;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1763,8 +1772,8 @@ static noinline int btrfs_ioctl_tree_search_v2(struct inode *inode,
 	struct btrfs_ioctl_search_args_v2 __user *uarg = argp;
 	struct btrfs_ioctl_search_args_v2 args;
 	int ret;
-	size_t buf_size;
-	const size_t buf_limit = SZ_16M;
+	u64 buf_size;
+	const u64 buf_limit = SZ_16M;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -4356,6 +4365,7 @@ static int _btrfs_ioctl_send(struct inode *inode, void __user *argp, bool compat
 		arg->clone_sources = compat_ptr(args32.clone_sources);
 		arg->parent_root = args32.parent_root;
 		arg->flags = args32.flags;
+		arg->version = args32.version;
 		memcpy(arg->reserved, args32.reserved,
 		       sizeof(args32.reserved));
 #else
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 574e8a55e24a2b..a82e1417c4d278 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -152,11 +152,12 @@ static struct btrfs_ordered_extent *alloc_ordered_extent(
 {
 	struct btrfs_ordered_extent *entry;
 	int ret;
+	u64 qgroup_rsv = 0;
 
 	if (flags &
 	    ((1 << BTRFS_ORDERED_NOCOW) | (1 << BTRFS_ORDERED_PREALLOC))) {
 		/* For nocow write, we can release the qgroup rsv right now */
-		ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes);
+		ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes, &qgroup_rsv);
 		if (ret < 0)
 			return ERR_PTR(ret);
 	} else {
@@ -164,7 +165,7 @@ static struct btrfs_ordered_extent *alloc_ordered_extent(
 		 * The ordered extent has reserved qgroup space, release now
 		 * and pass the reserved number for qgroup_record to free.
 		 */
-		ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes);
+		ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes, &qgroup_rsv);
 		if (ret < 0)
 			return ERR_PTR(ret);
 	}
@@ -182,7 +183,7 @@ static struct btrfs_ordered_extent *alloc_ordered_extent(
 	entry->inode = igrab(&inode->vfs_inode);
 	entry->compress_type = compress_type;
 	entry->truncated_len = (u64)-1;
-	entry->qgroup_rsv = ret;
+	entry->qgroup_rsv = qgroup_rsv;
 	entry->flags = flags;
 	refcount_set(&entry->refs, 1);
 	init_waitqueue_head(&entry->wait);
@@ -599,7 +600,9 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
 			release = entry->disk_num_bytes;
 		else
 			release = entry->num_bytes;
-		btrfs_delalloc_release_metadata(btrfs_inode, release, false);
+		btrfs_delalloc_release_metadata(btrfs_inode, release,
+						test_bit(BTRFS_ORDERED_IOERR,
+							 &entry->flags));
 	}
 
 	percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index edb84cc0323773..e46774e8f49fd6 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1888,7 +1888,7 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
 	u64 bytenr = record->bytenr;
 
 	if (!btrfs_qgroup_full_accounting(fs_info))
-		return 0;
+		return 1;
 
 	lockdep_assert_held(&delayed_refs->lock);
 	trace_btrfs_qgroup_trace_extent(fs_info, record);
@@ -2875,12 +2875,18 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 			       num_bytes, seq);
 
 	/*
+	 * We're done using the iterator, release all its qgroups while holding
+	 * fs_info->qgroup_lock so that we don't race with btrfs_remove_qgroup()
+	 * and trigger use-after-free accesses to qgroups.
+	 */
+	qgroup_iterator_nested_clean(&qgroups);
+
+	/*
 	 * Bump qgroup_seq to avoid seq overlap
 	 */
 	fs_info->qgroup_seq += max(nr_old_roots, nr_new_roots) + 1;
 	spin_unlock(&fs_info->qgroup_lock);
 out_free:
-	qgroup_iterator_nested_clean(&qgroups);
 	ulist_free(old_roots);
 	ulist_free(new_roots);
 	return ret;
@@ -4051,13 +4057,14 @@ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode,
 
 /* Free ranges specified by @reserved, normally in error path */
 static int qgroup_free_reserved_data(struct btrfs_inode *inode,
-			struct extent_changeset *reserved, u64 start, u64 len)
+				     struct extent_changeset *reserved,
+				     u64 start, u64 len, u64 *freed_ret)
 {
 	struct btrfs_root *root = inode->root;
 	struct ulist_node *unode;
 	struct ulist_iterator uiter;
 	struct extent_changeset changeset;
-	int freed = 0;
+	u64 freed = 0;
 	int ret;
 
 	extent_changeset_init(&changeset);
@@ -4098,7 +4105,9 @@ static int qgroup_free_reserved_data(struct btrfs_inode *inode,
 	}
 	btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, freed,
 				  BTRFS_QGROUP_RSV_DATA);
-	ret = freed;
+	if (freed_ret)
+		*freed_ret = freed;
+	ret = 0;
 out:
 	extent_changeset_release(&changeset);
 	return ret;
@@ -4106,7 +4115,7 @@ out:
 
 static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
 			struct extent_changeset *reserved, u64 start, u64 len,
-			int free)
+			u64 *released, int free)
 {
 	struct extent_changeset changeset;
 	int trace_op = QGROUP_RELEASE;
@@ -4122,7 +4131,7 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
 	/* In release case, we shouldn't have @reserved */
 	WARN_ON(!free && reserved);
 	if (free && reserved)
-		return qgroup_free_reserved_data(inode, reserved, start, len);
+		return qgroup_free_reserved_data(inode, reserved, start, len, released);
 	extent_changeset_init(&changeset);
 	ret = clear_record_extent_bits(&inode->io_tree, start, start + len -1,
 				       EXTENT_QGROUP_RESERVED, &changeset);
@@ -4137,7 +4146,8 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
 		btrfs_qgroup_free_refroot(inode->root->fs_info,
 				inode->root->root_key.objectid,
 				changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
-	ret = changeset.bytes_changed;
+	if (released)
+		*released = changeset.bytes_changed;
 out:
 	extent_changeset_release(&changeset);
 	return ret;
@@ -4156,9 +4166,10 @@ out:
  * NOTE: This function may sleep for memory allocation.
  */
 int btrfs_qgroup_free_data(struct btrfs_inode *inode,
-			struct extent_changeset *reserved, u64 start, u64 len)
+			   struct extent_changeset *reserved,
+			   u64 start, u64 len, u64 *freed)
 {
-	return __btrfs_qgroup_release_data(inode, reserved, start, len, 1);
+	return __btrfs_qgroup_release_data(inode, reserved, start, len, freed, 1);
 }
 
 /*
@@ -4176,9 +4187,9 @@ int btrfs_qgroup_free_data(struct btrfs_inode *inode,
  *
  * NOTE: This function may sleep for memory allocation.
  */
-int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len)
+int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released)
 {
-	return __btrfs_qgroup_release_data(inode, NULL, start, len, 0);
+	return __btrfs_qgroup_release_data(inode, NULL, start, len, released, 0);
 }
 
 static void add_root_meta_rsv(struct btrfs_root *root, int num_bytes,
@@ -4326,8 +4337,9 @@ static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root,
 
 		qgroup_rsv_release(fs_info, qgroup, num_bytes,
 				BTRFS_QGROUP_RSV_META_PREALLOC);
-		qgroup_rsv_add(fs_info, qgroup, num_bytes,
-				BTRFS_QGROUP_RSV_META_PERTRANS);
+		if (!sb_rdonly(fs_info->sb))
+			qgroup_rsv_add(fs_info, qgroup, num_bytes,
+				       BTRFS_QGROUP_RSV_META_PERTRANS);
 
 		list_for_each_entry(glist, &qgroup->groups, next_group)
 			qgroup_iterator_add(&qgroup_list, glist->group);
@@ -4649,6 +4661,17 @@ void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans)
 	*root = RB_ROOT;
 }
 
+void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes)
+{
+	if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE)
+		return;
+
+	if (!is_fstree(root))
+		return;
+
+	btrfs_qgroup_free_refroot(fs_info, root, rsv_bytes, BTRFS_QGROUP_RSV_DATA);
+}
+
 int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
 			      struct btrfs_squota_delta *delta)
 {
@@ -4693,8 +4716,5 @@ int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
 
 out:
 	spin_unlock(&fs_info->qgroup_lock);
-	if (!ret && delta->rsv_bytes)
-		btrfs_qgroup_free_refroot(fs_info, root, delta->rsv_bytes,
-					  BTRFS_QGROUP_RSV_DATA);
 	return ret;
 }
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 855a4f97876185..be18c862e64ede 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -274,8 +274,6 @@ struct btrfs_squota_delta {
 	u64 root;
 	/* The number of bytes in the extent being counted. */
 	u64 num_bytes;
-	/* The number of bytes reserved for this extent. */
-	u64 rsv_bytes;
 	/* The generation the extent was created in. */
 	u64 generation;
 	/* Whether we are using or freeing the extent. */
@@ -358,10 +356,10 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
 /* New io_tree based accurate qgroup reserve API */
 int btrfs_qgroup_reserve_data(struct btrfs_inode *inode,
 			struct extent_changeset **reserved, u64 start, u64 len);
-int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len);
+int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released);
 int btrfs_qgroup_free_data(struct btrfs_inode *inode,
 			   struct extent_changeset *reserved, u64 start,
-			   u64 len);
+			   u64 len, u64 *freed);
 int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 			      enum btrfs_qgroup_rsv_type type, bool enforce);
 int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
@@ -422,6 +420,7 @@ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
 		struct btrfs_root *root, struct extent_buffer *eb);
 void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans);
 bool btrfs_check_quota_leak(struct btrfs_fs_info *fs_info);
+void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes);
 int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
 			      struct btrfs_squota_delta *delta);
 
diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c
index 944e8f1862aaaa..9589362acfbf9e 100644
--- a/fs/btrfs/raid-stripe-tree.c
+++ b/fs/btrfs/raid-stripe-tree.c
@@ -145,7 +145,7 @@ int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans,
 		btrfs_put_bioc(bioc);
 	}
 
-	return ret;
+	return 0;
 }
 
 int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 1f62976bee829a..6486f0d7e9931b 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -794,6 +794,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 			dump_ref_action(fs_info, ra);
 			kfree(ref);
 			kfree(ra);
+			kfree(re);
 			goto out_unlock;
 		} else if (be->num_refs == 0) {
 			btrfs_err(fs_info,
@@ -803,6 +804,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 			dump_ref_action(fs_info, ra);
 			kfree(ref);
 			kfree(ra);
+			kfree(re);
 			goto out_unlock;
 		}
 
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 9ce5be21b03601..f62a408671cbc3 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1868,6 +1868,9 @@ static int queue_scrub_stripe(struct scrub_ctx *sctx, struct btrfs_block_group *
 	 */
 	ASSERT(sctx->cur_stripe < SCRUB_TOTAL_STRIPES);
 
+	/* @found_logical_ret must be specified. */
+	ASSERT(found_logical_ret);
+
 	stripe = &sctx->stripes[sctx->cur_stripe];
 	scrub_reset_stripe(stripe);
 	ret = scrub_find_fill_first_stripe(bg, &sctx->extent_path,
@@ -1876,8 +1879,7 @@ static int queue_scrub_stripe(struct scrub_ctx *sctx, struct btrfs_block_group *
 	/* Either >0 as no more extents or <0 for error. */
 	if (ret)
 		return ret;
-	if (found_logical_ret)
-		*found_logical_ret = stripe->logical;
+	*found_logical_ret = stripe->logical;
 	sctx->cur_stripe++;
 
 	/* We filled one group, submit it. */
@@ -2080,7 +2082,7 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
 
 	/* Go through each extent items inside the logical range */
 	while (cur_logical < logical_end) {
-		u64 found_logical;
+		u64 found_logical = U64_MAX;
 		u64 cur_physical = physical + cur_logical - logical_start;
 
 		/* Canceled? */
@@ -2115,6 +2117,8 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
 		if (ret < 0)
 			break;
 
+		/* queue_scrub_stripe() returned 0, @found_logical must be updated. */
+		ASSERT(found_logical != U64_MAX);
 		cur_logical = found_logical + BTRFS_STRIPE_LEN;
 
 		/* Don't hold CPU for too long time */
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 3b929f0e8f04f4..4e36550618e580 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -8158,7 +8158,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
 	}
 
 	sctx->send_filp = fget(arg->send_fd);
-	if (!sctx->send_filp) {
+	if (!sctx->send_filp || !(sctx->send_filp->f_mode & FMODE_WRITE)) {
 		ret = -EBADF;
 		goto out;
 	}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f638dc339693bc..ef256b944c72ac 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -80,7 +80,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data);
 
 static void btrfs_put_super(struct super_block *sb)
 {
-	close_ctree(btrfs_sb(sb));
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+
+	btrfs_info(fs_info, "last unmount of filesystem %pU", fs_info->fs_devices->fsid);
+	close_ctree(fs_info);
 }
 
 enum {
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 6e63816dddcbea..5b3333ceef0481 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -37,8 +37,6 @@
 
 static struct kmem_cache *btrfs_trans_handle_cachep;
 
-#define BTRFS_ROOT_TRANS_TAG 0
-
 /*
  * Transaction states and transitions
  *
@@ -1774,7 +1772,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	btrfs_release_path(path);
 
 	ret = btrfs_create_qgroup(trans, objectid);
-	if (ret) {
+	if (ret && ret != -EEXIST) {
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 18c4f6e83b7883..2bf8bbdfd0b38b 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -12,6 +12,9 @@
 #include "ctree.h"
 #include "misc.h"
 
+/* Radix-tree tag for roots that are part of the trasaction. */
+#define BTRFS_ROOT_TRANS_TAG			0
+
 enum btrfs_trans_state {
 	TRANS_STATE_RUNNING,
 	TRANS_STATE_COMMIT_PREP,
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index a416cbea75d1ff..50fdc69fdddf9d 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -31,6 +31,7 @@
 #include "inode-item.h"
 #include "dir-item.h"
 #include "raid-stripe-tree.h"
+#include "extent-tree.h"
 
 /*
  * Error message should follow the following format:
@@ -1276,6 +1277,8 @@ static int check_extent_item(struct extent_buffer *leaf,
 	unsigned long ptr;	/* Current pointer inside inline refs */
 	unsigned long end;	/* Extent item end */
 	const u32 item_size = btrfs_item_size(leaf, slot);
+	u8 last_type = 0;
+	u64 last_seq = U64_MAX;
 	u64 flags;
 	u64 generation;
 	u64 total_refs;		/* Total refs in btrfs_extent_item */
@@ -1322,6 +1325,18 @@ static int check_extent_item(struct extent_buffer *leaf,
 	 *    2.2) Ref type specific data
 	 *         Either using btrfs_extent_inline_ref::offset, or specific
 	 *         data structure.
+	 *
+	 *    All above inline items should follow the order:
+	 *
+	 *    - All btrfs_extent_inline_ref::type should be in an ascending
+	 *      order
+	 *
+	 *    - Within the same type, the items should follow a descending
+	 *      order by their sequence number. The sequence number is
+	 *      determined by:
+	 *      * btrfs_extent_inline_ref::offset for all types  other than
+	 *        EXTENT_DATA_REF
+	 *      * hash_extent_data_ref() for EXTENT_DATA_REF
 	 */
 	if (unlikely(item_size < sizeof(*ei))) {
 		extent_err(leaf, slot,
@@ -1403,6 +1418,7 @@ static int check_extent_item(struct extent_buffer *leaf,
 		struct btrfs_extent_inline_ref *iref;
 		struct btrfs_extent_data_ref *dref;
 		struct btrfs_shared_data_ref *sref;
+		u64 seq;
 		u64 dref_offset;
 		u64 inline_offset;
 		u8 inline_type;
@@ -1416,6 +1432,7 @@ static int check_extent_item(struct extent_buffer *leaf,
 		iref = (struct btrfs_extent_inline_ref *)ptr;
 		inline_type = btrfs_extent_inline_ref_type(leaf, iref);
 		inline_offset = btrfs_extent_inline_ref_offset(leaf, iref);
+		seq = inline_offset;
 		if (unlikely(ptr + btrfs_extent_inline_ref_size(inline_type) > end)) {
 			extent_err(leaf, slot,
 "inline ref item overflows extent item, ptr %lu iref size %u end %lu",
@@ -1446,6 +1463,10 @@ static int check_extent_item(struct extent_buffer *leaf,
 		case BTRFS_EXTENT_DATA_REF_KEY:
 			dref = (struct btrfs_extent_data_ref *)(&iref->offset);
 			dref_offset = btrfs_extent_data_ref_offset(leaf, dref);
+			seq = hash_extent_data_ref(
+					btrfs_extent_data_ref_root(leaf, dref),
+					btrfs_extent_data_ref_objectid(leaf, dref),
+					btrfs_extent_data_ref_offset(leaf, dref));
 			if (unlikely(!IS_ALIGNED(dref_offset,
 						 fs_info->sectorsize))) {
 				extent_err(leaf, slot,
@@ -1475,6 +1496,24 @@ static int check_extent_item(struct extent_buffer *leaf,
 				   inline_type);
 			return -EUCLEAN;
 		}
+		if (inline_type < last_type) {
+			extent_err(leaf, slot,
+				   "inline ref out-of-order: has type %u, prev type %u",
+				   inline_type, last_type);
+			return -EUCLEAN;
+		}
+		/* Type changed, allow the sequence starts from U64_MAX again. */
+		if (inline_type > last_type)
+			last_seq = U64_MAX;
+		if (seq > last_seq) {
+			extent_err(leaf, slot,
+"inline ref out-of-order: has type %u offset %llu seq 0x%llx, prev type %u seq 0x%llx",
+				   inline_type, inline_offset, seq,
+				   last_type, last_seq);
+			return -EUCLEAN;
+		}
+		last_type = inline_type;
+		last_seq = seq;
 		ptr += btrfs_extent_inline_ref_size(inline_type);
 	}
 	/* No padding is allowed */
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c87e18827a0a6c..f627674b37db50 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -748,13 +748,13 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 	if (!fs_devices) {
 		fs_devices = alloc_fs_devices(disk_super->fsid);
+		if (IS_ERR(fs_devices))
+			return ERR_CAST(fs_devices);
+
 		if (has_metadata_uuid)
 			memcpy(fs_devices->metadata_uuid,
 			       disk_super->metadata_uuid, BTRFS_FSID_SIZE);
 
-		if (IS_ERR(fs_devices))
-			return ERR_CAST(fs_devices);
-
 		if (same_fsid_diff_dev) {
 			generate_random_uuid(fs_devices->fsid);
 			fs_devices->temp_fsid = true;
@@ -3006,15 +3006,16 @@ struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
 	read_unlock(&em_tree->lock);
 
 	if (!em) {
-		btrfs_crit(fs_info, "unable to find logical %llu length %llu",
+		btrfs_crit(fs_info,
+			   "unable to find chunk map for logical %llu length %llu",
 			   logical, length);
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (em->start > logical || em->start + em->len < logical) {
+	if (em->start > logical || em->start + em->len <= logical) {
 		btrfs_crit(fs_info,
-			   "found a bad mapping, wanted %llu-%llu, found %llu-%llu",
-			   logical, length, em->start, em->start + em->len);
+			   "found a bad chunk map, wanted %llu-%llu, found %llu-%llu",
+			   logical, logical + length, em->start, em->start + em->len);
 		free_extent_map(em);
 		return ERR_PTR(-EINVAL);
 	}
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 3504ade30cb0c3..188378ca19c7f6 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1661,13 +1661,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	}
 
 out:
-	if (cache->alloc_offset > fs_info->zone_size) {
-		btrfs_err(fs_info,
-			"zoned: invalid write pointer %llu in block group %llu",
-			cache->alloc_offset, cache->start);
-		ret = -EIO;
-	}
-
 	if (cache->alloc_offset > cache->zone_capacity) {
 		btrfs_err(fs_info,
 "zoned: invalid write pointer %llu (larger than zone capacity %llu) in block group %llu",
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index c53a1d2206225c..1564eacc253dfd 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 
 #include "super.h"
+#include "mds_client.h"
 
 static inline void ceph_set_cached_acl(struct inode *inode,
 					int type, struct posix_acl *acl)
@@ -31,6 +32,7 @@ static inline void ceph_set_cached_acl(struct inode *inode,
 
 struct posix_acl *ceph_get_acl(struct inode *inode, int type, bool rcu)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int size;
 	unsigned int retry_cnt = 0;
 	const char *name;
@@ -72,8 +74,8 @@ retry:
 	} else if (size == -ENODATA || size == 0) {
 		acl = NULL;
 	} else {
-		pr_err_ratelimited("get acl %llx.%llx failed, err=%d\n",
-				   ceph_vinop(inode), size);
+		pr_err_ratelimited_client(cl, "%llx.%llx failed, err=%d\n",
+					  ceph_vinop(inode), size);
 		acl = ERR_PTR(-EIO);
 	}
 
@@ -105,7 +107,7 @@ int ceph_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 	case ACL_TYPE_ACCESS:
 		name = XATTR_NAME_POSIX_ACL_ACCESS;
 		if (acl) {
-			ret = posix_acl_update_mode(&nop_mnt_idmap, inode,
+			ret = posix_acl_update_mode(idmap, inode,
 						    &new_mode, &acl);
 			if (ret)
 				goto out;
@@ -140,7 +142,7 @@ int ceph_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		newattrs.ia_ctime = current_time(inode);
 		newattrs.ia_mode = new_mode;
 		newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-		ret = __ceph_setattr(inode, &newattrs, NULL);
+		ret = __ceph_setattr(idmap, inode, &newattrs, NULL);
 		if (ret)
 			goto out_free;
 	}
@@ -151,7 +153,7 @@ int ceph_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 			newattrs.ia_ctime = old_ctime;
 			newattrs.ia_mode = old_mode;
 			newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-			__ceph_setattr(inode, &newattrs, NULL);
+			__ceph_setattr(idmap, inode, &newattrs, NULL);
 		}
 		goto out_free;
 	}
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 936b9e0b351df7..85be3bf18cdf38 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -79,18 +79,18 @@ static inline struct ceph_snap_context *page_snap_context(struct page *page)
  */
 static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio)
 {
-	struct inode *inode;
+	struct inode *inode = mapping->host;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci;
 	struct ceph_snap_context *snapc;
 
 	if (folio_test_dirty(folio)) {
-		dout("%p dirty_folio %p idx %lu -- already dirty\n",
-		     mapping->host, folio, folio->index);
+		doutc(cl, "%llx.%llx %p idx %lu -- already dirty\n",
+		      ceph_vinop(inode), folio, folio->index);
 		VM_BUG_ON_FOLIO(!folio_test_private(folio), folio);
 		return false;
 	}
 
-	inode = mapping->host;
 	ci = ceph_inode(inode);
 
 	/* dirty the head */
@@ -111,12 +111,12 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio)
 	if (ci->i_wrbuffer_ref == 0)
 		ihold(inode);
 	++ci->i_wrbuffer_ref;
-	dout("%p dirty_folio %p idx %lu head %d/%d -> %d/%d "
-	     "snapc %p seq %lld (%d snaps)\n",
-	     mapping->host, folio, folio->index,
-	     ci->i_wrbuffer_ref-1, ci->i_wrbuffer_ref_head-1,
-	     ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
-	     snapc, snapc->seq, snapc->num_snaps);
+	doutc(cl, "%llx.%llx %p idx %lu head %d/%d -> %d/%d "
+	      "snapc %p seq %lld (%d snaps)\n",
+	      ceph_vinop(inode), folio, folio->index,
+	      ci->i_wrbuffer_ref-1, ci->i_wrbuffer_ref_head-1,
+	      ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
+	      snapc, snapc->seq, snapc->num_snaps);
 	spin_unlock(&ci->i_ceph_lock);
 
 	/*
@@ -137,23 +137,22 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio)
 static void ceph_invalidate_folio(struct folio *folio, size_t offset,
 				size_t length)
 {
-	struct inode *inode;
-	struct ceph_inode_info *ci;
+	struct inode *inode = folio->mapping->host;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_snap_context *snapc;
 
-	inode = folio->mapping->host;
-	ci = ceph_inode(inode);
 
 	if (offset != 0 || length != folio_size(folio)) {
-		dout("%p invalidate_folio idx %lu partial dirty page %zu~%zu\n",
-		     inode, folio->index, offset, length);
+		doutc(cl, "%llx.%llx idx %lu partial dirty page %zu~%zu\n",
+		      ceph_vinop(inode), folio->index, offset, length);
 		return;
 	}
 
 	WARN_ON(!folio_test_locked(folio));
 	if (folio_test_private(folio)) {
-		dout("%p invalidate_folio idx %lu full dirty page\n",
-		     inode, folio->index);
+		doutc(cl, "%llx.%llx idx %lu full dirty page\n",
+		      ceph_vinop(inode), folio->index);
 
 		snapc = folio_detach_private(folio);
 		ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
@@ -166,10 +165,10 @@ static void ceph_invalidate_folio(struct folio *folio, size_t offset,
 static bool ceph_release_folio(struct folio *folio, gfp_t gfp)
 {
 	struct inode *inode = folio->mapping->host;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 
-	dout("%llx:%llx release_folio idx %lu (%sdirty)\n",
-	     ceph_vinop(inode),
-	     folio->index, folio_test_dirty(folio) ? "" : "not ");
+	doutc(cl, "%llx.%llx idx %lu (%sdirty)\n", ceph_vinop(inode),
+	      folio->index, folio_test_dirty(folio) ? "" : "not ");
 
 	if (folio_test_private(folio))
 		return false;
@@ -229,7 +228,7 @@ static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq)
 static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq)
 {
 	struct inode *inode = subreq->rreq->inode;
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	u64 objno, objoff;
 	u32 xlen;
@@ -244,7 +243,8 @@ static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq)
 static void finish_netfs_read(struct ceph_osd_request *req)
 {
 	struct inode *inode = req->r_inode;
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);
 	struct netfs_io_subrequest *subreq = req->r_priv;
 	struct ceph_osd_req_op *op = &req->r_ops[0];
@@ -254,8 +254,8 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 	ceph_update_read_metrics(&fsc->mdsc->metric, req->r_start_latency,
 				 req->r_end_latency, osd_data->length, err);
 
-	dout("%s: result %d subreq->len=%zu i_size=%lld\n", __func__, req->r_result,
-	     subreq->len, i_size_read(req->r_inode));
+	doutc(cl, "result %d subreq->len=%zu i_size=%lld\n", req->r_result,
+	      subreq->len, i_size_read(req->r_inode));
 
 	/* no object means success but no data */
 	if (err == -ENOENT)
@@ -348,7 +348,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	struct netfs_io_request *rreq = subreq->rreq;
 	struct inode *inode = rreq->inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_osd_request *req = NULL;
 	struct ceph_vino vino = ceph_vino(inode);
 	struct iov_iter iter;
@@ -383,7 +384,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 			goto out;
 	}
 
-	dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
+	doutc(cl, "%llx.%llx pos=%llu orig_len=%zu len=%llu\n",
+	      ceph_vinop(inode), subreq->start, subreq->len, len);
 
 	iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len);
 
@@ -400,8 +402,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 
 		err = iov_iter_get_pages_alloc2(&iter, &pages, len, &page_off);
 		if (err < 0) {
-			dout("%s: iov_ter_get_pages_alloc returned %d\n",
-			     __func__, err);
+			doutc(cl, "%llx.%llx failed to allocate pages, %d\n",
+			      ceph_vinop(inode), err);
 			goto out;
 		}
 
@@ -429,12 +431,13 @@ out:
 	ceph_osdc_put_request(req);
 	if (err)
 		netfs_subreq_terminated(subreq, err, false);
-	dout("%s: result %d\n", __func__, err);
+	doutc(cl, "%llx.%llx result %d\n", ceph_vinop(inode), err);
 }
 
 static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
 {
 	struct inode *inode = rreq->inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int got = 0, want = CEPH_CAP_FILE_CACHE;
 	struct ceph_netfs_request_data *priv;
 	int ret = 0;
@@ -466,12 +469,12 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
 	 */
 	ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want, true, &got);
 	if (ret < 0) {
-		dout("start_read %p, error getting cap\n", inode);
+		doutc(cl, "%llx.%llx, error getting cap\n", ceph_vinop(inode));
 		goto out;
 	}
 
 	if (!(got & want)) {
-		dout("start_read %p, no cache cap\n", inode);
+		doutc(cl, "%llx.%llx, no cache cap\n", ceph_vinop(inode));
 		ret = -EACCES;
 		goto out;
 	}
@@ -563,13 +566,14 @@ get_oldest_context(struct inode *inode, struct ceph_writeback_ctl *ctl,
 		   struct ceph_snap_context *page_snapc)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_snap_context *snapc = NULL;
 	struct ceph_cap_snap *capsnap = NULL;
 
 	spin_lock(&ci->i_ceph_lock);
 	list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
-		dout(" cap_snap %p snapc %p has %d dirty pages\n", capsnap,
-		     capsnap->context, capsnap->dirty_pages);
+		doutc(cl, " capsnap %p snapc %p has %d dirty pages\n",
+		      capsnap, capsnap->context, capsnap->dirty_pages);
 		if (!capsnap->dirty_pages)
 			continue;
 
@@ -601,8 +605,8 @@ get_oldest_context(struct inode *inode, struct ceph_writeback_ctl *ctl,
 	}
 	if (!snapc && ci->i_wrbuffer_ref_head) {
 		snapc = ceph_get_snap_context(ci->i_head_snapc);
-		dout(" head snapc %p has %d dirty pages\n",
-		     snapc, ci->i_wrbuffer_ref_head);
+		doutc(cl, " head snapc %p has %d dirty pages\n", snapc,
+		      ci->i_wrbuffer_ref_head);
 		if (ctl) {
 			ctl->i_size = i_size_read(inode);
 			ctl->truncate_size = ci->i_truncate_size;
@@ -658,7 +662,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	struct folio *folio = page_folio(page);
 	struct inode *inode = page->mapping->host;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_snap_context *snapc, *oldest;
 	loff_t page_off = page_offset(page);
 	int err;
@@ -670,7 +675,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	bool caching = ceph_is_cache_enabled(inode);
 	struct page *bounce_page = NULL;
 
-	dout("writepage %p idx %lu\n", page, page->index);
+	doutc(cl, "%llx.%llx page %p idx %lu\n", ceph_vinop(inode), page,
+	      page->index);
 
 	if (ceph_inode_is_shutdown(inode))
 		return -EIO;
@@ -678,13 +684,14 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	/* verify this is a writeable snap context */
 	snapc = page_snap_context(page);
 	if (!snapc) {
-		dout("writepage %p page %p not dirty?\n", inode, page);
+		doutc(cl, "%llx.%llx page %p not dirty?\n", ceph_vinop(inode),
+		      page);
 		return 0;
 	}
 	oldest = get_oldest_context(inode, &ceph_wbc, snapc);
 	if (snapc->seq > oldest->seq) {
-		dout("writepage %p page %p snapc %p not writeable - noop\n",
-		     inode, page, snapc);
+		doutc(cl, "%llx.%llx page %p snapc %p not writeable - noop\n",
+		      ceph_vinop(inode), page, snapc);
 		/* we should only noop if called by kswapd */
 		WARN_ON(!(current->flags & PF_MEMALLOC));
 		ceph_put_snap_context(oldest);
@@ -695,8 +702,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 
 	/* is this a partial page at end of file? */
 	if (page_off >= ceph_wbc.i_size) {
-		dout("folio at %lu beyond eof %llu\n", folio->index,
-				ceph_wbc.i_size);
+		doutc(cl, "%llx.%llx folio at %lu beyond eof %llu\n",
+		      ceph_vinop(inode), folio->index, ceph_wbc.i_size);
 		folio_invalidate(folio, 0, folio_size(folio));
 		return 0;
 	}
@@ -705,8 +712,9 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 		len = ceph_wbc.i_size - page_off;
 
 	wlen = IS_ENCRYPTED(inode) ? round_up(len, CEPH_FSCRYPT_BLOCK_SIZE) : len;
-	dout("writepage %p page %p index %lu on %llu~%llu snapc %p seq %lld\n",
-	     inode, page, page->index, page_off, wlen, snapc, snapc->seq);
+	doutc(cl, "%llx.%llx page %p index %lu on %llu~%llu snapc %p seq %lld\n",
+	      ceph_vinop(inode), page, page->index, page_off, wlen, snapc,
+	      snapc->seq);
 
 	if (atomic_long_inc_return(&fsc->writeback_count) >
 	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
@@ -747,8 +755,9 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	osd_req_op_extent_osd_data_pages(req, 0,
 			bounce_page ? &bounce_page : &page, wlen, 0,
 			false, false);
-	dout("writepage %llu~%llu (%llu bytes, %sencrypted)\n",
-	     page_off, len, wlen, IS_ENCRYPTED(inode) ? "" : "not ");
+	doutc(cl, "%llx.%llx %llu~%llu (%llu bytes, %sencrypted)\n",
+	      ceph_vinop(inode), page_off, len, wlen,
+	      IS_ENCRYPTED(inode) ? "" : "not ");
 
 	req->r_mtime = inode_get_mtime(inode);
 	ceph_osdc_start_request(osdc, req);
@@ -767,19 +776,21 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 			wbc = &tmp_wbc;
 		if (err == -ERESTARTSYS) {
 			/* killed by SIGKILL */
-			dout("writepage interrupted page %p\n", page);
+			doutc(cl, "%llx.%llx interrupted page %p\n",
+			      ceph_vinop(inode), page);
 			redirty_page_for_writepage(wbc, page);
 			end_page_writeback(page);
 			return err;
 		}
 		if (err == -EBLOCKLISTED)
 			fsc->blocklisted = true;
-		dout("writepage setting page/mapping error %d %p\n",
-		     err, page);
+		doutc(cl, "%llx.%llx setting page/mapping error %d %p\n",
+		      ceph_vinop(inode), err, page);
 		mapping_set_error(&inode->i_data, err);
 		wbc->pages_skipped++;
 	} else {
-		dout("writepage cleaned page %p\n", page);
+		doutc(cl, "%llx.%llx cleaned page %p\n",
+		      ceph_vinop(inode), page);
 		err = 0;  /* vfs expects us to return 0 */
 	}
 	oldest = detach_page_private(page);
@@ -803,7 +814,7 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc)
 	ihold(inode);
 
 	if (wbc->sync_mode == WB_SYNC_NONE &&
-	    ceph_inode_to_client(inode)->write_congested)
+	    ceph_inode_to_fs_client(inode)->write_congested)
 		return AOP_WRITEPAGE_ACTIVATE;
 
 	wait_on_page_fscache(page);
@@ -829,6 +840,7 @@ static void writepages_finish(struct ceph_osd_request *req)
 {
 	struct inode *inode = req->r_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_osd_data *osd_data;
 	struct page *page;
 	int num_pages, total_pages = 0;
@@ -836,11 +848,11 @@ static void writepages_finish(struct ceph_osd_request *req)
 	int rc = req->r_result;
 	struct ceph_snap_context *snapc = req->r_snapc;
 	struct address_space *mapping = inode->i_mapping;
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 	unsigned int len = 0;
 	bool remove_page;
 
-	dout("writepages_finish %p rc %d\n", inode, rc);
+	doutc(cl, "%llx.%llx rc %d\n", ceph_vinop(inode), rc);
 	if (rc < 0) {
 		mapping_set_error(mapping, rc);
 		ceph_set_error_write(ci);
@@ -862,8 +874,10 @@ static void writepages_finish(struct ceph_osd_request *req)
 	/* clean all pages */
 	for (i = 0; i < req->r_num_ops; i++) {
 		if (req->r_ops[i].op != CEPH_OSD_OP_WRITE) {
-			pr_warn("%s incorrect op %d req %p index %d tid %llu\n",
-				__func__, req->r_ops[i].op, req, i, req->r_tid);
+			pr_warn_client(cl,
+				"%llx.%llx incorrect op %d req %p index %d tid %llu\n",
+				ceph_vinop(inode), req->r_ops[i].op, req, i,
+				req->r_tid);
 			break;
 		}
 
@@ -890,7 +904,7 @@ static void writepages_finish(struct ceph_osd_request *req)
 
 			ceph_put_snap_context(detach_page_private(page));
 			end_page_writeback(page);
-			dout("unlocking %p\n", page);
+			doutc(cl, "unlocking %p\n", page);
 
 			if (remove_page)
 				generic_error_remove_page(inode->i_mapping,
@@ -898,8 +912,9 @@ static void writepages_finish(struct ceph_osd_request *req)
 
 			unlock_page(page);
 		}
-		dout("writepages_finish %p wrote %llu bytes cleaned %d pages\n",
-		     inode, osd_data->length, rc >= 0 ? num_pages : 0);
+		doutc(cl, "%llx.%llx wrote %llu bytes cleaned %d pages\n",
+		      ceph_vinop(inode), osd_data->length,
+		      rc >= 0 ? num_pages : 0);
 
 		release_pages(osd_data->pages, num_pages);
 	}
@@ -926,7 +941,8 @@ static int ceph_writepages_start(struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_vino vino = ceph_vino(inode);
 	pgoff_t index, start_index, end = -1;
 	struct ceph_snap_context *snapc = NULL, *last_snapc = NULL, *pgsnapc;
@@ -944,15 +960,15 @@ static int ceph_writepages_start(struct address_space *mapping,
 	    fsc->write_congested)
 		return 0;
 
-	dout("writepages_start %p (mode=%s)\n", inode,
-	     wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
-	     (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
+	doutc(cl, "%llx.%llx (mode=%s)\n", ceph_vinop(inode),
+	      wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
+	      (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
 
 	if (ceph_inode_is_shutdown(inode)) {
 		if (ci->i_wrbuffer_ref > 0) {
-			pr_warn_ratelimited(
-				"writepage_start %p %lld forced umount\n",
-				inode, ceph_ino(inode));
+			pr_warn_ratelimited_client(cl,
+				"%llx.%llx %lld forced umount\n",
+				ceph_vinop(inode), ceph_ino(inode));
 		}
 		mapping_set_error(mapping, -EIO);
 		return -EIO; /* we're in a forced umount, don't write! */
@@ -976,11 +992,11 @@ retry:
 	if (!snapc) {
 		/* hmm, why does writepages get called when there
 		   is no dirty data? */
-		dout(" no snap context with dirty data?\n");
+		doutc(cl, " no snap context with dirty data?\n");
 		goto out;
 	}
-	dout(" oldest snapc is %p seq %lld (%d snaps)\n",
-	     snapc, snapc->seq, snapc->num_snaps);
+	doutc(cl, " oldest snapc is %p seq %lld (%d snaps)\n", snapc,
+	      snapc->seq, snapc->num_snaps);
 
 	should_loop = false;
 	if (ceph_wbc.head_snapc && snapc != last_snapc) {
@@ -990,13 +1006,13 @@ retry:
 			end = -1;
 			if (index > 0)
 				should_loop = true;
-			dout(" cyclic, start at %lu\n", index);
+			doutc(cl, " cyclic, start at %lu\n", index);
 		} else {
 			index = wbc->range_start >> PAGE_SHIFT;
 			end = wbc->range_end >> PAGE_SHIFT;
 			if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 				range_whole = true;
-			dout(" not cyclic, %lu to %lu\n", index, end);
+			doutc(cl, " not cyclic, %lu to %lu\n", index, end);
 		}
 	} else if (!ceph_wbc.head_snapc) {
 		/* Do not respect wbc->range_{start,end}. Dirty pages
@@ -1005,7 +1021,7 @@ retry:
 		 * associated with 'snapc' get written */
 		if (index > 0)
 			should_loop = true;
-		dout(" non-head snapc, range whole\n");
+		doutc(cl, " non-head snapc, range whole\n");
 	}
 
 	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
@@ -1028,12 +1044,12 @@ retry:
 get_more_pages:
 		nr_folios = filemap_get_folios_tag(mapping, &index,
 						   end, tag, &fbatch);
-		dout("pagevec_lookup_range_tag got %d\n", nr_folios);
+		doutc(cl, "pagevec_lookup_range_tag got %d\n", nr_folios);
 		if (!nr_folios && !locked_pages)
 			break;
 		for (i = 0; i < nr_folios && locked_pages < max_pages; i++) {
 			page = &fbatch.folios[i]->page;
-			dout("? %p idx %lu\n", page, page->index);
+			doutc(cl, "? %p idx %lu\n", page, page->index);
 			if (locked_pages == 0)
 				lock_page(page);  /* first page */
 			else if (!trylock_page(page))
@@ -1042,15 +1058,15 @@ get_more_pages:
 			/* only dirty pages, or our accounting breaks */
 			if (unlikely(!PageDirty(page)) ||
 			    unlikely(page->mapping != mapping)) {
-				dout("!dirty or !mapping %p\n", page);
+				doutc(cl, "!dirty or !mapping %p\n", page);
 				unlock_page(page);
 				continue;
 			}
 			/* only if matching snap context */
 			pgsnapc = page_snap_context(page);
 			if (pgsnapc != snapc) {
-				dout("page snapc %p %lld != oldest %p %lld\n",
-				     pgsnapc, pgsnapc->seq, snapc, snapc->seq);
+				doutc(cl, "page snapc %p %lld != oldest %p %lld\n",
+				      pgsnapc, pgsnapc->seq, snapc, snapc->seq);
 				if (!should_loop &&
 				    !ceph_wbc.head_snapc &&
 				    wbc->sync_mode != WB_SYNC_NONE)
@@ -1061,8 +1077,8 @@ get_more_pages:
 			if (page_offset(page) >= ceph_wbc.i_size) {
 				struct folio *folio = page_folio(page);
 
-				dout("folio at %lu beyond eof %llu\n",
-				     folio->index, ceph_wbc.i_size);
+				doutc(cl, "folio at %lu beyond eof %llu\n",
+				      folio->index, ceph_wbc.i_size);
 				if ((ceph_wbc.size_stable ||
 				    folio_pos(folio) >= i_size_read(inode)) &&
 				    folio_clear_dirty_for_io(folio))
@@ -1072,23 +1088,23 @@ get_more_pages:
 				continue;
 			}
 			if (strip_unit_end && (page->index > strip_unit_end)) {
-				dout("end of strip unit %p\n", page);
+				doutc(cl, "end of strip unit %p\n", page);
 				unlock_page(page);
 				break;
 			}
 			if (PageWriteback(page) || PageFsCache(page)) {
 				if (wbc->sync_mode == WB_SYNC_NONE) {
-					dout("%p under writeback\n", page);
+					doutc(cl, "%p under writeback\n", page);
 					unlock_page(page);
 					continue;
 				}
-				dout("waiting on writeback %p\n", page);
+				doutc(cl, "waiting on writeback %p\n", page);
 				wait_on_page_writeback(page);
 				wait_on_page_fscache(page);
 			}
 
 			if (!clear_page_dirty_for_io(page)) {
-				dout("%p !clear_page_dirty_for_io\n", page);
+				doutc(cl, "%p !clear_page_dirty_for_io\n", page);
 				unlock_page(page);
 				continue;
 			}
@@ -1143,8 +1159,8 @@ get_more_pages:
 			}
 
 			/* note position of first page in fbatch */
-			dout("%p will write page %p idx %lu\n",
-			     inode, page, page->index);
+			doutc(cl, "%llx.%llx will write page %p idx %lu\n",
+			      ceph_vinop(inode), page, page->index);
 
 			if (atomic_long_inc_return(&fsc->writeback_count) >
 			    CONGESTION_ON_THRESH(
@@ -1158,8 +1174,9 @@ get_more_pages:
 						locked_pages ? GFP_NOWAIT : GFP_NOFS);
 				if (IS_ERR(pages[locked_pages])) {
 					if (PTR_ERR(pages[locked_pages]) == -EINVAL)
-						pr_err("%s: inode->i_blkbits=%hhu\n",
-							__func__, inode->i_blkbits);
+						pr_err_client(cl,
+							"inode->i_blkbits=%hhu\n",
+							inode->i_blkbits);
 					/* better not fail on first page! */
 					BUG_ON(locked_pages == 0);
 					pages[locked_pages] = NULL;
@@ -1193,7 +1210,7 @@ get_more_pages:
 
 			if (nr_folios && i == nr_folios &&
 			    locked_pages < max_pages) {
-				dout("reached end fbatch, trying for more\n");
+				doutc(cl, "reached end fbatch, trying for more\n");
 				folio_batch_release(&fbatch);
 				goto get_more_pages;
 			}
@@ -1254,8 +1271,8 @@ new_request:
 				/* Start a new extent */
 				osd_req_op_extent_dup_last(req, op_idx,
 							   cur_offset - offset);
-				dout("writepages got pages at %llu~%llu\n",
-				     offset, len);
+				doutc(cl, "got pages at %llu~%llu\n", offset,
+				      len);
 				osd_req_op_extent_osd_data_pages(req, op_idx,
 							data_pages, len, 0,
 							from_pool, false);
@@ -1288,12 +1305,13 @@ new_request:
 		if (IS_ENCRYPTED(inode))
 			len = round_up(len, CEPH_FSCRYPT_BLOCK_SIZE);
 
-		dout("writepages got pages at %llu~%llu\n", offset, len);
+		doutc(cl, "got pages at %llu~%llu\n", offset, len);
 
 		if (IS_ENCRYPTED(inode) &&
 		    ((offset | len) & ~CEPH_FSCRYPT_BLOCK_MASK))
-			pr_warn("%s: bad encrypted write offset=%lld len=%llu\n",
-				__func__, offset, len);
+			pr_warn_client(cl,
+				"bad encrypted write offset=%lld len=%llu\n",
+				offset, len);
 
 		osd_req_op_extent_osd_data_pages(req, op_idx, data_pages, len,
 						 0, from_pool, false);
@@ -1345,14 +1363,14 @@ new_request:
 			done = true;
 
 release_folios:
-		dout("folio_batch release on %d folios (%p)\n", (int)fbatch.nr,
-		     fbatch.nr ? fbatch.folios[0] : NULL);
+		doutc(cl, "folio_batch release on %d folios (%p)\n",
+		      (int)fbatch.nr, fbatch.nr ? fbatch.folios[0] : NULL);
 		folio_batch_release(&fbatch);
 	}
 
 	if (should_loop && !done) {
 		/* more to do; loop back to beginning of file */
-		dout("writepages looping back to beginning of file\n");
+		doutc(cl, "looping back to beginning of file\n");
 		end = start_index - 1; /* OK even when start_index == 0 */
 
 		/* to write dirty pages associated with next snapc,
@@ -1390,7 +1408,8 @@ release_folios:
 out:
 	ceph_osdc_put_request(req);
 	ceph_put_snap_context(last_snapc);
-	dout("writepages dend - startone, rc = %d\n", rc);
+	doutc(cl, "%llx.%llx dend - startone, rc = %d\n", ceph_vinop(inode),
+	      rc);
 	return rc;
 }
 
@@ -1424,11 +1443,12 @@ static struct ceph_snap_context *
 ceph_find_incompatible(struct page *page)
 {
 	struct inode *inode = page->mapping->host;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
 	if (ceph_inode_is_shutdown(inode)) {
-		dout(" page %p %llx:%llx is shutdown\n", page,
-		     ceph_vinop(inode));
+		doutc(cl, " %llx.%llx page %p is shutdown\n",
+		      ceph_vinop(inode), page);
 		return ERR_PTR(-ESTALE);
 	}
 
@@ -1449,13 +1469,15 @@ ceph_find_incompatible(struct page *page)
 		if (snapc->seq > oldest->seq) {
 			/* not writeable -- return it for the caller to deal with */
 			ceph_put_snap_context(oldest);
-			dout(" page %p snapc %p not current or oldest\n", page, snapc);
+			doutc(cl, " %llx.%llx page %p snapc %p not current or oldest\n",
+			      ceph_vinop(inode), page, snapc);
 			return ceph_get_snap_context(snapc);
 		}
 		ceph_put_snap_context(oldest);
 
 		/* yay, writeable, do it now (without dropping page lock) */
-		dout(" page %p snapc %p not current, but oldest\n", page, snapc);
+		doutc(cl, " %llx.%llx page %p snapc %p not current, but oldest\n",
+		      ceph_vinop(inode), page, snapc);
 		if (clear_page_dirty_for_io(page)) {
 			int r = writepage_nounlock(page, NULL);
 			if (r < 0)
@@ -1524,10 +1546,11 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
 {
 	struct folio *folio = page_folio(subpage);
 	struct inode *inode = file_inode(file);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	bool check_cap = false;
 
-	dout("write_end file %p inode %p folio %p %d~%d (%d)\n", file,
-	     inode, folio, (int)pos, (int)copied, (int)len);
+	doutc(cl, "%llx.%llx file %p folio %p %d~%d (%d)\n", ceph_vinop(inode),
+	      file, folio, (int)pos, (int)copied, (int)len);
 
 	if (!folio_test_uptodate(folio)) {
 		/* just return that nothing was copied on a short copy */
@@ -1587,6 +1610,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 	struct vm_area_struct *vma = vmf->vma;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_file_info *fi = vma->vm_file->private_data;
 	loff_t off = (loff_t)vmf->pgoff << PAGE_SHIFT;
 	int want, got, err;
@@ -1598,8 +1622,8 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 
 	ceph_block_sigs(&oldset);
 
-	dout("filemap_fault %p %llx.%llx %llu trying to get caps\n",
-	     inode, ceph_vinop(inode), off);
+	doutc(cl, "%llx.%llx %llu trying to get caps\n",
+	      ceph_vinop(inode), off);
 	if (fi->fmode & CEPH_FILE_MODE_LAZY)
 		want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
 	else
@@ -1610,8 +1634,8 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 	if (err < 0)
 		goto out_restore;
 
-	dout("filemap_fault %p %llu got cap refs on %s\n",
-	     inode, off, ceph_cap_string(got));
+	doutc(cl, "%llx.%llx %llu got cap refs on %s\n", ceph_vinop(inode),
+	      off, ceph_cap_string(got));
 
 	if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
 	    !ceph_has_inline_data(ci)) {
@@ -1619,8 +1643,8 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 		ceph_add_rw_context(fi, &rw_ctx);
 		ret = filemap_fault(vmf);
 		ceph_del_rw_context(fi, &rw_ctx);
-		dout("filemap_fault %p %llu drop cap refs %s ret %x\n",
-		     inode, off, ceph_cap_string(got), ret);
+		doutc(cl, "%llx.%llx %llu drop cap refs %s ret %x\n",
+		      ceph_vinop(inode), off, ceph_cap_string(got), ret);
 	} else
 		err = -EAGAIN;
 
@@ -1661,8 +1685,8 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 		ret = VM_FAULT_MAJOR | VM_FAULT_LOCKED;
 out_inline:
 		filemap_invalidate_unlock_shared(mapping);
-		dout("filemap_fault %p %llu read inline data ret %x\n",
-		     inode, off, ret);
+		doutc(cl, "%llx.%llx %llu read inline data ret %x\n",
+		      ceph_vinop(inode), off, ret);
 	}
 out_restore:
 	ceph_restore_sigs(&oldset);
@@ -1676,6 +1700,7 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct inode *inode = file_inode(vma->vm_file);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_file_info *fi = vma->vm_file->private_data;
 	struct ceph_cap_flush *prealloc_cf;
@@ -1702,8 +1727,8 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
 	else
 		len = offset_in_thp(page, size);
 
-	dout("page_mkwrite %p %llx.%llx %llu~%zd getting caps i_size %llu\n",
-	     inode, ceph_vinop(inode), off, len, size);
+	doutc(cl, "%llx.%llx %llu~%zd getting caps i_size %llu\n",
+	      ceph_vinop(inode), off, len, size);
 	if (fi->fmode & CEPH_FILE_MODE_LAZY)
 		want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
 	else
@@ -1714,8 +1739,8 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
 	if (err < 0)
 		goto out_free;
 
-	dout("page_mkwrite %p %llu~%zd got cap refs on %s\n",
-	     inode, off, len, ceph_cap_string(got));
+	doutc(cl, "%llx.%llx %llu~%zd got cap refs on %s\n", ceph_vinop(inode),
+	      off, len, ceph_cap_string(got));
 
 	/* Update time before taking page lock */
 	file_update_time(vma->vm_file);
@@ -1763,8 +1788,8 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
 			__mark_inode_dirty(inode, dirty);
 	}
 
-	dout("page_mkwrite %p %llu~%zd dropping cap refs on %s ret %x\n",
-	     inode, off, len, ceph_cap_string(got), ret);
+	doutc(cl, "%llx.%llx %llu~%zd dropping cap refs on %s ret %x\n",
+	      ceph_vinop(inode), off, len, ceph_cap_string(got), ret);
 	ceph_put_cap_refs_async(ci, got);
 out_free:
 	ceph_restore_sigs(&oldset);
@@ -1778,6 +1803,7 @@ out_free:
 void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 			   char	*data, size_t len)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
 
@@ -1798,8 +1824,8 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 		}
 	}
 
-	dout("fill_inline_data %p %llx.%llx len %zu locked_page %p\n",
-	     inode, ceph_vinop(inode), len, locked_page);
+	doutc(cl, "%p %llx.%llx len %zu locked_page %p\n", inode,
+	      ceph_vinop(inode), len, locked_page);
 
 	if (len > 0) {
 		void *kaddr = kmap_atomic(page);
@@ -1823,7 +1849,8 @@ int ceph_uninline_data(struct file *file)
 {
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_osd_request *req = NULL;
 	struct ceph_cap_flush *prealloc_cf = NULL;
 	struct folio *folio = NULL;
@@ -1836,8 +1863,8 @@ int ceph_uninline_data(struct file *file)
 	inline_version = ci->i_inline_version;
 	spin_unlock(&ci->i_ceph_lock);
 
-	dout("uninline_data %p %llx.%llx inline_version %llu\n",
-	     inode, ceph_vinop(inode), inline_version);
+	doutc(cl, "%llx.%llx inline_version %llu\n", ceph_vinop(inode),
+	      inline_version);
 
 	if (ceph_inode_is_shutdown(inode)) {
 		err = -EIO;
@@ -1949,8 +1976,8 @@ out_unlock:
 	}
 out:
 	ceph_free_cap_flush(prealloc_cf);
-	dout("uninline_data %p %llx.%llx inline_version %llu = %d\n",
-	     inode, ceph_vinop(inode), inline_version, err);
+	doutc(cl, "%llx.%llx inline_version %llu = %d\n",
+	      ceph_vinop(inode), inline_version, err);
 	return err;
 }
 
@@ -1977,8 +2004,9 @@ enum {
 static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 				s64 pool, struct ceph_string *pool_ns)
 {
-	struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->netfs.inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(&ci->netfs.inode);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_client *cl = fsc->client;
 	struct ceph_osd_request *rd_req = NULL, *wr_req = NULL;
 	struct rb_node **p, *parent;
 	struct ceph_pool_perm *perm;
@@ -2013,10 +2041,10 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 		goto out;
 
 	if (pool_ns)
-		dout("__ceph_pool_perm_get pool %lld ns %.*s no perm cached\n",
-		     pool, (int)pool_ns->len, pool_ns->str);
+		doutc(cl, "pool %lld ns %.*s no perm cached\n", pool,
+		      (int)pool_ns->len, pool_ns->str);
 	else
-		dout("__ceph_pool_perm_get pool %lld no perm cached\n", pool);
+		doutc(cl, "pool %lld no perm cached\n", pool);
 
 	down_write(&mdsc->pool_perm_rwsem);
 	p = &mdsc->pool_perm_tree.rb_node;
@@ -2141,15 +2169,16 @@ out:
 	if (!err)
 		err = have;
 	if (pool_ns)
-		dout("__ceph_pool_perm_get pool %lld ns %.*s result = %d\n",
-		     pool, (int)pool_ns->len, pool_ns->str, err);
+		doutc(cl, "pool %lld ns %.*s result = %d\n", pool,
+		      (int)pool_ns->len, pool_ns->str, err);
 	else
-		dout("__ceph_pool_perm_get pool %lld result = %d\n", pool, err);
+		doutc(cl, "pool %lld result = %d\n", pool, err);
 	return err;
 }
 
 int ceph_pool_perm_check(struct inode *inode, int need)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_string *pool_ns;
 	s64 pool;
@@ -2168,7 +2197,7 @@ int ceph_pool_perm_check(struct inode *inode, int need)
 		return 0;
 	}
 
-	if (ceph_test_mount_opt(ceph_inode_to_client(inode),
+	if (ceph_test_mount_opt(ceph_inode_to_fs_client(inode),
 				NOPOOLPERM))
 		return 0;
 
@@ -2179,13 +2208,11 @@ int ceph_pool_perm_check(struct inode *inode, int need)
 check:
 	if (flags & CEPH_I_POOL_PERM) {
 		if ((need & CEPH_CAP_FILE_RD) && !(flags & CEPH_I_POOL_RD)) {
-			dout("ceph_pool_perm_check pool %lld no read perm\n",
-			     pool);
+			doutc(cl, "pool %lld no read perm\n", pool);
 			return -EPERM;
 		}
 		if ((need & CEPH_CAP_FILE_WR) && !(flags & CEPH_I_POOL_WR)) {
-			dout("ceph_pool_perm_check pool %lld no write perm\n",
-			     pool);
+			doutc(cl, "pool %lld no write perm\n", pool);
 			return -EPERM;
 		}
 		return 0;
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index de1dee46d3df72..930fbd54d2c8c8 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -15,7 +15,7 @@
 void ceph_fscache_register_inode_cookie(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 
 	/* No caching for filesystem? */
 	if (!fsc->fscache)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index a104669fcf4c7f..2c0b8dc3dd0d80 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -186,10 +186,10 @@ static void __ceph_unreserve_caps(struct ceph_mds_client *mdsc, int nr_caps)
 			mdsc->caps_avail_count += nr_caps;
 		}
 
-		dout("%s: caps %d = %d used + %d resv + %d avail\n",
-		     __func__,
-		     mdsc->caps_total_count, mdsc->caps_use_count,
-		     mdsc->caps_reserve_count, mdsc->caps_avail_count);
+		doutc(mdsc->fsc->client,
+		      "caps %d = %d used + %d resv + %d avail\n",
+		      mdsc->caps_total_count, mdsc->caps_use_count,
+		      mdsc->caps_reserve_count, mdsc->caps_avail_count);
 		BUG_ON(mdsc->caps_total_count != mdsc->caps_use_count +
 						 mdsc->caps_reserve_count +
 						 mdsc->caps_avail_count);
@@ -202,6 +202,7 @@ static void __ceph_unreserve_caps(struct ceph_mds_client *mdsc, int nr_caps)
 int ceph_reserve_caps(struct ceph_mds_client *mdsc,
 		      struct ceph_cap_reservation *ctx, int need)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	int i, j;
 	struct ceph_cap *cap;
 	int have;
@@ -212,7 +213,7 @@ int ceph_reserve_caps(struct ceph_mds_client *mdsc,
 	struct ceph_mds_session *s;
 	LIST_HEAD(newcaps);
 
-	dout("reserve caps ctx=%p need=%d\n", ctx, need);
+	doutc(cl, "ctx=%p need=%d\n", ctx, need);
 
 	/* first reserve any caps that are already allocated */
 	spin_lock(&mdsc->caps_list_lock);
@@ -272,8 +273,8 @@ int ceph_reserve_caps(struct ceph_mds_client *mdsc,
 			continue;
 		}
 
-		pr_warn("reserve caps ctx=%p ENOMEM need=%d got=%d\n",
-			ctx, need, have + alloc);
+		pr_warn_client(cl, "ctx=%p ENOMEM need=%d got=%d\n", ctx, need,
+			       have + alloc);
 		err = -ENOMEM;
 		break;
 	}
@@ -298,20 +299,21 @@ int ceph_reserve_caps(struct ceph_mds_client *mdsc,
 
 	spin_unlock(&mdsc->caps_list_lock);
 
-	dout("reserve caps ctx=%p %d = %d used + %d resv + %d avail\n",
-	     ctx, mdsc->caps_total_count, mdsc->caps_use_count,
-	     mdsc->caps_reserve_count, mdsc->caps_avail_count);
+	doutc(cl, "ctx=%p %d = %d used + %d resv + %d avail\n", ctx,
+	      mdsc->caps_total_count, mdsc->caps_use_count,
+	      mdsc->caps_reserve_count, mdsc->caps_avail_count);
 	return err;
 }
 
 void ceph_unreserve_caps(struct ceph_mds_client *mdsc,
 			 struct ceph_cap_reservation *ctx)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	bool reclaim = false;
 	if (!ctx->count)
 		return;
 
-	dout("unreserve caps ctx=%p count=%d\n", ctx, ctx->count);
+	doutc(cl, "ctx=%p count=%d\n", ctx, ctx->count);
 	spin_lock(&mdsc->caps_list_lock);
 	__ceph_unreserve_caps(mdsc, ctx->count);
 	ctx->count = 0;
@@ -328,6 +330,7 @@ void ceph_unreserve_caps(struct ceph_mds_client *mdsc,
 struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
 			      struct ceph_cap_reservation *ctx)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_cap *cap = NULL;
 
 	/* temporary, until we do something about cap import/export */
@@ -359,9 +362,9 @@ struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
 	}
 
 	spin_lock(&mdsc->caps_list_lock);
-	dout("get_cap ctx=%p (%d) %d = %d used + %d resv + %d avail\n",
-	     ctx, ctx->count, mdsc->caps_total_count, mdsc->caps_use_count,
-	     mdsc->caps_reserve_count, mdsc->caps_avail_count);
+	doutc(cl, "ctx=%p (%d) %d = %d used + %d resv + %d avail\n", ctx,
+	      ctx->count, mdsc->caps_total_count, mdsc->caps_use_count,
+	      mdsc->caps_reserve_count, mdsc->caps_avail_count);
 	BUG_ON(!ctx->count);
 	BUG_ON(ctx->count > mdsc->caps_reserve_count);
 	BUG_ON(list_empty(&mdsc->caps_list));
@@ -382,10 +385,12 @@ struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
 
 void ceph_put_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
+
 	spin_lock(&mdsc->caps_list_lock);
-	dout("put_cap %p %d = %d used + %d resv + %d avail\n",
-	     cap, mdsc->caps_total_count, mdsc->caps_use_count,
-	     mdsc->caps_reserve_count, mdsc->caps_avail_count);
+	doutc(cl, "%p %d = %d used + %d resv + %d avail\n", cap,
+	      mdsc->caps_total_count, mdsc->caps_use_count,
+	      mdsc->caps_reserve_count, mdsc->caps_avail_count);
 	mdsc->caps_use_count--;
 	/*
 	 * Keep some preallocated caps around (ceph_min_count), to
@@ -491,11 +496,13 @@ static void __insert_cap_node(struct ceph_inode_info *ci,
 static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
 			       struct ceph_inode_info *ci)
 {
+	struct inode *inode = &ci->netfs.inode;
 	struct ceph_mount_options *opt = mdsc->fsc->mount_options;
+
 	ci->i_hold_caps_max = round_jiffies(jiffies +
 					    opt->caps_wanted_delay_max * HZ);
-	dout("__cap_set_timeouts %p %lu\n", &ci->netfs.inode,
-	     ci->i_hold_caps_max - jiffies);
+	doutc(mdsc->fsc->client, "%p %llx.%llx %lu\n", inode,
+	      ceph_vinop(inode), ci->i_hold_caps_max - jiffies);
 }
 
 /*
@@ -509,8 +516,11 @@ static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
 static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
 				struct ceph_inode_info *ci)
 {
-	dout("__cap_delay_requeue %p flags 0x%lx at %lu\n", &ci->netfs.inode,
-	     ci->i_ceph_flags, ci->i_hold_caps_max);
+	struct inode *inode = &ci->netfs.inode;
+
+	doutc(mdsc->fsc->client, "%p %llx.%llx flags 0x%lx at %lu\n",
+	      inode, ceph_vinop(inode), ci->i_ceph_flags,
+	      ci->i_hold_caps_max);
 	if (!mdsc->stopping) {
 		spin_lock(&mdsc->cap_delay_lock);
 		if (!list_empty(&ci->i_cap_delay_list)) {
@@ -533,7 +543,9 @@ no_change:
 static void __cap_delay_requeue_front(struct ceph_mds_client *mdsc,
 				      struct ceph_inode_info *ci)
 {
-	dout("__cap_delay_requeue_front %p\n", &ci->netfs.inode);
+	struct inode *inode = &ci->netfs.inode;
+
+	doutc(mdsc->fsc->client, "%p %llx.%llx\n", inode, ceph_vinop(inode));
 	spin_lock(&mdsc->cap_delay_lock);
 	ci->i_ceph_flags |= CEPH_I_FLUSH;
 	if (!list_empty(&ci->i_cap_delay_list))
@@ -550,7 +562,9 @@ static void __cap_delay_requeue_front(struct ceph_mds_client *mdsc,
 static void __cap_delay_cancel(struct ceph_mds_client *mdsc,
 			       struct ceph_inode_info *ci)
 {
-	dout("__cap_delay_cancel %p\n", &ci->netfs.inode);
+	struct inode *inode = &ci->netfs.inode;
+
+	doutc(mdsc->fsc->client, "%p %llx.%llx\n", inode, ceph_vinop(inode));
 	if (list_empty(&ci->i_cap_delay_list))
 		return;
 	spin_lock(&mdsc->cap_delay_lock);
@@ -562,6 +576,9 @@ static void __cap_delay_cancel(struct ceph_mds_client *mdsc,
 static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
 			      unsigned issued)
 {
+	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+
 	unsigned had = __ceph_caps_issued(ci, NULL);
 
 	lockdep_assert_held(&ci->i_ceph_lock);
@@ -586,7 +603,7 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
 		if (issued & CEPH_CAP_FILE_SHARED)
 			atomic_inc(&ci->i_shared_gen);
 		if (S_ISDIR(ci->netfs.inode.i_mode)) {
-			dout(" marking %p NOT complete\n", &ci->netfs.inode);
+			doutc(cl, " marking %p NOT complete\n", inode);
 			__ceph_dir_clear_complete(ci);
 		}
 	}
@@ -635,7 +652,8 @@ void ceph_add_cap(struct inode *inode,
 		  unsigned seq, unsigned mseq, u64 realmino, int flags,
 		  struct ceph_cap **new_cap)
 {
-	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_cap *cap;
 	int mds = session->s_mds;
@@ -644,8 +662,9 @@ void ceph_add_cap(struct inode *inode,
 
 	lockdep_assert_held(&ci->i_ceph_lock);
 
-	dout("add_cap %p mds%d cap %llx %s seq %d\n", inode,
-	     session->s_mds, cap_id, ceph_cap_string(issued), seq);
+	doutc(cl, "%p %llx.%llx mds%d cap %llx %s seq %d\n", inode,
+	      ceph_vinop(inode), session->s_mds, cap_id,
+	      ceph_cap_string(issued), seq);
 
 	gen = atomic_read(&session->s_cap_gen);
 
@@ -723,9 +742,9 @@ void ceph_add_cap(struct inode *inode,
 	actual_wanted = __ceph_caps_wanted(ci);
 	if ((wanted & ~actual_wanted) ||
 	    (issued & ~actual_wanted & CEPH_CAP_ANY_WR)) {
-		dout(" issued %s, mds wanted %s, actual %s, queueing\n",
-		     ceph_cap_string(issued), ceph_cap_string(wanted),
-		     ceph_cap_string(actual_wanted));
+		doutc(cl, "issued %s, mds wanted %s, actual %s, queueing\n",
+		      ceph_cap_string(issued), ceph_cap_string(wanted),
+		      ceph_cap_string(actual_wanted));
 		__cap_delay_requeue(mdsc, ci);
 	}
 
@@ -742,9 +761,9 @@ void ceph_add_cap(struct inode *inode,
 		WARN_ON(ci->i_auth_cap == cap);
 	}
 
-	dout("add_cap inode %p (%llx.%llx) cap %p %s now %s seq %d mds%d\n",
-	     inode, ceph_vinop(inode), cap, ceph_cap_string(issued),
-	     ceph_cap_string(issued|cap->issued), seq, mds);
+	doutc(cl, "inode %p %llx.%llx cap %p %s now %s seq %d mds%d\n",
+	      inode, ceph_vinop(inode), cap, ceph_cap_string(issued),
+	      ceph_cap_string(issued|cap->issued), seq, mds);
 	cap->cap_id = cap_id;
 	cap->issued = issued;
 	cap->implemented |= issued;
@@ -766,6 +785,8 @@ void ceph_add_cap(struct inode *inode,
  */
 static int __cap_is_valid(struct ceph_cap *cap)
 {
+	struct inode *inode = &cap->ci->netfs.inode;
+	struct ceph_client *cl = cap->session->s_mdsc->fsc->client;
 	unsigned long ttl;
 	u32 gen;
 
@@ -773,9 +794,9 @@ static int __cap_is_valid(struct ceph_cap *cap)
 	ttl = cap->session->s_cap_ttl;
 
 	if (cap->cap_gen < gen || time_after_eq(jiffies, ttl)) {
-		dout("__cap_is_valid %p cap %p issued %s "
-		     "but STALE (gen %u vs %u)\n", &cap->ci->netfs.inode,
-		     cap, ceph_cap_string(cap->issued), cap->cap_gen, gen);
+		doutc(cl, "%p %llx.%llx cap %p issued %s but STALE (gen %u vs %u)\n",
+		      inode, ceph_vinop(inode), cap,
+		      ceph_cap_string(cap->issued), cap->cap_gen, gen);
 		return 0;
 	}
 
@@ -789,6 +810,8 @@ static int __cap_is_valid(struct ceph_cap *cap)
  */
 int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented)
 {
+	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int have = ci->i_snap_caps;
 	struct ceph_cap *cap;
 	struct rb_node *p;
@@ -799,8 +822,8 @@ int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented)
 		cap = rb_entry(p, struct ceph_cap, ci_node);
 		if (!__cap_is_valid(cap))
 			continue;
-		dout("__ceph_caps_issued %p cap %p issued %s\n",
-		     &ci->netfs.inode, cap, ceph_cap_string(cap->issued));
+		doutc(cl, "%p %llx.%llx cap %p issued %s\n", inode,
+		      ceph_vinop(inode), cap, ceph_cap_string(cap->issued));
 		have |= cap->issued;
 		if (implemented)
 			*implemented |= cap->implemented;
@@ -843,16 +866,18 @@ int __ceph_caps_issued_other(struct ceph_inode_info *ci, struct ceph_cap *ocap)
  */
 static void __touch_cap(struct ceph_cap *cap)
 {
+	struct inode *inode = &cap->ci->netfs.inode;
 	struct ceph_mds_session *s = cap->session;
+	struct ceph_client *cl = s->s_mdsc->fsc->client;
 
 	spin_lock(&s->s_cap_lock);
 	if (!s->s_cap_iterator) {
-		dout("__touch_cap %p cap %p mds%d\n", &cap->ci->netfs.inode, cap,
-		     s->s_mds);
+		doutc(cl, "%p %llx.%llx cap %p mds%d\n", inode,
+		      ceph_vinop(inode), cap, s->s_mds);
 		list_move_tail(&cap->session_caps, &s->s_caps);
 	} else {
-		dout("__touch_cap %p cap %p mds%d NOP, iterating over caps\n",
-		     &cap->ci->netfs.inode, cap, s->s_mds);
+		doutc(cl, "%p %llx.%llx cap %p mds%d NOP, iterating over caps\n",
+		      inode, ceph_vinop(inode), cap, s->s_mds);
 	}
 	spin_unlock(&s->s_cap_lock);
 }
@@ -864,15 +889,16 @@ static void __touch_cap(struct ceph_cap *cap)
  */
 int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 {
+	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_cap *cap;
 	struct rb_node *p;
 	int have = ci->i_snap_caps;
 
 	if ((have & mask) == mask) {
-		dout("__ceph_caps_issued_mask ino 0x%llx snap issued %s"
-		     " (mask %s)\n", ceph_ino(&ci->netfs.inode),
-		     ceph_cap_string(have),
-		     ceph_cap_string(mask));
+		doutc(cl, "mask %p %llx.%llx snap issued %s (mask %s)\n",
+		      inode, ceph_vinop(inode), ceph_cap_string(have),
+		      ceph_cap_string(mask));
 		return 1;
 	}
 
@@ -881,10 +907,10 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 		if (!__cap_is_valid(cap))
 			continue;
 		if ((cap->issued & mask) == mask) {
-			dout("__ceph_caps_issued_mask ino 0x%llx cap %p issued %s"
-			     " (mask %s)\n", ceph_ino(&ci->netfs.inode), cap,
-			     ceph_cap_string(cap->issued),
-			     ceph_cap_string(mask));
+			doutc(cl, "mask %p %llx.%llx cap %p issued %s (mask %s)\n",
+			      inode, ceph_vinop(inode), cap,
+			      ceph_cap_string(cap->issued),
+			      ceph_cap_string(mask));
 			if (touch)
 				__touch_cap(cap);
 			return 1;
@@ -893,10 +919,10 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 		/* does a combination of caps satisfy mask? */
 		have |= cap->issued;
 		if ((have & mask) == mask) {
-			dout("__ceph_caps_issued_mask ino 0x%llx combo issued %s"
-			     " (mask %s)\n", ceph_ino(&ci->netfs.inode),
-			     ceph_cap_string(cap->issued),
-			     ceph_cap_string(mask));
+			doutc(cl, "mask %p %llx.%llx combo issued %s (mask %s)\n",
+			      inode, ceph_vinop(inode),
+			      ceph_cap_string(cap->issued),
+			      ceph_cap_string(mask));
 			if (touch) {
 				struct rb_node *q;
 
@@ -922,7 +948,7 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 int __ceph_caps_issued_mask_metric(struct ceph_inode_info *ci, int mask,
 				   int touch)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(ci->netfs.inode.i_sb);
 	int r;
 
 	r = __ceph_caps_issued_mask(ci, mask, touch);
@@ -954,13 +980,14 @@ int __ceph_caps_revoking_other(struct ceph_inode_info *ci,
 int ceph_caps_revoking(struct ceph_inode_info *ci, int mask)
 {
 	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int ret;
 
 	spin_lock(&ci->i_ceph_lock);
 	ret = __ceph_caps_revoking_other(ci, NULL, mask);
 	spin_unlock(&ci->i_ceph_lock);
-	dout("ceph_caps_revoking %p %s = %d\n", inode,
-	     ceph_cap_string(mask), ret);
+	doutc(cl, "%p %llx.%llx %s = %d\n", inode, ceph_vinop(inode),
+	      ceph_cap_string(mask), ret);
 	return ret;
 }
 
@@ -996,7 +1023,7 @@ int __ceph_caps_file_wanted(struct ceph_inode_info *ci)
 	const int WR_SHIFT = ffs(CEPH_FILE_MODE_WR);
 	const int LAZY_SHIFT = ffs(CEPH_FILE_MODE_LAZY);
 	struct ceph_mount_options *opt =
-		ceph_inode_to_client(&ci->netfs.inode)->mount_options;
+		ceph_inode_to_fs_client(&ci->netfs.inode)->mount_options;
 	unsigned long used_cutoff = jiffies - opt->caps_wanted_delay_max * HZ;
 	unsigned long idle_cutoff = jiffies - opt->caps_wanted_delay_min * HZ;
 
@@ -1107,21 +1134,23 @@ int ceph_is_any_caps(struct inode *inode)
 void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 {
 	struct ceph_mds_session *session = cap->session;
+	struct ceph_client *cl = session->s_mdsc->fsc->client;
 	struct ceph_inode_info *ci = cap->ci;
+	struct inode *inode = &ci->netfs.inode;
 	struct ceph_mds_client *mdsc;
 	int removed = 0;
 
 	/* 'ci' being NULL means the remove have already occurred */
 	if (!ci) {
-		dout("%s: cap inode is NULL\n", __func__);
+		doutc(cl, "inode is NULL\n");
 		return;
 	}
 
 	lockdep_assert_held(&ci->i_ceph_lock);
 
-	dout("__ceph_remove_cap %p from %p\n", cap, &ci->netfs.inode);
+	doutc(cl, "%p from %p %llx.%llx\n", cap, inode, ceph_vinop(inode));
 
-	mdsc = ceph_inode_to_client(&ci->netfs.inode)->mdsc;
+	mdsc = ceph_inode_to_fs_client(&ci->netfs.inode)->mdsc;
 
 	/* remove from inode's cap rbtree, and clear auth cap */
 	rb_erase(&cap->ci_node, &ci->i_caps);
@@ -1132,8 +1161,8 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 	spin_lock(&session->s_cap_lock);
 	if (session->s_cap_iterator == cap) {
 		/* not yet, we are iterating over this very cap */
-		dout("__ceph_remove_cap  delaying %p removal from session %p\n",
-		     cap, cap->session);
+		doutc(cl, "delaying %p removal from session %p\n", cap,
+		      cap->session);
 	} else {
 		list_del_init(&cap->session_caps);
 		session->s_nr_caps--;
@@ -1178,20 +1207,21 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 	}
 }
 
-void ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
+void ceph_remove_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
+		     bool queue_release)
 {
 	struct ceph_inode_info *ci = cap->ci;
 	struct ceph_fs_client *fsc;
 
 	/* 'ci' being NULL means the remove have already occurred */
 	if (!ci) {
-		dout("%s: cap inode is NULL\n", __func__);
+		doutc(mdsc->fsc->client, "inode is NULL\n");
 		return;
 	}
 
 	lockdep_assert_held(&ci->i_ceph_lock);
 
-	fsc = ceph_inode_to_client(&ci->netfs.inode);
+	fsc = ceph_inode_to_fs_client(&ci->netfs.inode);
 	WARN_ON_ONCE(ci->i_auth_cap == cap &&
 		     !list_empty(&ci->i_dirty_item) &&
 		     !fsc->blocklisted &&
@@ -1227,15 +1257,19 @@ static void encode_cap_msg(struct ceph_msg *msg, struct cap_msg_args *arg)
 {
 	struct ceph_mds_caps *fc;
 	void *p;
-	struct ceph_osd_client *osdc = &arg->session->s_mdsc->fsc->client->osdc;
-
-	dout("%s %s %llx %llx caps %s wanted %s dirty %s seq %u/%u tid %llu/%llu mseq %u follows %lld size %llu/%llu xattr_ver %llu xattr_len %d\n",
-	     __func__, ceph_cap_op_name(arg->op), arg->cid, arg->ino,
-	     ceph_cap_string(arg->caps), ceph_cap_string(arg->wanted),
-	     ceph_cap_string(arg->dirty), arg->seq, arg->issue_seq,
-	     arg->flush_tid, arg->oldest_flush_tid, arg->mseq, arg->follows,
-	     arg->size, arg->max_size, arg->xattr_version,
-	     arg->xattr_buf ? (int)arg->xattr_buf->vec.iov_len : 0);
+	struct ceph_mds_client *mdsc = arg->session->s_mdsc;
+	struct ceph_osd_client *osdc = &mdsc->fsc->client->osdc;
+
+	doutc(mdsc->fsc->client,
+	      "%s %llx %llx caps %s wanted %s dirty %s seq %u/%u"
+	      " tid %llu/%llu mseq %u follows %lld size %llu/%llu"
+	      " xattr_ver %llu xattr_len %d\n",
+	      ceph_cap_op_name(arg->op), arg->cid, arg->ino,
+	      ceph_cap_string(arg->caps), ceph_cap_string(arg->wanted),
+	      ceph_cap_string(arg->dirty), arg->seq, arg->issue_seq,
+	      arg->flush_tid, arg->oldest_flush_tid, arg->mseq, arg->follows,
+	      arg->size, arg->max_size, arg->xattr_version,
+	      arg->xattr_buf ? (int)arg->xattr_buf->vec.iov_len : 0);
 
 	msg->hdr.version = cpu_to_le16(12);
 	msg->hdr.tid = cpu_to_le64(arg->flush_tid);
@@ -1342,6 +1376,8 @@ static void encode_cap_msg(struct ceph_msg *msg, struct cap_msg_args *arg)
  */
 void __ceph_remove_caps(struct ceph_inode_info *ci)
 {
+	struct inode *inode = &ci->netfs.inode;
+	struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc;
 	struct rb_node *p;
 
 	/* lock i_ceph_lock, because ceph_d_revalidate(..., LOOKUP_RCU)
@@ -1351,7 +1387,7 @@ void __ceph_remove_caps(struct ceph_inode_info *ci)
 	while (p) {
 		struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node);
 		p = rb_next(p);
-		ceph_remove_cap(cap, true);
+		ceph_remove_cap(mdsc, cap, true);
 	}
 	spin_unlock(&ci->i_ceph_lock);
 }
@@ -1370,6 +1406,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 {
 	struct ceph_inode_info *ci = cap->ci;
 	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int held, revoking;
 
 	lockdep_assert_held(&ci->i_ceph_lock);
@@ -1378,10 +1415,10 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 	revoking = cap->implemented & ~cap->issued;
 	retain &= ~revoking;
 
-	dout("%s %p cap %p session %p %s -> %s (revoking %s)\n",
-	     __func__, inode, cap, cap->session,
-	     ceph_cap_string(held), ceph_cap_string(held & retain),
-	     ceph_cap_string(revoking));
+	doutc(cl, "%p %llx.%llx cap %p session %p %s -> %s (revoking %s)\n",
+	      inode, ceph_vinop(inode), cap, cap->session,
+	      ceph_cap_string(held), ceph_cap_string(held & retain),
+	      ceph_cap_string(revoking));
 	BUG_ON((retain & CEPH_CAP_PIN) == 0);
 
 	ci->i_ceph_flags &= ~CEPH_I_FLUSH;
@@ -1497,13 +1534,16 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci)
 {
 	struct ceph_msg *msg;
 	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 
 	msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, cap_msg_size(arg), GFP_NOFS,
 			   false);
 	if (!msg) {
-		pr_err("error allocating cap msg: ino (%llx.%llx) flushing %s tid %llu, requeuing cap.\n",
-		       ceph_vinop(inode), ceph_cap_string(arg->dirty),
-		       arg->flush_tid);
+		pr_err_client(cl,
+			      "error allocating cap msg: ino (%llx.%llx)"
+			      " flushing %s tid %llu, requeuing cap.\n",
+			      ceph_vinop(inode), ceph_cap_string(arg->dirty),
+			      arg->flush_tid);
 		spin_lock(&ci->i_ceph_lock);
 		__cap_delay_requeue(arg->session->s_mdsc, ci);
 		spin_unlock(&ci->i_ceph_lock);
@@ -1592,11 +1632,13 @@ static void __ceph_flush_snaps(struct ceph_inode_info *ci,
 {
 	struct inode *inode = &ci->netfs.inode;
 	struct ceph_mds_client *mdsc = session->s_mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_cap_snap *capsnap;
 	u64 oldest_flush_tid = 0;
 	u64 first_tid = 1, last_tid = 0;
 
-	dout("__flush_snaps %p session %p\n", inode, session);
+	doutc(cl, "%p %llx.%llx session %p\n", inode, ceph_vinop(inode),
+	      session);
 
 	list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
 		/*
@@ -1611,7 +1653,7 @@ static void __ceph_flush_snaps(struct ceph_inode_info *ci,
 
 		/* only flush each capsnap once */
 		if (capsnap->cap_flush.tid > 0) {
-			dout(" already flushed %p, skipping\n", capsnap);
+			doutc(cl, "already flushed %p, skipping\n", capsnap);
 			continue;
 		}
 
@@ -1643,8 +1685,8 @@ static void __ceph_flush_snaps(struct ceph_inode_info *ci,
 		int ret;
 
 		if (!(cap && cap->session == session)) {
-			dout("__flush_snaps %p auth cap %p not mds%d, "
-			     "stop\n", inode, cap, session->s_mds);
+			doutc(cl, "%p %llx.%llx auth cap %p not mds%d, stop\n",
+			      inode, ceph_vinop(inode), cap, session->s_mds);
 			break;
 		}
 
@@ -1665,15 +1707,17 @@ static void __ceph_flush_snaps(struct ceph_inode_info *ci,
 		refcount_inc(&capsnap->nref);
 		spin_unlock(&ci->i_ceph_lock);
 
-		dout("__flush_snaps %p capsnap %p tid %llu %s\n",
-		     inode, capsnap, cf->tid, ceph_cap_string(capsnap->dirty));
+		doutc(cl, "%p %llx.%llx capsnap %p tid %llu %s\n", inode,
+		      ceph_vinop(inode), capsnap, cf->tid,
+		      ceph_cap_string(capsnap->dirty));
 
 		ret = __send_flush_snap(inode, session, capsnap, cap->mseq,
 					oldest_flush_tid);
 		if (ret < 0) {
-			pr_err("__flush_snaps: error sending cap flushsnap, "
-			       "ino (%llx.%llx) tid %llu follows %llu\n",
-				ceph_vinop(inode), cf->tid, capsnap->follows);
+			pr_err_client(cl, "error sending cap flushsnap, "
+				      "ino (%llx.%llx) tid %llu follows %llu\n",
+				      ceph_vinop(inode), cf->tid,
+				      capsnap->follows);
 		}
 
 		ceph_put_cap_snap(capsnap);
@@ -1685,28 +1729,29 @@ void ceph_flush_snaps(struct ceph_inode_info *ci,
 		      struct ceph_mds_session **psession)
 {
 	struct inode *inode = &ci->netfs.inode;
-	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_mds_session *session = NULL;
 	bool need_put = false;
 	int mds;
 
-	dout("ceph_flush_snaps %p\n", inode);
+	doutc(cl, "%p %llx.%llx\n", inode, ceph_vinop(inode));
 	if (psession)
 		session = *psession;
 retry:
 	spin_lock(&ci->i_ceph_lock);
 	if (!(ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS)) {
-		dout(" no capsnap needs flush, doing nothing\n");
+		doutc(cl, " no capsnap needs flush, doing nothing\n");
 		goto out;
 	}
 	if (!ci->i_auth_cap) {
-		dout(" no auth cap (migrating?), doing nothing\n");
+		doutc(cl, " no auth cap (migrating?), doing nothing\n");
 		goto out;
 	}
 
 	mds = ci->i_auth_cap->session->s_mds;
 	if (session && session->s_mds != mds) {
-		dout(" oops, wrong session %p mutex\n", session);
+		doutc(cl, " oops, wrong session %p mutex\n", session);
 		ceph_put_mds_session(session);
 		session = NULL;
 	}
@@ -1750,23 +1795,25 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
 			   struct ceph_cap_flush **pcf)
 {
 	struct ceph_mds_client *mdsc =
-		ceph_sb_to_client(ci->netfs.inode.i_sb)->mdsc;
+		ceph_sb_to_fs_client(ci->netfs.inode.i_sb)->mdsc;
 	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int was = ci->i_dirty_caps;
 	int dirty = 0;
 
 	lockdep_assert_held(&ci->i_ceph_lock);
 
 	if (!ci->i_auth_cap) {
-		pr_warn("__mark_dirty_caps %p %llx mask %s, "
-			"but no auth cap (session was closed?)\n",
-			inode, ceph_ino(inode), ceph_cap_string(mask));
+		pr_warn_client(cl, "%p %llx.%llx mask %s, "
+			       "but no auth cap (session was closed?)\n",
+				inode, ceph_vinop(inode),
+				ceph_cap_string(mask));
 		return 0;
 	}
 
-	dout("__mark_dirty_caps %p %s dirty %s -> %s\n", &ci->netfs.inode,
-	     ceph_cap_string(mask), ceph_cap_string(was),
-	     ceph_cap_string(was | mask));
+	doutc(cl, "%p %llx.%llx %s dirty %s -> %s\n", inode,
+	      ceph_vinop(inode), ceph_cap_string(mask),
+	      ceph_cap_string(was), ceph_cap_string(was | mask));
 	ci->i_dirty_caps |= mask;
 	if (was == 0) {
 		struct ceph_mds_session *session = ci->i_auth_cap->session;
@@ -1779,8 +1826,9 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
 			ci->i_head_snapc = ceph_get_snap_context(
 				ci->i_snap_realm->cached_context);
 		}
-		dout(" inode %p now dirty snapc %p auth cap %p\n",
-		     &ci->netfs.inode, ci->i_head_snapc, ci->i_auth_cap);
+		doutc(cl, "%p %llx.%llx now dirty snapc %p auth cap %p\n",
+		      inode, ceph_vinop(inode), ci->i_head_snapc,
+		      ci->i_auth_cap);
 		BUG_ON(!list_empty(&ci->i_dirty_item));
 		spin_lock(&mdsc->cap_dirty_lock);
 		list_add(&ci->i_dirty_item, &session->s_cap_dirty);
@@ -1873,7 +1921,8 @@ static u64 __mark_caps_flushing(struct inode *inode,
 				struct ceph_mds_session *session, bool wake,
 				u64 *oldest_flush_tid)
 {
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_cap_flush *cf = NULL;
 	int flushing;
@@ -1884,13 +1933,13 @@ static u64 __mark_caps_flushing(struct inode *inode,
 	BUG_ON(!ci->i_prealloc_cap_flush);
 
 	flushing = ci->i_dirty_caps;
-	dout("__mark_caps_flushing flushing %s, flushing_caps %s -> %s\n",
-	     ceph_cap_string(flushing),
-	     ceph_cap_string(ci->i_flushing_caps),
-	     ceph_cap_string(ci->i_flushing_caps | flushing));
+	doutc(cl, "flushing %s, flushing_caps %s -> %s\n",
+	      ceph_cap_string(flushing),
+	      ceph_cap_string(ci->i_flushing_caps),
+	      ceph_cap_string(ci->i_flushing_caps | flushing));
 	ci->i_flushing_caps |= flushing;
 	ci->i_dirty_caps = 0;
-	dout(" inode %p now !dirty\n", inode);
+	doutc(cl, "%p %llx.%llx now !dirty\n", inode, ceph_vinop(inode));
 
 	swap(cf, ci->i_prealloc_cap_flush);
 	cf->caps = flushing;
@@ -1921,6 +1970,7 @@ static int try_nonblocking_invalidate(struct inode *inode)
 	__releases(ci->i_ceph_lock)
 	__acquires(ci->i_ceph_lock)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	u32 invalidating_gen = ci->i_rdcache_gen;
 
@@ -1932,12 +1982,13 @@ static int try_nonblocking_invalidate(struct inode *inode)
 	if (inode->i_data.nrpages == 0 &&
 	    invalidating_gen == ci->i_rdcache_gen) {
 		/* success. */
-		dout("try_nonblocking_invalidate %p success\n", inode);
+		doutc(cl, "%p %llx.%llx success\n", inode,
+		      ceph_vinop(inode));
 		/* save any racing async invalidate some trouble */
 		ci->i_rdcache_revoking = ci->i_rdcache_gen - 1;
 		return 0;
 	}
-	dout("try_nonblocking_invalidate %p failed\n", inode);
+	doutc(cl, "%p %llx.%llx failed\n", inode, ceph_vinop(inode));
 	return -1;
 }
 
@@ -1969,6 +2020,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags)
 {
 	struct inode *inode = &ci->netfs.inode;
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_cap *cap;
 	u64 flush_tid, oldest_flush_tid;
 	int file_wanted, used, cap_used;
@@ -2043,9 +2095,9 @@ retry:
 		}
 	}
 
-	dout("check_caps %llx.%llx file_want %s used %s dirty %s flushing %s"
-	     " issued %s revoking %s retain %s %s%s%s\n", ceph_vinop(inode),
-	     ceph_cap_string(file_wanted),
+	doutc(cl, "%p %llx.%llx file_want %s used %s dirty %s "
+	      "flushing %s issued %s revoking %s retain %s %s%s%s\n",
+	     inode, ceph_vinop(inode), ceph_cap_string(file_wanted),
 	     ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps),
 	     ceph_cap_string(ci->i_flushing_caps),
 	     ceph_cap_string(issued), ceph_cap_string(revoking),
@@ -2066,10 +2118,10 @@ retry:
 	    (revoking & (CEPH_CAP_FILE_CACHE|
 			 CEPH_CAP_FILE_LAZYIO)) && /*  or revoking cache */
 	    !tried_invalidate) {
-		dout("check_caps trying to invalidate on %llx.%llx\n",
-		     ceph_vinop(inode));
+		doutc(cl, "trying to invalidate on %p %llx.%llx\n",
+		      inode, ceph_vinop(inode));
 		if (try_nonblocking_invalidate(inode) < 0) {
-			dout("check_caps queuing invalidate\n");
+			doutc(cl, "queuing invalidate\n");
 			queue_invalidate = true;
 			ci->i_rdcache_revoking = ci->i_rdcache_gen;
 		}
@@ -2097,35 +2149,35 @@ retry:
 			cap_used &= ~ci->i_auth_cap->issued;
 
 		revoking = cap->implemented & ~cap->issued;
-		dout(" mds%d cap %p used %s issued %s implemented %s revoking %s\n",
-		     cap->mds, cap, ceph_cap_string(cap_used),
-		     ceph_cap_string(cap->issued),
-		     ceph_cap_string(cap->implemented),
-		     ceph_cap_string(revoking));
+		doutc(cl, " mds%d cap %p used %s issued %s implemented %s revoking %s\n",
+		      cap->mds, cap, ceph_cap_string(cap_used),
+		      ceph_cap_string(cap->issued),
+		      ceph_cap_string(cap->implemented),
+		      ceph_cap_string(revoking));
 
 		if (cap == ci->i_auth_cap &&
 		    (cap->issued & CEPH_CAP_FILE_WR)) {
 			/* request larger max_size from MDS? */
 			if (ci->i_wanted_max_size > ci->i_max_size &&
 			    ci->i_wanted_max_size > ci->i_requested_max_size) {
-				dout("requesting new max_size\n");
+				doutc(cl, "requesting new max_size\n");
 				goto ack;
 			}
 
 			/* approaching file_max? */
 			if (__ceph_should_report_size(ci)) {
-				dout("i_size approaching max_size\n");
+				doutc(cl, "i_size approaching max_size\n");
 				goto ack;
 			}
 		}
 		/* flush anything dirty? */
 		if (cap == ci->i_auth_cap) {
 			if ((flags & CHECK_CAPS_FLUSH) && ci->i_dirty_caps) {
-				dout("flushing dirty caps\n");
+				doutc(cl, "flushing dirty caps\n");
 				goto ack;
 			}
 			if (ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS) {
-				dout("flushing snap caps\n");
+				doutc(cl, "flushing snap caps\n");
 				goto ack;
 			}
 		}
@@ -2133,7 +2185,7 @@ retry:
 		/* completed revocation? going down and there are no caps? */
 		if (revoking) {
 			if ((revoking & cap_used) == 0) {
-				dout("completed revocation of %s\n",
+				doutc(cl, "completed revocation of %s\n",
 				      ceph_cap_string(cap->implemented & ~cap->issued));
 				goto ack;
 			}
@@ -2232,7 +2284,7 @@ ack:
  */
 static int try_flush_caps(struct inode *inode, u64 *ptid)
 {
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int flushing = 0;
 	u64 flush_tid = 0, oldest_flush_tid = 0;
@@ -2310,7 +2362,8 @@ static int caps_are_flushed(struct inode *inode, u64 flush_tid)
  */
 static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode)
 {
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_request *req1 = NULL, *req2 = NULL;
 	int ret, err = 0;
@@ -2400,8 +2453,9 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode)
 		kfree(sessions);
 	}
 
-	dout("%s %p wait on tid %llu %llu\n", __func__,
-	     inode, req1 ? req1->r_tid : 0ULL, req2 ? req2->r_tid : 0ULL);
+	doutc(cl, "%p %llx.%llx wait on tid %llu %llu\n", inode,
+	      ceph_vinop(inode), req1 ? req1->r_tid : 0ULL,
+	      req2 ? req2->r_tid : 0ULL);
 	if (req1) {
 		ret = !wait_for_completion_timeout(&req1->r_safe_completion,
 					ceph_timeout_jiffies(req1->r_timeout));
@@ -2427,11 +2481,13 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct inode *inode = file->f_mapping->host;
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	u64 flush_tid;
 	int ret, err;
 	int dirty;
 
-	dout("fsync %p%s\n", inode, datasync ? " datasync" : "");
+	doutc(cl, "%p %llx.%llx%s\n", inode, ceph_vinop(inode),
+	      datasync ? " datasync" : "");
 
 	ret = file_write_and_wait_range(file, start, end);
 	if (datasync)
@@ -2442,7 +2498,7 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		goto out;
 
 	dirty = try_flush_caps(inode, &flush_tid);
-	dout("fsync dirty caps are %s\n", ceph_cap_string(dirty));
+	doutc(cl, "dirty caps are %s\n", ceph_cap_string(dirty));
 
 	err = flush_mdlog_and_wait_inode_unsafe_requests(inode);
 
@@ -2463,7 +2519,8 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	if (err < 0)
 		ret = err;
 out:
-	dout("fsync %p%s result=%d\n", inode, datasync ? " datasync" : "", ret);
+	doutc(cl, "%p %llx.%llx%s result=%d\n", inode, ceph_vinop(inode),
+	      datasync ? " datasync" : "", ret);
 	return ret;
 }
 
@@ -2476,12 +2533,13 @@ out:
 int ceph_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	u64 flush_tid;
 	int err = 0;
 	int dirty;
 	int wait = (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync);
 
-	dout("write_inode %p wait=%d\n", inode, wait);
+	doutc(cl, "%p %llx.%llx wait=%d\n", inode, ceph_vinop(inode), wait);
 	ceph_fscache_unpin_writeback(inode, wbc);
 	if (wait) {
 		err = ceph_wait_on_async_create(inode);
@@ -2493,7 +2551,7 @@ int ceph_write_inode(struct inode *inode, struct writeback_control *wbc)
 				       caps_are_flushed(inode, flush_tid));
 	} else {
 		struct ceph_mds_client *mdsc =
-			ceph_sb_to_client(inode->i_sb)->mdsc;
+			ceph_sb_to_fs_client(inode->i_sb)->mdsc;
 
 		spin_lock(&ci->i_ceph_lock);
 		if (__ceph_caps_dirty(ci))
@@ -2511,6 +2569,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
 	__acquires(ci->i_ceph_lock)
 {
 	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_cap *cap;
 	struct ceph_cap_flush *cf;
 	int ret;
@@ -2536,8 +2595,8 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
 
 		cap = ci->i_auth_cap;
 		if (!(cap && cap->session == session)) {
-			pr_err("%p auth cap %p not mds%d ???\n",
-			       inode, cap, session->s_mds);
+			pr_err_client(cl, "%p auth cap %p not mds%d ???\n",
+				      inode, cap, session->s_mds);
 			break;
 		}
 
@@ -2546,8 +2605,9 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
 		if (!cf->is_capsnap) {
 			struct cap_msg_args arg;
 
-			dout("kick_flushing_caps %p cap %p tid %llu %s\n",
-			     inode, cap, cf->tid, ceph_cap_string(cf->caps));
+			doutc(cl, "%p %llx.%llx cap %p tid %llu %s\n",
+			      inode, ceph_vinop(inode), cap, cf->tid,
+			      ceph_cap_string(cf->caps));
 			__prep_cap(&arg, cap, CEPH_CAP_OP_FLUSH,
 					 (cf->tid < last_snap_flush ?
 					  CEPH_CLIENT_CAPS_PENDING_CAPSNAP : 0),
@@ -2561,9 +2621,9 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
 			struct ceph_cap_snap *capsnap =
 					container_of(cf, struct ceph_cap_snap,
 						    cap_flush);
-			dout("kick_flushing_caps %p capsnap %p tid %llu %s\n",
-			     inode, capsnap, cf->tid,
-			     ceph_cap_string(capsnap->dirty));
+			doutc(cl, "%p %llx.%llx capsnap %p tid %llu %s\n",
+			      inode, ceph_vinop(inode), capsnap, cf->tid,
+			      ceph_cap_string(capsnap->dirty));
 
 			refcount_inc(&capsnap->nref);
 			spin_unlock(&ci->i_ceph_lock);
@@ -2571,11 +2631,10 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
 			ret = __send_flush_snap(inode, session, capsnap, cap->mseq,
 						oldest_flush_tid);
 			if (ret < 0) {
-				pr_err("kick_flushing_caps: error sending "
-					"cap flushsnap, ino (%llx.%llx) "
-					"tid %llu follows %llu\n",
-					ceph_vinop(inode), cf->tid,
-					capsnap->follows);
+				pr_err_client(cl, "error sending cap flushsnap,"
+					      " %p %llx.%llx tid %llu follows %llu\n",
+					      inode, ceph_vinop(inode), cf->tid,
+					      capsnap->follows);
 			}
 
 			ceph_put_cap_snap(capsnap);
@@ -2588,22 +2647,26 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
 void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
 				   struct ceph_mds_session *session)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_inode_info *ci;
 	struct ceph_cap *cap;
 	u64 oldest_flush_tid;
 
-	dout("early_kick_flushing_caps mds%d\n", session->s_mds);
+	doutc(cl, "mds%d\n", session->s_mds);
 
 	spin_lock(&mdsc->cap_dirty_lock);
 	oldest_flush_tid = __get_oldest_flush_tid(mdsc);
 	spin_unlock(&mdsc->cap_dirty_lock);
 
 	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
+		struct inode *inode = &ci->netfs.inode;
+
 		spin_lock(&ci->i_ceph_lock);
 		cap = ci->i_auth_cap;
 		if (!(cap && cap->session == session)) {
-			pr_err("%p auth cap %p not mds%d ???\n",
-				&ci->netfs.inode, cap, session->s_mds);
+			pr_err_client(cl, "%p %llx.%llx auth cap %p not mds%d ???\n",
+				      inode, ceph_vinop(inode), cap,
+				      session->s_mds);
 			spin_unlock(&ci->i_ceph_lock);
 			continue;
 		}
@@ -2636,24 +2699,28 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
 void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
 			     struct ceph_mds_session *session)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_inode_info *ci;
 	struct ceph_cap *cap;
 	u64 oldest_flush_tid;
 
 	lockdep_assert_held(&session->s_mutex);
 
-	dout("kick_flushing_caps mds%d\n", session->s_mds);
+	doutc(cl, "mds%d\n", session->s_mds);
 
 	spin_lock(&mdsc->cap_dirty_lock);
 	oldest_flush_tid = __get_oldest_flush_tid(mdsc);
 	spin_unlock(&mdsc->cap_dirty_lock);
 
 	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
+		struct inode *inode = &ci->netfs.inode;
+
 		spin_lock(&ci->i_ceph_lock);
 		cap = ci->i_auth_cap;
 		if (!(cap && cap->session == session)) {
-			pr_err("%p auth cap %p not mds%d ???\n",
-				&ci->netfs.inode, cap, session->s_mds);
+			pr_err_client(cl, "%p %llx.%llx auth cap %p not mds%d ???\n",
+				      inode, ceph_vinop(inode), cap,
+				      session->s_mds);
 			spin_unlock(&ci->i_ceph_lock);
 			continue;
 		}
@@ -2670,11 +2737,13 @@ void ceph_kick_flushing_inode_caps(struct ceph_mds_session *session,
 {
 	struct ceph_mds_client *mdsc = session->s_mdsc;
 	struct ceph_cap *cap = ci->i_auth_cap;
+	struct inode *inode = &ci->netfs.inode;
 
 	lockdep_assert_held(&ci->i_ceph_lock);
 
-	dout("%s %p flushing %s\n", __func__, &ci->netfs.inode,
-	     ceph_cap_string(ci->i_flushing_caps));
+	doutc(mdsc->fsc->client, "%p %llx.%llx flushing %s\n",
+	      inode, ceph_vinop(inode),
+	      ceph_cap_string(ci->i_flushing_caps));
 
 	if (!list_empty(&ci->i_cap_flush_list)) {
 		u64 oldest_flush_tid;
@@ -2696,6 +2765,9 @@ void ceph_kick_flushing_inode_caps(struct ceph_mds_session *session,
 void ceph_take_cap_refs(struct ceph_inode_info *ci, int got,
 			    bool snap_rwsem_locked)
 {
+	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+
 	lockdep_assert_held(&ci->i_ceph_lock);
 
 	if (got & CEPH_CAP_PIN)
@@ -2716,10 +2788,10 @@ void ceph_take_cap_refs(struct ceph_inode_info *ci, int got,
 	}
 	if (got & CEPH_CAP_FILE_BUFFER) {
 		if (ci->i_wb_ref == 0)
-			ihold(&ci->netfs.inode);
+			ihold(inode);
 		ci->i_wb_ref++;
-		dout("%s %p wb %d -> %d (?)\n", __func__,
-		     &ci->netfs.inode, ci->i_wb_ref-1, ci->i_wb_ref);
+		doutc(cl, "%p %llx.%llx wb %d -> %d (?)\n", inode,
+		      ceph_vinop(inode), ci->i_wb_ref-1, ci->i_wb_ref);
 	}
 }
 
@@ -2746,20 +2818,23 @@ static int try_get_cap_refs(struct inode *inode, int need, int want,
 			    loff_t endoff, int flags, int *got)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int ret = 0;
 	int have, implemented;
 	bool snap_rwsem_locked = false;
 
-	dout("get_cap_refs %p need %s want %s\n", inode,
-	     ceph_cap_string(need), ceph_cap_string(want));
+	doutc(cl, "%p %llx.%llx need %s want %s\n", inode,
+	      ceph_vinop(inode), ceph_cap_string(need),
+	      ceph_cap_string(want));
 
 again:
 	spin_lock(&ci->i_ceph_lock);
 
 	if ((flags & CHECK_FILELOCK) &&
 	    (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK)) {
-		dout("try_get_cap_refs %p error filelock\n", inode);
+		doutc(cl, "%p %llx.%llx error filelock\n", inode,
+		      ceph_vinop(inode));
 		ret = -EIO;
 		goto out_unlock;
 	}
@@ -2779,8 +2854,8 @@ again:
 
 	if (have & need & CEPH_CAP_FILE_WR) {
 		if (endoff >= 0 && endoff > (loff_t)ci->i_max_size) {
-			dout("get_cap_refs %p endoff %llu > maxsize %llu\n",
-			     inode, endoff, ci->i_max_size);
+			doutc(cl, "%p %llx.%llx endoff %llu > maxsize %llu\n",
+			      inode, ceph_vinop(inode), endoff, ci->i_max_size);
 			if (endoff > ci->i_requested_max_size)
 				ret = ci->i_auth_cap ? -EFBIG : -EUCLEAN;
 			goto out_unlock;
@@ -2790,7 +2865,8 @@ again:
 		 * can get a final snapshot value for size+mtime.
 		 */
 		if (__ceph_have_pending_cap_snap(ci)) {
-			dout("get_cap_refs %p cap_snap_pending\n", inode);
+			doutc(cl, "%p %llx.%llx cap_snap_pending\n", inode,
+			      ceph_vinop(inode));
 			goto out_unlock;
 		}
 	}
@@ -2808,9 +2884,9 @@ again:
 		int not = want & ~(have & need);
 		int revoking = implemented & ~have;
 		int exclude = revoking & not;
-		dout("get_cap_refs %p have %s but not %s (revoking %s)\n",
-		     inode, ceph_cap_string(have), ceph_cap_string(not),
-		     ceph_cap_string(revoking));
+		doutc(cl, "%p %llx.%llx have %s but not %s (revoking %s)\n",
+		      inode, ceph_vinop(inode), ceph_cap_string(have),
+		      ceph_cap_string(not), ceph_cap_string(revoking));
 		if (!exclude || !(exclude & CEPH_CAP_FILE_BUFFER)) {
 			if (!snap_rwsem_locked &&
 			    !ci->i_head_snapc &&
@@ -2850,28 +2926,31 @@ again:
 			spin_unlock(&s->s_cap_lock);
 		}
 		if (session_readonly) {
-			dout("get_cap_refs %p need %s but mds%d readonly\n",
-			     inode, ceph_cap_string(need), ci->i_auth_cap->mds);
+			doutc(cl, "%p %llx.%llx need %s but mds%d readonly\n",
+			      inode, ceph_vinop(inode), ceph_cap_string(need),
+			      ci->i_auth_cap->mds);
 			ret = -EROFS;
 			goto out_unlock;
 		}
 
 		if (ceph_inode_is_shutdown(inode)) {
-			dout("get_cap_refs %p inode is shutdown\n", inode);
+			doutc(cl, "%p %llx.%llx inode is shutdown\n",
+			      inode, ceph_vinop(inode));
 			ret = -ESTALE;
 			goto out_unlock;
 		}
 		mds_wanted = __ceph_caps_mds_wanted(ci, false);
 		if (need & ~mds_wanted) {
-			dout("get_cap_refs %p need %s > mds_wanted %s\n",
-			     inode, ceph_cap_string(need),
-			     ceph_cap_string(mds_wanted));
+			doutc(cl, "%p %llx.%llx need %s > mds_wanted %s\n",
+			      inode, ceph_vinop(inode), ceph_cap_string(need),
+			      ceph_cap_string(mds_wanted));
 			ret = -EUCLEAN;
 			goto out_unlock;
 		}
 
-		dout("get_cap_refs %p have %s need %s\n", inode,
-		     ceph_cap_string(have), ceph_cap_string(need));
+		doutc(cl, "%p %llx.%llx have %s need %s\n", inode,
+		      ceph_vinop(inode), ceph_cap_string(have),
+		      ceph_cap_string(need));
 	}
 out_unlock:
 
@@ -2886,8 +2965,8 @@ out_unlock:
 	else if (ret == 1)
 		ceph_update_cap_hit(&mdsc->metric);
 
-	dout("get_cap_refs %p ret %d got %s\n", inode,
-	     ret, ceph_cap_string(*got));
+	doutc(cl, "%p %llx.%llx ret %d got %s\n", inode,
+	      ceph_vinop(inode), ret, ceph_cap_string(*got));
 	return ret;
 }
 
@@ -2899,13 +2978,14 @@ out_unlock:
 static void check_max_size(struct inode *inode, loff_t endoff)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int check = 0;
 
 	/* do we need to explicitly request a larger max_size? */
 	spin_lock(&ci->i_ceph_lock);
 	if (endoff >= ci->i_max_size && endoff > ci->i_wanted_max_size) {
-		dout("write %p at large endoff %llu, req max_size\n",
-		     inode, endoff);
+		doutc(cl, "write %p %llx.%llx at large endoff %llu, req max_size\n",
+		      inode, ceph_vinop(inode), endoff);
 		ci->i_wanted_max_size = endoff;
 	}
 	/* duplicate ceph_check_caps()'s logic */
@@ -2964,7 +3044,7 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
 		    int want, loff_t endoff, int *got)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 	int ret, _got, flags;
 
 	ret = ceph_pool_perm_check(inode, need);
@@ -3115,10 +3195,12 @@ void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps)
 static int ceph_try_drop_cap_snap(struct ceph_inode_info *ci,
 				  struct ceph_cap_snap *capsnap)
 {
+	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+
 	if (!capsnap->need_flush &&
 	    !capsnap->writing && !capsnap->dirty_pages) {
-		dout("dropping cap_snap %p follows %llu\n",
-		     capsnap, capsnap->follows);
+		doutc(cl, "%p follows %llu\n", capsnap, capsnap->follows);
 		BUG_ON(capsnap->cap_flush.tid > 0);
 		ceph_put_snap_context(capsnap->context);
 		if (!list_is_last(&capsnap->ci_item, &ci->i_cap_snaps))
@@ -3150,6 +3232,7 @@ static void __ceph_put_cap_refs(struct ceph_inode_info *ci, int had,
 				enum put_cap_refs_mode mode)
 {
 	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int last = 0, put = 0, flushsnaps = 0, wake = 0;
 	bool check_flushsnaps = false;
 
@@ -3172,8 +3255,8 @@ static void __ceph_put_cap_refs(struct ceph_inode_info *ci, int had,
 			put++;
 			check_flushsnaps = true;
 		}
-		dout("put_cap_refs %p wb %d -> %d (?)\n",
-		     inode, ci->i_wb_ref+1, ci->i_wb_ref);
+		doutc(cl, "%p %llx.%llx wb %d -> %d (?)\n", inode,
+		      ceph_vinop(inode), ci->i_wb_ref+1, ci->i_wb_ref);
 	}
 	if (had & CEPH_CAP_FILE_WR) {
 		if (--ci->i_wr_ref == 0) {
@@ -3213,8 +3296,8 @@ static void __ceph_put_cap_refs(struct ceph_inode_info *ci, int had,
 	}
 	spin_unlock(&ci->i_ceph_lock);
 
-	dout("put_cap_refs %p had %s%s%s\n", inode, ceph_cap_string(had),
-	     last ? " last" : "", put ? " put" : "");
+	doutc(cl, "%p %llx.%llx had %s%s%s\n", inode, ceph_vinop(inode),
+	      ceph_cap_string(had), last ? " last" : "", put ? " put" : "");
 
 	switch (mode) {
 	case PUT_CAP_REFS_SYNC:
@@ -3264,6 +3347,7 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 				struct ceph_snap_context *snapc)
 {
 	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_cap_snap *capsnap = NULL, *iter;
 	int put = 0;
 	bool last = false;
@@ -3287,11 +3371,10 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 			ceph_put_snap_context(ci->i_head_snapc);
 			ci->i_head_snapc = NULL;
 		}
-		dout("put_wrbuffer_cap_refs on %p head %d/%d -> %d/%d %s\n",
-		     inode,
-		     ci->i_wrbuffer_ref+nr, ci->i_wrbuffer_ref_head+nr,
-		     ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
-		     last ? " LAST" : "");
+		doutc(cl, "on %p %llx.%llx head %d/%d -> %d/%d %s\n",
+		      inode, ceph_vinop(inode), ci->i_wrbuffer_ref+nr,
+		      ci->i_wrbuffer_ref_head+nr, ci->i_wrbuffer_ref,
+		      ci->i_wrbuffer_ref_head, last ? " LAST" : "");
 	} else {
 		list_for_each_entry(iter, &ci->i_cap_snaps, ci_item) {
 			if (iter->context == snapc) {
@@ -3321,13 +3404,12 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 				}
 			}
 		}
-		dout("put_wrbuffer_cap_refs on %p cap_snap %p "
-		     " snap %lld %d/%d -> %d/%d %s%s\n",
-		     inode, capsnap, capsnap->context->seq,
-		     ci->i_wrbuffer_ref+nr, capsnap->dirty_pages + nr,
-		     ci->i_wrbuffer_ref, capsnap->dirty_pages,
-		     last ? " (wrbuffer last)" : "",
-		     complete_capsnap ? " (complete capsnap)" : "");
+		doutc(cl, "%p %llx.%llx cap_snap %p snap %lld %d/%d -> %d/%d %s%s\n",
+		      inode, ceph_vinop(inode), capsnap, capsnap->context->seq,
+		      ci->i_wrbuffer_ref+nr, capsnap->dirty_pages + nr,
+		      ci->i_wrbuffer_ref, capsnap->dirty_pages,
+		      last ? " (wrbuffer last)" : "",
+		      complete_capsnap ? " (complete capsnap)" : "");
 	}
 
 unlock:
@@ -3350,9 +3432,10 @@ unlock:
  */
 static void invalidate_aliases(struct inode *inode)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct dentry *dn, *prev = NULL;
 
-	dout("invalidate_aliases inode %p\n", inode);
+	doutc(cl, "%p %llx.%llx\n", inode, ceph_vinop(inode));
 	d_prune_aliases(inode);
 	/*
 	 * For non-directory inode, d_find_alias() only returns
@@ -3411,6 +3494,7 @@ static void handle_cap_grant(struct inode *inode,
 	__releases(ci->i_ceph_lock)
 	__releases(session->s_mdsc->snap_rwsem)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int seq = le32_to_cpu(grant->seq);
 	int newcaps = le32_to_cpu(grant->caps);
@@ -3434,10 +3518,11 @@ static void handle_cap_grant(struct inode *inode,
 	if (IS_ENCRYPTED(inode) && size)
 		size = extra_info->fscrypt_file_size;
 
-	dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
-	     inode, cap, session->s_mds, seq, ceph_cap_string(newcaps));
-	dout(" size %llu max_size %llu, i_size %llu\n", size, max_size,
-		i_size_read(inode));
+	doutc(cl, "%p %llx.%llx cap %p mds%d seq %d %s\n", inode,
+	      ceph_vinop(inode), cap, session->s_mds, seq,
+	      ceph_cap_string(newcaps));
+	doutc(cl, " size %llu max_size %llu, i_size %llu\n", size,
+	      max_size, i_size_read(inode));
 
 
 	/*
@@ -3497,15 +3582,17 @@ static void handle_cap_grant(struct inode *inode,
 		inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
 		inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
 		ci->i_btime = extra_info->btime;
-		dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
-		     from_kuid(&init_user_ns, inode->i_uid),
-		     from_kgid(&init_user_ns, inode->i_gid));
+		doutc(cl, "%p %llx.%llx mode 0%o uid.gid %d.%d\n", inode,
+		      ceph_vinop(inode), inode->i_mode,
+		      from_kuid(&init_user_ns, inode->i_uid),
+		      from_kgid(&init_user_ns, inode->i_gid));
 #if IS_ENABLED(CONFIG_FS_ENCRYPTION)
 		if (ci->fscrypt_auth_len != extra_info->fscrypt_auth_len ||
 		    memcmp(ci->fscrypt_auth, extra_info->fscrypt_auth,
 			   ci->fscrypt_auth_len))
-			pr_warn_ratelimited("%s: cap grant attempt to change fscrypt_auth on non-I_NEW inode (old len %d new len %d)\n",
-				__func__, ci->fscrypt_auth_len,
+			pr_warn_ratelimited_client(cl,
+				"cap grant attempt to change fscrypt_auth on non-I_NEW inode (old len %d new len %d)\n",
+				ci->fscrypt_auth_len,
 				extra_info->fscrypt_auth_len);
 #endif
 	}
@@ -3523,8 +3610,8 @@ static void handle_cap_grant(struct inode *inode,
 		u64 version = le64_to_cpu(grant->xattr_version);
 
 		if (version > ci->i_xattrs.version) {
-			dout(" got new xattrs v%llu on %p len %d\n",
-			     version, inode, len);
+			doutc(cl, " got new xattrs v%llu on %p %llx.%llx len %d\n",
+			      version, inode, ceph_vinop(inode), len);
 			if (ci->i_xattrs.blob)
 				ceph_buffer_put(ci->i_xattrs.blob);
 			ci->i_xattrs.blob = ceph_buffer_get(xattr_buf);
@@ -3575,8 +3662,8 @@ static void handle_cap_grant(struct inode *inode,
 
 	if (ci->i_auth_cap == cap && (newcaps & CEPH_CAP_ANY_FILE_WR)) {
 		if (max_size != ci->i_max_size) {
-			dout("max_size %lld -> %llu\n",
-			     ci->i_max_size, max_size);
+			doutc(cl, "max_size %lld -> %llu\n", ci->i_max_size,
+			      max_size);
 			ci->i_max_size = max_size;
 			if (max_size >= ci->i_wanted_max_size) {
 				ci->i_wanted_max_size = 0;  /* reset */
@@ -3590,10 +3677,9 @@ static void handle_cap_grant(struct inode *inode,
 	wanted = __ceph_caps_wanted(ci);
 	used = __ceph_caps_used(ci);
 	dirty = __ceph_caps_dirty(ci);
-	dout(" my wanted = %s, used = %s, dirty %s\n",
-	     ceph_cap_string(wanted),
-	     ceph_cap_string(used),
-	     ceph_cap_string(dirty));
+	doutc(cl, " my wanted = %s, used = %s, dirty %s\n",
+	      ceph_cap_string(wanted), ceph_cap_string(used),
+	      ceph_cap_string(dirty));
 
 	if ((was_stale || le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) &&
 	    (wanted & ~(cap->mds_wanted | newcaps))) {
@@ -3614,10 +3700,9 @@ static void handle_cap_grant(struct inode *inode,
 	if (cap->issued & ~newcaps) {
 		int revoking = cap->issued & ~newcaps;
 
-		dout("revocation: %s -> %s (revoking %s)\n",
-		     ceph_cap_string(cap->issued),
-		     ceph_cap_string(newcaps),
-		     ceph_cap_string(revoking));
+		doutc(cl, "revocation: %s -> %s (revoking %s)\n",
+		      ceph_cap_string(cap->issued), ceph_cap_string(newcaps),
+		      ceph_cap_string(revoking));
 		if (S_ISREG(inode->i_mode) &&
 		    (revoking & used & CEPH_CAP_FILE_BUFFER))
 			writeback = true;  /* initiate writeback; will delay ack */
@@ -3635,11 +3720,12 @@ static void handle_cap_grant(struct inode *inode,
 		cap->issued = newcaps;
 		cap->implemented |= newcaps;
 	} else if (cap->issued == newcaps) {
-		dout("caps unchanged: %s -> %s\n",
-		     ceph_cap_string(cap->issued), ceph_cap_string(newcaps));
+		doutc(cl, "caps unchanged: %s -> %s\n",
+		      ceph_cap_string(cap->issued),
+		      ceph_cap_string(newcaps));
 	} else {
-		dout("grant: %s -> %s\n", ceph_cap_string(cap->issued),
-		     ceph_cap_string(newcaps));
+		doutc(cl, "grant: %s -> %s\n", ceph_cap_string(cap->issued),
+		      ceph_cap_string(newcaps));
 		/* non-auth MDS is revoking the newly grant caps ? */
 		if (cap == ci->i_auth_cap &&
 		    __ceph_caps_revoking_other(ci, cap, newcaps))
@@ -3727,7 +3813,8 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
 	__releases(ci->i_ceph_lock)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_cap_flush *cf, *tmp_cf;
 	LIST_HEAD(to_remove);
 	unsigned seq = le32_to_cpu(m->seq);
@@ -3764,11 +3851,11 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
 		}
 	}
 
-	dout("handle_cap_flush_ack inode %p mds%d seq %d on %s cleaned %s,"
-	     " flushing %s -> %s\n",
-	     inode, session->s_mds, seq, ceph_cap_string(dirty),
-	     ceph_cap_string(cleaned), ceph_cap_string(ci->i_flushing_caps),
-	     ceph_cap_string(ci->i_flushing_caps & ~cleaned));
+	doutc(cl, "%p %llx.%llx mds%d seq %d on %s cleaned %s, flushing %s -> %s\n",
+	      inode, ceph_vinop(inode), session->s_mds, seq,
+	      ceph_cap_string(dirty), ceph_cap_string(cleaned),
+	      ceph_cap_string(ci->i_flushing_caps),
+	      ceph_cap_string(ci->i_flushing_caps & ~cleaned));
 
 	if (list_empty(&to_remove) && !cleaned)
 		goto out;
@@ -3784,18 +3871,21 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
 		if (list_empty(&ci->i_cap_flush_list)) {
 			list_del_init(&ci->i_flushing_item);
 			if (!list_empty(&session->s_cap_flushing)) {
-				dout(" mds%d still flushing cap on %p\n",
-				     session->s_mds,
-				     &list_first_entry(&session->s_cap_flushing,
-						struct ceph_inode_info,
-						i_flushing_item)->netfs.inode);
+				struct inode *inode =
+					    &list_first_entry(&session->s_cap_flushing,
+							      struct ceph_inode_info,
+							      i_flushing_item)->netfs.inode;
+				doutc(cl, " mds%d still flushing cap on %p %llx.%llx\n",
+				      session->s_mds, inode, ceph_vinop(inode));
 			}
 		}
 		mdsc->num_cap_flushing--;
-		dout(" inode %p now !flushing\n", inode);
+		doutc(cl, " %p %llx.%llx now !flushing\n", inode,
+		      ceph_vinop(inode));
 
 		if (ci->i_dirty_caps == 0) {
-			dout(" inode %p now clean\n", inode);
+			doutc(cl, " %p %llx.%llx now clean\n", inode,
+			      ceph_vinop(inode));
 			BUG_ON(!list_empty(&ci->i_dirty_item));
 			drop = true;
 			if (ci->i_wr_ref == 0 &&
@@ -3833,12 +3923,14 @@ void __ceph_remove_capsnap(struct inode *inode, struct ceph_cap_snap *capsnap,
 			   bool *wake_ci, bool *wake_mdsc)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	bool ret;
 
 	lockdep_assert_held(&ci->i_ceph_lock);
 
-	dout("removing capsnap %p, inode %p ci %p\n", capsnap, inode, ci);
+	doutc(cl, "removing capsnap %p, %p %llx.%llx ci %p\n", capsnap,
+	      inode, ceph_vinop(inode), ci);
 
 	list_del_init(&capsnap->ci_item);
 	ret = __detach_cap_flush_from_ci(ci, &capsnap->cap_flush);
@@ -3877,29 +3969,31 @@ static void handle_cap_flushsnap_ack(struct inode *inode, u64 flush_tid,
 				     struct ceph_mds_session *session)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	u64 follows = le64_to_cpu(m->snap_follows);
 	struct ceph_cap_snap *capsnap = NULL, *iter;
 	bool wake_ci = false;
 	bool wake_mdsc = false;
 
-	dout("handle_cap_flushsnap_ack inode %p ci %p mds%d follows %lld\n",
-	     inode, ci, session->s_mds, follows);
+	doutc(cl, "%p %llx.%llx ci %p mds%d follows %lld\n", inode,
+	      ceph_vinop(inode), ci, session->s_mds, follows);
 
 	spin_lock(&ci->i_ceph_lock);
 	list_for_each_entry(iter, &ci->i_cap_snaps, ci_item) {
 		if (iter->follows == follows) {
 			if (iter->cap_flush.tid != flush_tid) {
-				dout(" cap_snap %p follows %lld tid %lld !="
-				     " %lld\n", iter, follows,
-				     flush_tid, iter->cap_flush.tid);
+				doutc(cl, " cap_snap %p follows %lld "
+				      "tid %lld != %lld\n", iter,
+				      follows, flush_tid,
+				      iter->cap_flush.tid);
 				break;
 			}
 			capsnap = iter;
 			break;
 		} else {
-			dout(" skipping cap_snap %p follows %lld\n",
-			     iter, iter->follows);
+			doutc(cl, " skipping cap_snap %p follows %lld\n",
+			      iter, iter->follows);
 		}
 	}
 	if (capsnap)
@@ -3928,6 +4022,7 @@ static bool handle_cap_trunc(struct inode *inode,
 			     struct cap_extra_info *extra_info)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int mds = session->s_mds;
 	int seq = le32_to_cpu(trunc->seq);
 	u32 truncate_seq = le32_to_cpu(trunc->truncate_seq);
@@ -3950,8 +4045,8 @@ static bool handle_cap_trunc(struct inode *inode,
 	if (IS_ENCRYPTED(inode) && size)
 		size = extra_info->fscrypt_file_size;
 
-	dout("%s inode %p mds%d seq %d to %lld truncate seq %d\n",
-	     __func__, inode, mds, seq, truncate_size, truncate_seq);
+	doutc(cl, "%p %llx.%llx mds%d seq %d to %lld truncate seq %d\n",
+	      inode, ceph_vinop(inode), mds, seq, truncate_size, truncate_seq);
 	queue_trunc = ceph_fill_file_size(inode, issued,
 					  truncate_seq, truncate_size, size);
 	return queue_trunc;
@@ -3969,7 +4064,8 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
 			      struct ceph_mds_cap_peer *ph,
 			      struct ceph_mds_session *session)
 {
-	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_session *tsession = NULL;
 	struct ceph_cap *cap, *tcap, *new_cap = NULL;
 	struct ceph_inode_info *ci = ceph_inode(inode);
@@ -3989,8 +4085,8 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
 		target = -1;
 	}
 
-	dout("handle_cap_export inode %p ci %p mds%d mseq %d target %d\n",
-	     inode, ci, mds, mseq, target);
+	doutc(cl, "%p %llx.%llx ci %p mds%d mseq %d target %d\n",
+	      inode, ceph_vinop(inode), ci, mds, mseq, target);
 retry:
 	down_read(&mdsc->snap_rwsem);
 	spin_lock(&ci->i_ceph_lock);
@@ -3999,7 +4095,7 @@ retry:
 		goto out_unlock;
 
 	if (target < 0) {
-		ceph_remove_cap(cap, false);
+		ceph_remove_cap(mdsc, cap, false);
 		goto out_unlock;
 	}
 
@@ -4010,12 +4106,13 @@ retry:
 
 	issued = cap->issued;
 	if (issued != cap->implemented)
-		pr_err_ratelimited("handle_cap_export: issued != implemented: "
-				"ino (%llx.%llx) mds%d seq %d mseq %d "
-				"issued %s implemented %s\n",
-				ceph_vinop(inode), mds, cap->seq, cap->mseq,
-				ceph_cap_string(issued),
-				ceph_cap_string(cap->implemented));
+		pr_err_ratelimited_client(cl, "issued != implemented: "
+					  "%p %llx.%llx mds%d seq %d mseq %d"
+					  " issued %s implemented %s\n",
+					  inode, ceph_vinop(inode), mds,
+					  cap->seq, cap->mseq,
+					  ceph_cap_string(issued),
+					  ceph_cap_string(cap->implemented));
 
 
 	tcap = __get_cap_for_mds(ci, target);
@@ -4023,7 +4120,8 @@ retry:
 		/* already have caps from the target */
 		if (tcap->cap_id == t_cap_id &&
 		    ceph_seq_cmp(tcap->seq, t_seq) < 0) {
-			dout(" updating import cap %p mds%d\n", tcap, target);
+			doutc(cl, " updating import cap %p mds%d\n", tcap,
+			      target);
 			tcap->cap_id = t_cap_id;
 			tcap->seq = t_seq - 1;
 			tcap->issue_seq = t_seq - 1;
@@ -4034,7 +4132,7 @@ retry:
 				change_auth_cap_ses(ci, tcap->session);
 			}
 		}
-		ceph_remove_cap(cap, false);
+		ceph_remove_cap(mdsc, cap, false);
 		goto out_unlock;
 	} else if (tsession) {
 		/* add placeholder for the export tagert */
@@ -4051,7 +4149,7 @@ retry:
 			spin_unlock(&mdsc->cap_dirty_lock);
 		}
 
-		ceph_remove_cap(cap, false);
+		ceph_remove_cap(mdsc, cap, false);
 		goto out_unlock;
 	}
 
@@ -4104,6 +4202,7 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
 			      struct ceph_cap **target_cap, int *old_issued)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_cap *cap, *ocap, *new_cap = NULL;
 	int mds = session->s_mds;
 	int issued;
@@ -4124,8 +4223,8 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
 		peer = -1;
 	}
 
-	dout("handle_cap_import inode %p ci %p mds%d mseq %d peer %d\n",
-	     inode, ci, mds, mseq, peer);
+	doutc(cl, "%p %llx.%llx ci %p mds%d mseq %d peer %d\n",
+	      inode, ceph_vinop(inode), ci, mds, mseq, peer);
 retry:
 	cap = __get_cap_for_mds(ci, mds);
 	if (!cap) {
@@ -4151,20 +4250,20 @@ retry:
 
 	ocap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
 	if (ocap && ocap->cap_id == p_cap_id) {
-		dout(" remove export cap %p mds%d flags %d\n",
-		     ocap, peer, ph->flags);
+		doutc(cl, " remove export cap %p mds%d flags %d\n",
+		      ocap, peer, ph->flags);
 		if ((ph->flags & CEPH_CAP_FLAG_AUTH) &&
 		    (ocap->seq != le32_to_cpu(ph->seq) ||
 		     ocap->mseq != le32_to_cpu(ph->mseq))) {
-			pr_err_ratelimited("handle_cap_import: "
-					"mismatched seq/mseq: ino (%llx.%llx) "
-					"mds%d seq %d mseq %d importer mds%d "
-					"has peer seq %d mseq %d\n",
-					ceph_vinop(inode), peer, ocap->seq,
-					ocap->mseq, mds, le32_to_cpu(ph->seq),
+			pr_err_ratelimited_client(cl, "mismatched seq/mseq: "
+					"%p %llx.%llx mds%d seq %d mseq %d"
+					" importer mds%d has peer seq %d mseq %d\n",
+					inode, ceph_vinop(inode), peer,
+					ocap->seq, ocap->mseq, mds,
+					le32_to_cpu(ph->seq),
 					le32_to_cpu(ph->mseq));
 		}
-		ceph_remove_cap(ocap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
+		ceph_remove_cap(mdsc, ocap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
 	}
 
 	*old_issued = issued;
@@ -4227,6 +4326,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		      struct ceph_msg *msg)
 {
 	struct ceph_mds_client *mdsc = session->s_mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct inode *inode;
 	struct ceph_inode_info *ci;
 	struct ceph_cap *cap;
@@ -4245,7 +4345,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	bool close_sessions = false;
 	bool do_cap_release = false;
 
-	dout("handle_caps from mds%d\n", session->s_mds);
+	doutc(cl, "from mds%d\n", session->s_mds);
 
 	if (!ceph_inc_mds_stopping_blocker(mdsc, session))
 		return;
@@ -4347,15 +4447,15 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 
 	/* lookup ino */
 	inode = ceph_find_inode(mdsc->fsc->sb, vino);
-	dout(" op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op), vino.ino,
-	     vino.snap, inode);
+	doutc(cl, " op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op),
+	      vino.ino, vino.snap, inode);
 
 	mutex_lock(&session->s_mutex);
-	dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq,
-	     (unsigned)seq);
+	doutc(cl, " mds%d seq %lld cap seq %u\n", session->s_mds,
+	      session->s_seq, (unsigned)seq);
 
 	if (!inode) {
-		dout(" i don't have ino %llx\n", vino.ino);
+		doutc(cl, " i don't have ino %llx\n", vino.ino);
 
 		switch (op) {
 		case CEPH_CAP_OP_IMPORT:
@@ -4410,9 +4510,9 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	spin_lock(&ci->i_ceph_lock);
 	cap = __get_cap_for_mds(ceph_inode(inode), session->s_mds);
 	if (!cap) {
-		dout(" no cap on %p ino %llx.%llx from mds%d\n",
-		     inode, ceph_ino(inode), ceph_snap(inode),
-		     session->s_mds);
+		doutc(cl, " no cap on %p ino %llx.%llx from mds%d\n",
+		      inode, ceph_ino(inode), ceph_snap(inode),
+		      session->s_mds);
 		spin_unlock(&ci->i_ceph_lock);
 		switch (op) {
 		case CEPH_CAP_OP_REVOKE:
@@ -4450,8 +4550,8 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 
 	default:
 		spin_unlock(&ci->i_ceph_lock);
-		pr_err("ceph_handle_caps: unknown cap op %d %s\n", op,
-		       ceph_cap_op_name(op));
+		pr_err_client(cl, "unknown cap op %d %s\n", op,
+			      ceph_cap_op_name(op));
 	}
 
 done:
@@ -4492,7 +4592,7 @@ flush_cap_releases:
 	goto done;
 
 bad:
-	pr_err("ceph_handle_caps: corrupt message\n");
+	pr_err_client(cl, "corrupt message\n");
 	ceph_msg_dump(msg);
 	goto out;
 }
@@ -4506,6 +4606,7 @@ bad:
  */
 unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct inode *inode;
 	struct ceph_inode_info *ci;
 	struct ceph_mount_options *opt = mdsc->fsc->mount_options;
@@ -4513,14 +4614,14 @@ unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
 	unsigned long loop_start = jiffies;
 	unsigned long delay = 0;
 
-	dout("check_delayed_caps\n");
+	doutc(cl, "begin\n");
 	spin_lock(&mdsc->cap_delay_lock);
 	while (!list_empty(&mdsc->cap_delay_list)) {
 		ci = list_first_entry(&mdsc->cap_delay_list,
 				      struct ceph_inode_info,
 				      i_cap_delay_list);
 		if (time_before(loop_start, ci->i_hold_caps_max - delay_max)) {
-			dout("%s caps added recently.  Exiting loop", __func__);
+			doutc(cl, "caps added recently.  Exiting loop");
 			delay = ci->i_hold_caps_max;
 			break;
 		}
@@ -4532,13 +4633,15 @@ unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
 		inode = igrab(&ci->netfs.inode);
 		if (inode) {
 			spin_unlock(&mdsc->cap_delay_lock);
-			dout("check_delayed_caps on %p\n", inode);
+			doutc(cl, "on %p %llx.%llx\n", inode,
+			      ceph_vinop(inode));
 			ceph_check_caps(ci, 0);
 			iput(inode);
 			spin_lock(&mdsc->cap_delay_lock);
 		}
 	}
 	spin_unlock(&mdsc->cap_delay_lock);
+	doutc(cl, "done\n");
 
 	return delay;
 }
@@ -4549,17 +4652,18 @@ unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
 static void flush_dirty_session_caps(struct ceph_mds_session *s)
 {
 	struct ceph_mds_client *mdsc = s->s_mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_inode_info *ci;
 	struct inode *inode;
 
-	dout("flush_dirty_caps\n");
+	doutc(cl, "begin\n");
 	spin_lock(&mdsc->cap_dirty_lock);
 	while (!list_empty(&s->s_cap_dirty)) {
 		ci = list_first_entry(&s->s_cap_dirty, struct ceph_inode_info,
 				      i_dirty_item);
 		inode = &ci->netfs.inode;
 		ihold(inode);
-		dout("flush_dirty_caps %llx.%llx\n", ceph_vinop(inode));
+		doutc(cl, "%p %llx.%llx\n", inode, ceph_vinop(inode));
 		spin_unlock(&mdsc->cap_dirty_lock);
 		ceph_wait_on_async_create(inode);
 		ceph_check_caps(ci, CHECK_CAPS_FLUSH);
@@ -4567,7 +4671,7 @@ static void flush_dirty_session_caps(struct ceph_mds_session *s)
 		spin_lock(&mdsc->cap_dirty_lock);
 	}
 	spin_unlock(&mdsc->cap_dirty_lock);
-	dout("flush_dirty_caps done\n");
+	doutc(cl, "done\n");
 }
 
 void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc)
@@ -4672,7 +4776,7 @@ int ceph_drop_caps_for_unlink(struct inode *inode)
 
 		if (__ceph_caps_dirty(ci)) {
 			struct ceph_mds_client *mdsc =
-				ceph_inode_to_client(inode)->mdsc;
+				ceph_inode_to_fs_client(inode)->mdsc;
 			__cap_delay_requeue_front(mdsc, ci);
 		}
 	}
@@ -4692,6 +4796,7 @@ int ceph_encode_inode_release(void **p, struct inode *inode,
 			      int mds, int drop, int unless, int force)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_cap *cap;
 	struct ceph_mds_request_release *rel = *p;
 	int used, dirty;
@@ -4701,9 +4806,9 @@ int ceph_encode_inode_release(void **p, struct inode *inode,
 	used = __ceph_caps_used(ci);
 	dirty = __ceph_caps_dirty(ci);
 
-	dout("encode_inode_release %p mds%d used|dirty %s drop %s unless %s\n",
-	     inode, mds, ceph_cap_string(used|dirty), ceph_cap_string(drop),
-	     ceph_cap_string(unless));
+	doutc(cl, "%p %llx.%llx mds%d used|dirty %s drop %s unless %s\n",
+	      inode, ceph_vinop(inode), mds, ceph_cap_string(used|dirty),
+	      ceph_cap_string(drop), ceph_cap_string(unless));
 
 	/* only drop unused, clean caps */
 	drop &= ~(used | dirty);
@@ -4725,12 +4830,13 @@ int ceph_encode_inode_release(void **p, struct inode *inode,
 		if (force || (cap->issued & drop)) {
 			if (cap->issued & drop) {
 				int wanted = __ceph_caps_wanted(ci);
-				dout("encode_inode_release %p cap %p "
-				     "%s -> %s, wanted %s -> %s\n", inode, cap,
-				     ceph_cap_string(cap->issued),
-				     ceph_cap_string(cap->issued & ~drop),
-				     ceph_cap_string(cap->mds_wanted),
-				     ceph_cap_string(wanted));
+				doutc(cl, "%p %llx.%llx cap %p %s -> %s, "
+				      "wanted %s -> %s\n", inode,
+				      ceph_vinop(inode), cap,
+				      ceph_cap_string(cap->issued),
+				      ceph_cap_string(cap->issued & ~drop),
+				      ceph_cap_string(cap->mds_wanted),
+				      ceph_cap_string(wanted));
 
 				cap->issued &= ~drop;
 				cap->implemented &= ~drop;
@@ -4739,9 +4845,9 @@ int ceph_encode_inode_release(void **p, struct inode *inode,
 				    !(wanted & CEPH_CAP_ANY_FILE_WR))
 					ci->i_requested_max_size = 0;
 			} else {
-				dout("encode_inode_release %p cap %p %s"
-				     " (force)\n", inode, cap,
-				     ceph_cap_string(cap->issued));
+				doutc(cl, "%p %llx.%llx cap %p %s (force)\n",
+				      inode, ceph_vinop(inode), cap,
+				      ceph_cap_string(cap->issued));
 			}
 
 			rel->ino = cpu_to_le64(ceph_ino(inode));
@@ -4756,8 +4862,9 @@ int ceph_encode_inode_release(void **p, struct inode *inode,
 			*p += sizeof(*rel);
 			ret = 1;
 		} else {
-			dout("encode_inode_release %p cap %p %s (noop)\n",
-			     inode, cap, ceph_cap_string(cap->issued));
+			doutc(cl, "%p %llx.%llx cap %p %s (noop)\n",
+			      inode, ceph_vinop(inode), cap,
+			      ceph_cap_string(cap->issued));
 		}
 	}
 	spin_unlock(&ci->i_ceph_lock);
@@ -4783,6 +4890,7 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry,
 	struct dentry *parent = NULL;
 	struct ceph_mds_request_release *rel = *p;
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
+	struct ceph_client *cl;
 	int force = 0;
 	int ret;
 
@@ -4804,10 +4912,11 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry,
 	ret = ceph_encode_inode_release(p, dir, mds, drop, unless, force);
 	dput(parent);
 
+	cl = ceph_inode_to_client(dir);
 	spin_lock(&dentry->d_lock);
 	if (ret && di->lease_session && di->lease_session->s_mds == mds) {
-		dout("encode_dentry_release %p mds%d seq %d\n",
-		     dentry, mds, (int)di->lease_seq);
+		doutc(cl, "%p mds%d seq %d\n",  dentry, mds,
+		      (int)di->lease_seq);
 		rel->dname_seq = cpu_to_le32(di->lease_seq);
 		__ceph_mdsc_drop_dentry_lease(dentry);
 		spin_unlock(&dentry->d_lock);
@@ -4833,12 +4942,14 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry,
 static int remove_capsnaps(struct ceph_mds_client *mdsc, struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_cap_snap *capsnap;
 	int capsnap_release = 0;
 
 	lockdep_assert_held(&ci->i_ceph_lock);
 
-	dout("removing capsnaps, ci is %p, inode is %p\n", ci, inode);
+	doutc(cl, "removing capsnaps, ci is %p, %p %llx.%llx\n",
+	      ci, inode, ceph_vinop(inode));
 
 	while (!list_empty(&ci->i_cap_snaps)) {
 		capsnap = list_first_entry(&ci->i_cap_snaps,
@@ -4855,8 +4966,9 @@ static int remove_capsnaps(struct ceph_mds_client *mdsc, struct inode *inode)
 
 int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate)
 {
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_client *cl = fsc->client;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	bool is_auth;
 	bool dirty_dropped = false;
@@ -4864,8 +4976,8 @@ int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invali
 
 	lockdep_assert_held(&ci->i_ceph_lock);
 
-	dout("removing cap %p, ci is %p, inode is %p\n",
-	     cap, ci, &ci->netfs.inode);
+	doutc(cl, "removing cap %p, ci is %p, %p %llx.%llx\n",
+	      cap, ci, inode, ceph_vinop(inode));
 
 	is_auth = (cap == ci->i_auth_cap);
 	__ceph_remove_cap(cap, false);
@@ -4892,19 +5004,19 @@ int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invali
 		}
 
 		if (!list_empty(&ci->i_dirty_item)) {
-			pr_warn_ratelimited(
-				" dropping dirty %s state for %p %lld\n",
+			pr_warn_ratelimited_client(cl,
+				" dropping dirty %s state for %p %llx.%llx\n",
 				ceph_cap_string(ci->i_dirty_caps),
-				inode, ceph_ino(inode));
+				inode, ceph_vinop(inode));
 			ci->i_dirty_caps = 0;
 			list_del_init(&ci->i_dirty_item);
 			dirty_dropped = true;
 		}
 		if (!list_empty(&ci->i_flushing_item)) {
-			pr_warn_ratelimited(
-				" dropping dirty+flushing %s state for %p %lld\n",
+			pr_warn_ratelimited_client(cl,
+				" dropping dirty+flushing %s state for %p %llx.%llx\n",
 				ceph_cap_string(ci->i_flushing_caps),
-				inode, ceph_ino(inode));
+				inode, ceph_vinop(inode));
 			ci->i_flushing_caps = 0;
 			list_del_init(&ci->i_flushing_item);
 			mdsc->num_cap_flushing--;
@@ -4927,8 +5039,9 @@ int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invali
 		if (atomic_read(&ci->i_filelock_ref) > 0) {
 			/* make further file lock syscall return -EIO */
 			ci->i_ceph_flags |= CEPH_I_ERROR_FILELOCK;
-			pr_warn_ratelimited(" dropping file locks for %p %lld\n",
-					    inode, ceph_ino(inode));
+			pr_warn_ratelimited_client(cl,
+				" dropping file locks for %p %llx.%llx\n",
+				inode, ceph_vinop(inode));
 		}
 
 		if (!ci->i_dirty_caps && ci->i_prealloc_cap_flush) {
diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index e3b1c3fab4127f..3b3c4d8d401ece 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -113,7 +113,7 @@ static int ceph_crypt_set_context(struct inode *inode, const void *ctx,
 
 	cia.fscrypt_auth = cfa;
 
-	ret = __ceph_setattr(inode, &attr, &cia);
+	ret = __ceph_setattr(&nop_mnt_idmap, inode, &attr, &cia);
 	if (ret == 0)
 		inode_set_flags(inode, S_ENCRYPTED, S_ENCRYPTED);
 	kfree(cia.fscrypt_auth);
@@ -129,7 +129,7 @@ static bool ceph_crypt_empty_dir(struct inode *inode)
 
 static const union fscrypt_policy *ceph_get_dummy_policy(struct super_block *sb)
 {
-	return ceph_sb_to_client(sb)->fsc_dummy_enc_policy.policy;
+	return ceph_sb_to_fs_client(sb)->fsc_dummy_enc_policy.policy;
 }
 
 static struct fscrypt_operations ceph_fscrypt_ops = {
@@ -212,6 +212,7 @@ void ceph_fscrypt_as_ctx_to_req(struct ceph_mds_request *req,
 static struct inode *parse_longname(const struct inode *parent,
 				    const char *name, int *name_len)
 {
+	struct ceph_client *cl = ceph_inode_to_client(parent);
 	struct inode *dir = NULL;
 	struct ceph_vino vino = { .snap = CEPH_NOSNAP };
 	char *inode_number;
@@ -223,12 +224,12 @@ static struct inode *parse_longname(const struct inode *parent,
 	name++;
 	name_end = strrchr(name, '_');
 	if (!name_end) {
-		dout("Failed to parse long snapshot name: %s\n", name);
+		doutc(cl, "failed to parse long snapshot name: %s\n", name);
 		return ERR_PTR(-EIO);
 	}
 	*name_len = (name_end - name);
 	if (*name_len <= 0) {
-		pr_err("Failed to parse long snapshot name\n");
+		pr_err_client(cl, "failed to parse long snapshot name\n");
 		return ERR_PTR(-EIO);
 	}
 
@@ -240,7 +241,7 @@ static struct inode *parse_longname(const struct inode *parent,
 		return ERR_PTR(-ENOMEM);
 	ret = kstrtou64(inode_number, 10, &vino.ino);
 	if (ret) {
-		dout("Failed to parse inode number: %s\n", name);
+		doutc(cl, "failed to parse inode number: %s\n", name);
 		dir = ERR_PTR(ret);
 		goto out;
 	}
@@ -251,7 +252,7 @@ static struct inode *parse_longname(const struct inode *parent,
 		/* This can happen if we're not mounting cephfs on the root */
 		dir = ceph_get_inode(parent->i_sb, vino, NULL);
 		if (IS_ERR(dir))
-			dout("Can't find inode %s (%s)\n", inode_number, name);
+			doutc(cl, "can't find inode %s (%s)\n", inode_number, name);
 	}
 
 out:
@@ -262,6 +263,7 @@ out:
 int ceph_encode_encrypted_dname(struct inode *parent, struct qstr *d_name,
 				char *buf)
 {
+	struct ceph_client *cl = ceph_inode_to_client(parent);
 	struct inode *dir = parent;
 	struct qstr iname;
 	u32 len;
@@ -330,7 +332,7 @@ int ceph_encode_encrypted_dname(struct inode *parent, struct qstr *d_name,
 
 	/* base64 encode the encrypted name */
 	elen = ceph_base64_encode(cryptbuf, len, buf);
-	dout("base64-encoded ciphertext name = %.*s\n", elen, buf);
+	doutc(cl, "base64-encoded ciphertext name = %.*s\n", elen, buf);
 
 	/* To understand the 240 limit, see CEPH_NOHASH_NAME_MAX comments */
 	WARN_ON(elen > 240);
@@ -505,7 +507,10 @@ int ceph_fscrypt_decrypt_block_inplace(const struct inode *inode,
 				  struct page *page, unsigned int len,
 				  unsigned int offs, u64 lblk_num)
 {
-	dout("%s: len %u offs %u blk %llu\n", __func__, len, offs, lblk_num);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+
+	doutc(cl, "%p %llx.%llx len %u offs %u blk %llu\n", inode,
+	      ceph_vinop(inode), len, offs, lblk_num);
 	return fscrypt_decrypt_block_inplace(inode, page, len, offs, lblk_num);
 }
 
@@ -514,7 +519,10 @@ int ceph_fscrypt_encrypt_block_inplace(const struct inode *inode,
 				  unsigned int offs, u64 lblk_num,
 				  gfp_t gfp_flags)
 {
-	dout("%s: len %u offs %u blk %llu\n", __func__, len, offs, lblk_num);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
+
+	doutc(cl, "%p %llx.%llx len %u offs %u blk %llu\n", inode,
+	      ceph_vinop(inode), len, offs, lblk_num);
 	return fscrypt_encrypt_block_inplace(inode, page, len, offs, lblk_num,
 					     gfp_flags);
 }
@@ -583,6 +591,7 @@ int ceph_fscrypt_decrypt_extents(struct inode *inode, struct page **page,
 				 u64 off, struct ceph_sparse_extent *map,
 				 u32 ext_cnt)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int i, ret = 0;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	u64 objno, objoff;
@@ -590,7 +599,8 @@ int ceph_fscrypt_decrypt_extents(struct inode *inode, struct page **page,
 
 	/* Nothing to do for empty array */
 	if (ext_cnt == 0) {
-		dout("%s: empty array, ret 0\n", __func__);
+		doutc(cl, "%p %llx.%llx empty array, ret 0\n", inode,
+		      ceph_vinop(inode));
 		return 0;
 	}
 
@@ -604,14 +614,17 @@ int ceph_fscrypt_decrypt_extents(struct inode *inode, struct page **page,
 		int fret;
 
 		if ((ext->off | ext->len) & ~CEPH_FSCRYPT_BLOCK_MASK) {
-			pr_warn("%s: bad encrypted sparse extent idx %d off %llx len %llx\n",
-				__func__, i, ext->off, ext->len);
+			pr_warn_client(cl,
+				"%p %llx.%llx bad encrypted sparse extent "
+				"idx %d off %llx len %llx\n",
+				inode, ceph_vinop(inode), i, ext->off,
+				ext->len);
 			return -EIO;
 		}
 		fret = ceph_fscrypt_decrypt_pages(inode, &page[pgidx],
 						 off + pgsoff, ext->len);
-		dout("%s: [%d] 0x%llx~0x%llx fret %d\n", __func__, i,
-				ext->off, ext->len, fret);
+		doutc(cl, "%p %llx.%llx [%d] 0x%llx~0x%llx fret %d\n", inode,
+		      ceph_vinop(inode), i, ext->off, ext->len, fret);
 		if (fret < 0) {
 			if (ret == 0)
 				ret = fret;
@@ -619,7 +632,7 @@ int ceph_fscrypt_decrypt_extents(struct inode *inode, struct page **page,
 		}
 		ret = pgsoff + fret;
 	}
-	dout("%s: ret %d\n", __func__, ret);
+	doutc(cl, "ret %d\n", ret);
 	return ret;
 }
 
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 3904333fa6c38b..24c08078f5aa3e 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -81,7 +81,7 @@ static int mdsc_show(struct seq_file *s, void *p)
 		if (req->r_inode) {
 			seq_printf(s, " #%llx", ceph_ino(req->r_inode));
 		} else if (req->r_dentry) {
-			path = ceph_mdsc_build_path(req->r_dentry, &pathlen,
+			path = ceph_mdsc_build_path(mdsc, req->r_dentry, &pathlen,
 						    &pathbase, 0);
 			if (IS_ERR(path))
 				path = NULL;
@@ -100,7 +100,7 @@ static int mdsc_show(struct seq_file *s, void *p)
 		}
 
 		if (req->r_old_dentry) {
-			path = ceph_mdsc_build_path(req->r_old_dentry, &pathlen,
+			path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &pathlen,
 						    &pathbase, 0);
 			if (IS_ERR(path))
 				path = NULL;
@@ -398,7 +398,7 @@ DEFINE_SIMPLE_ATTRIBUTE(congestion_kb_fops, congestion_kb_get,
 
 void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
 {
-	dout("ceph_fs_debugfs_cleanup\n");
+	doutc(fsc->client, "begin\n");
 	debugfs_remove(fsc->debugfs_bdi);
 	debugfs_remove(fsc->debugfs_congestion_kb);
 	debugfs_remove(fsc->debugfs_mdsmap);
@@ -407,13 +407,14 @@ void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
 	debugfs_remove(fsc->debugfs_status);
 	debugfs_remove(fsc->debugfs_mdsc);
 	debugfs_remove_recursive(fsc->debugfs_metrics_dir);
+	doutc(fsc->client, "done\n");
 }
 
 void ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 {
 	char name[100];
 
-	dout("ceph_fs_debugfs_init\n");
+	doutc(fsc->client, "begin\n");
 	fsc->debugfs_congestion_kb =
 		debugfs_create_file("writeback_congestion_kb",
 				    0600,
@@ -469,6 +470,7 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 			    &metrics_size_fops);
 	debugfs_create_file("caps", 0400, fsc->debugfs_metrics_dir, fsc,
 			    &metrics_caps_fops);
+	doutc(fsc->client, "done\n");
 }
 
 
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 854cbdd666619a..91709934c8b143 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -109,7 +109,9 @@ static int fpos_cmp(loff_t l, loff_t r)
  * regardless of what dir changes take place on the
  * server.
  */
-static int note_last_dentry(struct ceph_dir_file_info *dfi, const char *name,
+static int note_last_dentry(struct ceph_fs_client *fsc,
+			    struct ceph_dir_file_info *dfi,
+			    const char *name,
 		            int len, unsigned next_offset)
 {
 	char *buf = kmalloc(len+1, GFP_KERNEL);
@@ -120,7 +122,7 @@ static int note_last_dentry(struct ceph_dir_file_info *dfi, const char *name,
 	memcpy(dfi->last_name, name, len);
 	dfi->last_name[len] = 0;
 	dfi->next_offset = next_offset;
-	dout("note_last_dentry '%s'\n", dfi->last_name);
+	doutc(fsc->client, "'%s'\n", dfi->last_name);
 	return 0;
 }
 
@@ -130,6 +132,7 @@ __dcache_find_get_entry(struct dentry *parent, u64 idx,
 			struct ceph_readdir_cache_control *cache_ctl)
 {
 	struct inode *dir = d_inode(parent);
+	struct ceph_client *cl = ceph_inode_to_client(dir);
 	struct dentry *dentry;
 	unsigned idx_mask = (PAGE_SIZE / sizeof(struct dentry *)) - 1;
 	loff_t ptr_pos = idx * sizeof(struct dentry *);
@@ -142,7 +145,7 @@ __dcache_find_get_entry(struct dentry *parent, u64 idx,
 		ceph_readdir_cache_release(cache_ctl);
 		cache_ctl->page = find_lock_page(&dir->i_data, ptr_pgoff);
 		if (!cache_ctl->page) {
-			dout(" page %lu not found\n", ptr_pgoff);
+			doutc(cl, " page %lu not found\n", ptr_pgoff);
 			return ERR_PTR(-EAGAIN);
 		}
 		/* reading/filling the cache are serialized by
@@ -185,13 +188,16 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 	struct ceph_dir_file_info *dfi = file->private_data;
 	struct dentry *parent = file->f_path.dentry;
 	struct inode *dir = d_inode(parent);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(dir);
+	struct ceph_client *cl = ceph_inode_to_client(dir);
 	struct dentry *dentry, *last = NULL;
 	struct ceph_dentry_info *di;
 	struct ceph_readdir_cache_control cache_ctl = {};
 	u64 idx = 0;
 	int err = 0;
 
-	dout("__dcache_readdir %p v%u at %llx\n", dir, (unsigned)shared_gen, ctx->pos);
+	doutc(cl, "%p %llx.%llx v%u at %llx\n", dir, ceph_vinop(dir),
+	      (unsigned)shared_gen, ctx->pos);
 
 	/* search start position */
 	if (ctx->pos > 2) {
@@ -221,7 +227,8 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 			dput(dentry);
 		}
 
-		dout("__dcache_readdir %p cache idx %llu\n", dir, idx);
+		doutc(cl, "%p %llx.%llx cache idx %llu\n", dir,
+		      ceph_vinop(dir), idx);
 	}
 
 
@@ -257,8 +264,8 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 		spin_unlock(&dentry->d_lock);
 
 		if (emit_dentry) {
-			dout(" %llx dentry %p %pd %p\n", di->offset,
-			     dentry, dentry, d_inode(dentry));
+			doutc(cl, " %llx dentry %p %pd %p\n", di->offset,
+			      dentry, dentry, d_inode(dentry));
 			ctx->pos = di->offset;
 			if (!dir_emit(ctx, dentry->d_name.name,
 				      dentry->d_name.len, ceph_present_inode(d_inode(dentry)),
@@ -281,7 +288,8 @@ out:
 	if (last) {
 		int ret;
 		di = ceph_dentry(last);
-		ret = note_last_dentry(dfi, last->d_name.name, last->d_name.len,
+		ret = note_last_dentry(fsc, dfi, last->d_name.name,
+				       last->d_name.len,
 				       fpos_off(di->offset) + 1);
 		if (ret < 0)
 			err = ret;
@@ -310,20 +318,23 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	struct ceph_dir_file_info *dfi = file->private_data;
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_client *cl = fsc->client;
 	int i;
 	int err;
 	unsigned frag = -1;
 	struct ceph_mds_reply_info_parsed *rinfo;
 
-	dout("readdir %p file %p pos %llx\n", inode, file, ctx->pos);
+	doutc(cl, "%p %llx.%llx file %p pos %llx\n", inode,
+	      ceph_vinop(inode), file, ctx->pos);
 	if (dfi->file_info.flags & CEPH_F_ATEND)
 		return 0;
 
 	/* always start with . and .. */
 	if (ctx->pos == 0) {
-		dout("readdir off 0 -> '.'\n");
+		doutc(cl, "%p %llx.%llx off 0 -> '.'\n", inode,
+		      ceph_vinop(inode));
 		if (!dir_emit(ctx, ".", 1, ceph_present_inode(inode),
 			    inode->i_mode >> 12))
 			return 0;
@@ -337,7 +348,8 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 		ino = ceph_present_inode(dentry->d_parent->d_inode);
 		spin_unlock(&dentry->d_lock);
 
-		dout("readdir off 1 -> '..'\n");
+		doutc(cl, "%p %llx.%llx off 1 -> '..'\n", inode,
+		      ceph_vinop(inode));
 		if (!dir_emit(ctx, "..", 2, ino, inode->i_mode >> 12))
 			return 0;
 		ctx->pos = 2;
@@ -391,8 +403,8 @@ more:
 			frag = fpos_frag(ctx->pos);
 		}
 
-		dout("readdir fetching %llx.%llx frag %x offset '%s'\n",
-		     ceph_vinop(inode), frag, dfi->last_name);
+		doutc(cl, "fetching %p %llx.%llx frag %x offset '%s'\n",
+		      inode, ceph_vinop(inode), frag, dfi->last_name);
 		req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
 		if (IS_ERR(req))
 			return PTR_ERR(req);
@@ -446,12 +458,12 @@ more:
 			ceph_mdsc_put_request(req);
 			return err;
 		}
-		dout("readdir got and parsed readdir result=%d on "
-		     "frag %x, end=%d, complete=%d, hash_order=%d\n",
-		     err, frag,
-		     (int)req->r_reply_info.dir_end,
-		     (int)req->r_reply_info.dir_complete,
-		     (int)req->r_reply_info.hash_order);
+		doutc(cl, "%p %llx.%llx got and parsed readdir result=%d"
+		      "on frag %x, end=%d, complete=%d, hash_order=%d\n",
+		      inode, ceph_vinop(inode), err, frag,
+		      (int)req->r_reply_info.dir_end,
+		      (int)req->r_reply_info.dir_complete,
+		      (int)req->r_reply_info.hash_order);
 
 		rinfo = &req->r_reply_info;
 		if (le32_to_cpu(rinfo->dir_dir->frag) != frag) {
@@ -481,7 +493,8 @@ more:
 				dfi->dir_ordered_count = req->r_dir_ordered_cnt;
 			}
 		} else {
-			dout("readdir !did_prepopulate\n");
+			doutc(cl, "%p %llx.%llx !did_prepopulate\n", inode,
+			      ceph_vinop(inode));
 			/* disable readdir cache */
 			dfi->readdir_cache_idx = -1;
 			/* preclude from marking dir complete */
@@ -494,8 +507,8 @@ more:
 					rinfo->dir_entries + (rinfo->dir_nr-1);
 			unsigned next_offset = req->r_reply_info.dir_end ?
 					2 : (fpos_off(rde->offset) + 1);
-			err = note_last_dentry(dfi, rde->name, rde->name_len,
-					       next_offset);
+			err = note_last_dentry(fsc, dfi, rde->name,
+					       rde->name_len, next_offset);
 			if (err) {
 				ceph_mdsc_put_request(dfi->last_readdir);
 				dfi->last_readdir = NULL;
@@ -508,9 +521,9 @@ more:
 	}
 
 	rinfo = &dfi->last_readdir->r_reply_info;
-	dout("readdir frag %x num %d pos %llx chunk first %llx\n",
-	     dfi->frag, rinfo->dir_nr, ctx->pos,
-	     rinfo->dir_nr ? rinfo->dir_entries[0].offset : 0LL);
+	doutc(cl, "%p %llx.%llx frag %x num %d pos %llx chunk first %llx\n",
+	      inode, ceph_vinop(inode), dfi->frag, rinfo->dir_nr, ctx->pos,
+	      rinfo->dir_nr ? rinfo->dir_entries[0].offset : 0LL);
 
 	i = 0;
 	/* search start position */
@@ -530,8 +543,9 @@ more:
 		struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
 
 		if (rde->offset < ctx->pos) {
-			pr_warn("%s: rde->offset 0x%llx ctx->pos 0x%llx\n",
-				__func__, rde->offset, ctx->pos);
+			pr_warn_client(cl,
+				"%p %llx.%llx rde->offset 0x%llx ctx->pos 0x%llx\n",
+				inode, ceph_vinop(inode), rde->offset, ctx->pos);
 			return -EIO;
 		}
 
@@ -539,9 +553,9 @@ more:
 			return -EIO;
 
 		ctx->pos = rde->offset;
-		dout("readdir (%d/%d) -> %llx '%.*s' %p\n",
-		     i, rinfo->dir_nr, ctx->pos,
-		     rde->name_len, rde->name, &rde->inode.in);
+		doutc(cl, "%p %llx.%llx (%d/%d) -> %llx '%.*s' %p\n", inode,
+		      ceph_vinop(inode), i, rinfo->dir_nr, ctx->pos,
+		      rde->name_len, rde->name, &rde->inode.in);
 
 		if (!dir_emit(ctx, rde->name, rde->name_len,
 			      ceph_present_ino(inode->i_sb, le64_to_cpu(rde->inode.in->ino)),
@@ -552,7 +566,7 @@ more:
 			 * doesn't have enough memory, etc. So for next readdir
 			 * it will continue.
 			 */
-			dout("filldir stopping us...\n");
+			doutc(cl, "filldir stopping us...\n");
 			return 0;
 		}
 
@@ -583,7 +597,8 @@ more:
 			kfree(dfi->last_name);
 			dfi->last_name = NULL;
 		}
-		dout("readdir next frag is %x\n", frag);
+		doutc(cl, "%p %llx.%llx next frag is %x\n", inode,
+		      ceph_vinop(inode), frag);
 		goto more;
 	}
 	dfi->file_info.flags |= CEPH_F_ATEND;
@@ -598,20 +613,23 @@ more:
 		spin_lock(&ci->i_ceph_lock);
 		if (dfi->dir_ordered_count ==
 				atomic64_read(&ci->i_ordered_count)) {
-			dout(" marking %p complete and ordered\n", inode);
+			doutc(cl, " marking %p %llx.%llx complete and ordered\n",
+			      inode, ceph_vinop(inode));
 			/* use i_size to track number of entries in
 			 * readdir cache */
 			BUG_ON(dfi->readdir_cache_idx < 0);
 			i_size_write(inode, dfi->readdir_cache_idx *
 				     sizeof(struct dentry*));
 		} else {
-			dout(" marking %p complete\n", inode);
+			doutc(cl, " marking %llx.%llx complete\n",
+			      ceph_vinop(inode));
 		}
 		__ceph_dir_set_complete(ci, dfi->dir_release_count,
 					dfi->dir_ordered_count);
 		spin_unlock(&ci->i_ceph_lock);
 	}
-	dout("readdir %p file %p done.\n", inode, file);
+	doutc(cl, "%p %llx.%llx file %p done.\n", inode, ceph_vinop(inode),
+	      file);
 	return 0;
 }
 
@@ -657,6 +675,7 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct ceph_dir_file_info *dfi = file->private_data;
 	struct inode *inode = file->f_mapping->host;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	loff_t retval;
 
 	inode_lock(inode);
@@ -676,7 +695,8 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
 
 	if (offset >= 0) {
 		if (need_reset_readdir(dfi, offset)) {
-			dout("dir_llseek dropping %p content\n", file);
+			doutc(cl, "%p %llx.%llx dropping %p content\n",
+			      inode, ceph_vinop(inode), file);
 			reset_readdir(dfi);
 		} else if (is_hash_order(offset) && offset > file->f_pos) {
 			/* for hash offset, we don't know if a forward seek
@@ -703,8 +723,9 @@ out:
 struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req,
 				   struct dentry *dentry)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(dentry->d_sb);
 	struct inode *parent = d_inode(dentry->d_parent); /* we hold i_rwsem */
+	struct ceph_client *cl = ceph_inode_to_client(parent);
 
 	/* .snap dir? */
 	if (ceph_snap(parent) == CEPH_NOSNAP &&
@@ -713,8 +734,9 @@ struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req,
 		struct inode *inode = ceph_get_snapdir(parent);
 
 		res = d_splice_alias(inode, dentry);
-		dout("ENOENT on snapdir %p '%pd', linking to snapdir %p. Spliced dentry %p\n",
-		     dentry, dentry, inode, res);
+		doutc(cl, "ENOENT on snapdir %p '%pd', linking to "
+		      "snapdir %p %llx.%llx. Spliced dentry %p\n",
+		      dentry, dentry, inode, ceph_vinop(inode), res);
 		if (res)
 			dentry = res;
 	}
@@ -735,12 +757,15 @@ struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req,
 struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
 				  struct dentry *dentry, int err)
 {
+	struct ceph_client *cl = req->r_mdsc->fsc->client;
+
 	if (err == -ENOENT) {
 		/* no trace? */
 		err = 0;
 		if (!req->r_reply_info.head->is_dentry) {
-			dout("ENOENT and no trace, dentry %p inode %p\n",
-			     dentry, d_inode(dentry));
+			doutc(cl,
+			      "ENOENT and no trace, dentry %p inode %llx.%llx\n",
+			      dentry, ceph_vinop(d_inode(dentry)));
 			if (d_really_is_positive(dentry)) {
 				d_drop(dentry);
 				err = -ENOENT;
@@ -771,15 +796,16 @@ static bool is_root_ceph_dentry(struct inode *inode, struct dentry *dentry)
 static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 				  unsigned int flags)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(dir->i_sb);
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_mds_request *req;
 	int op;
 	int mask;
 	int err;
 
-	dout("lookup %p dentry %p '%pd'\n",
-	     dir, dentry, dentry);
+	doutc(cl, "%p %llx.%llx/'%pd' dentry %p\n", dir, ceph_vinop(dir),
+	      dentry, dentry);
 
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);
@@ -802,7 +828,8 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 		struct ceph_dentry_info *di = ceph_dentry(dentry);
 
 		spin_lock(&ci->i_ceph_lock);
-		dout(" dir %p flags are 0x%lx\n", dir, ci->i_ceph_flags);
+		doutc(cl, " dir %llx.%llx flags are 0x%lx\n",
+		      ceph_vinop(dir), ci->i_ceph_flags);
 		if (strncmp(dentry->d_name.name,
 			    fsc->mount_options->snapdir_name,
 			    dentry->d_name.len) &&
@@ -812,7 +839,8 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 		    __ceph_caps_issued_mask_metric(ci, CEPH_CAP_FILE_SHARED, 1)) {
 			__ceph_touch_fmode(ci, mdsc, CEPH_FILE_MODE_RD);
 			spin_unlock(&ci->i_ceph_lock);
-			dout(" dir %p complete, -ENOENT\n", dir);
+			doutc(cl, " dir %llx.%llx complete, -ENOENT\n",
+			      ceph_vinop(dir));
 			d_add(dentry, NULL);
 			di->lease_shared_gen = atomic_read(&ci->i_shared_gen);
 			return NULL;
@@ -850,7 +878,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 	}
 	dentry = ceph_finish_lookup(req, dentry, err);
 	ceph_mdsc_put_request(req);  /* will dput(dentry) */
-	dout("lookup result=%p\n", dentry);
+	doutc(cl, "result=%p\n", dentry);
 	return dentry;
 }
 
@@ -885,6 +913,7 @@ static int ceph_mknod(struct mnt_idmap *idmap, struct inode *dir,
 		      struct dentry *dentry, umode_t mode, dev_t rdev)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *req;
 	struct ceph_acl_sec_ctx as_ctx = {};
 	int err;
@@ -901,8 +930,8 @@ static int ceph_mknod(struct mnt_idmap *idmap, struct inode *dir,
 		goto out;
 	}
 
-	dout("mknod in dir %p dentry %p mode 0%ho rdev %d\n",
-	     dir, dentry, mode, rdev);
+	doutc(cl, "%p %llx.%llx/'%pd' dentry %p mode 0%ho rdev %d\n",
+	      dir, ceph_vinop(dir), dentry, dentry, mode, rdev);
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_MKNOD, USE_AUTH_MDS);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
@@ -924,6 +953,7 @@ static int ceph_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	req->r_parent = dir;
 	ihold(dir);
 	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
+	req->r_mnt_idmap = mnt_idmap_get(idmap);
 	req->r_args.mknod.mode = cpu_to_le32(mode);
 	req->r_args.mknod.rdev = cpu_to_le32(rdev);
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL |
@@ -993,6 +1023,7 @@ static int ceph_symlink(struct mnt_idmap *idmap, struct inode *dir,
 			struct dentry *dentry, const char *dest)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *req;
 	struct ceph_acl_sec_ctx as_ctx = {};
 	umode_t mode = S_IFLNK | 0777;
@@ -1010,7 +1041,8 @@ static int ceph_symlink(struct mnt_idmap *idmap, struct inode *dir,
 		goto out;
 	}
 
-	dout("symlink in dir %p dentry %p to '%s'\n", dir, dentry, dest);
+	doutc(cl, "%p %llx.%llx/'%pd' to '%s'\n", dir, ceph_vinop(dir), dentry,
+	      dest);
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SYMLINK, USE_AUTH_MDS);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
@@ -1040,6 +1072,7 @@ static int ceph_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	}
 
 	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
+	req->r_mnt_idmap = mnt_idmap_get(idmap);
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL |
@@ -1064,6 +1097,7 @@ static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 		      struct dentry *dentry, umode_t mode)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *req;
 	struct ceph_acl_sec_ctx as_ctx = {};
 	int err;
@@ -1076,10 +1110,11 @@ static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	if (ceph_snap(dir) == CEPH_SNAPDIR) {
 		/* mkdir .snap/foo is a MKSNAP */
 		op = CEPH_MDS_OP_MKSNAP;
-		dout("mksnap dir %p snap '%pd' dn %p\n", dir,
-		     dentry, dentry);
+		doutc(cl, "mksnap %llx.%llx/'%pd' dentry %p\n",
+		      ceph_vinop(dir), dentry, dentry);
 	} else if (ceph_snap(dir) == CEPH_NOSNAP) {
-		dout("mkdir dir %p dn %p mode 0%ho\n", dir, dentry, mode);
+		doutc(cl, "mkdir %llx.%llx/'%pd' dentry %p mode 0%ho\n",
+		      ceph_vinop(dir), dentry, dentry, mode);
 		op = CEPH_MDS_OP_MKDIR;
 	} else {
 		err = -EROFS;
@@ -1117,6 +1152,8 @@ static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	req->r_parent = dir;
 	ihold(dir);
 	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
+	if (op == CEPH_MDS_OP_MKDIR)
+		req->r_mnt_idmap = mnt_idmap_get(idmap);
 	req->r_args.mkdir.mode = cpu_to_le32(mode);
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL |
 			     CEPH_CAP_XATTR_EXCL;
@@ -1144,6 +1181,7 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
 		     struct dentry *dentry)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *req;
 	int err;
 
@@ -1161,8 +1199,8 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
 	if (err)
 		return err;
 
-	dout("link in dir %p %llx.%llx old_dentry %p:'%pd' dentry %p:'%pd'\n",
-	     dir, ceph_vinop(dir), old_dentry, old_dentry, dentry, dentry);
+	doutc(cl, "%p %llx.%llx/'%pd' to '%pd'\n", dir, ceph_vinop(dir),
+	      old_dentry, dentry);
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LINK, USE_AUTH_MDS);
 	if (IS_ERR(req)) {
 		d_drop(dentry);
@@ -1199,14 +1237,16 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
 				 struct ceph_mds_request *req)
 {
 	struct dentry *dentry = req->r_dentry;
-	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(dentry->d_sb);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
 	int result = req->r_err ? req->r_err :
 			le32_to_cpu(req->r_reply_info.head->result);
 
 	if (!test_bit(CEPH_DENTRY_ASYNC_UNLINK_BIT, &di->flags))
-		pr_warn("%s dentry %p:%pd async unlink bit is not set\n",
-			__func__, dentry, dentry);
+		pr_warn_client(cl,
+			"dentry %p:%pd async unlink bit is not set\n",
+			dentry, dentry);
 
 	spin_lock(&fsc->async_unlink_conflict_lock);
 	hash_del_rcu(&di->hnode);
@@ -1226,7 +1266,7 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
 	if (result) {
 		int pathlen = 0;
 		u64 base = 0;
-		char *path = ceph_mdsc_build_path(dentry, &pathlen,
+		char *path = ceph_mdsc_build_path(mdsc, dentry, &pathlen,
 						  &base, 0);
 
 		/* mark error on parent + clear complete */
@@ -1240,8 +1280,8 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
 		/* mark inode itself for an error (since metadata is bogus) */
 		mapping_set_error(req->r_old_inode->i_mapping, result);
 
-		pr_warn("async unlink failure path=(%llx)%s result=%d!\n",
-			base, IS_ERR(path) ? "<<bad>>" : path, result);
+		pr_warn_client(cl, "failure path=(%llx)%s result=%d!\n",
+			       base, IS_ERR(path) ? "<<bad>>" : path, result);
 		ceph_mdsc_free_path(path, pathlen);
 	}
 out:
@@ -1290,7 +1330,8 @@ static int get_caps_for_async_unlink(struct inode *dir, struct dentry *dentry)
  */
 static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(dir->i_sb);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct inode *inode = d_inode(dentry);
 	struct ceph_mds_request *req;
@@ -1300,11 +1341,12 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 
 	if (ceph_snap(dir) == CEPH_SNAPDIR) {
 		/* rmdir .snap/foo is RMSNAP */
-		dout("rmsnap dir %p '%pd' dn %p\n", dir, dentry, dentry);
+		doutc(cl, "rmsnap %llx.%llx/'%pd' dn\n", ceph_vinop(dir),
+		      dentry);
 		op = CEPH_MDS_OP_RMSNAP;
 	} else if (ceph_snap(dir) == CEPH_NOSNAP) {
-		dout("unlink/rmdir dir %p dn %p inode %p\n",
-		     dir, dentry, inode);
+		doutc(cl, "unlink/rmdir %llx.%llx/'%pd' inode %llx.%llx\n",
+		      ceph_vinop(dir), dentry, ceph_vinop(inode));
 		op = d_is_dir(dentry) ?
 			CEPH_MDS_OP_RMDIR : CEPH_MDS_OP_UNLINK;
 	} else
@@ -1327,9 +1369,9 @@ retry:
 	    (req->r_dir_caps = get_caps_for_async_unlink(dir, dentry))) {
 		struct ceph_dentry_info *di = ceph_dentry(dentry);
 
-		dout("async unlink on %llu/%.*s caps=%s", ceph_ino(dir),
-		     dentry->d_name.len, dentry->d_name.name,
-		     ceph_cap_string(req->r_dir_caps));
+		doutc(cl, "async unlink on %llx.%llx/'%pd' caps=%s",
+		      ceph_vinop(dir), dentry,
+		      ceph_cap_string(req->r_dir_caps));
 		set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags);
 		req->r_callback = ceph_async_unlink_cb;
 		req->r_old_inode = d_inode(dentry);
@@ -1384,6 +1426,7 @@ static int ceph_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 		       struct dentry *new_dentry, unsigned int flags)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(old_dir->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *req;
 	int op = CEPH_MDS_OP_RENAME;
 	int err;
@@ -1413,8 +1456,9 @@ static int ceph_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 	if (err)
 		return err;
 
-	dout("rename dir %p dentry %p to dir %p dentry %p\n",
-	     old_dir, old_dentry, new_dir, new_dentry);
+	doutc(cl, "%llx.%llx/'%pd' to %llx.%llx/'%pd'\n",
+	      ceph_vinop(old_dir), old_dentry, ceph_vinop(new_dir),
+	      new_dentry);
 	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
@@ -1459,9 +1503,10 @@ static int ceph_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 void __ceph_dentry_lease_touch(struct ceph_dentry_info *di)
 {
 	struct dentry *dn = di->dentry;
-	struct ceph_mds_client *mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(dn->d_sb)->mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 
-	dout("dentry_lease_touch %p %p '%pd'\n", di, dn, dn);
+	doutc(cl, "%p %p '%pd'\n", di, dn, dn);
 
 	di->flags |= CEPH_DENTRY_LEASE_LIST;
 	if (di->flags & CEPH_DENTRY_SHRINK_LIST) {
@@ -1469,7 +1514,6 @@ void __ceph_dentry_lease_touch(struct ceph_dentry_info *di)
 		return;
 	}
 
-	mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
 	spin_lock(&mdsc->dentry_list_lock);
 	list_move_tail(&di->lease_list, &mdsc->dentry_leases);
 	spin_unlock(&mdsc->dentry_list_lock);
@@ -1493,10 +1537,10 @@ static void __dentry_dir_lease_touch(struct ceph_mds_client* mdsc,
 void __ceph_dentry_dir_lease_touch(struct ceph_dentry_info *di)
 {
 	struct dentry *dn = di->dentry;
-	struct ceph_mds_client *mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(dn->d_sb)->mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 
-	dout("dentry_dir_lease_touch %p %p '%pd' (offset 0x%llx)\n",
-	     di, dn, dn, di->offset);
+	doutc(cl, "%p %p '%pd' (offset 0x%llx)\n", di, dn, dn, di->offset);
 
 	if (!list_empty(&di->lease_list)) {
 		if (di->flags & CEPH_DENTRY_LEASE_LIST) {
@@ -1516,7 +1560,6 @@ void __ceph_dentry_dir_lease_touch(struct ceph_dentry_info *di)
 		return;
 	}
 
-	mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
 	spin_lock(&mdsc->dentry_list_lock);
 	__dentry_dir_lease_touch(mdsc, di),
 	spin_unlock(&mdsc->dentry_list_lock);
@@ -1530,7 +1573,7 @@ static void __dentry_lease_unlist(struct ceph_dentry_info *di)
 	if (list_empty(&di->lease_list))
 		return;
 
-	mdsc = ceph_sb_to_client(di->dentry->d_sb)->mdsc;
+	mdsc = ceph_sb_to_fs_client(di->dentry->d_sb)->mdsc;
 	spin_lock(&mdsc->dentry_list_lock);
 	list_del_init(&di->lease_list);
 	spin_unlock(&mdsc->dentry_list_lock);
@@ -1757,6 +1800,8 @@ static int dentry_lease_is_valid(struct dentry *dentry, unsigned int flags)
 {
 	struct ceph_dentry_info *di;
 	struct ceph_mds_session *session = NULL;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(dentry->d_sb)->mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	u32 seq = 0;
 	int valid = 0;
 
@@ -1789,7 +1834,7 @@ static int dentry_lease_is_valid(struct dentry *dentry, unsigned int flags)
 					 CEPH_MDS_LEASE_RENEW, seq);
 		ceph_put_mds_session(session);
 	}
-	dout("dentry_lease_is_valid - dentry %p = %d\n", dentry, valid);
+	doutc(cl, "dentry %p = %d\n", dentry, valid);
 	return valid;
 }
 
@@ -1832,6 +1877,7 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry,
 			      struct ceph_mds_client *mdsc)
 {
 	struct ceph_inode_info *ci = ceph_inode(dir);
+	struct ceph_client *cl = mdsc->fsc->client;
 	int valid;
 	int shared_gen;
 
@@ -1853,8 +1899,9 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry,
 			valid = 0;
 		spin_unlock(&dentry->d_lock);
 	}
-	dout("dir_lease_is_valid dir %p v%u dentry %p = %d\n",
-	     dir, (unsigned)atomic_read(&ci->i_shared_gen), dentry, valid);
+	doutc(cl, "dir %p %llx.%llx v%u dentry %p '%pd' = %d\n", dir,
+	      ceph_vinop(dir), (unsigned)atomic_read(&ci->i_shared_gen),
+	      dentry, dentry, valid);
 	return valid;
 }
 
@@ -1863,10 +1910,11 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry,
  */
 static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(dentry->d_sb)->mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	int valid = 0;
 	struct dentry *parent;
 	struct inode *dir, *inode;
-	struct ceph_mds_client *mdsc;
 
 	valid = fscrypt_d_revalidate(dentry, flags);
 	if (valid <= 0)
@@ -1884,16 +1932,16 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 		inode = d_inode(dentry);
 	}
 
-	dout("d_revalidate %p '%pd' inode %p offset 0x%llx nokey %d\n", dentry,
-	     dentry, inode, ceph_dentry(dentry)->offset,
-	     !!(dentry->d_flags & DCACHE_NOKEY_NAME));
+	doutc(cl, "%p '%pd' inode %p offset 0x%llx nokey %d\n",
+	      dentry, dentry, inode, ceph_dentry(dentry)->offset,
+	      !!(dentry->d_flags & DCACHE_NOKEY_NAME));
 
-	mdsc = ceph_sb_to_client(dir->i_sb)->mdsc;
+	mdsc = ceph_sb_to_fs_client(dir->i_sb)->mdsc;
 
 	/* always trust cached snapped dentries, snapdir dentry */
 	if (ceph_snap(dir) != CEPH_NOSNAP) {
-		dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry,
-		     dentry, inode);
+		doutc(cl, "%p '%pd' inode %p is SNAPPED\n", dentry,
+		      dentry, inode);
 		valid = 1;
 	} else if (inode && ceph_snap(inode) == CEPH_SNAPDIR) {
 		valid = 1;
@@ -1948,14 +1996,14 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 				break;
 			}
 			ceph_mdsc_put_request(req);
-			dout("d_revalidate %p lookup result=%d\n",
-			     dentry, err);
+			doutc(cl, "%p '%pd', lookup result=%d\n", dentry,
+			      dentry, err);
 		}
 	} else {
 		percpu_counter_inc(&mdsc->metric.d_lease_hit);
 	}
 
-	dout("d_revalidate %p %s\n", dentry, valid ? "valid" : "invalid");
+	doutc(cl, "%p '%pd' %s\n", dentry, dentry, valid ? "valid" : "invalid");
 	if (!valid)
 		ceph_dir_clear_complete(dir);
 
@@ -1995,9 +2043,9 @@ static int ceph_d_delete(const struct dentry *dentry)
 static void ceph_d_release(struct dentry *dentry)
 {
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
-	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(dentry->d_sb);
 
-	dout("d_release %p\n", dentry);
+	doutc(fsc->client, "dentry %p '%pd'\n", dentry, dentry);
 
 	atomic64_dec(&fsc->mdsc->metric.total_dentries);
 
@@ -2018,10 +2066,12 @@ static void ceph_d_release(struct dentry *dentry)
  */
 static void ceph_d_prune(struct dentry *dentry)
 {
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dentry->d_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_inode_info *dir_ci;
 	struct ceph_dentry_info *di;
 
-	dout("ceph_d_prune %pd %p\n", dentry, dentry);
+	doutc(cl, "dentry %p '%pd'\n", dentry, dentry);
 
 	/* do we have a valid parent? */
 	if (IS_ROOT(dentry))
@@ -2064,7 +2114,7 @@ static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size,
 	int left;
 	const int bufsize = 1024;
 
-	if (!ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), DIRSTAT))
+	if (!ceph_test_mount_opt(ceph_sb_to_fs_client(inode->i_sb), DIRSTAT))
 		return -EISDIR;
 
 	if (!dfi->dir_info) {
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 8559990a59a5c5..726af69d4d62cd 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -36,6 +36,7 @@ struct ceph_nfs_snapfh {
 static int ceph_encode_snapfh(struct inode *inode, u32 *rawfh, int *max_len,
 			      struct inode *parent_inode)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	static const int snap_handle_length =
 		sizeof(struct ceph_nfs_snapfh) >> 2;
 	struct ceph_nfs_snapfh *sfh = (void *)rawfh;
@@ -79,13 +80,14 @@ static int ceph_encode_snapfh(struct inode *inode, u32 *rawfh, int *max_len,
 	*max_len = snap_handle_length;
 	ret = FILEID_BTRFS_WITH_PARENT;
 out:
-	dout("encode_snapfh %llx.%llx ret=%d\n", ceph_vinop(inode), ret);
+	doutc(cl, "%p %llx.%llx ret=%d\n", inode, ceph_vinop(inode), ret);
 	return ret;
 }
 
 static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
 			  struct inode *parent_inode)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	static const int handle_length =
 		sizeof(struct ceph_nfs_fh) >> 2;
 	static const int connected_handle_length =
@@ -105,15 +107,15 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
 
 	if (parent_inode) {
 		struct ceph_nfs_confh *cfh = (void *)rawfh;
-		dout("encode_fh %llx with parent %llx\n",
-		     ceph_ino(inode), ceph_ino(parent_inode));
+		doutc(cl, "%p %llx.%llx with parent %p %llx.%llx\n", inode,
+		      ceph_vinop(inode), parent_inode, ceph_vinop(parent_inode));
 		cfh->ino = ceph_ino(inode);
 		cfh->parent_ino = ceph_ino(parent_inode);
 		*max_len = connected_handle_length;
 		type = FILEID_INO32_GEN_PARENT;
 	} else {
 		struct ceph_nfs_fh *fh = (void *)rawfh;
-		dout("encode_fh %llx\n", ceph_ino(inode));
+		doutc(cl, "%p %llx.%llx\n", inode, ceph_vinop(inode));
 		fh->ino = ceph_ino(inode);
 		*max_len = handle_length;
 		type = FILEID_INO32_GEN;
@@ -123,7 +125,7 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
 
 static struct inode *__lookup_inode(struct super_block *sb, u64 ino)
 {
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(sb)->mdsc;
 	struct inode *inode;
 	struct ceph_vino vino;
 	int err;
@@ -205,7 +207,8 @@ static struct dentry *__snapfh_to_dentry(struct super_block *sb,
 					  struct ceph_nfs_snapfh *sfh,
 					  bool want_parent)
 {
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(sb)->mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *req;
 	struct inode *inode;
 	struct ceph_vino vino;
@@ -278,11 +281,10 @@ static struct dentry *__snapfh_to_dentry(struct super_block *sb,
 	ceph_mdsc_put_request(req);
 
 	if (want_parent) {
-		dout("snapfh_to_parent %llx.%llx\n err=%d\n",
-		     vino.ino, vino.snap, err);
+		doutc(cl, "%llx.%llx\n err=%d\n", vino.ino, vino.snap, err);
 	} else {
-		dout("snapfh_to_dentry %llx.%llx parent %llx hash %x err=%d",
-		      vino.ino, vino.snap, sfh->parent_ino, sfh->hash, err);
+		doutc(cl, "%llx.%llx parent %llx hash %x err=%d", vino.ino,
+		      vino.snap, sfh->parent_ino, sfh->hash, err);
 	}
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
@@ -297,6 +299,7 @@ static struct dentry *ceph_fh_to_dentry(struct super_block *sb,
 					struct fid *fid,
 					int fh_len, int fh_type)
 {
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb);
 	struct ceph_nfs_fh *fh = (void *)fid->raw;
 
 	if (fh_type == FILEID_BTRFS_WITH_PARENT) {
@@ -310,14 +313,14 @@ static struct dentry *ceph_fh_to_dentry(struct super_block *sb,
 	if (fh_len < sizeof(*fh) / 4)
 		return NULL;
 
-	dout("fh_to_dentry %llx\n", fh->ino);
+	doutc(fsc->client, "%llx\n", fh->ino);
 	return __fh_to_dentry(sb, fh->ino);
 }
 
 static struct dentry *__get_parent(struct super_block *sb,
 				   struct dentry *child, u64 ino)
 {
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(sb)->mdsc;
 	struct ceph_mds_request *req;
 	struct inode *inode;
 	int mask;
@@ -363,6 +366,7 @@ static struct dentry *__get_parent(struct super_block *sb,
 static struct dentry *ceph_get_parent(struct dentry *child)
 {
 	struct inode *inode = d_inode(child);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct dentry *dn;
 
 	if (ceph_snap(inode) != CEPH_NOSNAP) {
@@ -402,8 +406,8 @@ static struct dentry *ceph_get_parent(struct dentry *child)
 		dn = __get_parent(child->d_sb, child, 0);
 	}
 out:
-	dout("get_parent %p ino %llx.%llx err=%ld\n",
-	     child, ceph_vinop(inode), (long)PTR_ERR_OR_ZERO(dn));
+	doutc(cl, "child %p %p %llx.%llx err=%ld\n", child, inode,
+	      ceph_vinop(inode), (long)PTR_ERR_OR_ZERO(dn));
 	return dn;
 }
 
@@ -414,6 +418,7 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb,
 					struct fid *fid,
 					int fh_len, int fh_type)
 {
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb);
 	struct ceph_nfs_confh *cfh = (void *)fid->raw;
 	struct dentry *dentry;
 
@@ -427,7 +432,7 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb,
 	if (fh_len < sizeof(*cfh) / 4)
 		return NULL;
 
-	dout("fh_to_parent %llx\n", cfh->parent_ino);
+	doutc(fsc->client, "%llx\n", cfh->parent_ino);
 	dentry = __get_parent(sb, NULL, cfh->ino);
 	if (unlikely(dentry == ERR_PTR(-ENOENT)))
 		dentry = __fh_to_dentry(sb, cfh->parent_ino);
@@ -439,7 +444,7 @@ static int __get_snap_name(struct dentry *parent, char *name,
 {
 	struct inode *inode = d_inode(child);
 	struct inode *dir = d_inode(parent);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 	struct ceph_mds_request *req = NULL;
 	char *last_name = NULL;
 	unsigned next_offset = 2;
@@ -526,8 +531,8 @@ out:
 	if (req)
 		ceph_mdsc_put_request(req);
 	kfree(last_name);
-	dout("get_snap_name %p ino %llx.%llx err=%d\n",
-	     child, ceph_vinop(inode), err);
+	doutc(fsc->client, "child dentry %p %p %llx.%llx err=%d\n", child,
+	      inode, ceph_vinop(inode), err);
 	return err;
 }
 
@@ -544,7 +549,7 @@ static int ceph_get_name(struct dentry *parent, char *name,
 	if (ceph_snap(inode) != CEPH_NOSNAP)
 		return __get_snap_name(parent, name, child);
 
-	mdsc = ceph_inode_to_client(inode)->mdsc;
+	mdsc = ceph_inode_to_fs_client(inode)->mdsc;
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME,
 				       USE_ANY_MDS);
 	if (IS_ERR(req))
@@ -588,9 +593,9 @@ static int ceph_get_name(struct dentry *parent, char *name,
 		ceph_fname_free_buffer(dir, &oname);
 	}
 out:
-	dout("get_name %p ino %llx.%llx err %d %s%s\n",
-		     child, ceph_vinop(inode), err,
-		     err ? "" : "name ", err ? "" : name);
+	doutc(mdsc->fsc->client, "child dentry %p %p %llx.%llx err %d %s%s\n",
+	      child, inode, ceph_vinop(inode), err, err ? "" : "name ",
+	      err ? "" : name);
 	ceph_mdsc_put_request(req);
 	return err;
 }
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 649600d0a7b6c0..3b5aae29e94478 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -19,8 +19,9 @@
 #include "io.h"
 #include "metric.h"
 
-static __le32 ceph_flags_sys2wire(u32 flags)
+static __le32 ceph_flags_sys2wire(struct ceph_mds_client *mdsc, u32 flags)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	u32 wire_flags = 0;
 
 	switch (flags & O_ACCMODE) {
@@ -48,7 +49,7 @@ static __le32 ceph_flags_sys2wire(u32 flags)
 #undef ceph_sys2wire
 
 	if (flags)
-		dout("unused open flags: %x\n", flags);
+		doutc(cl, "unused open flags: %x\n", flags);
 
 	return cpu_to_le32(wire_flags);
 }
@@ -189,7 +190,7 @@ prepare_open_request(struct super_block *sb, int flags, int create_mode)
 	if (IS_ERR(req))
 		goto out;
 	req->r_fmode = ceph_flags_to_mode(flags);
-	req->r_args.open.flags = ceph_flags_sys2wire(flags);
+	req->r_args.open.flags = ceph_flags_sys2wire(mdsc, flags);
 	req->r_args.open.mode = cpu_to_le32(create_mode);
 out:
 	return req;
@@ -200,12 +201,13 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mount_options *opt =
-		ceph_inode_to_client(&ci->netfs.inode)->mount_options;
+		ceph_inode_to_fs_client(&ci->netfs.inode)->mount_options;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_file_info *fi;
 	int ret;
 
-	dout("%s %p %p 0%o (%s)\n", __func__, inode, file,
-			inode->i_mode, isdir ? "dir" : "regular");
+	doutc(cl, "%p %llx.%llx %p 0%o (%s)\n", inode, ceph_vinop(inode),
+	      file, inode->i_mode, isdir ? "dir" : "regular");
 	BUG_ON(inode->i_fop->release != ceph_release);
 
 	if (isdir) {
@@ -234,7 +236,7 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
 
 	spin_lock_init(&fi->rw_contexts_lock);
 	INIT_LIST_HEAD(&fi->rw_contexts);
-	fi->filp_gen = READ_ONCE(ceph_inode_to_client(inode)->filp_gen);
+	fi->filp_gen = READ_ONCE(ceph_inode_to_fs_client(inode)->filp_gen);
 
 	if ((file->f_mode & FMODE_WRITE) && ceph_has_inline_data(ci)) {
 		ret = ceph_uninline_data(file);
@@ -259,6 +261,7 @@ error:
  */
 static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int ret = 0;
 
 	switch (inode->i_mode & S_IFMT) {
@@ -271,13 +274,13 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
 		break;
 
 	case S_IFLNK:
-		dout("init_file %p %p 0%o (symlink)\n", inode, file,
-		     inode->i_mode);
+		doutc(cl, "%p %llx.%llx %p 0%o (symlink)\n", inode,
+		      ceph_vinop(inode), file, inode->i_mode);
 		break;
 
 	default:
-		dout("init_file %p %p 0%o (special)\n", inode, file,
-		     inode->i_mode);
+		doutc(cl, "%p %llx.%llx %p 0%o (special)\n", inode,
+		      ceph_vinop(inode), file, inode->i_mode);
 		/*
 		 * we need to drop the open ref now, since we don't
 		 * have .release set to ceph_release.
@@ -296,6 +299,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
 int ceph_renew_caps(struct inode *inode, int fmode)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_request *req;
 	int err, flags, wanted;
@@ -307,8 +311,9 @@ int ceph_renew_caps(struct inode *inode, int fmode)
 	    (!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap)) {
 		int issued = __ceph_caps_issued(ci, NULL);
 		spin_unlock(&ci->i_ceph_lock);
-		dout("renew caps %p want %s issued %s updating mds_wanted\n",
-		     inode, ceph_cap_string(wanted), ceph_cap_string(issued));
+		doutc(cl, "%p %llx.%llx want %s issued %s updating mds_wanted\n",
+		      inode, ceph_vinop(inode), ceph_cap_string(wanted),
+		      ceph_cap_string(issued));
 		ceph_check_caps(ci, 0);
 		return 0;
 	}
@@ -339,7 +344,8 @@ int ceph_renew_caps(struct inode *inode, int fmode)
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	ceph_mdsc_put_request(req);
 out:
-	dout("renew caps %p open result=%d\n", inode, err);
+	doutc(cl, "%p %llx.%llx open result=%d\n", inode, ceph_vinop(inode),
+	      err);
 	return err < 0 ? err : 0;
 }
 
@@ -352,7 +358,8 @@ out:
 int ceph_open(struct inode *inode, struct file *file)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(inode->i_sb);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	struct ceph_file_info *fi = file->private_data;
@@ -360,7 +367,7 @@ int ceph_open(struct inode *inode, struct file *file)
 	int flags, fmode, wanted;
 
 	if (fi) {
-		dout("open file %p is already opened\n", file);
+		doutc(cl, "file %p is already opened\n", file);
 		return 0;
 	}
 
@@ -374,8 +381,8 @@ int ceph_open(struct inode *inode, struct file *file)
 			return err;
 	}
 
-	dout("open inode %p ino %llx.%llx file %p flags %d (%d)\n", inode,
-	     ceph_vinop(inode), file, flags, file->f_flags);
+	doutc(cl, "%p %llx.%llx file %p flags %d (%d)\n", inode,
+	      ceph_vinop(inode), file, flags, file->f_flags);
 	fmode = ceph_flags_to_mode(flags);
 	wanted = ceph_caps_for_mode(fmode);
 
@@ -399,9 +406,9 @@ int ceph_open(struct inode *inode, struct file *file)
 		int mds_wanted = __ceph_caps_mds_wanted(ci, true);
 		int issued = __ceph_caps_issued(ci, NULL);
 
-		dout("open %p fmode %d want %s issued %s using existing\n",
-		     inode, fmode, ceph_cap_string(wanted),
-		     ceph_cap_string(issued));
+		doutc(cl, "open %p fmode %d want %s issued %s using existing\n",
+		      inode, fmode, ceph_cap_string(wanted),
+		      ceph_cap_string(issued));
 		__ceph_touch_fmode(ci, mdsc, fmode);
 		spin_unlock(&ci->i_ceph_lock);
 
@@ -421,7 +428,7 @@ int ceph_open(struct inode *inode, struct file *file)
 
 	spin_unlock(&ci->i_ceph_lock);
 
-	dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
+	doutc(cl, "open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
 	req = prepare_open_request(inode->i_sb, flags, 0);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
@@ -435,7 +442,7 @@ int ceph_open(struct inode *inode, struct file *file)
 	if (!err)
 		err = ceph_init_file(inode, file, req->r_fmode);
 	ceph_mdsc_put_request(req);
-	dout("open result=%d on %llx.%llx\n", err, ceph_vinop(inode));
+	doutc(cl, "open result=%d on %llx.%llx\n", err, ceph_vinop(inode));
 out:
 	return err;
 }
@@ -515,6 +522,7 @@ no_async:
 
 static void restore_deleg_ino(struct inode *dir, u64 ino)
 {
+	struct ceph_client *cl = ceph_inode_to_client(dir);
 	struct ceph_inode_info *ci = ceph_inode(dir);
 	struct ceph_mds_session *s = NULL;
 
@@ -525,7 +533,8 @@ static void restore_deleg_ino(struct inode *dir, u64 ino)
 	if (s) {
 		int err = ceph_restore_deleg_ino(s, ino);
 		if (err)
-			pr_warn("ceph: unable to restore delegated ino 0x%llx to session: %d\n",
+			pr_warn_client(cl,
+				"unable to restore delegated ino 0x%llx to session: %d\n",
 				ino, err);
 		ceph_put_mds_session(s);
 	}
@@ -557,6 +566,7 @@ static void wake_async_create_waiters(struct inode *inode,
 static void ceph_async_create_cb(struct ceph_mds_client *mdsc,
                                  struct ceph_mds_request *req)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct dentry *dentry = req->r_dentry;
 	struct inode *dinode = d_inode(dentry);
 	struct inode *tinode = req->r_target_inode;
@@ -574,10 +584,11 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc,
 	if (result) {
 		int pathlen = 0;
 		u64 base = 0;
-		char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen,
+		char *path = ceph_mdsc_build_path(mdsc, req->r_dentry, &pathlen,
 						  &base, 0);
 
-		pr_warn("async create failure path=(%llx)%s result=%d!\n",
+		pr_warn_client(cl,
+			"async create failure path=(%llx)%s result=%d!\n",
 			base, IS_ERR(path) ? "<<bad>>" : path, result);
 		ceph_mdsc_free_path(path, pathlen);
 
@@ -596,14 +607,15 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc,
 		u64 ino = ceph_vino(tinode).ino;
 
 		if (req->r_deleg_ino != ino)
-			pr_warn("%s: inode number mismatch! err=%d deleg_ino=0x%llx target=0x%llx\n",
-				__func__, req->r_err, req->r_deleg_ino, ino);
+			pr_warn_client(cl,
+				"inode number mismatch! err=%d deleg_ino=0x%llx target=0x%llx\n",
+				req->r_err, req->r_deleg_ino, ino);
 
 		mapping_set_error(tinode->i_mapping, result);
 		wake_async_create_waiters(tinode, req->r_session);
 	} else if (!result) {
-		pr_warn("%s: no req->r_target_inode for 0x%llx\n", __func__,
-			req->r_deleg_ino);
+		pr_warn_client(cl, "no req->r_target_inode for 0x%llx\n",
+			       req->r_deleg_ino);
 	}
 out:
 	ceph_mdsc_release_dir_caps(req);
@@ -625,6 +637,7 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode,
 	struct timespec64 now;
 	struct ceph_string *pool_ns;
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_vino vino = { .ino = req->r_deleg_ino,
 				  .snap = CEPH_NOSNAP };
 
@@ -655,7 +668,9 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode,
 	in.truncate_seq = cpu_to_le32(1);
 	in.truncate_size = cpu_to_le64(-1ULL);
 	in.xattr_version = cpu_to_le64(1);
-	in.uid = cpu_to_le32(from_kuid(&init_user_ns, current_fsuid()));
+	in.uid = cpu_to_le32(from_kuid(&init_user_ns,
+				       mapped_fsuid(req->r_mnt_idmap,
+						    &init_user_ns)));
 	if (dir->i_mode & S_ISGID) {
 		in.gid = cpu_to_le32(from_kgid(&init_user_ns, dir->i_gid));
 
@@ -663,7 +678,9 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode,
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
 	} else {
-		in.gid = cpu_to_le32(from_kgid(&init_user_ns, current_fsgid()));
+		in.gid = cpu_to_le32(from_kgid(&init_user_ns,
+				     mapped_fsgid(req->r_mnt_idmap,
+						  &init_user_ns)));
 	}
 	in.mode = cpu_to_le32((u32)mode);
 
@@ -683,7 +700,7 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode,
 			      req->r_fmode, NULL);
 	up_read(&mdsc->snap_rwsem);
 	if (ret) {
-		dout("%s failed to fill inode: %d\n", __func__, ret);
+		doutc(cl, "failed to fill inode: %d\n", ret);
 		ceph_dir_clear_complete(dir);
 		if (!d_unhashed(dentry))
 			d_drop(dentry);
@@ -691,8 +708,8 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode,
 	} else {
 		struct dentry *dn;
 
-		dout("%s d_adding new inode 0x%llx to 0x%llx/%s\n", __func__,
-			vino.ino, ceph_ino(dir), dentry->d_name.name);
+		doutc(cl, "d_adding new inode 0x%llx to 0x%llx/%s\n",
+		      vino.ino, ceph_ino(dir), dentry->d_name.name);
 		ceph_dir_clear_ordered(dir);
 		ceph_init_inode_acls(inode, as_ctx);
 		if (inode->i_state & I_NEW) {
@@ -730,7 +747,9 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode,
 int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 		     struct file *file, unsigned flags, umode_t mode)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct mnt_idmap *idmap = file_mnt_idmap(file);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(dir->i_sb);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	struct inode *new_inode = NULL;
@@ -740,9 +759,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	int mask;
 	int err;
 
-	dout("atomic_open %p dentry %p '%pd' %s flags %d mode 0%o\n",
-	     dir, dentry, dentry,
-	     d_unhashed(dentry) ? "unhashed" : "hashed", flags, mode);
+	doutc(cl, "%p %llx.%llx dentry %p '%pd' %s flags %d mode 0%o\n",
+	      dir, ceph_vinop(dir), dentry, dentry,
+	      d_unhashed(dentry) ? "unhashed" : "hashed", flags, mode);
 
 	if (dentry->d_name.len > NAME_MAX)
 		return -ENAMETOOLONG;
@@ -788,6 +807,8 @@ retry:
 		mask |= CEPH_CAP_XATTR_SHARED;
 	req->r_args.open.mask = cpu_to_le32(mask);
 	req->r_parent = dir;
+	if (req->r_op == CEPH_MDS_OP_CREATE)
+		req->r_mnt_idmap = mnt_idmap_get(idmap);
 	ihold(dir);
 	if (IS_ENCRYPTED(dir)) {
 		set_bit(CEPH_MDS_R_FSCRYPT_FILE, &req->r_req_flags);
@@ -880,17 +901,18 @@ retry:
 		goto out_req;
 	if (dn || d_really_is_negative(dentry) || d_is_symlink(dentry)) {
 		/* make vfs retry on splice, ENOENT, or symlink */
-		dout("atomic_open finish_no_open on dn %p\n", dn);
+		doutc(cl, "finish_no_open on dn %p\n", dn);
 		err = finish_no_open(file, dn);
 	} else {
 		if (IS_ENCRYPTED(dir) &&
 		    !fscrypt_has_permitted_context(dir, d_inode(dentry))) {
-			pr_warn("Inconsistent encryption context (parent %llx:%llx child %llx:%llx)\n",
+			pr_warn_client(cl,
+				"Inconsistent encryption context (parent %llx:%llx child %llx:%llx)\n",
 				ceph_vinop(dir), ceph_vinop(d_inode(dentry)));
 			goto out_req;
 		}
 
-		dout("atomic_open finish_open on dn %p\n", dn);
+		doutc(cl, "finish_open on dn %p\n", dn);
 		if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
 			struct inode *newino = d_inode(dentry);
 
@@ -905,17 +927,19 @@ out_req:
 	iput(new_inode);
 out_ctx:
 	ceph_release_acl_sec_ctx(&as_ctx);
-	dout("atomic_open result=%d\n", err);
+	doutc(cl, "result=%d\n", err);
 	return err;
 }
 
 int ceph_release(struct inode *inode, struct file *file)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
 	if (S_ISDIR(inode->i_mode)) {
 		struct ceph_dir_file_info *dfi = file->private_data;
-		dout("release inode %p dir file %p\n", inode, file);
+		doutc(cl, "%p %llx.%llx dir file %p\n", inode,
+		      ceph_vinop(inode), file);
 		WARN_ON(!list_empty(&dfi->file_info.rw_contexts));
 
 		ceph_put_fmode(ci, dfi->file_info.fmode, 1);
@@ -927,7 +951,8 @@ int ceph_release(struct inode *inode, struct file *file)
 		kmem_cache_free(ceph_dir_file_cachep, dfi);
 	} else {
 		struct ceph_file_info *fi = file->private_data;
-		dout("release inode %p regular file %p\n", inode, file);
+		doutc(cl, "%p %llx.%llx regular file %p\n", inode,
+		      ceph_vinop(inode), file);
 		WARN_ON(!list_empty(&fi->rw_contexts));
 
 		ceph_fscache_unuse_cookie(inode, file->f_mode & FMODE_WRITE);
@@ -962,7 +987,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 			 u64 *last_objver)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	ssize_t ret;
 	u64 off = *ki_pos;
@@ -971,7 +997,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 	bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD);
 	u64 objver = 0;
 
-	dout("sync_read on inode %p %llx~%llx\n", inode, *ki_pos, len);
+	doutc(cl, "on inode %p %llx.%llx %llx~%llx\n", inode,
+	      ceph_vinop(inode), *ki_pos, len);
 
 	if (ceph_inode_is_shutdown(inode))
 		return -EIO;
@@ -1005,8 +1032,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		/* determine new offset/length if encrypted */
 		ceph_fscrypt_adjust_off_and_len(inode, &read_off, &read_len);
 
-		dout("sync_read orig %llu~%llu reading %llu~%llu",
-		     off, len, read_off, read_len);
+		doutc(cl, "orig %llu~%llu reading %llu~%llu", off, len,
+		      read_off, read_len);
 
 		req = ceph_osdc_new_request(osdc, &ci->i_layout,
 					ci->i_vino, read_off, &read_len, 0, 1,
@@ -1059,8 +1086,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 			objver = req->r_version;
 
 		i_size = i_size_read(inode);
-		dout("sync_read %llu~%llu got %zd i_size %llu%s\n",
-		     off, len, ret, i_size, (more ? " MORE" : ""));
+		doutc(cl, "%llu~%llu got %zd i_size %llu%s\n", off, len,
+		      ret, i_size, (more ? " MORE" : ""));
 
 		/* Fix it to go to end of extent map */
 		if (sparse && ret >= 0)
@@ -1101,8 +1128,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 			int zlen = min(len - ret, i_size - off - ret);
 			int zoff = page_off + ret;
 
-			dout("sync_read zero gap %llu~%llu\n",
-				off + ret, off + ret + zlen);
+			doutc(cl, "zero gap %llu~%llu\n", off + ret,
+			      off + ret + zlen);
 			ceph_zero_page_vector_range(zoff, zlen, pages);
 			ret += zlen;
 		}
@@ -1151,7 +1178,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		if (last_objver)
 			*last_objver = objver;
 	}
-	dout("sync_read result %zd retry_op %d\n", ret, *retry_op);
+	doutc(cl, "result %zd retry_op %d\n", ret, *retry_op);
 	return ret;
 }
 
@@ -1160,9 +1187,11 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 
-	dout("sync_read on file %p %llx~%zx %s\n", file, iocb->ki_pos,
-	     iov_iter_count(to), (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
+	doutc(cl, "on file %p %llx~%zx %s\n", file, iocb->ki_pos,
+	      iov_iter_count(to),
+	      (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
 
 	return __ceph_sync_read(inode, &iocb->ki_pos, to, retry_op, NULL);
 }
@@ -1190,6 +1219,7 @@ static void ceph_aio_retry_work(struct work_struct *work);
 static void ceph_aio_complete(struct inode *inode,
 			      struct ceph_aio_request *aio_req)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int ret;
 
@@ -1203,7 +1233,7 @@ static void ceph_aio_complete(struct inode *inode,
 	if (!ret)
 		ret = aio_req->total_len;
 
-	dout("ceph_aio_complete %p rc %d\n", inode, ret);
+	doutc(cl, "%p %llx.%llx rc %d\n", inode, ceph_vinop(inode), ret);
 
 	if (ret >= 0 && aio_req->write) {
 		int dirty;
@@ -1242,11 +1272,13 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
 	struct ceph_client_metric *metric = &ceph_sb_to_mdsc(inode->i_sb)->metric;
 	unsigned int len = osd_data->bvec_pos.iter.bi_size;
 	bool sparse = (op->op == CEPH_OSD_OP_SPARSE_READ);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 
 	BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_BVECS);
 	BUG_ON(!osd_data->num_bvecs);
 
-	dout("ceph_aio_complete_req %p rc %d bytes %u\n", inode, rc, len);
+	doutc(cl, "req %p inode %p %llx.%llx, rc %d bytes %u\n", req,
+	      inode, ceph_vinop(inode), rc, len);
 
 	if (rc == -EOLDSNAPC) {
 		struct ceph_aio_work *aio_work;
@@ -1256,7 +1288,7 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req)
 		if (aio_work) {
 			INIT_WORK(&aio_work->work, ceph_aio_retry_work);
 			aio_work->req = req;
-			queue_work(ceph_inode_to_client(inode)->inode_wq,
+			queue_work(ceph_inode_to_fs_client(inode)->inode_wq,
 				   &aio_work->work);
 			return;
 		}
@@ -1386,7 +1418,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_client_metric *metric = &fsc->mdsc->metric;
 	struct ceph_vino vino;
 	struct ceph_osd_request *req;
@@ -1405,9 +1438,9 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 	if (write && ceph_snap(file_inode(file)) != CEPH_NOSNAP)
 		return -EROFS;
 
-	dout("sync_direct_%s on file %p %lld~%u snapc %p seq %lld\n",
-	     (write ? "write" : "read"), file, pos, (unsigned)count,
-	     snapc, snapc ? snapc->seq : 0);
+	doutc(cl, "sync_direct_%s on file %p %lld~%u snapc %p seq %lld\n",
+	      (write ? "write" : "read"), file, pos, (unsigned)count,
+	      snapc, snapc ? snapc->seq : 0);
 
 	if (write) {
 		int ret2;
@@ -1418,7 +1451,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 					pos >> PAGE_SHIFT,
 					(pos + count - 1) >> PAGE_SHIFT);
 		if (ret2 < 0)
-			dout("invalidate_inode_pages2_range returned %d\n", ret2);
+			doutc(cl, "invalidate_inode_pages2_range returned %d\n",
+			      ret2);
 
 		flags = /* CEPH_OSD_FLAG_ORDERSNAP | */ CEPH_OSD_FLAG_WRITE;
 	} else {
@@ -1610,7 +1644,8 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	struct ceph_osd_request *req;
 	struct page **pages;
@@ -1625,8 +1660,8 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
 		return -EROFS;
 
-	dout("sync_write on file %p %lld~%u snapc %p seq %lld\n",
-	     file, pos, (unsigned)count, snapc, snapc->seq);
+	doutc(cl, "on file %p %lld~%u snapc %p seq %lld\n", file, pos,
+	      (unsigned)count, snapc, snapc->seq);
 
 	ret = filemap_write_and_wait_range(inode->i_mapping,
 					   pos, pos + count - 1);
@@ -1670,9 +1705,9 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 		last = (pos + len) != (write_pos + write_len);
 		rmw = first || last;
 
-		dout("sync_write ino %llx %lld~%llu adjusted %lld~%llu -- %srmw\n",
-		     ci->i_vino.ino, pos, len, write_pos, write_len,
-		     rmw ? "" : "no ");
+		doutc(cl, "ino %llx %lld~%llu adjusted %lld~%llu -- %srmw\n",
+		      ci->i_vino.ino, pos, len, write_pos, write_len,
+		      rmw ? "" : "no ");
 
 		/*
 		 * The data is emplaced into the page as it would be if it were
@@ -1881,7 +1916,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 			left -= ret;
 		}
 		if (ret < 0) {
-			dout("sync_write write failed with %d\n", ret);
+			doutc(cl, "write failed with %d\n", ret);
 			ceph_release_page_vector(pages, num_pages);
 			break;
 		}
@@ -1891,7 +1926,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 							 write_pos, write_len,
 							 GFP_KERNEL);
 			if (ret < 0) {
-				dout("encryption failed with %d\n", ret);
+				doutc(cl, "encryption failed with %d\n", ret);
 				ceph_release_page_vector(pages, num_pages);
 				break;
 			}
@@ -1910,7 +1945,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 			break;
 		}
 
-		dout("sync_write write op %lld~%llu\n", write_pos, write_len);
+		doutc(cl, "write op %lld~%llu\n", write_pos, write_len);
 		osd_req_op_extent_osd_data_pages(req, rmw ? 1 : 0, pages, write_len,
 						 offset_in_page(write_pos), false,
 						 true);
@@ -1941,7 +1976,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 					  req->r_end_latency, len, ret);
 		ceph_osdc_put_request(req);
 		if (ret != 0) {
-			dout("sync_write osd write returned %d\n", ret);
+			doutc(cl, "osd write returned %d\n", ret);
 			/* Version changed! Must re-do the rmw cycle */
 			if ((assert_ver && (ret == -ERANGE || ret == -EOVERFLOW)) ||
 			    (!assert_ver && ret == -EEXIST)) {
@@ -1971,13 +2006,13 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 				pos >> PAGE_SHIFT,
 				(pos + len - 1) >> PAGE_SHIFT);
 		if (ret < 0) {
-			dout("invalidate_inode_pages2_range returned %d\n",
-			     ret);
+			doutc(cl, "invalidate_inode_pages2_range returned %d\n",
+			      ret);
 			ret = 0;
 		}
 		pos += len;
 		written += len;
-		dout("sync_write written %d\n", written);
+		doutc(cl, "written %d\n", written);
 		if (pos > i_size_read(inode)) {
 			check_caps = ceph_inode_set_size(inode, pos);
 			if (check_caps)
@@ -1991,7 +2026,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 		ret = written;
 		iocb->ki_pos = pos;
 	}
-	dout("sync_write returning %d\n", ret);
+	doutc(cl, "returning %d\n", ret);
 	return ret;
 }
 
@@ -2010,13 +2045,14 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *inode = file_inode(filp);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	bool direct_lock = iocb->ki_flags & IOCB_DIRECT;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	ssize_t ret;
 	int want = 0, got = 0;
 	int retry_op = 0, read = 0;
 
 again:
-	dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n",
-	     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, inode);
+	doutc(cl, "%llu~%u trying to get caps on %p %llx.%llx\n",
+	      iocb->ki_pos, (unsigned)len, inode, ceph_vinop(inode));
 
 	if (ceph_inode_is_shutdown(inode))
 		return -ESTALE;
@@ -2044,9 +2080,9 @@ again:
 	    (iocb->ki_flags & IOCB_DIRECT) ||
 	    (fi->flags & CEPH_F_SYNC)) {
 
-		dout("aio_sync_read %p %llx.%llx %llu~%u got cap refs on %s\n",
-		     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
-		     ceph_cap_string(got));
+		doutc(cl, "sync %p %llx.%llx %llu~%u got cap refs on %s\n",
+		      inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
+		      ceph_cap_string(got));
 
 		if (!ceph_has_inline_data(ci)) {
 			if (!retry_op &&
@@ -2064,16 +2100,16 @@ again:
 		}
 	} else {
 		CEPH_DEFINE_RW_CONTEXT(rw_ctx, got);
-		dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n",
-		     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
-		     ceph_cap_string(got));
+		doutc(cl, "async %p %llx.%llx %llu~%u got cap refs on %s\n",
+		      inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
+		      ceph_cap_string(got));
 		ceph_add_rw_context(fi, &rw_ctx);
 		ret = generic_file_read_iter(iocb, to);
 		ceph_del_rw_context(fi, &rw_ctx);
 	}
 
-	dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
-	     inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
+	doutc(cl, "%p %llx.%llx dropping cap refs on %s = %d\n",
+	      inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
 	ceph_put_cap_refs(ci, got);
 
 	if (direct_lock)
@@ -2133,8 +2169,8 @@ again:
 		/* hit EOF or hole? */
 		if (retry_op == CHECK_EOF && iocb->ki_pos < i_size &&
 		    ret < len) {
-			dout("sync_read hit hole, ppos %lld < size %lld"
-			     ", reading more\n", iocb->ki_pos, i_size);
+			doutc(cl, "hit hole, ppos %lld < size %lld, reading more\n",
+			      iocb->ki_pos, i_size);
 
 			read += ret;
 			len -= ret;
@@ -2228,7 +2264,8 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct ceph_file_info *fi = file->private_data;
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	struct ceph_cap_flush *prealloc_cf;
 	ssize_t count, written = 0;
@@ -2296,8 +2333,9 @@ retry_snap:
 	if (err)
 		goto out;
 
-	dout("aio_write %p %llx.%llx %llu~%zd getting caps. i_size %llu\n",
-	     inode, ceph_vinop(inode), pos, count, i_size_read(inode));
+	doutc(cl, "%p %llx.%llx %llu~%zd getting caps. i_size %llu\n",
+	      inode, ceph_vinop(inode), pos, count,
+	      i_size_read(inode));
 	if (!(fi->flags & CEPH_F_SYNC) && !direct_lock)
 		want |= CEPH_CAP_FILE_BUFFER;
 	if (fi->fmode & CEPH_FILE_MODE_LAZY)
@@ -2313,8 +2351,8 @@ retry_snap:
 
 	inode_inc_iversion_raw(inode);
 
-	dout("aio_write %p %llx.%llx %llu~%zd got cap refs on %s\n",
-	     inode, ceph_vinop(inode), pos, count, ceph_cap_string(got));
+	doutc(cl, "%p %llx.%llx %llu~%zd got cap refs on %s\n",
+	      inode, ceph_vinop(inode), pos, count, ceph_cap_string(got));
 
 	if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
 	    (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC) ||
@@ -2374,14 +2412,14 @@ retry_snap:
 			ceph_check_caps(ci, CHECK_CAPS_FLUSH);
 	}
 
-	dout("aio_write %p %llx.%llx %llu~%u  dropping cap refs on %s\n",
-	     inode, ceph_vinop(inode), pos, (unsigned)count,
-	     ceph_cap_string(got));
+	doutc(cl, "%p %llx.%llx %llu~%u  dropping cap refs on %s\n",
+	      inode, ceph_vinop(inode), pos, (unsigned)count,
+	      ceph_cap_string(got));
 	ceph_put_cap_refs(ci, got);
 
 	if (written == -EOLDSNAPC) {
-		dout("aio_write %p %llx.%llx %llu~%u" "got EOLDSNAPC, retrying\n",
-		     inode, ceph_vinop(inode), pos, (unsigned)count);
+		doutc(cl, "%p %llx.%llx %llu~%u" "got EOLDSNAPC, retrying\n",
+		      inode, ceph_vinop(inode), pos, (unsigned)count);
 		goto retry_snap;
 	}
 
@@ -2462,7 +2500,7 @@ static int ceph_zero_partial_object(struct inode *inode,
 				    loff_t offset, loff_t *length)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 	struct ceph_osd_request *req;
 	int ret = 0;
 	loff_t zero = 0;
@@ -2553,14 +2591,15 @@ static long ceph_fallocate(struct file *file, int mode,
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_cap_flush *prealloc_cf;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int want, got = 0;
 	int dirty;
 	int ret = 0;
 	loff_t endoff = 0;
 	loff_t size;
 
-	dout("%s %p %llx.%llx mode %x, offset %llu length %llu\n", __func__,
-	     inode, ceph_vinop(inode), mode, offset, length);
+	doutc(cl, "%p %llx.%llx mode %x, offset %llu length %llu\n",
+	      inode, ceph_vinop(inode), mode, offset, length);
 
 	if (mode != (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
 		return -EOPNOTSUPP;
@@ -2689,6 +2728,7 @@ static void put_rd_wr_caps(struct ceph_inode_info *src_ci, int src_got,
 static int is_file_size_ok(struct inode *src_inode, struct inode *dst_inode,
 			   loff_t src_off, loff_t dst_off, size_t len)
 {
+	struct ceph_client *cl = ceph_inode_to_client(src_inode);
 	loff_t size, endoff;
 
 	size = i_size_read(src_inode);
@@ -2699,8 +2739,8 @@ static int is_file_size_ok(struct inode *src_inode, struct inode *dst_inode,
 	 * inode.
 	 */
 	if (src_off + len > size) {
-		dout("Copy beyond EOF (%llu + %zu > %llu)\n",
-		     src_off, len, size);
+		doutc(cl, "Copy beyond EOF (%llu + %zu > %llu)\n", src_off,
+		      len, size);
 		return -EOPNOTSUPP;
 	}
 	size = i_size_read(dst_inode);
@@ -2776,6 +2816,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off
 	u64 src_objnum, src_objoff, dst_objnum, dst_objoff;
 	u32 src_objlen, dst_objlen;
 	u32 object_size = src_ci->i_layout.object_size;
+	struct ceph_client *cl = fsc->client;
 	int ret;
 
 	src_oloc.pool = src_ci->i_layout.pool_id;
@@ -2817,9 +2858,10 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off
 		if (ret) {
 			if (ret == -EOPNOTSUPP) {
 				fsc->have_copy_from2 = false;
-				pr_notice("OSDs don't support copy-from2; disabling copy offload\n");
+				pr_notice_client(cl,
+					"OSDs don't support copy-from2; disabling copy offload\n");
 			}
-			dout("ceph_osdc_copy_from returned %d\n", ret);
+			doutc(cl, "returned %d\n", ret);
 			if (!bytes)
 				bytes = ret;
 			goto out;
@@ -2845,7 +2887,8 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 	struct ceph_inode_info *src_ci = ceph_inode(src_inode);
 	struct ceph_inode_info *dst_ci = ceph_inode(dst_inode);
 	struct ceph_cap_flush *prealloc_cf;
-	struct ceph_fs_client *src_fsc = ceph_inode_to_client(src_inode);
+	struct ceph_fs_client *src_fsc = ceph_inode_to_fs_client(src_inode);
+	struct ceph_client *cl = src_fsc->client;
 	loff_t size;
 	ssize_t ret = -EIO, bytes;
 	u64 src_objnum, dst_objnum, src_objoff, dst_objoff;
@@ -2853,7 +2896,7 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 	int src_got = 0, dst_got = 0, err, dirty;
 
 	if (src_inode->i_sb != dst_inode->i_sb) {
-		struct ceph_fs_client *dst_fsc = ceph_inode_to_client(dst_inode);
+		struct ceph_fs_client *dst_fsc = ceph_inode_to_fs_client(dst_inode);
 
 		if (ceph_fsid_compare(&src_fsc->client->fsid,
 				      &dst_fsc->client->fsid)) {
@@ -2888,7 +2931,7 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 	    (src_ci->i_layout.stripe_count != 1) ||
 	    (dst_ci->i_layout.stripe_count != 1) ||
 	    (src_ci->i_layout.object_size != dst_ci->i_layout.object_size)) {
-		dout("Invalid src/dst files layout\n");
+		doutc(cl, "Invalid src/dst files layout\n");
 		return -EOPNOTSUPP;
 	}
 
@@ -2906,12 +2949,12 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 	/* Start by sync'ing the source and destination files */
 	ret = file_write_and_wait_range(src_file, src_off, (src_off + len));
 	if (ret < 0) {
-		dout("failed to write src file (%zd)\n", ret);
+		doutc(cl, "failed to write src file (%zd)\n", ret);
 		goto out;
 	}
 	ret = file_write_and_wait_range(dst_file, dst_off, (dst_off + len));
 	if (ret < 0) {
-		dout("failed to write dst file (%zd)\n", ret);
+		doutc(cl, "failed to write dst file (%zd)\n", ret);
 		goto out;
 	}
 
@@ -2923,7 +2966,7 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 	err = get_rd_wr_caps(src_file, &src_got,
 			     dst_file, (dst_off + len), &dst_got);
 	if (err < 0) {
-		dout("get_rd_wr_caps returned %d\n", err);
+		doutc(cl, "get_rd_wr_caps returned %d\n", err);
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
@@ -2938,7 +2981,8 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 					    dst_off >> PAGE_SHIFT,
 					    (dst_off + len) >> PAGE_SHIFT);
 	if (ret < 0) {
-		dout("Failed to invalidate inode pages (%zd)\n", ret);
+		doutc(cl, "Failed to invalidate inode pages (%zd)\n",
+			    ret);
 		ret = 0; /* XXX */
 	}
 	ceph_calc_file_object_mapping(&src_ci->i_layout, src_off,
@@ -2959,7 +3003,7 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 	 * starting at the src_off
 	 */
 	if (src_objoff) {
-		dout("Initial partial copy of %u bytes\n", src_objlen);
+		doutc(cl, "Initial partial copy of %u bytes\n", src_objlen);
 
 		/*
 		 * we need to temporarily drop all caps as we'll be calling
@@ -2970,7 +3014,7 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 				       &dst_off, src_objlen, flags);
 		/* Abort on short copies or on error */
 		if (ret < (long)src_objlen) {
-			dout("Failed partial copy (%zd)\n", ret);
+			doutc(cl, "Failed partial copy (%zd)\n", ret);
 			goto out;
 		}
 		len -= ret;
@@ -2992,7 +3036,7 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 			ret = bytes;
 		goto out_caps;
 	}
-	dout("Copied %zu bytes out of %zu\n", bytes, len);
+	doutc(cl, "Copied %zu bytes out of %zu\n", bytes, len);
 	len -= bytes;
 	ret += bytes;
 
@@ -3020,13 +3064,13 @@ out_caps:
 	 * there were errors in remote object copies (len >= object_size).
 	 */
 	if (len && (len < src_ci->i_layout.object_size)) {
-		dout("Final partial copy of %zu bytes\n", len);
+		doutc(cl, "Final partial copy of %zu bytes\n", len);
 		bytes = do_splice_direct(src_file, &src_off, dst_file,
 					 &dst_off, len, flags);
 		if (bytes > 0)
 			ret += bytes;
 		else
-			dout("Failed partial copy (%zd)\n", bytes);
+			doutc(cl, "Failed partial copy (%zd)\n", bytes);
 	}
 
 out:
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 2e2a303b9e649d..0679240f06db92 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -129,6 +129,8 @@ void ceph_as_ctx_to_req(struct ceph_mds_request *req,
 struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino,
 			     struct inode *newino)
 {
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct inode *inode;
 
 	if (ceph_vino_is_reserved(vino))
@@ -145,12 +147,13 @@ struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino,
 	}
 
 	if (!inode) {
-		dout("No inode found for %llx.%llx\n", vino.ino, vino.snap);
+		doutc(cl, "no inode found for %llx.%llx\n", vino.ino, vino.snap);
 		return ERR_PTR(-ENOMEM);
 	}
 
-	dout("get_inode on %llu=%llx.%llx got %p new %d\n", ceph_present_inode(inode),
-	     ceph_vinop(inode), inode, !!(inode->i_state & I_NEW));
+	doutc(cl, "on %llx=%llx.%llx got %p new %d\n",
+	      ceph_present_inode(inode), ceph_vinop(inode), inode,
+	      !!(inode->i_state & I_NEW));
 	return inode;
 }
 
@@ -159,6 +162,7 @@ struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino,
  */
 struct inode *ceph_get_snapdir(struct inode *parent)
 {
+	struct ceph_client *cl = ceph_inode_to_client(parent);
 	struct ceph_vino vino = {
 		.ino = ceph_ino(parent),
 		.snap = CEPH_SNAPDIR,
@@ -171,14 +175,14 @@ struct inode *ceph_get_snapdir(struct inode *parent)
 		return inode;
 
 	if (!S_ISDIR(parent->i_mode)) {
-		pr_warn_once("bad snapdir parent type (mode=0%o)\n",
-			     parent->i_mode);
+		pr_warn_once_client(cl, "bad snapdir parent type (mode=0%o)\n",
+				    parent->i_mode);
 		goto err;
 	}
 
 	if (!(inode->i_state & I_NEW) && !S_ISDIR(inode->i_mode)) {
-		pr_warn_once("bad snapdir inode type (mode=0%o)\n",
-			     inode->i_mode);
+		pr_warn_once_client(cl, "bad snapdir inode type (mode=0%o)\n",
+				    inode->i_mode);
 		goto err;
 	}
 
@@ -203,7 +207,7 @@ struct inode *ceph_get_snapdir(struct inode *parent)
 			inode->i_flags |= S_ENCRYPTED;
 			ci->fscrypt_auth_len = pci->fscrypt_auth_len;
 		} else {
-			dout("Failed to alloc snapdir fscrypt_auth\n");
+			doutc(cl, "Failed to alloc snapdir fscrypt_auth\n");
 			ret = -ENOMEM;
 			goto err;
 		}
@@ -249,6 +253,8 @@ const struct inode_operations ceph_file_iops = {
 static struct ceph_inode_frag *__get_or_create_frag(struct ceph_inode_info *ci,
 						    u32 f)
 {
+	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct ceph_inode_frag *frag;
@@ -279,8 +285,7 @@ static struct ceph_inode_frag *__get_or_create_frag(struct ceph_inode_info *ci,
 	rb_link_node(&frag->node, parent, p);
 	rb_insert_color(&frag->node, &ci->i_fragtree);
 
-	dout("get_or_create_frag added %llx.%llx frag %x\n",
-	     ceph_vinop(&ci->netfs.inode), f);
+	doutc(cl, "added %p %llx.%llx frag %x\n", inode, ceph_vinop(inode), f);
 	return frag;
 }
 
@@ -313,6 +318,7 @@ struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci, u32 f)
 static u32 __ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
 			      struct ceph_inode_frag *pfrag, int *found)
 {
+	struct ceph_client *cl = ceph_inode_to_client(&ci->netfs.inode);
 	u32 t = ceph_frag_make(0, 0);
 	struct ceph_inode_frag *frag;
 	unsigned nway, i;
@@ -336,8 +342,8 @@ static u32 __ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
 
 		/* choose child */
 		nway = 1 << frag->split_by;
-		dout("choose_frag(%x) %x splits by %d (%d ways)\n", v, t,
-		     frag->split_by, nway);
+		doutc(cl, "frag(%x) %x splits by %d (%d ways)\n", v, t,
+		      frag->split_by, nway);
 		for (i = 0; i < nway; i++) {
 			n = ceph_frag_make_child(t, frag->split_by, i);
 			if (ceph_frag_contains_value(n, v)) {
@@ -347,7 +353,7 @@ static u32 __ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
 		}
 		BUG_ON(i == nway);
 	}
-	dout("choose_frag(%x) = %x\n", v, t);
+	doutc(cl, "frag(%x) = %x\n", v, t);
 
 	return t;
 }
@@ -371,6 +377,7 @@ static int ceph_fill_dirfrag(struct inode *inode,
 			     struct ceph_mds_reply_dirfrag *dirinfo)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_frag *frag;
 	u32 id = le32_to_cpu(dirinfo->frag);
 	int mds = le32_to_cpu(dirinfo->auth);
@@ -395,14 +402,14 @@ static int ceph_fill_dirfrag(struct inode *inode,
 			goto out;
 		if (frag->split_by == 0) {
 			/* tree leaf, remove */
-			dout("fill_dirfrag removed %llx.%llx frag %x"
-			     " (no ref)\n", ceph_vinop(inode), id);
+			doutc(cl, "removed %p %llx.%llx frag %x (no ref)\n",
+			      inode, ceph_vinop(inode), id);
 			rb_erase(&frag->node, &ci->i_fragtree);
 			kfree(frag);
 		} else {
 			/* tree branch, keep and clear */
-			dout("fill_dirfrag cleared %llx.%llx frag %x"
-			     " referral\n", ceph_vinop(inode), id);
+			doutc(cl, "cleared %p %llx.%llx frag %x referral\n",
+			      inode, ceph_vinop(inode), id);
 			frag->mds = -1;
 			frag->ndist = 0;
 		}
@@ -415,8 +422,9 @@ static int ceph_fill_dirfrag(struct inode *inode,
 	if (IS_ERR(frag)) {
 		/* this is not the end of the world; we can continue
 		   with bad/inaccurate delegation info */
-		pr_err("fill_dirfrag ENOMEM on mds ref %llx.%llx fg %x\n",
-		       ceph_vinop(inode), le32_to_cpu(dirinfo->frag));
+		pr_err_client(cl, "ENOMEM on mds ref %p %llx.%llx fg %x\n",
+			      inode, ceph_vinop(inode),
+			      le32_to_cpu(dirinfo->frag));
 		err = -ENOMEM;
 		goto out;
 	}
@@ -425,8 +433,8 @@ static int ceph_fill_dirfrag(struct inode *inode,
 	frag->ndist = min_t(u32, ndist, CEPH_MAX_DIRFRAG_REP);
 	for (i = 0; i < frag->ndist; i++)
 		frag->dist[i] = le32_to_cpu(dirinfo->dist[i]);
-	dout("fill_dirfrag %llx.%llx frag %x ndist=%d\n",
-	     ceph_vinop(inode), frag->frag, frag->ndist);
+	doutc(cl, "%p %llx.%llx frag %x ndist=%d\n", inode,
+	      ceph_vinop(inode), frag->frag, frag->ndist);
 
 out:
 	mutex_unlock(&ci->i_fragtree_mutex);
@@ -454,6 +462,7 @@ static int ceph_fill_fragtree(struct inode *inode,
 			      struct ceph_frag_tree_head *fragtree,
 			      struct ceph_mds_reply_dirfrag *dirinfo)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_inode_frag *frag, *prev_frag = NULL;
 	struct rb_node *rb_node;
@@ -489,15 +498,15 @@ static int ceph_fill_fragtree(struct inode *inode,
 		     frag_tree_split_cmp, NULL);
 	}
 
-	dout("fill_fragtree %llx.%llx\n", ceph_vinop(inode));
+	doutc(cl, "%p %llx.%llx\n", inode, ceph_vinop(inode));
 	rb_node = rb_first(&ci->i_fragtree);
 	for (i = 0; i < nsplits; i++) {
 		id = le32_to_cpu(fragtree->splits[i].frag);
 		split_by = le32_to_cpu(fragtree->splits[i].by);
 		if (split_by == 0 || ceph_frag_bits(id) + split_by > 24) {
-			pr_err("fill_fragtree %llx.%llx invalid split %d/%u, "
-			       "frag %x split by %d\n", ceph_vinop(inode),
-			       i, nsplits, id, split_by);
+			pr_err_client(cl, "%p %llx.%llx invalid split %d/%u, "
+			       "frag %x split by %d\n", inode,
+			       ceph_vinop(inode), i, nsplits, id, split_by);
 			continue;
 		}
 		frag = NULL;
@@ -529,7 +538,7 @@ static int ceph_fill_fragtree(struct inode *inode,
 		if (frag->split_by == 0)
 			ci->i_fragtree_nsplits++;
 		frag->split_by = split_by;
-		dout(" frag %x split by %d\n", frag->frag, frag->split_by);
+		doutc(cl, " frag %x split by %d\n", frag->frag, frag->split_by);
 		prev_frag = frag;
 	}
 	while (rb_node) {
@@ -554,6 +563,7 @@ out_unlock:
  */
 struct inode *ceph_alloc_inode(struct super_block *sb)
 {
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb);
 	struct ceph_inode_info *ci;
 	int i;
 
@@ -561,7 +571,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	if (!ci)
 		return NULL;
 
-	dout("alloc_inode %p\n", &ci->netfs.inode);
+	doutc(fsc->client, "%p\n", &ci->netfs.inode);
 
 	/* Set parameters for the netfs library */
 	netfs_inode_init(&ci->netfs, &ceph_netfs_ops);
@@ -675,10 +685,11 @@ void ceph_evict_inode(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_frag *frag;
 	struct rb_node *n;
 
-	dout("evict_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode));
+	doutc(cl, "%p ino %llx.%llx\n", inode, ceph_vinop(inode));
 
 	percpu_counter_dec(&mdsc->metric.total_inodes);
 
@@ -701,8 +712,8 @@ void ceph_evict_inode(struct inode *inode)
 	 */
 	if (ci->i_snap_realm) {
 		if (ceph_snap(inode) == CEPH_NOSNAP) {
-			dout(" dropping residual ref to snap realm %p\n",
-			     ci->i_snap_realm);
+			doutc(cl, " dropping residual ref to snap realm %p\n",
+			      ci->i_snap_realm);
 			ceph_change_snap_realm(inode, NULL);
 		} else {
 			ceph_put_snapid_map(mdsc, ci->i_snapid_map);
@@ -743,15 +754,16 @@ static inline blkcnt_t calc_inode_blocks(u64 size)
 int ceph_fill_file_size(struct inode *inode, int issued,
 			u32 truncate_seq, u64 truncate_size, u64 size)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int queue_trunc = 0;
 	loff_t isize = i_size_read(inode);
 
 	if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) > 0 ||
 	    (truncate_seq == ci->i_truncate_seq && size > isize)) {
-		dout("size %lld -> %llu\n", isize, size);
+		doutc(cl, "size %lld -> %llu\n", isize, size);
 		if (size > 0 && S_ISDIR(inode->i_mode)) {
-			pr_err("fill_file_size non-zero size for directory\n");
+			pr_err_client(cl, "non-zero size for directory\n");
 			size = 0;
 		}
 		i_size_write(inode, size);
@@ -764,8 +776,8 @@ int ceph_fill_file_size(struct inode *inode, int issued,
 			ceph_fscache_update(inode);
 		ci->i_reported_size = size;
 		if (truncate_seq != ci->i_truncate_seq) {
-			dout("%s truncate_seq %u -> %u\n", __func__,
-			     ci->i_truncate_seq, truncate_seq);
+			doutc(cl, "truncate_seq %u -> %u\n",
+			      ci->i_truncate_seq, truncate_seq);
 			ci->i_truncate_seq = truncate_seq;
 
 			/* the MDS should have revoked these caps */
@@ -794,14 +806,15 @@ int ceph_fill_file_size(struct inode *inode, int issued,
 	 * anyway.
 	 */
 	if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) >= 0) {
-		dout("%s truncate_size %lld -> %llu, encrypted %d\n", __func__,
-		     ci->i_truncate_size, truncate_size, !!IS_ENCRYPTED(inode));
+		doutc(cl, "truncate_size %lld -> %llu, encrypted %d\n",
+		      ci->i_truncate_size, truncate_size,
+		      !!IS_ENCRYPTED(inode));
 
 		ci->i_truncate_size = truncate_size;
 
 		if (IS_ENCRYPTED(inode)) {
-			dout("%s truncate_pagecache_size %lld -> %llu\n",
-			     __func__, ci->i_truncate_pagecache_size, size);
+			doutc(cl, "truncate_pagecache_size %lld -> %llu\n",
+			      ci->i_truncate_pagecache_size, size);
 			ci->i_truncate_pagecache_size = size;
 		} else {
 			ci->i_truncate_pagecache_size = truncate_size;
@@ -814,6 +827,7 @@ void ceph_fill_file_time(struct inode *inode, int issued,
 			 u64 time_warp_seq, struct timespec64 *ctime,
 			 struct timespec64 *mtime, struct timespec64 *atime)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct timespec64 ictime = inode_get_ctime(inode);
 	int warn = 0;
@@ -825,7 +839,7 @@ void ceph_fill_file_time(struct inode *inode, int issued,
 		      CEPH_CAP_XATTR_EXCL)) {
 		if (ci->i_version == 0 ||
 		    timespec64_compare(ctime, &ictime) > 0) {
-			dout("ctime %lld.%09ld -> %lld.%09ld inc w/ cap\n",
+			doutc(cl, "ctime %lld.%09ld -> %lld.%09ld inc w/ cap\n",
 			     ictime.tv_sec, ictime.tv_nsec,
 			     ctime->tv_sec, ctime->tv_nsec);
 			inode_set_ctime_to_ts(inode, *ctime);
@@ -833,8 +847,7 @@ void ceph_fill_file_time(struct inode *inode, int issued,
 		if (ci->i_version == 0 ||
 		    ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) > 0) {
 			/* the MDS did a utimes() */
-			dout("mtime %lld.%09ld -> %lld.%09ld "
-			     "tw %d -> %d\n",
+			doutc(cl, "mtime %lld.%09ld -> %lld.%09ld tw %d -> %d\n",
 			     inode_get_mtime_sec(inode),
 			     inode_get_mtime_nsec(inode),
 			     mtime->tv_sec, mtime->tv_nsec,
@@ -849,14 +862,14 @@ void ceph_fill_file_time(struct inode *inode, int issued,
 			/* nobody did utimes(); take the max */
 			ts = inode_get_mtime(inode);
 			if (timespec64_compare(mtime, &ts) > 0) {
-				dout("mtime %lld.%09ld -> %lld.%09ld inc\n",
+				doutc(cl, "mtime %lld.%09ld -> %lld.%09ld inc\n",
 				     ts.tv_sec, ts.tv_nsec,
 				     mtime->tv_sec, mtime->tv_nsec);
 				inode_set_mtime_to_ts(inode, *mtime);
 			}
 			ts = inode_get_atime(inode);
 			if (timespec64_compare(atime, &ts) > 0) {
-				dout("atime %lld.%09ld -> %lld.%09ld inc\n",
+				doutc(cl, "atime %lld.%09ld -> %lld.%09ld inc\n",
 				     ts.tv_sec, ts.tv_nsec,
 				     atime->tv_sec, atime->tv_nsec);
 				inode_set_atime_to_ts(inode, *atime);
@@ -878,13 +891,16 @@ void ceph_fill_file_time(struct inode *inode, int issued,
 		}
 	}
 	if (warn) /* time_warp_seq shouldn't go backwards */
-		dout("%p mds time_warp_seq %llu < %u\n",
-		     inode, time_warp_seq, ci->i_time_warp_seq);
+		doutc(cl, "%p mds time_warp_seq %llu < %u\n", inode,
+		      time_warp_seq, ci->i_time_warp_seq);
 }
 
 #if IS_ENABLED(CONFIG_FS_ENCRYPTION)
-static int decode_encrypted_symlink(const char *encsym, int enclen, u8 **decsym)
+static int decode_encrypted_symlink(struct ceph_mds_client *mdsc,
+				    const char *encsym,
+				    int enclen, u8 **decsym)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	int declen;
 	u8 *sym;
 
@@ -894,8 +910,9 @@ static int decode_encrypted_symlink(const char *encsym, int enclen, u8 **decsym)
 
 	declen = ceph_base64_decode(encsym, enclen, sym);
 	if (declen < 0) {
-		pr_err("%s: can't decode symlink (%d). Content: %.*s\n",
-		       __func__, declen, enclen, encsym);
+		pr_err_client(cl,
+			"can't decode symlink (%d). Content: %.*s\n",
+			declen, enclen, encsym);
 		kfree(sym);
 		return -EIO;
 	}
@@ -904,7 +921,9 @@ static int decode_encrypted_symlink(const char *encsym, int enclen, u8 **decsym)
 	return declen;
 }
 #else
-static int decode_encrypted_symlink(const char *encsym, int symlen, u8 **decsym)
+static int decode_encrypted_symlink(struct ceph_mds_client *mdsc,
+				    const char *encsym,
+				    int symlen, u8 **decsym)
 {
 	return -EOPNOTSUPP;
 }
@@ -921,6 +940,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 		    struct ceph_cap_reservation *caps_reservation)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_reply_inode *info = iinfo->in;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int issued, new_issued, info_caps;
@@ -939,25 +959,26 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 
 	lockdep_assert_held(&mdsc->snap_rwsem);
 
-	dout("%s %p ino %llx.%llx v %llu had %llu\n", __func__,
-	     inode, ceph_vinop(inode), le64_to_cpu(info->version),
-	     ci->i_version);
+	doutc(cl, "%p ino %llx.%llx v %llu had %llu\n", inode, ceph_vinop(inode),
+	      le64_to_cpu(info->version), ci->i_version);
 
 	/* Once I_NEW is cleared, we can't change type or dev numbers */
 	if (inode->i_state & I_NEW) {
 		inode->i_mode = mode;
 	} else {
 		if (inode_wrong_type(inode, mode)) {
-			pr_warn_once("inode type changed! (ino %llx.%llx is 0%o, mds says 0%o)\n",
-				     ceph_vinop(inode), inode->i_mode, mode);
+			pr_warn_once_client(cl,
+				"inode type changed! (ino %llx.%llx is 0%o, mds says 0%o)\n",
+				ceph_vinop(inode), inode->i_mode, mode);
 			return -ESTALE;
 		}
 
 		if ((S_ISCHR(mode) || S_ISBLK(mode)) && inode->i_rdev != rdev) {
-			pr_warn_once("dev inode rdev changed! (ino %llx.%llx is %u:%u, mds says %u:%u)\n",
-				     ceph_vinop(inode), MAJOR(inode->i_rdev),
-				     MINOR(inode->i_rdev), MAJOR(rdev),
-				     MINOR(rdev));
+			pr_warn_once_client(cl,
+				"dev inode rdev changed! (ino %llx.%llx is %u:%u, mds says %u:%u)\n",
+				ceph_vinop(inode), MAJOR(inode->i_rdev),
+				MINOR(inode->i_rdev), MAJOR(rdev),
+				MINOR(rdev));
 			return -ESTALE;
 		}
 	}
@@ -979,8 +1000,8 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 	if (iinfo->xattr_len > 4) {
 		xattr_blob = ceph_buffer_new(iinfo->xattr_len, GFP_NOFS);
 		if (!xattr_blob)
-			pr_err("%s ENOMEM xattr blob %d bytes\n", __func__,
-			       iinfo->xattr_len);
+			pr_err_client(cl, "ENOMEM xattr blob %d bytes\n",
+				      iinfo->xattr_len);
 	}
 
 	if (iinfo->pool_ns_len > 0)
@@ -1034,9 +1055,10 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 		inode->i_mode = mode;
 		inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(info->uid));
 		inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(info->gid));
-		dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
-		     from_kuid(&init_user_ns, inode->i_uid),
-		     from_kgid(&init_user_ns, inode->i_gid));
+		doutc(cl, "%p %llx.%llx mode 0%o uid.gid %d.%d\n", inode,
+		      ceph_vinop(inode), inode->i_mode,
+		      from_kuid(&init_user_ns, inode->i_uid),
+		      from_kgid(&init_user_ns, inode->i_gid));
 		ceph_decode_timespec64(&ci->i_btime, &iinfo->btime);
 		ceph_decode_timespec64(&ci->i_snap_btime, &iinfo->snap_btime);
 	}
@@ -1092,7 +1114,8 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 			if (size == round_up(fsize, CEPH_FSCRYPT_BLOCK_SIZE)) {
 				size = fsize;
 			} else {
-				pr_warn("fscrypt size mismatch: size=%llu fscrypt_file=%llu, discarding fscrypt_file size.\n",
+				pr_warn_client(cl,
+					"fscrypt size mismatch: size=%llu fscrypt_file=%llu, discarding fscrypt_file size.\n",
 					info->size, size);
 			}
 		}
@@ -1104,8 +1127,8 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 		/* only update max_size on auth cap */
 		if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
 		    ci->i_max_size != le64_to_cpu(info->max_size)) {
-			dout("max_size %lld -> %llu\n", ci->i_max_size,
-					le64_to_cpu(info->max_size));
+			doutc(cl, "max_size %lld -> %llu\n",
+			    ci->i_max_size, le64_to_cpu(info->max_size));
 			ci->i_max_size = le64_to_cpu(info->max_size);
 		}
 	}
@@ -1168,15 +1191,17 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 
 			if (IS_ENCRYPTED(inode)) {
 				if (symlen != i_size_read(inode))
-					pr_err("%s %llx.%llx BAD symlink size %lld\n",
-						__func__, ceph_vinop(inode),
+					pr_err_client(cl,
+						"%p %llx.%llx BAD symlink size %lld\n",
+						inode, ceph_vinop(inode),
 						i_size_read(inode));
 
-				err = decode_encrypted_symlink(iinfo->symlink,
+				err = decode_encrypted_symlink(mdsc, iinfo->symlink,
 							       symlen, (u8 **)&sym);
 				if (err < 0) {
-					pr_err("%s decoding encrypted symlink failed: %d\n",
-						__func__, err);
+					pr_err_client(cl,
+						"decoding encrypted symlink failed: %d\n",
+						err);
 					goto out;
 				}
 				symlen = err;
@@ -1184,8 +1209,9 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 				inode->i_blocks = calc_inode_blocks(symlen);
 			} else {
 				if (symlen != i_size_read(inode)) {
-					pr_err("%s %llx.%llx BAD symlink size %lld\n",
-						__func__, ceph_vinop(inode),
+					pr_err_client(cl,
+						"%p %llx.%llx BAD symlink size %lld\n",
+						inode, ceph_vinop(inode),
 						i_size_read(inode));
 					i_size_write(inode, symlen);
 					inode->i_blocks = calc_inode_blocks(symlen);
@@ -1220,8 +1246,8 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 		inode->i_fop = &ceph_dir_fops;
 		break;
 	default:
-		pr_err("%s %llx.%llx BAD mode 0%o\n", __func__,
-		       ceph_vinop(inode), inode->i_mode);
+		pr_err_client(cl, "%p %llx.%llx BAD mode 0%o\n", inode,
+			      ceph_vinop(inode), inode->i_mode);
 	}
 
 	/* were we issued a capability? */
@@ -1242,7 +1268,8 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 			    (info_caps & CEPH_CAP_FILE_SHARED) &&
 			    (issued & CEPH_CAP_FILE_EXCL) == 0 &&
 			    !__ceph_dir_is_complete(ci)) {
-				dout(" marking %p complete (empty)\n", inode);
+				doutc(cl, " marking %p complete (empty)\n",
+				      inode);
 				i_size_write(inode, 0);
 				__ceph_dir_set_complete(ci,
 					atomic64_read(&ci->i_release_count),
@@ -1251,8 +1278,8 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 
 			wake = true;
 		} else {
-			dout(" %p got snap_caps %s\n", inode,
-			     ceph_cap_string(info_caps));
+			doutc(cl, " %p got snap_caps %s\n", inode,
+			      ceph_cap_string(info_caps));
 			ci->i_snap_caps |= info_caps;
 		}
 	}
@@ -1268,8 +1295,8 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 
 	if (cap_fmode >= 0) {
 		if (!info_caps)
-			pr_warn("mds issued no caps on %llx.%llx\n",
-				ceph_vinop(inode));
+			pr_warn_client(cl, "mds issued no caps on %llx.%llx\n",
+				       ceph_vinop(inode));
 		__ceph_touch_fmode(ci, mdsc, cap_fmode);
 	}
 
@@ -1315,14 +1342,14 @@ static void __update_dentry_lease(struct inode *dir, struct dentry *dentry,
 				  unsigned long from_time,
 				  struct ceph_mds_session **old_lease_session)
 {
+	struct ceph_client *cl = ceph_inode_to_client(dir);
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
 	unsigned mask = le16_to_cpu(lease->mask);
 	long unsigned duration = le32_to_cpu(lease->duration_ms);
 	long unsigned ttl = from_time + (duration * HZ) / 1000;
 	long unsigned half_ttl = from_time + (duration * HZ / 2) / 1000;
 
-	dout("update_dentry_lease %p duration %lu ms ttl %lu\n",
-	     dentry, duration, ttl);
+	doutc(cl, "%p duration %lu ms ttl %lu\n", dentry, duration, ttl);
 
 	/* only track leases on regular dentries */
 	if (ceph_snap(dir) != CEPH_NOSNAP)
@@ -1423,6 +1450,7 @@ out_unlock:
  */
 static int splice_dentry(struct dentry **pdn, struct inode *in)
 {
+	struct ceph_client *cl = ceph_inode_to_client(in);
 	struct dentry *dn = *pdn;
 	struct dentry *realdn;
 
@@ -1454,23 +1482,21 @@ static int splice_dentry(struct dentry **pdn, struct inode *in)
 		d_drop(dn);
 	realdn = d_splice_alias(in, dn);
 	if (IS_ERR(realdn)) {
-		pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
-		       PTR_ERR(realdn), dn, in, ceph_vinop(in));
+		pr_err_client(cl, "error %ld %p inode %p ino %llx.%llx\n",
+			      PTR_ERR(realdn), dn, in, ceph_vinop(in));
 		return PTR_ERR(realdn);
 	}
 
 	if (realdn) {
-		dout("dn %p (%d) spliced with %p (%d) "
-		     "inode %p ino %llx.%llx\n",
-		     dn, d_count(dn),
-		     realdn, d_count(realdn),
-		     d_inode(realdn), ceph_vinop(d_inode(realdn)));
+		doutc(cl, "dn %p (%d) spliced with %p (%d) inode %p ino %llx.%llx\n",
+		      dn, d_count(dn), realdn, d_count(realdn),
+		      d_inode(realdn), ceph_vinop(d_inode(realdn)));
 		dput(dn);
 		*pdn = realdn;
 	} else {
 		BUG_ON(!ceph_dentry(dn));
-		dout("dn %p attached to %p ino %llx.%llx\n",
-		     dn, d_inode(dn), ceph_vinop(d_inode(dn)));
+		doutc(cl, "dn %p attached to %p ino %llx.%llx\n", dn,
+		      d_inode(dn), ceph_vinop(d_inode(dn)));
 	}
 	return 0;
 }
@@ -1492,14 +1518,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 	struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
 	struct inode *in = NULL;
 	struct ceph_vino tvino, dvino;
-	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb);
+	struct ceph_client *cl = fsc->client;
 	int err = 0;
 
-	dout("fill_trace %p is_dentry %d is_target %d\n", req,
-	     rinfo->head->is_dentry, rinfo->head->is_target);
+	doutc(cl, "%p is_dentry %d is_target %d\n", req,
+	      rinfo->head->is_dentry, rinfo->head->is_target);
 
 	if (!rinfo->head->is_target && !rinfo->head->is_dentry) {
-		dout("fill_trace reply is empty!\n");
+		doutc(cl, "reply is empty!\n");
 		if (rinfo->head->result == 0 && req->r_parent)
 			ceph_invalidate_dir_request(req);
 		return 0;
@@ -1556,13 +1583,13 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 			tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
 retry_lookup:
 			dn = d_lookup(parent, &dname);
-			dout("d_lookup on parent=%p name=%.*s got %p\n",
-			     parent, dname.len, dname.name, dn);
+			doutc(cl, "d_lookup on parent=%p name=%.*s got %p\n",
+			      parent, dname.len, dname.name, dn);
 
 			if (!dn) {
 				dn = d_alloc(parent, &dname);
-				dout("d_alloc %p '%.*s' = %p\n", parent,
-				     dname.len, dname.name, dn);
+				doutc(cl, "d_alloc %p '%.*s' = %p\n", parent,
+				      dname.len, dname.name, dn);
 				if (!dn) {
 					dput(parent);
 					ceph_fname_free_buffer(dir, &oname);
@@ -1578,8 +1605,8 @@ retry_lookup:
 			} else if (d_really_is_positive(dn) &&
 				   (ceph_ino(d_inode(dn)) != tvino.ino ||
 				    ceph_snap(d_inode(dn)) != tvino.snap)) {
-				dout(" dn %p points to wrong inode %p\n",
-				     dn, d_inode(dn));
+				doutc(cl, " dn %p points to wrong inode %p\n",
+				      dn, d_inode(dn));
 				ceph_dir_clear_ordered(dir);
 				d_delete(dn);
 				dput(dn);
@@ -1604,8 +1631,8 @@ retry_lookup:
 				 rinfo->head->result == 0) ?  req->r_fmode : -1,
 				&req->r_caps_reservation);
 		if (err < 0) {
-			pr_err("ceph_fill_inode badness %p %llx.%llx\n",
-				in, ceph_vinop(in));
+			pr_err_client(cl, "badness %p %llx.%llx\n", in,
+				      ceph_vinop(in));
 			req->r_target_inode = NULL;
 			if (in->i_state & I_NEW)
 				discard_new_inode(in);
@@ -1655,36 +1682,32 @@ retry_lookup:
 		have_lease = have_dir_cap ||
 			le32_to_cpu(rinfo->dlease->duration_ms);
 		if (!have_lease)
-			dout("fill_trace  no dentry lease or dir cap\n");
+			doutc(cl, "no dentry lease or dir cap\n");
 
 		/* rename? */
 		if (req->r_old_dentry && req->r_op == CEPH_MDS_OP_RENAME) {
 			struct inode *olddir = req->r_old_dentry_dir;
 			BUG_ON(!olddir);
 
-			dout(" src %p '%pd' dst %p '%pd'\n",
-			     req->r_old_dentry,
-			     req->r_old_dentry,
-			     dn, dn);
-			dout("fill_trace doing d_move %p -> %p\n",
-			     req->r_old_dentry, dn);
+			doutc(cl, " src %p '%pd' dst %p '%pd'\n",
+			      req->r_old_dentry, req->r_old_dentry, dn, dn);
+			doutc(cl, "doing d_move %p -> %p\n", req->r_old_dentry, dn);
 
 			/* d_move screws up sibling dentries' offsets */
 			ceph_dir_clear_ordered(dir);
 			ceph_dir_clear_ordered(olddir);
 
 			d_move(req->r_old_dentry, dn);
-			dout(" src %p '%pd' dst %p '%pd'\n",
-			     req->r_old_dentry,
-			     req->r_old_dentry,
-			     dn, dn);
+			doutc(cl, " src %p '%pd' dst %p '%pd'\n",
+			      req->r_old_dentry, req->r_old_dentry, dn, dn);
 
 			/* ensure target dentry is invalidated, despite
 			   rehashing bug in vfs_rename_dir */
 			ceph_invalidate_dentry_lease(dn);
 
-			dout("dn %p gets new offset %lld\n", req->r_old_dentry,
-			     ceph_dentry(req->r_old_dentry)->offset);
+			doutc(cl, "dn %p gets new offset %lld\n",
+			      req->r_old_dentry,
+			      ceph_dentry(req->r_old_dentry)->offset);
 
 			/* swap r_dentry and r_old_dentry in case that
 			 * splice_dentry() gets called later. This is safe
@@ -1696,9 +1719,9 @@ retry_lookup:
 
 		/* null dentry? */
 		if (!rinfo->head->is_target) {
-			dout("fill_trace null dentry\n");
+			doutc(cl, "null dentry\n");
 			if (d_really_is_positive(dn)) {
-				dout("d_delete %p\n", dn);
+				doutc(cl, "d_delete %p\n", dn);
 				ceph_dir_clear_ordered(dir);
 				d_delete(dn);
 			} else if (have_lease) {
@@ -1722,9 +1745,9 @@ retry_lookup:
 				goto done;
 			dn = req->r_dentry;  /* may have spliced */
 		} else if (d_really_is_positive(dn) && d_inode(dn) != in) {
-			dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
-			     dn, d_inode(dn), ceph_vinop(d_inode(dn)),
-			     ceph_vinop(in));
+			doutc(cl, " %p links to %p %llx.%llx, not %llx.%llx\n",
+			      dn, d_inode(dn), ceph_vinop(d_inode(dn)),
+			      ceph_vinop(in));
 			d_invalidate(dn);
 			have_lease = false;
 		}
@@ -1734,7 +1757,7 @@ retry_lookup:
 					    rinfo->dlease, session,
 					    req->r_request_started);
 		}
-		dout(" final dn %p\n", dn);
+		doutc(cl, " final dn %p\n", dn);
 	} else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
 		    req->r_op == CEPH_MDS_OP_MKSNAP) &&
 	           test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) &&
@@ -1745,7 +1768,8 @@ retry_lookup:
 		BUG_ON(!dir);
 		BUG_ON(ceph_snap(dir) != CEPH_SNAPDIR);
 		BUG_ON(!req->r_dentry);
-		dout(" linking snapped dir %p to dn %p\n", in, req->r_dentry);
+		doutc(cl, " linking snapped dir %p to dn %p\n", in,
+		      req->r_dentry);
 		ceph_dir_clear_ordered(dir);
 		ihold(in);
 		err = splice_dentry(&req->r_dentry, in);
@@ -1767,7 +1791,7 @@ retry_lookup:
 					    &dvino, ptvino);
 	}
 done:
-	dout("fill_trace done err=%d\n", err);
+	doutc(cl, "done err=%d\n", err);
 	return err;
 }
 
@@ -1778,6 +1802,7 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
 					   struct ceph_mds_session *session)
 {
 	struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
+	struct ceph_client *cl = session->s_mdsc->fsc->client;
 	int i, err = 0;
 
 	for (i = 0; i < rinfo->dir_nr; i++) {
@@ -1792,14 +1817,14 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
 		in = ceph_get_inode(req->r_dentry->d_sb, vino, NULL);
 		if (IS_ERR(in)) {
 			err = PTR_ERR(in);
-			dout("new_inode badness got %d\n", err);
+			doutc(cl, "badness got %d\n", err);
 			continue;
 		}
 		rc = ceph_fill_inode(in, NULL, &rde->inode, NULL, session,
 				     -1, &req->r_caps_reservation);
 		if (rc < 0) {
-			pr_err("ceph_fill_inode badness on %p got %d\n",
-			       in, rc);
+			pr_err_client(cl, "inode badness on %p got %d\n", in,
+				      rc);
 			err = rc;
 			if (in->i_state & I_NEW) {
 				ihold(in);
@@ -1828,6 +1853,7 @@ static int fill_readdir_cache(struct inode *dir, struct dentry *dn,
 			      struct ceph_readdir_cache_control *ctl,
 			      struct ceph_mds_request *req)
 {
+	struct ceph_client *cl = ceph_inode_to_client(dir);
 	struct ceph_inode_info *ci = ceph_inode(dir);
 	unsigned nsize = PAGE_SIZE / sizeof(struct dentry*);
 	unsigned idx = ctl->index % nsize;
@@ -1853,11 +1879,11 @@ static int fill_readdir_cache(struct inode *dir, struct dentry *dn,
 
 	if (req->r_dir_release_cnt == atomic64_read(&ci->i_release_count) &&
 	    req->r_dir_ordered_cnt == atomic64_read(&ci->i_ordered_count)) {
-		dout("readdir cache dn %p idx %d\n", dn, ctl->index);
+		doutc(cl, "dn %p idx %d\n", dn, ctl->index);
 		ctl->dentries[idx] = dn;
 		ctl->index++;
 	} else {
-		dout("disable readdir cache\n");
+		doutc(cl, "disable readdir cache\n");
 		ctl->index = -1;
 	}
 	return 0;
@@ -1870,6 +1896,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 	struct inode *inode = d_inode(parent);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
+	struct ceph_client *cl = session->s_mdsc->fsc->client;
 	struct qstr dname;
 	struct dentry *dn;
 	struct inode *in;
@@ -1897,19 +1924,18 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 
 	if (rinfo->dir_dir &&
 	    le32_to_cpu(rinfo->dir_dir->frag) != frag) {
-		dout("readdir_prepopulate got new frag %x -> %x\n",
-		     frag, le32_to_cpu(rinfo->dir_dir->frag));
+		doutc(cl, "got new frag %x -> %x\n", frag,
+			    le32_to_cpu(rinfo->dir_dir->frag));
 		frag = le32_to_cpu(rinfo->dir_dir->frag);
 		if (!rinfo->hash_order)
 			req->r_readdir_offset = 2;
 	}
 
 	if (le32_to_cpu(rinfo->head->op) == CEPH_MDS_OP_LSSNAP) {
-		dout("readdir_prepopulate %d items under SNAPDIR dn %p\n",
-		     rinfo->dir_nr, parent);
+		doutc(cl, "%d items under SNAPDIR dn %p\n",
+		      rinfo->dir_nr, parent);
 	} else {
-		dout("readdir_prepopulate %d items under dn %p\n",
-		     rinfo->dir_nr, parent);
+		doutc(cl, "%d items under dn %p\n", rinfo->dir_nr, parent);
 		if (rinfo->dir_dir)
 			ceph_fill_dirfrag(d_inode(parent), rinfo->dir_dir);
 
@@ -1953,15 +1979,15 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 
 retry_lookup:
 		dn = d_lookup(parent, &dname);
-		dout("d_lookup on parent=%p name=%.*s got %p\n",
-		     parent, dname.len, dname.name, dn);
+		doutc(cl, "d_lookup on parent=%p name=%.*s got %p\n",
+		      parent, dname.len, dname.name, dn);
 
 		if (!dn) {
 			dn = d_alloc(parent, &dname);
-			dout("d_alloc %p '%.*s' = %p\n", parent,
-			     dname.len, dname.name, dn);
+			doutc(cl, "d_alloc %p '%.*s' = %p\n", parent,
+			      dname.len, dname.name, dn);
 			if (!dn) {
-				dout("d_alloc badness\n");
+				doutc(cl, "d_alloc badness\n");
 				err = -ENOMEM;
 				goto out;
 			}
@@ -1974,8 +2000,8 @@ retry_lookup:
 			   (ceph_ino(d_inode(dn)) != tvino.ino ||
 			    ceph_snap(d_inode(dn)) != tvino.snap)) {
 			struct ceph_dentry_info *di = ceph_dentry(dn);
-			dout(" dn %p points to wrong inode %p\n",
-			     dn, d_inode(dn));
+			doutc(cl, " dn %p points to wrong inode %p\n",
+			      dn, d_inode(dn));
 
 			spin_lock(&dn->d_lock);
 			if (di->offset > 0 &&
@@ -1997,7 +2023,7 @@ retry_lookup:
 		} else {
 			in = ceph_get_inode(parent->d_sb, tvino, NULL);
 			if (IS_ERR(in)) {
-				dout("new_inode badness\n");
+				doutc(cl, "new_inode badness\n");
 				d_drop(dn);
 				dput(dn);
 				err = PTR_ERR(in);
@@ -2008,7 +2034,8 @@ retry_lookup:
 		ret = ceph_fill_inode(in, NULL, &rde->inode, NULL, session,
 				      -1, &req->r_caps_reservation);
 		if (ret < 0) {
-			pr_err("ceph_fill_inode badness on %p\n", in);
+			pr_err_client(cl, "badness on %p %llx.%llx\n", in,
+				      ceph_vinop(in));
 			if (d_really_is_negative(dn)) {
 				if (in->i_state & I_NEW) {
 					ihold(in);
@@ -2025,8 +2052,8 @@ retry_lookup:
 
 		if (d_really_is_negative(dn)) {
 			if (ceph_security_xattr_deadlock(in)) {
-				dout(" skip splicing dn %p to inode %p"
-				     " (security xattr deadlock)\n", dn, in);
+				doutc(cl, " skip splicing dn %p to inode %p"
+				      " (security xattr deadlock)\n", dn, in);
 				iput(in);
 				skipped++;
 				goto next_item;
@@ -2058,17 +2085,18 @@ out:
 		req->r_readdir_cache_idx = cache_ctl.index;
 	}
 	ceph_readdir_cache_release(&cache_ctl);
-	dout("readdir_prepopulate done\n");
+	doutc(cl, "done\n");
 	return err;
 }
 
 bool ceph_inode_set_size(struct inode *inode, loff_t size)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	bool ret;
 
 	spin_lock(&ci->i_ceph_lock);
-	dout("set_size %p %llu -> %llu\n", inode, i_size_read(inode), size);
+	doutc(cl, "set_size %p %llu -> %llu\n", inode, i_size_read(inode), size);
 	i_size_write(inode, size);
 	ceph_fscache_update(inode);
 	inode->i_blocks = calc_inode_blocks(size);
@@ -2082,22 +2110,25 @@ bool ceph_inode_set_size(struct inode *inode, loff_t size)
 
 void ceph_queue_inode_work(struct inode *inode, int work_bit)
 {
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	set_bit(work_bit, &ci->i_work_mask);
 
 	ihold(inode);
 	if (queue_work(fsc->inode_wq, &ci->i_work)) {
-		dout("queue_inode_work %p, mask=%lx\n", inode, ci->i_work_mask);
+		doutc(cl, "%p %llx.%llx mask=%lx\n", inode,
+		      ceph_vinop(inode), ci->i_work_mask);
 	} else {
-		dout("queue_inode_work %p already queued, mask=%lx\n",
-		     inode, ci->i_work_mask);
+		doutc(cl, "%p %llx.%llx already queued, mask=%lx\n",
+		      inode, ceph_vinop(inode), ci->i_work_mask);
 		iput(inode);
 	}
 }
 
 static void ceph_do_invalidate_pages(struct inode *inode)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	u32 orig_gen;
 	int check = 0;
@@ -2107,8 +2138,9 @@ static void ceph_do_invalidate_pages(struct inode *inode)
 	mutex_lock(&ci->i_truncate_mutex);
 
 	if (ceph_inode_is_shutdown(inode)) {
-		pr_warn_ratelimited("%s: inode %llx.%llx is shut down\n",
-				    __func__, ceph_vinop(inode));
+		pr_warn_ratelimited_client(cl,
+			"%p %llx.%llx is shut down\n", inode,
+			ceph_vinop(inode));
 		mapping_set_error(inode->i_mapping, -EIO);
 		truncate_pagecache(inode, 0);
 		mutex_unlock(&ci->i_truncate_mutex);
@@ -2116,8 +2148,8 @@ static void ceph_do_invalidate_pages(struct inode *inode)
 	}
 
 	spin_lock(&ci->i_ceph_lock);
-	dout("invalidate_pages %p gen %d revoking %d\n", inode,
-	     ci->i_rdcache_gen, ci->i_rdcache_revoking);
+	doutc(cl, "%p %llx.%llx gen %d revoking %d\n", inode,
+	      ceph_vinop(inode), ci->i_rdcache_gen, ci->i_rdcache_revoking);
 	if (ci->i_rdcache_revoking != ci->i_rdcache_gen) {
 		if (__ceph_caps_revoking_other(ci, NULL, CEPH_CAP_FILE_CACHE))
 			check = 1;
@@ -2129,21 +2161,21 @@ static void ceph_do_invalidate_pages(struct inode *inode)
 	spin_unlock(&ci->i_ceph_lock);
 
 	if (invalidate_inode_pages2(inode->i_mapping) < 0) {
-		pr_err("invalidate_inode_pages2 %llx.%llx failed\n",
-		       ceph_vinop(inode));
+		pr_err_client(cl, "invalidate_inode_pages2 %llx.%llx failed\n",
+			      ceph_vinop(inode));
 	}
 
 	spin_lock(&ci->i_ceph_lock);
 	if (orig_gen == ci->i_rdcache_gen &&
 	    orig_gen == ci->i_rdcache_revoking) {
-		dout("invalidate_pages %p gen %d successful\n", inode,
-		     ci->i_rdcache_gen);
+		doutc(cl, "%p %llx.%llx gen %d successful\n", inode,
+		      ceph_vinop(inode), ci->i_rdcache_gen);
 		ci->i_rdcache_revoking--;
 		check = 1;
 	} else {
-		dout("invalidate_pages %p gen %d raced, now %d revoking %d\n",
-		     inode, orig_gen, ci->i_rdcache_gen,
-		     ci->i_rdcache_revoking);
+		doutc(cl, "%p %llx.%llx gen %d raced, now %d revoking %d\n",
+		      inode, ceph_vinop(inode), orig_gen, ci->i_rdcache_gen,
+		      ci->i_rdcache_revoking);
 		if (__ceph_caps_revoking_other(ci, NULL, CEPH_CAP_FILE_CACHE))
 			check = 1;
 	}
@@ -2160,6 +2192,7 @@ out:
  */
 void __ceph_do_pending_vmtruncate(struct inode *inode)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	u64 to;
 	int wrbuffer_refs, finish = 0;
@@ -2168,7 +2201,8 @@ void __ceph_do_pending_vmtruncate(struct inode *inode)
 retry:
 	spin_lock(&ci->i_ceph_lock);
 	if (ci->i_truncate_pending == 0) {
-		dout("%s %p none pending\n", __func__, inode);
+		doutc(cl, "%p %llx.%llx none pending\n", inode,
+		      ceph_vinop(inode));
 		spin_unlock(&ci->i_ceph_lock);
 		mutex_unlock(&ci->i_truncate_mutex);
 		return;
@@ -2180,7 +2214,8 @@ retry:
 	 */
 	if (ci->i_wrbuffer_ref_head < ci->i_wrbuffer_ref) {
 		spin_unlock(&ci->i_ceph_lock);
-		dout("%s %p flushing snaps first\n", __func__, inode);
+		doutc(cl, "%p %llx.%llx flushing snaps first\n", inode,
+		      ceph_vinop(inode));
 		filemap_write_and_wait_range(&inode->i_data, 0,
 					     inode->i_sb->s_maxbytes);
 		goto retry;
@@ -2191,8 +2226,8 @@ retry:
 
 	to = ci->i_truncate_pagecache_size;
 	wrbuffer_refs = ci->i_wrbuffer_ref;
-	dout("%s %p (%d) to %lld\n", __func__, inode,
-	     ci->i_truncate_pending, to);
+	doutc(cl, "%p %llx.%llx (%d) to %lld\n", inode, ceph_vinop(inode),
+	      ci->i_truncate_pending, to);
 	spin_unlock(&ci->i_ceph_lock);
 
 	ceph_fscache_resize(inode, to);
@@ -2220,9 +2255,10 @@ static void ceph_inode_work(struct work_struct *work)
 	struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
 						 i_work);
 	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 
 	if (test_and_clear_bit(CEPH_I_WORK_WRITEBACK, &ci->i_work_mask)) {
-		dout("writeback %p\n", inode);
+		doutc(cl, "writeback %p %llx.%llx\n", inode, ceph_vinop(inode));
 		filemap_fdatawrite(&inode->i_data);
 	}
 	if (test_and_clear_bit(CEPH_I_WORK_INVALIDATE_PAGES, &ci->i_work_mask))
@@ -2294,6 +2330,7 @@ static int fill_fscrypt_truncate(struct inode *inode,
 				 struct ceph_mds_request *req,
 				 struct iattr *attr)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int boff = attr->ia_size % CEPH_FSCRYPT_BLOCK_SIZE;
 	loff_t pos, orig_pos = round_down(attr->ia_size,
@@ -2316,9 +2353,9 @@ static int fill_fscrypt_truncate(struct inode *inode,
 
 	issued = __ceph_caps_issued(ci, NULL);
 
-	dout("%s size %lld -> %lld got cap refs on %s, issued %s\n", __func__,
-	     i_size, attr->ia_size, ceph_cap_string(got),
-	     ceph_cap_string(issued));
+	doutc(cl, "size %lld -> %lld got cap refs on %s, issued %s\n",
+	      i_size, attr->ia_size, ceph_cap_string(got),
+	      ceph_cap_string(issued));
 
 	/* Try to writeback the dirty pagecaches */
 	if (issued & (CEPH_CAP_FILE_BUFFER)) {
@@ -2373,8 +2410,7 @@ static int fill_fscrypt_truncate(struct inode *inode,
 	 * If the Rados object doesn't exist, it will be set to 0.
 	 */
 	if (!objver) {
-		dout("%s hit hole, ppos %lld < size %lld\n", __func__,
-		     pos, i_size);
+		doutc(cl, "hit hole, ppos %lld < size %lld\n", pos, i_size);
 
 		header.data_len = cpu_to_le32(8 + 8 + 4);
 		header.file_offset = 0;
@@ -2383,8 +2419,8 @@ static int fill_fscrypt_truncate(struct inode *inode,
 		header.data_len = cpu_to_le32(8 + 8 + 4 + CEPH_FSCRYPT_BLOCK_SIZE);
 		header.file_offset = cpu_to_le64(orig_pos);
 
-		dout("%s encrypt block boff/bsize %d/%lu\n", __func__,
-		     boff, CEPH_FSCRYPT_BLOCK_SIZE);
+		doutc(cl, "encrypt block boff/bsize %d/%lu\n", boff,
+		      CEPH_FSCRYPT_BLOCK_SIZE);
 
 		/* truncate and zero out the extra contents for the last block */
 		memset(iov.iov_base + boff, 0, PAGE_SIZE - boff);
@@ -2412,8 +2448,8 @@ static int fill_fscrypt_truncate(struct inode *inode,
 	}
 	req->r_pagelist = pagelist;
 out:
-	dout("%s %p size dropping cap refs on %s\n", __func__,
-	     inode, ceph_cap_string(got));
+	doutc(cl, "%p %llx.%llx size dropping cap refs on %s\n", inode,
+	      ceph_vinop(inode), ceph_cap_string(got));
 	ceph_put_cap_refs(ci, got);
 	if (iov.iov_base)
 		kunmap_local(iov.iov_base);
@@ -2424,13 +2460,14 @@ out:
 	return ret;
 }
 
-int __ceph_setattr(struct inode *inode, struct iattr *attr,
-		   struct ceph_iattr *cia)
+int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
+		   struct iattr *attr, struct ceph_iattr *cia)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	unsigned int ia_valid = attr->ia_valid;
 	struct ceph_mds_request *req;
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_cap_flush *prealloc_cf;
 	loff_t isize = i_size_read(inode);
 	int issued;
@@ -2469,7 +2506,8 @@ retry:
 		}
 	}
 
-	dout("setattr %p issued %s\n", inode, ceph_cap_string(issued));
+	doutc(cl, "%p %llx.%llx issued %s\n", inode, ceph_vinop(inode),
+	      ceph_cap_string(issued));
 #if IS_ENABLED(CONFIG_FS_ENCRYPTION)
 	if (cia && cia->fscrypt_auth) {
 		u32 len = ceph_fscrypt_auth_len(cia->fscrypt_auth);
@@ -2480,8 +2518,8 @@ retry:
 			goto out;
 		}
 
-		dout("setattr %llx:%llx fscrypt_auth len %u to %u)\n",
-			ceph_vinop(inode), ci->fscrypt_auth_len, len);
+		doutc(cl, "%p %llx.%llx fscrypt_auth len %u to %u)\n", inode,
+		      ceph_vinop(inode), ci->fscrypt_auth_len, len);
 
 		/* It should never be re-set once set */
 		WARN_ON_ONCE(ci->fscrypt_auth);
@@ -2509,38 +2547,44 @@ retry:
 #endif /* CONFIG_FS_ENCRYPTION */
 
 	if (ia_valid & ATTR_UID) {
-		dout("setattr %p uid %d -> %d\n", inode,
-		     from_kuid(&init_user_ns, inode->i_uid),
-		     from_kuid(&init_user_ns, attr->ia_uid));
+		kuid_t fsuid = from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid);
+
+		doutc(cl, "%p %llx.%llx uid %d -> %d\n", inode,
+		      ceph_vinop(inode),
+		      from_kuid(&init_user_ns, inode->i_uid),
+		      from_kuid(&init_user_ns, attr->ia_uid));
 		if (issued & CEPH_CAP_AUTH_EXCL) {
-			inode->i_uid = attr->ia_uid;
+			inode->i_uid = fsuid;
 			dirtied |= CEPH_CAP_AUTH_EXCL;
 		} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
-			   !uid_eq(attr->ia_uid, inode->i_uid)) {
+			   !uid_eq(fsuid, inode->i_uid)) {
 			req->r_args.setattr.uid = cpu_to_le32(
-				from_kuid(&init_user_ns, attr->ia_uid));
+				from_kuid(&init_user_ns, fsuid));
 			mask |= CEPH_SETATTR_UID;
 			release |= CEPH_CAP_AUTH_SHARED;
 		}
 	}
 	if (ia_valid & ATTR_GID) {
-		dout("setattr %p gid %d -> %d\n", inode,
-		     from_kgid(&init_user_ns, inode->i_gid),
-		     from_kgid(&init_user_ns, attr->ia_gid));
+		kgid_t fsgid = from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid);
+
+		doutc(cl, "%p %llx.%llx gid %d -> %d\n", inode,
+		      ceph_vinop(inode),
+		      from_kgid(&init_user_ns, inode->i_gid),
+		      from_kgid(&init_user_ns, attr->ia_gid));
 		if (issued & CEPH_CAP_AUTH_EXCL) {
-			inode->i_gid = attr->ia_gid;
+			inode->i_gid = fsgid;
 			dirtied |= CEPH_CAP_AUTH_EXCL;
 		} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
-			   !gid_eq(attr->ia_gid, inode->i_gid)) {
+			   !gid_eq(fsgid, inode->i_gid)) {
 			req->r_args.setattr.gid = cpu_to_le32(
-				from_kgid(&init_user_ns, attr->ia_gid));
+				from_kgid(&init_user_ns, fsgid));
 			mask |= CEPH_SETATTR_GID;
 			release |= CEPH_CAP_AUTH_SHARED;
 		}
 	}
 	if (ia_valid & ATTR_MODE) {
-		dout("setattr %p mode 0%o -> 0%o\n", inode, inode->i_mode,
-		     attr->ia_mode);
+		doutc(cl, "%p %llx.%llx mode 0%o -> 0%o\n", inode,
+		      ceph_vinop(inode), inode->i_mode, attr->ia_mode);
 		if (issued & CEPH_CAP_AUTH_EXCL) {
 			inode->i_mode = attr->ia_mode;
 			dirtied |= CEPH_CAP_AUTH_EXCL;
@@ -2556,9 +2600,10 @@ retry:
 	if (ia_valid & ATTR_ATIME) {
 		struct timespec64 atime = inode_get_atime(inode);
 
-		dout("setattr %p atime %lld.%ld -> %lld.%ld\n", inode,
-		     atime.tv_sec, atime.tv_nsec,
-		     attr->ia_atime.tv_sec, attr->ia_atime.tv_nsec);
+		doutc(cl, "%p %llx.%llx atime %lld.%09ld -> %lld.%09ld\n",
+		      inode, ceph_vinop(inode),
+		      atime.tv_sec, atime.tv_nsec,
+		      attr->ia_atime.tv_sec, attr->ia_atime.tv_nsec);
 		if (issued & CEPH_CAP_FILE_EXCL) {
 			ci->i_time_warp_seq++;
 			inode_set_atime_to_ts(inode, attr->ia_atime);
@@ -2578,7 +2623,8 @@ retry:
 		}
 	}
 	if (ia_valid & ATTR_SIZE) {
-		dout("setattr %p size %lld -> %lld\n", inode, isize, attr->ia_size);
+		doutc(cl, "%p %llx.%llx size %lld -> %lld\n", inode,
+		      ceph_vinop(inode), isize, attr->ia_size);
 		/*
 		 * Only when the new size is smaller and not aligned to
 		 * CEPH_FSCRYPT_BLOCK_SIZE will the RMW is needed.
@@ -2631,9 +2677,10 @@ retry:
 	if (ia_valid & ATTR_MTIME) {
 		struct timespec64 mtime = inode_get_mtime(inode);
 
-		dout("setattr %p mtime %lld.%ld -> %lld.%ld\n", inode,
-		     mtime.tv_sec, mtime.tv_nsec,
-		     attr->ia_mtime.tv_sec, attr->ia_mtime.tv_nsec);
+		doutc(cl, "%p %llx.%llx mtime %lld.%09ld -> %lld.%09ld\n",
+		      inode, ceph_vinop(inode),
+		      mtime.tv_sec, mtime.tv_nsec,
+		      attr->ia_mtime.tv_sec, attr->ia_mtime.tv_nsec);
 		if (issued & CEPH_CAP_FILE_EXCL) {
 			ci->i_time_warp_seq++;
 			inode_set_mtime_to_ts(inode, attr->ia_mtime);
@@ -2656,11 +2703,12 @@ retry:
 	if (ia_valid & ATTR_CTIME) {
 		bool only = (ia_valid & (ATTR_SIZE|ATTR_MTIME|ATTR_ATIME|
 					 ATTR_MODE|ATTR_UID|ATTR_GID)) == 0;
-		dout("setattr %p ctime %lld.%ld -> %lld.%ld (%s)\n", inode,
-		     inode_get_ctime_sec(inode),
-		     inode_get_ctime_nsec(inode),
-		     attr->ia_ctime.tv_sec, attr->ia_ctime.tv_nsec,
-		     only ? "ctime only" : "ignored");
+		doutc(cl, "%p %llx.%llx ctime %lld.%09ld -> %lld.%09ld (%s)\n",
+		      inode, ceph_vinop(inode),
+		      inode_get_ctime_sec(inode),
+		      inode_get_ctime_nsec(inode),
+		      attr->ia_ctime.tv_sec, attr->ia_ctime.tv_nsec,
+		      only ? "ctime only" : "ignored");
 		if (only) {
 			/*
 			 * if kernel wants to dirty ctime but nothing else,
@@ -2678,7 +2726,8 @@ retry:
 		}
 	}
 	if (ia_valid & ATTR_FILE)
-		dout("setattr %p ATTR_FILE ... hrm!\n", inode);
+		doutc(cl, "%p %llx.%llx ATTR_FILE ... hrm!\n", inode,
+		      ceph_vinop(inode));
 
 	if (dirtied) {
 		inode_dirty_flags = __ceph_mark_dirty_caps(ci, dirtied,
@@ -2719,16 +2768,17 @@ retry:
 		 */
 		err = ceph_mdsc_do_request(mdsc, NULL, req);
 		if (err == -EAGAIN && truncate_retry--) {
-			dout("setattr %p result=%d (%s locally, %d remote), retry it!\n",
-			     inode, err, ceph_cap_string(dirtied), mask);
+			doutc(cl, "%p %llx.%llx result=%d (%s locally, %d remote), retry it!\n",
+			      inode, ceph_vinop(inode), err,
+			      ceph_cap_string(dirtied), mask);
 			ceph_mdsc_put_request(req);
 			ceph_free_cap_flush(prealloc_cf);
 			goto retry;
 		}
 	}
 out:
-	dout("setattr %p result=%d (%s locally, %d remote)\n", inode, err,
-	     ceph_cap_string(dirtied), mask);
+	doutc(cl, "%p %llx.%llx result=%d (%s locally, %d remote)\n", inode,
+	      ceph_vinop(inode), err, ceph_cap_string(dirtied), mask);
 
 	ceph_mdsc_put_request(req);
 	ceph_free_cap_flush(prealloc_cf);
@@ -2746,7 +2796,7 @@ int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		 struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 	int err;
 
 	if (ceph_snap(inode) != CEPH_NOSNAP)
@@ -2759,7 +2809,7 @@ int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	if (err)
 		return err;
 
-	err = setattr_prepare(&nop_mnt_idmap, dentry, attr);
+	err = setattr_prepare(idmap, dentry, attr);
 	if (err != 0)
 		return err;
 
@@ -2771,10 +2821,10 @@ int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	    ceph_quota_is_max_bytes_exceeded(inode, attr->ia_size))
 		return -EDQUOT;
 
-	err = __ceph_setattr(inode, attr, NULL);
+	err = __ceph_setattr(idmap, inode, attr, NULL);
 
 	if (err >= 0 && (attr->ia_valid & ATTR_MODE))
-		err = posix_acl_chmod(&nop_mnt_idmap, dentry, attr->ia_mode);
+		err = posix_acl_chmod(idmap, dentry, attr->ia_mode);
 
 	return err;
 }
@@ -2816,19 +2866,21 @@ int ceph_try_to_choose_auth_mds(struct inode *inode, int mask)
 int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
 		      int mask, bool force)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(inode->i_sb);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int mode;
 	int err;
 
 	if (ceph_snap(inode) == CEPH_SNAPDIR) {
-		dout("do_getattr inode %p SNAPDIR\n", inode);
+		doutc(cl, "inode %p %llx.%llx SNAPDIR\n", inode,
+		      ceph_vinop(inode));
 		return 0;
 	}
 
-	dout("do_getattr inode %p mask %s mode 0%o\n",
-	     inode, ceph_cap_string(mask), inode->i_mode);
+	doutc(cl, "inode %p %llx.%llx mask %s mode 0%o\n", inode,
+	      ceph_vinop(inode), ceph_cap_string(mask), inode->i_mode);
 	if (!force && ceph_caps_issued_mask_metric(ceph_inode(inode), mask, 1))
 			return 0;
 
@@ -2855,14 +2907,15 @@ int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
 		}
 	}
 	ceph_mdsc_put_request(req);
-	dout("do_getattr result=%d\n", err);
+	doutc(cl, "result=%d\n", err);
 	return err;
 }
 
 int ceph_do_getvxattr(struct inode *inode, const char *name, void *value,
 		      size_t size)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(inode->i_sb);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int mode = USE_AUTH_MDS;
@@ -2892,7 +2945,7 @@ int ceph_do_getvxattr(struct inode *inode, const char *name, void *value,
 	xattr_value = req->r_reply_info.xattr_info.xattr_value;
 	xattr_value_len = req->r_reply_info.xattr_info.xattr_value_len;
 
-	dout("do_getvxattr xattr_value_len:%zu, size:%zu\n", xattr_value_len, size);
+	doutc(cl, "xattr_value_len:%zu, size:%zu\n", xattr_value_len, size);
 
 	err = (int)xattr_value_len;
 	if (size == 0)
@@ -2907,7 +2960,7 @@ int ceph_do_getvxattr(struct inode *inode, const char *name, void *value,
 put:
 	ceph_mdsc_put_request(req);
 out:
-	dout("do_getvxattr result=%d\n", err);
+	doutc(cl, "result=%d\n", err);
 	return err;
 }
 
@@ -2927,7 +2980,7 @@ int ceph_permission(struct mnt_idmap *idmap, struct inode *inode,
 	err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED, false);
 
 	if (!err)
-		err = generic_permission(&nop_mnt_idmap, inode, mask);
+		err = generic_permission(idmap, inode, mask);
 	return err;
 }
 
@@ -2984,7 +3037,7 @@ int ceph_getattr(struct mnt_idmap *idmap, const struct path *path,
 			return err;
 	}
 
-	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
+	generic_fillattr(idmap, request_mask, inode, stat);
 	stat->ino = ceph_present_inode(inode);
 
 	/*
@@ -3007,7 +3060,7 @@ int ceph_getattr(struct mnt_idmap *idmap, const struct path *path,
 		stat->dev = ci->i_snapid_map ? ci->i_snapid_map->dev : 0;
 
 	if (S_ISDIR(inode->i_mode)) {
-		if (ceph_test_mount_opt(ceph_sb_to_client(sb), RBYTES)) {
+		if (ceph_test_mount_opt(ceph_sb_to_fs_client(sb), RBYTES)) {
 			stat->size = ci->i_rbytes;
 		} else if (ceph_snap(inode) == CEPH_SNAPDIR) {
 			struct ceph_inode_info *pci;
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 91a84917d203c5..e861de3c79b9e1 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -65,7 +65,7 @@ static long __validate_layout(struct ceph_mds_client *mdsc,
 static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc;
 	struct ceph_mds_request *req;
 	struct ceph_ioctl_layout l;
 	struct ceph_inode_info *ci = ceph_inode(file_inode(file));
@@ -140,7 +140,7 @@ static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
 	struct ceph_mds_request *req;
 	struct ceph_ioctl_layout l;
 	int err;
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc;
 
 	/* copy and validate */
 	if (copy_from_user(&l, arg, sizeof(l)))
@@ -183,7 +183,7 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_osd_client *osdc =
-		&ceph_sb_to_client(inode->i_sb)->client->osdc;
+		&ceph_sb_to_fs_client(inode->i_sb)->client->osdc;
 	struct ceph_object_locator oloc;
 	CEPH_DEFINE_OID_ONSTACK(oid);
 	u32 xlen;
@@ -244,7 +244,8 @@ static long ceph_ioctl_lazyio(struct file *file)
 	struct ceph_file_info *fi = file->private_data;
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 
 	if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
 		spin_lock(&ci->i_ceph_lock);
@@ -252,11 +253,13 @@ static long ceph_ioctl_lazyio(struct file *file)
 		ci->i_nr_by_mode[ffs(CEPH_FILE_MODE_LAZY)]++;
 		__ceph_touch_fmode(ci, mdsc, fi->fmode);
 		spin_unlock(&ci->i_ceph_lock);
-		dout("ioctl_layzio: file %p marked lazy\n", file);
+		doutc(cl, "file %p %p %llx.%llx marked lazy\n", file, inode,
+		      ceph_vinop(inode));
 
 		ceph_check_caps(ci, 0);
 	} else {
-		dout("ioctl_layzio: file %p already lazy\n", file);
+		doutc(cl, "file %p %p %llx.%llx already lazy\n", file, inode,
+		      ceph_vinop(inode));
 	}
 	return 0;
 }
@@ -355,10 +358,12 @@ static const char *ceph_ioctl_cmd_name(const unsigned int cmd)
 
 long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
+	struct inode *inode = file_inode(file);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 	int ret;
 
-	dout("ioctl file %p cmd %s arg %lu\n", file,
-	     ceph_ioctl_cmd_name(cmd), arg);
+	doutc(fsc->client, "file %p %p %llx.%llx cmd %s arg %lu\n", file,
+	      inode, ceph_vinop(inode), ceph_ioctl_cmd_name(cmd), arg);
 	switch (cmd) {
 	case CEPH_IOC_GET_LAYOUT:
 		return ceph_ioctl_get_layout(file, (void __user *)arg);
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index cb51c7e9c8e22c..e07ad29ff8b972 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -77,6 +77,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
 			     int cmd, u8 wait, struct file_lock *fl)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *req;
 	int err;
 	u64 length = 0;
@@ -111,10 +112,10 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
 
 	owner = secure_addr(fl->fl_owner);
 
-	dout("ceph_lock_message: rule: %d, op: %d, owner: %llx, pid: %llu, "
-	     "start: %llu, length: %llu, wait: %d, type: %d\n", (int)lock_type,
-	     (int)operation, owner, (u64)fl->fl_pid, fl->fl_start, length,
-	     wait, fl->fl_type);
+	doutc(cl, "rule: %d, op: %d, owner: %llx, pid: %llu, "
+		    "start: %llu, length: %llu, wait: %d, type: %d\n",
+		    (int)lock_type, (int)operation, owner, (u64)fl->fl_pid,
+		    fl->fl_start, length, wait, fl->fl_type);
 
 	req->r_args.filelock_change.rule = lock_type;
 	req->r_args.filelock_change.type = cmd;
@@ -147,16 +148,17 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
 
 	}
 	ceph_mdsc_put_request(req);
-	dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
-	     "length: %llu, wait: %d, type: %d, err code %d\n", (int)lock_type,
-	     (int)operation, (u64)fl->fl_pid, fl->fl_start,
-	     length, wait, fl->fl_type, err);
+	doutc(cl, "rule: %d, op: %d, pid: %llu, start: %llu, "
+	      "length: %llu, wait: %d, type: %d, err code %d\n",
+	      (int)lock_type, (int)operation, (u64)fl->fl_pid,
+	      fl->fl_start, length, wait, fl->fl_type, err);
 	return err;
 }
 
 static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
                                          struct ceph_mds_request *req)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *intr_req;
 	struct inode *inode = req->r_inode;
 	int err, lock_type;
@@ -174,8 +176,7 @@ static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
 	if (!err)
 		return 0;
 
-	dout("ceph_lock_wait_for_completion: request %llu was interrupted\n",
-	     req->r_tid);
+	doutc(cl, "request %llu was interrupted\n", req->r_tid);
 
 	mutex_lock(&mdsc->mutex);
 	if (test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags)) {
@@ -246,6 +247,7 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 {
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int err = 0;
 	u16 op = CEPH_MDS_OP_SETFILELOCK;
 	u8 wait = 0;
@@ -257,7 +259,7 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 	if (ceph_inode_is_shutdown(inode))
 		return -ESTALE;
 
-	dout("ceph_lock, fl_owner: %p\n", fl->fl_owner);
+	doutc(cl, "fl_owner: %p\n", fl->fl_owner);
 
 	/* set wait bit as appropriate, then make command as Ceph expects it*/
 	if (IS_GETLK(cmd))
@@ -292,7 +294,7 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 	err = ceph_lock_message(CEPH_LOCK_FCNTL, op, inode, lock_cmd, wait, fl);
 	if (!err) {
 		if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK != fl->fl_type) {
-			dout("mds locked, locking locally\n");
+			doutc(cl, "locking locally\n");
 			err = posix_lock_file(file, fl, NULL);
 			if (err) {
 				/* undo! This should only happen if
@@ -300,8 +302,8 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 				 * deadlock. */
 				ceph_lock_message(CEPH_LOCK_FCNTL, op, inode,
 						  CEPH_LOCK_UNLOCK, 0, fl);
-				dout("got %d on posix_lock_file, undid lock\n",
-				     err);
+				doutc(cl, "got %d on posix_lock_file, undid lock\n",
+				      err);
 			}
 		}
 	}
@@ -312,6 +314,7 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 {
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int err = 0;
 	u8 wait = 0;
 	u8 lock_cmd;
@@ -322,7 +325,7 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 	if (ceph_inode_is_shutdown(inode))
 		return -ESTALE;
 
-	dout("ceph_flock, fl_file: %p\n", fl->fl_file);
+	doutc(cl, "fl_file: %p\n", fl->fl_file);
 
 	spin_lock(&ci->i_ceph_lock);
 	if (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) {
@@ -359,7 +362,8 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 			ceph_lock_message(CEPH_LOCK_FLOCK,
 					  CEPH_MDS_OP_SETFILELOCK,
 					  inode, CEPH_LOCK_UNLOCK, 0, fl);
-			dout("got %d on locks_lock_file_wait, undid lock\n", err);
+			doutc(cl, "got %d on locks_lock_file_wait, undid lock\n",
+			      err);
 		}
 	}
 	return err;
@@ -371,6 +375,7 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
  */
 void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct file_lock *lock;
 	struct file_lock_context *ctx;
 
@@ -386,17 +391,20 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
 			++(*flock_count);
 		spin_unlock(&ctx->flc_lock);
 	}
-	dout("counted %d flock locks and %d fcntl locks\n",
-	     *flock_count, *fcntl_count);
+	doutc(cl, "counted %d flock locks and %d fcntl locks\n",
+	      *flock_count, *fcntl_count);
 }
 
 /*
  * Given a pointer to a lock, convert it to a ceph filelock
  */
-static int lock_to_ceph_filelock(struct file_lock *lock,
+static int lock_to_ceph_filelock(struct inode *inode,
+				 struct file_lock *lock,
 				 struct ceph_filelock *cephlock)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int err = 0;
+
 	cephlock->start = cpu_to_le64(lock->fl_start);
 	cephlock->length = cpu_to_le64(lock->fl_end - lock->fl_start + 1);
 	cephlock->client = cpu_to_le64(0);
@@ -414,7 +422,7 @@ static int lock_to_ceph_filelock(struct file_lock *lock,
 		cephlock->type = CEPH_LOCK_UNLOCK;
 		break;
 	default:
-		dout("Have unknown lock type %d\n", lock->fl_type);
+		doutc(cl, "Have unknown lock type %d\n", lock->fl_type);
 		err = -EINVAL;
 	}
 
@@ -432,13 +440,14 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 {
 	struct file_lock *lock;
 	struct file_lock_context *ctx = locks_inode_context(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int err = 0;
 	int seen_fcntl = 0;
 	int seen_flock = 0;
 	int l = 0;
 
-	dout("encoding %d flock and %d fcntl locks\n", num_flock_locks,
-	     num_fcntl_locks);
+	doutc(cl, "encoding %d flock and %d fcntl locks\n", num_flock_locks,
+	      num_fcntl_locks);
 
 	if (!ctx)
 		return 0;
@@ -450,7 +459,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 			err = -ENOSPC;
 			goto fail;
 		}
-		err = lock_to_ceph_filelock(lock, &flocks[l]);
+		err = lock_to_ceph_filelock(inode, lock, &flocks[l]);
 		if (err)
 			goto fail;
 		++l;
@@ -461,7 +470,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 			err = -ENOSPC;
 			goto fail;
 		}
-		err = lock_to_ceph_filelock(lock, &flocks[l]);
+		err = lock_to_ceph_filelock(inode, lock, &flocks[l]);
 		if (err)
 			goto fail;
 		++l;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index de798444bb9741..d95eb525519a64 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -12,6 +12,7 @@
 #include <linux/bits.h>
 #include <linux/ktime.h>
 #include <linux/bitmap.h>
+#include <linux/mnt_idmapping.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -411,6 +412,7 @@ static int parse_reply_info_readdir(void **p, void *end,
 				    u64 features)
 {
 	struct ceph_mds_reply_info_parsed *info = &req->r_reply_info;
+	struct ceph_client *cl = req->r_mdsc->fsc->client;
 	u32 num, i = 0;
 	int err;
 
@@ -433,7 +435,7 @@ static int parse_reply_info_readdir(void **p, void *end,
 	BUG_ON(!info->dir_entries);
 	if ((unsigned long)(info->dir_entries + num) >
 	    (unsigned long)info->dir_entries + info->dir_buf_size) {
-		pr_err("dir contents are larger than expected\n");
+		pr_err_client(cl, "dir contents are larger than expected\n");
 		WARN_ON(1);
 		goto bad;
 	}
@@ -454,7 +456,7 @@ static int parse_reply_info_readdir(void **p, void *end,
 		ceph_decode_need(p, end, _name_len, bad);
 		_name = *p;
 		*p += _name_len;
-		dout("parsed dir dname '%.*s'\n", _name_len, _name);
+		doutc(cl, "parsed dir dname '%.*s'\n", _name_len, _name);
 
 		if (info->hash_order)
 			rde->raw_hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
@@ -514,8 +516,8 @@ static int parse_reply_info_readdir(void **p, void *end,
 		rde->is_nokey = false;
 		err = ceph_fname_to_usr(&fname, &tname, &oname, &rde->is_nokey);
 		if (err) {
-			pr_err("%s unable to decode %.*s, got %d\n", __func__,
-			       _name_len, _name, err);
+			pr_err_client(cl, "unable to decode %.*s, got %d\n",
+				      _name_len, _name, err);
 			goto out_bad;
 		}
 		rde->name = oname.name;
@@ -539,7 +541,7 @@ done:
 bad:
 	err = -EIO;
 out_bad:
-	pr_err("problem parsing dir contents %d\n", err);
+	pr_err_client(cl, "problem parsing dir contents %d\n", err);
 	return err;
 }
 
@@ -570,10 +572,11 @@ bad:
 static int ceph_parse_deleg_inos(void **p, void *end,
 				 struct ceph_mds_session *s)
 {
+	struct ceph_client *cl = s->s_mdsc->fsc->client;
 	u32 sets;
 
 	ceph_decode_32_safe(p, end, sets, bad);
-	dout("got %u sets of delegated inodes\n", sets);
+	doutc(cl, "got %u sets of delegated inodes\n", sets);
 	while (sets--) {
 		u64 start, len;
 
@@ -582,8 +585,9 @@ static int ceph_parse_deleg_inos(void **p, void *end,
 
 		/* Don't accept a delegation of system inodes */
 		if (start < CEPH_INO_SYSTEM_BASE) {
-			pr_warn_ratelimited("ceph: ignoring reserved inode range delegation (start=0x%llx len=0x%llx)\n",
-					start, len);
+			pr_warn_ratelimited_client(cl,
+				"ignoring reserved inode range delegation (start=0x%llx len=0x%llx)\n",
+				start, len);
 			continue;
 		}
 		while (len--) {
@@ -591,10 +595,10 @@ static int ceph_parse_deleg_inos(void **p, void *end,
 					    DELEGATED_INO_AVAILABLE,
 					    GFP_KERNEL);
 			if (!err) {
-				dout("added delegated inode 0x%llx\n",
-				     start - 1);
+				doutc(cl, "added delegated inode 0x%llx\n", start - 1);
 			} else if (err == -EBUSY) {
-				pr_warn("MDS delegated inode 0x%llx more than once.\n",
+				pr_warn_client(cl,
+					"MDS delegated inode 0x%llx more than once.\n",
 					start - 1);
 			} else {
 				return err;
@@ -744,6 +748,7 @@ static int parse_reply_info(struct ceph_mds_session *s, struct ceph_msg *msg,
 			    struct ceph_mds_request *req, u64 features)
 {
 	struct ceph_mds_reply_info_parsed *info = &req->r_reply_info;
+	struct ceph_client *cl = s->s_mdsc->fsc->client;
 	void *p, *end;
 	u32 len;
 	int err;
@@ -783,7 +788,7 @@ static int parse_reply_info(struct ceph_mds_session *s, struct ceph_msg *msg,
 bad:
 	err = -EIO;
 out_bad:
-	pr_err("mds parse_reply err %d\n", err);
+	pr_err_client(cl, "mds parse_reply err %d\n", err);
 	ceph_msg_dump(msg);
 	return err;
 }
@@ -830,7 +835,8 @@ static void destroy_reply_info(struct ceph_mds_reply_info_parsed *info)
  */
 int ceph_wait_on_conflict_unlink(struct dentry *dentry)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(dentry->d_sb);
+	struct ceph_client *cl = fsc->client;
 	struct dentry *pdentry = dentry->d_parent;
 	struct dentry *udentry, *found = NULL;
 	struct ceph_dentry_info *di;
@@ -855,8 +861,8 @@ int ceph_wait_on_conflict_unlink(struct dentry *dentry)
 			goto next;
 
 		if (!test_bit(CEPH_DENTRY_ASYNC_UNLINK_BIT, &di->flags))
-			pr_warn("%s dentry %p:%pd async unlink bit is not set\n",
-				__func__, dentry, dentry);
+			pr_warn_client(cl, "dentry %p:%pd async unlink bit is not set\n",
+				       dentry, dentry);
 
 		if (!d_same_name(udentry, pdentry, &dname))
 			goto next;
@@ -872,8 +878,8 @@ next:
 	if (likely(!found))
 		return 0;
 
-	dout("%s dentry %p:%pd conflict with old %p:%pd\n", __func__,
-	     dentry, dentry, found, found);
+	doutc(cl, "dentry %p:%pd conflict with old %p:%pd\n", dentry, dentry,
+	      found, found);
 
 	err = wait_on_bit(&di->flags, CEPH_DENTRY_ASYNC_UNLINK_BIT,
 			  TASK_KILLABLE);
@@ -957,6 +963,7 @@ static int __verify_registered_session(struct ceph_mds_client *mdsc,
 static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 						 int mds)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_session *s;
 
 	if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO)
@@ -973,7 +980,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 		int newmax = 1 << get_count_order(mds + 1);
 		struct ceph_mds_session **sa;
 
-		dout("%s: realloc to %d\n", __func__, newmax);
+		doutc(cl, "realloc to %d\n", newmax);
 		sa = kcalloc(newmax, sizeof(void *), GFP_NOFS);
 		if (!sa)
 			goto fail_realloc;
@@ -986,7 +993,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 		mdsc->max_sessions = newmax;
 	}
 
-	dout("%s: mds%d\n", __func__, mds);
+	doutc(cl, "mds%d\n", mds);
 	s->s_mdsc = mdsc;
 	s->s_mds = mds;
 	s->s_state = CEPH_MDS_SESSION_NEW;
@@ -1029,7 +1036,7 @@ fail_realloc:
 static void __unregister_session(struct ceph_mds_client *mdsc,
 			       struct ceph_mds_session *s)
 {
-	dout("__unregister_session mds%d %p\n", s->s_mds, s);
+	doutc(mdsc->fsc->client, "mds%d %p\n", s->s_mds, s);
 	BUG_ON(mdsc->sessions[s->s_mds] != s);
 	mdsc->sessions[s->s_mds] = NULL;
 	ceph_con_close(&s->s_con);
@@ -1116,6 +1123,8 @@ void ceph_mdsc_release_request(struct kref *kref)
 	kfree(req->r_path1);
 	kfree(req->r_path2);
 	put_cred(req->r_cred);
+	if (req->r_mnt_idmap)
+		mnt_idmap_put(req->r_mnt_idmap);
 	if (req->r_pagelist)
 		ceph_pagelist_release(req->r_pagelist);
 	kfree(req->r_fscrypt_auth);
@@ -1155,6 +1164,7 @@ static void __register_request(struct ceph_mds_client *mdsc,
 			       struct ceph_mds_request *req,
 			       struct inode *dir)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	int ret = 0;
 
 	req->r_tid = ++mdsc->last_tid;
@@ -1162,18 +1172,20 @@ static void __register_request(struct ceph_mds_client *mdsc,
 		ret = ceph_reserve_caps(mdsc, &req->r_caps_reservation,
 					req->r_num_caps);
 		if (ret < 0) {
-			pr_err("__register_request %p "
-			       "failed to reserve caps: %d\n", req, ret);
+			pr_err_client(cl, "%p failed to reserve caps: %d\n",
+				      req, ret);
 			/* set req->r_err to fail early from __do_request */
 			req->r_err = ret;
 			return;
 		}
 	}
-	dout("__register_request %p tid %lld\n", req, req->r_tid);
+	doutc(cl, "%p tid %lld\n", req, req->r_tid);
 	ceph_mdsc_get_request(req);
 	insert_request(&mdsc->request_tree, req);
 
 	req->r_cred = get_current_cred();
+	if (!req->r_mnt_idmap)
+		req->r_mnt_idmap = &nop_mnt_idmap;
 
 	if (mdsc->oldest_tid == 0 && req->r_op != CEPH_MDS_OP_SETFILELOCK)
 		mdsc->oldest_tid = req->r_tid;
@@ -1192,7 +1204,7 @@ static void __register_request(struct ceph_mds_client *mdsc,
 static void __unregister_request(struct ceph_mds_client *mdsc,
 				 struct ceph_mds_request *req)
 {
-	dout("__unregister_request %p tid %lld\n", req, req->r_tid);
+	doutc(mdsc->fsc->client, "%p tid %lld\n", req, req->r_tid);
 
 	/* Never leave an unregistered request on an unsafe list! */
 	list_del_init(&req->r_unsafe_item);
@@ -1278,6 +1290,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 	int mds = -1;
 	u32 hash = req->r_direct_hash;
 	bool is_hash = test_bit(CEPH_MDS_R_DIRECT_IS_HASH, &req->r_req_flags);
+	struct ceph_client *cl = mdsc->fsc->client;
 
 	if (random)
 		*random = false;
@@ -1289,8 +1302,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 	if (req->r_resend_mds >= 0 &&
 	    (__have_session(mdsc, req->r_resend_mds) ||
 	     ceph_mdsmap_get_state(mdsc->mdsmap, req->r_resend_mds) > 0)) {
-		dout("%s using resend_mds mds%d\n", __func__,
-		     req->r_resend_mds);
+		doutc(cl, "using resend_mds mds%d\n", req->r_resend_mds);
 		return req->r_resend_mds;
 	}
 
@@ -1307,7 +1319,8 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 			rcu_read_lock();
 			inode = get_nonsnap_parent(req->r_dentry);
 			rcu_read_unlock();
-			dout("%s using snapdir's parent %p\n", __func__, inode);
+			doutc(cl, "using snapdir's parent %p %llx.%llx\n",
+			      inode, ceph_vinop(inode));
 		}
 	} else if (req->r_dentry) {
 		/* ignore race with rename; old or new d_parent is okay */
@@ -1327,7 +1340,8 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 			/* direct snapped/virtual snapdir requests
 			 * based on parent dir inode */
 			inode = get_nonsnap_parent(parent);
-			dout("%s using nonsnap parent %p\n", __func__, inode);
+			doutc(cl, "using nonsnap parent %p %llx.%llx\n",
+			      inode, ceph_vinop(inode));
 		} else {
 			/* dentry target */
 			inode = d_inode(req->r_dentry);
@@ -1343,10 +1357,11 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 		rcu_read_unlock();
 	}
 
-	dout("%s %p is_hash=%d (0x%x) mode %d\n", __func__, inode, (int)is_hash,
-	     hash, mode);
 	if (!inode)
 		goto random;
+
+	doutc(cl, "%p %llx.%llx is_hash=%d (0x%x) mode %d\n", inode,
+	      ceph_vinop(inode), (int)is_hash, hash, mode);
 	ci = ceph_inode(inode);
 
 	if (is_hash && S_ISDIR(inode->i_mode)) {
@@ -1362,9 +1377,9 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 				get_random_bytes(&r, 1);
 				r %= frag.ndist;
 				mds = frag.dist[r];
-				dout("%s %p %llx.%llx frag %u mds%d (%d/%d)\n",
-				     __func__, inode, ceph_vinop(inode),
-				     frag.frag, mds, (int)r, frag.ndist);
+				doutc(cl, "%p %llx.%llx frag %u mds%d (%d/%d)\n",
+				      inode, ceph_vinop(inode), frag.frag,
+				      mds, (int)r, frag.ndist);
 				if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
 				    CEPH_MDS_STATE_ACTIVE &&
 				    !ceph_mdsmap_is_laggy(mdsc->mdsmap, mds))
@@ -1377,9 +1392,8 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 			if (frag.mds >= 0) {
 				/* choose auth mds */
 				mds = frag.mds;
-				dout("%s %p %llx.%llx frag %u mds%d (auth)\n",
-				     __func__, inode, ceph_vinop(inode),
-				     frag.frag, mds);
+				doutc(cl, "%p %llx.%llx frag %u mds%d (auth)\n",
+				      inode, ceph_vinop(inode), frag.frag, mds);
 				if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
 				    CEPH_MDS_STATE_ACTIVE) {
 					if (!ceph_mdsmap_is_laggy(mdsc->mdsmap,
@@ -1403,9 +1417,9 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 		goto random;
 	}
 	mds = cap->session->s_mds;
-	dout("%s %p %llx.%llx mds%d (%scap %p)\n", __func__,
-	     inode, ceph_vinop(inode), mds,
-	     cap == ci->i_auth_cap ? "auth " : "", cap);
+	doutc(cl, "%p %llx.%llx mds%d (%scap %p)\n", inode,
+	      ceph_vinop(inode), mds,
+	      cap == ci->i_auth_cap ? "auth " : "", cap);
 	spin_unlock(&ci->i_ceph_lock);
 out:
 	iput(inode);
@@ -1416,7 +1430,7 @@ random:
 		*random = true;
 
 	mds = ceph_mdsmap_get_random_mds(mdsc->mdsmap);
-	dout("%s chose random mds%d\n", __func__, mds);
+	doutc(cl, "chose random mds%d\n", mds);
 	return mds;
 }
 
@@ -1529,6 +1543,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 	int metadata_key_count = 0;
 	struct ceph_options *opt = mdsc->fsc->client->options;
 	struct ceph_mount_options *fsopt = mdsc->fsc->mount_options;
+	struct ceph_client *cl = mdsc->fsc->client;
 	size_t size, count;
 	void *p, *end;
 	int ret;
@@ -1567,7 +1582,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 	msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h) + extra_bytes,
 			   GFP_NOFS, false);
 	if (!msg) {
-		pr_err("ENOMEM creating session open msg\n");
+		pr_err_client(cl, "ENOMEM creating session open msg\n");
 		return ERR_PTR(-ENOMEM);
 	}
 	p = msg->front.iov_base;
@@ -1607,14 +1622,14 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 
 	ret = encode_supported_features(&p, end);
 	if (ret) {
-		pr_err("encode_supported_features failed!\n");
+		pr_err_client(cl, "encode_supported_features failed!\n");
 		ceph_msg_put(msg);
 		return ERR_PTR(ret);
 	}
 
 	ret = encode_metric_spec(&p, end);
 	if (ret) {
-		pr_err("encode_metric_spec failed!\n");
+		pr_err_client(cl, "encode_metric_spec failed!\n");
 		ceph_msg_put(msg);
 		return ERR_PTR(ret);
 	}
@@ -1642,8 +1657,8 @@ static int __open_session(struct ceph_mds_client *mdsc,
 
 	/* wait for mds to go active? */
 	mstate = ceph_mdsmap_get_state(mdsc->mdsmap, mds);
-	dout("open_session to mds%d (%s)\n", mds,
-	     ceph_mds_state_name(mstate));
+	doutc(mdsc->fsc->client, "open_session to mds%d (%s)\n", mds,
+	      ceph_mds_state_name(mstate));
 	session->s_state = CEPH_MDS_SESSION_OPENING;
 	session->s_renew_requested = jiffies;
 
@@ -1686,8 +1701,9 @@ struct ceph_mds_session *
 ceph_mdsc_open_export_target_session(struct ceph_mds_client *mdsc, int target)
 {
 	struct ceph_mds_session *session;
+	struct ceph_client *cl = mdsc->fsc->client;
 
-	dout("open_export_target_session to mds%d\n", target);
+	doutc(cl, "to mds%d\n", target);
 
 	mutex_lock(&mdsc->mutex);
 	session = __open_export_target_session(mdsc, target);
@@ -1702,13 +1718,14 @@ static void __open_export_target_sessions(struct ceph_mds_client *mdsc,
 	struct ceph_mds_info *mi;
 	struct ceph_mds_session *ts;
 	int i, mds = session->s_mds;
+	struct ceph_client *cl = mdsc->fsc->client;
 
 	if (mds >= mdsc->mdsmap->possible_max_rank)
 		return;
 
 	mi = &mdsc->mdsmap->m_info[mds];
-	dout("open_export_target_sessions for mds%d (%d targets)\n",
-	     session->s_mds, mi->num_export_targets);
+	doutc(cl, "for mds%d (%d targets)\n", session->s_mds,
+	      mi->num_export_targets);
 
 	for (i = 0; i < mi->num_export_targets; i++) {
 		ts = __open_export_target_session(mdsc, mi->export_targets[i]);
@@ -1731,11 +1748,13 @@ void ceph_mdsc_open_export_target_sessions(struct ceph_mds_client *mdsc,
 static void detach_cap_releases(struct ceph_mds_session *session,
 				struct list_head *target)
 {
+	struct ceph_client *cl = session->s_mdsc->fsc->client;
+
 	lockdep_assert_held(&session->s_cap_lock);
 
 	list_splice_init(&session->s_cap_releases, target);
 	session->s_num_cap_releases = 0;
-	dout("dispose_cap_releases mds%d\n", session->s_mds);
+	doutc(cl, "mds%d\n", session->s_mds);
 }
 
 static void dispose_cap_releases(struct ceph_mds_client *mdsc,
@@ -1753,16 +1772,17 @@ static void dispose_cap_releases(struct ceph_mds_client *mdsc,
 static void cleanup_session_requests(struct ceph_mds_client *mdsc,
 				     struct ceph_mds_session *session)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *req;
 	struct rb_node *p;
 
-	dout("cleanup_session_requests mds%d\n", session->s_mds);
+	doutc(cl, "mds%d\n", session->s_mds);
 	mutex_lock(&mdsc->mutex);
 	while (!list_empty(&session->s_unsafe)) {
 		req = list_first_entry(&session->s_unsafe,
 				       struct ceph_mds_request, r_unsafe_item);
-		pr_warn_ratelimited(" dropping unsafe request %llu\n",
-				    req->r_tid);
+		pr_warn_ratelimited_client(cl, " dropping unsafe request %llu\n",
+					   req->r_tid);
 		if (req->r_target_inode)
 			mapping_set_error(req->r_target_inode->i_mapping, -EIO);
 		if (req->r_unsafe_dir)
@@ -1791,13 +1811,14 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session,
 			      int (*cb)(struct inode *, int mds, void *),
 			      void *arg)
 {
+	struct ceph_client *cl = session->s_mdsc->fsc->client;
 	struct list_head *p;
 	struct ceph_cap *cap;
 	struct inode *inode, *last_inode = NULL;
 	struct ceph_cap *old_cap = NULL;
 	int ret;
 
-	dout("iterate_session_caps %p mds%d\n", session, session->s_mds);
+	doutc(cl, "%p mds%d\n", session, session->s_mds);
 	spin_lock(&session->s_cap_lock);
 	p = session->s_caps.next;
 	while (p != &session->s_caps) {
@@ -1828,8 +1849,7 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session,
 		spin_lock(&session->s_cap_lock);
 		p = p->next;
 		if (!cap->ci) {
-			dout("iterate_session_caps  finishing cap %p removal\n",
-			     cap);
+			doutc(cl, "finishing cap %p removal\n", cap);
 			BUG_ON(cap->session != session);
 			cap->session = NULL;
 			list_del_init(&cap->session_caps);
@@ -1858,6 +1878,7 @@ out:
 static int remove_session_caps_cb(struct inode *inode, int mds, void *arg)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	bool invalidate = false;
 	struct ceph_cap *cap;
 	int iputs = 0;
@@ -1865,8 +1886,8 @@ static int remove_session_caps_cb(struct inode *inode, int mds, void *arg)
 	spin_lock(&ci->i_ceph_lock);
 	cap = __get_cap_for_mds(ci, mds);
 	if (cap) {
-		dout(" removing cap %p, ci is %p, inode is %p\n",
-		     cap, ci, &ci->netfs.inode);
+		doutc(cl, " removing cap %p, ci is %p, inode is %p\n",
+		      cap, ci, &ci->netfs.inode);
 
 		iputs = ceph_purge_inode_cap(inode, cap, &invalidate);
 	}
@@ -1890,7 +1911,7 @@ static void remove_session_caps(struct ceph_mds_session *session)
 	struct super_block *sb = fsc->sb;
 	LIST_HEAD(dispose);
 
-	dout("remove_session_caps on %p\n", session);
+	doutc(fsc->client, "on %p\n", session);
 	ceph_iterate_session_caps(session, remove_session_caps_cb, fsc);
 
 	wake_up_all(&fsc->mdsc->cap_flushing_wq);
@@ -1971,7 +1992,9 @@ static int wake_up_session_cb(struct inode *inode, int mds, void *arg)
 
 static void wake_up_session_caps(struct ceph_mds_session *session, int ev)
 {
-	dout("wake_up_session_caps %p mds%d\n", session, session->s_mds);
+	struct ceph_client *cl = session->s_mdsc->fsc->client;
+
+	doutc(cl, "session %p mds%d\n", session, session->s_mds);
 	ceph_iterate_session_caps(session, wake_up_session_cb,
 				  (void *)(unsigned long)ev);
 }
@@ -1985,25 +2008,26 @@ static void wake_up_session_caps(struct ceph_mds_session *session, int ev)
 static int send_renew_caps(struct ceph_mds_client *mdsc,
 			   struct ceph_mds_session *session)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_msg *msg;
 	int state;
 
 	if (time_after_eq(jiffies, session->s_cap_ttl) &&
 	    time_after_eq(session->s_cap_ttl, session->s_renew_requested))
-		pr_info("mds%d caps stale\n", session->s_mds);
+		pr_info_client(cl, "mds%d caps stale\n", session->s_mds);
 	session->s_renew_requested = jiffies;
 
 	/* do not try to renew caps until a recovering mds has reconnected
 	 * with its clients. */
 	state = ceph_mdsmap_get_state(mdsc->mdsmap, session->s_mds);
 	if (state < CEPH_MDS_STATE_RECONNECT) {
-		dout("send_renew_caps ignoring mds%d (%s)\n",
-		     session->s_mds, ceph_mds_state_name(state));
+		doutc(cl, "ignoring mds%d (%s)\n", session->s_mds,
+		      ceph_mds_state_name(state));
 		return 0;
 	}
 
-	dout("send_renew_caps to mds%d (%s)\n", session->s_mds,
-		ceph_mds_state_name(state));
+	doutc(cl, "to mds%d (%s)\n", session->s_mds,
+	      ceph_mds_state_name(state));
 	msg = ceph_create_session_msg(CEPH_SESSION_REQUEST_RENEWCAPS,
 				      ++session->s_renew_seq);
 	if (!msg)
@@ -2015,10 +2039,11 @@ static int send_renew_caps(struct ceph_mds_client *mdsc,
 static int send_flushmsg_ack(struct ceph_mds_client *mdsc,
 			     struct ceph_mds_session *session, u64 seq)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_msg *msg;
 
-	dout("send_flushmsg_ack to mds%d (%s)s seq %lld\n",
-	     session->s_mds, ceph_session_state_name(session->s_state), seq);
+	doutc(cl, "to mds%d (%s)s seq %lld\n", session->s_mds,
+	      ceph_session_state_name(session->s_state), seq);
 	msg = ceph_create_session_msg(CEPH_SESSION_FLUSHMSG_ACK, seq);
 	if (!msg)
 		return -ENOMEM;
@@ -2035,6 +2060,7 @@ static int send_flushmsg_ack(struct ceph_mds_client *mdsc,
 static void renewed_caps(struct ceph_mds_client *mdsc,
 			 struct ceph_mds_session *session, int is_renew)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	int was_stale;
 	int wake = 0;
 
@@ -2046,15 +2072,17 @@ static void renewed_caps(struct ceph_mds_client *mdsc,
 
 	if (was_stale) {
 		if (time_before(jiffies, session->s_cap_ttl)) {
-			pr_info("mds%d caps renewed\n", session->s_mds);
+			pr_info_client(cl, "mds%d caps renewed\n",
+				       session->s_mds);
 			wake = 1;
 		} else {
-			pr_info("mds%d caps still stale\n", session->s_mds);
+			pr_info_client(cl, "mds%d caps still stale\n",
+				       session->s_mds);
 		}
 	}
-	dout("renewed_caps mds%d ttl now %lu, was %s, now %s\n",
-	     session->s_mds, session->s_cap_ttl, was_stale ? "stale" : "fresh",
-	     time_before(jiffies, session->s_cap_ttl) ? "stale" : "fresh");
+	doutc(cl, "mds%d ttl now %lu, was %s, now %s\n", session->s_mds,
+	      session->s_cap_ttl, was_stale ? "stale" : "fresh",
+	      time_before(jiffies, session->s_cap_ttl) ? "stale" : "fresh");
 	spin_unlock(&session->s_cap_lock);
 
 	if (wake)
@@ -2066,11 +2094,11 @@ static void renewed_caps(struct ceph_mds_client *mdsc,
  */
 static int request_close_session(struct ceph_mds_session *session)
 {
+	struct ceph_client *cl = session->s_mdsc->fsc->client;
 	struct ceph_msg *msg;
 
-	dout("request_close_session mds%d state %s seq %lld\n",
-	     session->s_mds, ceph_session_state_name(session->s_state),
-	     session->s_seq);
+	doutc(cl, "mds%d state %s seq %lld\n", session->s_mds,
+	      ceph_session_state_name(session->s_state), session->s_seq);
 	msg = ceph_create_session_msg(CEPH_SESSION_REQUEST_CLOSE,
 				      session->s_seq);
 	if (!msg)
@@ -2126,6 +2154,8 @@ out:
  */
 static int trim_caps_cb(struct inode *inode, int mds, void *arg)
 {
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 	int *remaining = arg;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int used, wanted, oissued, mine;
@@ -2145,9 +2175,10 @@ static int trim_caps_cb(struct inode *inode, int mds, void *arg)
 	wanted = __ceph_caps_file_wanted(ci);
 	oissued = __ceph_caps_issued_other(ci, cap);
 
-	dout("trim_caps_cb %p cap %p mine %s oissued %s used %s wanted %s\n",
-	     inode, cap, ceph_cap_string(mine), ceph_cap_string(oissued),
-	     ceph_cap_string(used), ceph_cap_string(wanted));
+	doutc(cl, "%p %llx.%llx cap %p mine %s oissued %s used %s wanted %s\n",
+	      inode, ceph_vinop(inode), cap, ceph_cap_string(mine),
+	      ceph_cap_string(oissued), ceph_cap_string(used),
+	      ceph_cap_string(wanted));
 	if (cap == ci->i_auth_cap) {
 		if (ci->i_dirty_caps || ci->i_flushing_caps ||
 		    !list_empty(&ci->i_cap_snaps))
@@ -2173,7 +2204,7 @@ static int trim_caps_cb(struct inode *inode, int mds, void *arg)
 
 	if (oissued) {
 		/* we aren't the only cap.. just remove us */
-		ceph_remove_cap(cap, true);
+		ceph_remove_cap(mdsc, cap, true);
 		(*remaining)--;
 	} else {
 		struct dentry *dentry;
@@ -2187,8 +2218,8 @@ static int trim_caps_cb(struct inode *inode, int mds, void *arg)
 			count = atomic_read(&inode->i_count);
 			if (count == 1)
 				(*remaining)--;
-			dout("trim_caps_cb %p cap %p pruned, count now %d\n",
-			     inode, cap, count);
+			doutc(cl, "%p %llx.%llx cap %p pruned, count now %d\n",
+			      inode, ceph_vinop(inode), cap, count);
 		} else {
 			dput(dentry);
 		}
@@ -2207,17 +2238,18 @@ int ceph_trim_caps(struct ceph_mds_client *mdsc,
 		   struct ceph_mds_session *session,
 		   int max_caps)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	int trim_caps = session->s_nr_caps - max_caps;
 
-	dout("trim_caps mds%d start: %d / %d, trim %d\n",
-	     session->s_mds, session->s_nr_caps, max_caps, trim_caps);
+	doutc(cl, "mds%d start: %d / %d, trim %d\n", session->s_mds,
+	      session->s_nr_caps, max_caps, trim_caps);
 	if (trim_caps > 0) {
 		int remaining = trim_caps;
 
 		ceph_iterate_session_caps(session, trim_caps_cb, &remaining);
-		dout("trim_caps mds%d done: %d / %d, trimmed %d\n",
-		     session->s_mds, session->s_nr_caps, max_caps,
-			trim_caps - remaining);
+		doutc(cl, "mds%d done: %d / %d, trimmed %d\n",
+		      session->s_mds, session->s_nr_caps, max_caps,
+		      trim_caps - remaining);
 	}
 
 	ceph_flush_cap_releases(mdsc, session);
@@ -2227,6 +2259,7 @@ int ceph_trim_caps(struct ceph_mds_client *mdsc,
 static int check_caps_flush(struct ceph_mds_client *mdsc,
 			    u64 want_flush_tid)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	int ret = 1;
 
 	spin_lock(&mdsc->cap_dirty_lock);
@@ -2235,8 +2268,8 @@ static int check_caps_flush(struct ceph_mds_client *mdsc,
 			list_first_entry(&mdsc->cap_flush_list,
 					 struct ceph_cap_flush, g_list);
 		if (cf->tid <= want_flush_tid) {
-			dout("check_caps_flush still flushing tid "
-			     "%llu <= %llu\n", cf->tid, want_flush_tid);
+			doutc(cl, "still flushing tid %llu <= %llu\n",
+			      cf->tid, want_flush_tid);
 			ret = 0;
 		}
 	}
@@ -2252,12 +2285,14 @@ static int check_caps_flush(struct ceph_mds_client *mdsc,
 static void wait_caps_flush(struct ceph_mds_client *mdsc,
 			    u64 want_flush_tid)
 {
-	dout("check_caps_flush want %llu\n", want_flush_tid);
+	struct ceph_client *cl = mdsc->fsc->client;
+
+	doutc(cl, "want %llu\n", want_flush_tid);
 
 	wait_event(mdsc->cap_flushing_wq,
 		   check_caps_flush(mdsc, want_flush_tid));
 
-	dout("check_caps_flush ok, flushed thru %llu\n", want_flush_tid);
+	doutc(cl, "ok, flushed thru %llu\n", want_flush_tid);
 }
 
 /*
@@ -2266,6 +2301,7 @@ static void wait_caps_flush(struct ceph_mds_client *mdsc,
 static void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
 				   struct ceph_mds_session *session)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_msg *msg = NULL;
 	struct ceph_mds_cap_release *head;
 	struct ceph_mds_cap_item *item;
@@ -2324,7 +2360,7 @@ again:
 			msg->front.iov_len += sizeof(*cap_barrier);
 
 			msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
-			dout("send_cap_releases mds%d %p\n", session->s_mds, msg);
+			doutc(cl, "mds%d %p\n", session->s_mds, msg);
 			ceph_con_send(&session->s_con, msg);
 			msg = NULL;
 		}
@@ -2344,13 +2380,13 @@ again:
 		msg->front.iov_len += sizeof(*cap_barrier);
 
 		msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
-		dout("send_cap_releases mds%d %p\n", session->s_mds, msg);
+		doutc(cl, "mds%d %p\n", session->s_mds, msg);
 		ceph_con_send(&session->s_con, msg);
 	}
 	return;
 out_err:
-	pr_err("send_cap_releases mds%d, failed to allocate message\n",
-		session->s_mds);
+	pr_err_client(cl, "mds%d, failed to allocate message\n",
+		      session->s_mds);
 	spin_lock(&session->s_cap_lock);
 	list_splice(&tmp_list, &session->s_cap_releases);
 	session->s_num_cap_releases += num_cap_releases;
@@ -2373,16 +2409,17 @@ static void ceph_cap_release_work(struct work_struct *work)
 void ceph_flush_cap_releases(struct ceph_mds_client *mdsc,
 		             struct ceph_mds_session *session)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	if (mdsc->stopping)
 		return;
 
 	ceph_get_mds_session(session);
 	if (queue_work(mdsc->fsc->cap_wq,
 		       &session->s_cap_release_work)) {
-		dout("cap release work queued\n");
+		doutc(cl, "cap release work queued\n");
 	} else {
 		ceph_put_mds_session(session);
-		dout("failed to queue cap release work\n");
+		doutc(cl, "failed to queue cap release work\n");
 	}
 }
 
@@ -2410,13 +2447,14 @@ static void ceph_cap_reclaim_work(struct work_struct *work)
 
 void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	if (mdsc->stopping)
 		return;
 
         if (queue_work(mdsc->fsc->cap_wq, &mdsc->cap_reclaim_work)) {
-                dout("caps reclaim work queued\n");
+                doutc(cl, "caps reclaim work queued\n");
         } else {
-                dout("failed to queue caps release work\n");
+                doutc(cl, "failed to queue caps release work\n");
         }
 }
 
@@ -2588,6 +2626,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
 
 /**
  * ceph_mdsc_build_path - build a path string to a given dentry
+ * @mdsc: mds client
  * @dentry: dentry to which path should be built
  * @plen: returned length of string
  * @pbase: returned base inode number
@@ -2607,9 +2646,10 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
  * Encode hidden .snap dirs as a double /, i.e.
  *   foo/.snap/bar -> foo//bar
  */
-char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *pbase,
-			   int for_wire)
+char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
+			   int *plen, u64 *pbase, int for_wire)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct dentry *cur;
 	struct inode *inode;
 	char *path;
@@ -2635,8 +2675,7 @@ retry:
 		spin_lock(&cur->d_lock);
 		inode = d_inode(cur);
 		if (inode && ceph_snap(inode) == CEPH_SNAPDIR) {
-			dout("build_path path+%d: %p SNAPDIR\n",
-			     pos, cur);
+			doutc(cl, "path+%d: %p SNAPDIR\n", pos, cur);
 			spin_unlock(&cur->d_lock);
 			parent = dget_parent(cur);
 		} else if (for_wire && inode && dentry != cur &&
@@ -2714,21 +2753,21 @@ retry:
 		 * A rename didn't occur, but somehow we didn't end up where
 		 * we thought we would. Throw a warning and try again.
 		 */
-		pr_warn("build_path did not end path lookup where expected (pos = %d)\n",
-			pos);
+		pr_warn_client(cl, "did not end path lookup where expected (pos = %d)\n",
+			       pos);
 		goto retry;
 	}
 
 	*pbase = base;
 	*plen = PATH_MAX - 1 - pos;
-	dout("build_path on %p %d built %llx '%.*s'\n",
-	     dentry, d_count(dentry), base, *plen, path + pos);
+	doutc(cl, "on %p %d built %llx '%.*s'\n", dentry, d_count(dentry),
+	      base, *plen, path + pos);
 	return path + pos;
 }
 
-static int build_dentry_path(struct dentry *dentry, struct inode *dir,
-			     const char **ppath, int *ppathlen, u64 *pino,
-			     bool *pfreepath, bool parent_locked)
+static int build_dentry_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
+			     struct inode *dir, const char **ppath, int *ppathlen,
+			     u64 *pino, bool *pfreepath, bool parent_locked)
 {
 	char *path;
 
@@ -2744,7 +2783,7 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir,
 		return 0;
 	}
 	rcu_read_unlock();
-	path = ceph_mdsc_build_path(dentry, ppathlen, pino, 1);
+	path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 	*ppath = path;
@@ -2756,6 +2795,7 @@ static int build_inode_path(struct inode *inode,
 			    const char **ppath, int *ppathlen, u64 *pino,
 			    bool *pfreepath)
 {
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
 	struct dentry *dentry;
 	char *path;
 
@@ -2765,7 +2805,7 @@ static int build_inode_path(struct inode *inode,
 		return 0;
 	}
 	dentry = d_find_alias(inode);
-	path = ceph_mdsc_build_path(dentry, ppathlen, pino, 1);
+	path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1);
 	dput(dentry);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
@@ -2778,27 +2818,28 @@ static int build_inode_path(struct inode *inode,
  * request arguments may be specified via an inode *, a dentry *, or
  * an explicit ino+path.
  */
-static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
-				  struct inode *rdiri, const char *rpath,
-				  u64 rino, const char **ppath, int *pathlen,
-				  u64 *ino, bool *freepath, bool parent_locked)
+static int set_request_path_attr(struct ceph_mds_client *mdsc, struct inode *rinode,
+				 struct dentry *rdentry, struct inode *rdiri,
+				 const char *rpath, u64 rino, const char **ppath,
+				 int *pathlen, u64 *ino, bool *freepath,
+				 bool parent_locked)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	int r = 0;
 
 	if (rinode) {
 		r = build_inode_path(rinode, ppath, pathlen, ino, freepath);
-		dout(" inode %p %llx.%llx\n", rinode, ceph_ino(rinode),
-		     ceph_snap(rinode));
+		doutc(cl, " inode %p %llx.%llx\n", rinode, ceph_ino(rinode),
+		      ceph_snap(rinode));
 	} else if (rdentry) {
-		r = build_dentry_path(rdentry, rdiri, ppath, pathlen, ino,
+		r = build_dentry_path(mdsc, rdentry, rdiri, ppath, pathlen, ino,
 					freepath, parent_locked);
-		dout(" dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen,
-		     *ppath);
+		doutc(cl, " dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen, *ppath);
 	} else if (rpath || rino) {
 		*ino = rino;
 		*ppath = rpath;
 		*pathlen = rpath ? strlen(rpath) : 0;
-		dout(" path %.*s\n", *pathlen, rpath);
+		doutc(cl, " path %.*s\n", *pathlen, rpath);
 	}
 
 	return r;
@@ -2840,6 +2881,17 @@ static void encode_mclientrequest_tail(void **p,
 	}
 }
 
+static inline u16 mds_supported_head_version(struct ceph_mds_session *session)
+{
+	if (!test_bit(CEPHFS_FEATURE_32BITS_RETRY_FWD, &session->s_features))
+		return 1;
+
+	if (!test_bit(CEPHFS_FEATURE_HAS_OWNER_UIDGID, &session->s_features))
+		return 2;
+
+	return CEPH_MDS_REQUEST_HEAD_VERSION;
+}
+
 static struct ceph_mds_request_head_legacy *
 find_legacy_request_head(void *p, u64 features)
 {
@@ -2861,6 +2913,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 {
 	int mds = session->s_mds;
 	struct ceph_mds_client *mdsc = session->s_mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_msg *msg;
 	struct ceph_mds_request_head_legacy *lhead;
 	const char *path1 = NULL;
@@ -2874,10 +2927,11 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	void *p, *end;
 	int ret;
 	bool legacy = !(session->s_con.peer_features & CEPH_FEATURE_FS_BTIME);
-	bool old_version = !test_bit(CEPHFS_FEATURE_32BITS_RETRY_FWD,
-				     &session->s_features);
+	u16 request_head_version = mds_supported_head_version(session);
+	kuid_t caller_fsuid = req->r_cred->fsuid;
+	kgid_t caller_fsgid = req->r_cred->fsgid;
 
-	ret = set_request_path_attr(req->r_inode, req->r_dentry,
+	ret = set_request_path_attr(mdsc, req->r_inode, req->r_dentry,
 			      req->r_parent, req->r_path1, req->r_ino1.ino,
 			      &path1, &pathlen1, &ino1, &freepath1,
 			      test_bit(CEPH_MDS_R_PARENT_LOCKED,
@@ -2891,7 +2945,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	if (req->r_old_dentry &&
 	    !(req->r_old_dentry->d_flags & DCACHE_DISCONNECTED))
 		old_dentry = req->r_old_dentry;
-	ret = set_request_path_attr(NULL, old_dentry,
+	ret = set_request_path_attr(mdsc, NULL, old_dentry,
 			      req->r_old_dentry_dir,
 			      req->r_path2, req->r_ino2.ino,
 			      &path2, &pathlen2, &ino2, &freepath2, true);
@@ -2916,8 +2970,10 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	 */
 	if (legacy)
 		len = sizeof(struct ceph_mds_request_head_legacy);
-	else if (old_version)
+	else if (request_head_version == 1)
 		len = sizeof(struct ceph_mds_request_head_old);
+	else if (request_head_version == 2)
+		len = offsetofend(struct ceph_mds_request_head, ext_num_fwd);
 	else
 		len = sizeof(struct ceph_mds_request_head);
 
@@ -2967,6 +3023,30 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	lhead = find_legacy_request_head(msg->front.iov_base,
 					 session->s_con.peer_features);
 
+	if ((req->r_mnt_idmap != &nop_mnt_idmap) &&
+	    !test_bit(CEPHFS_FEATURE_HAS_OWNER_UIDGID, &session->s_features)) {
+		WARN_ON_ONCE(!IS_CEPH_MDS_OP_NEWINODE(req->r_op));
+
+		if (enable_unsafe_idmap) {
+			pr_warn_once_client(cl,
+				"idmapped mount is used and CEPHFS_FEATURE_HAS_OWNER_UIDGID"
+				" is not supported by MDS. UID/GID-based restrictions may"
+				" not work properly.\n");
+
+			caller_fsuid = from_vfsuid(req->r_mnt_idmap, &init_user_ns,
+						   VFSUIDT_INIT(req->r_cred->fsuid));
+			caller_fsgid = from_vfsgid(req->r_mnt_idmap, &init_user_ns,
+						   VFSGIDT_INIT(req->r_cred->fsgid));
+		} else {
+			pr_err_ratelimited_client(cl,
+				"idmapped mount is used and CEPHFS_FEATURE_HAS_OWNER_UIDGID"
+				" is not supported by MDS. Fail request with -EIO.\n");
+
+			ret = -EIO;
+			goto out_err;
+		}
+	}
+
 	/*
 	 * The ceph_mds_request_head_legacy didn't contain a version field, and
 	 * one was added when we moved the message version from 3->4.
@@ -2974,17 +3054,40 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	if (legacy) {
 		msg->hdr.version = cpu_to_le16(3);
 		p = msg->front.iov_base + sizeof(*lhead);
-	} else if (old_version) {
+	} else if (request_head_version == 1) {
 		struct ceph_mds_request_head_old *ohead = msg->front.iov_base;
 
 		msg->hdr.version = cpu_to_le16(4);
 		ohead->version = cpu_to_le16(1);
 		p = msg->front.iov_base + sizeof(*ohead);
+	} else if (request_head_version == 2) {
+		struct ceph_mds_request_head *nhead = msg->front.iov_base;
+
+		msg->hdr.version = cpu_to_le16(6);
+		nhead->version = cpu_to_le16(2);
+
+		p = msg->front.iov_base + offsetofend(struct ceph_mds_request_head, ext_num_fwd);
 	} else {
 		struct ceph_mds_request_head *nhead = msg->front.iov_base;
+		kuid_t owner_fsuid;
+		kgid_t owner_fsgid;
 
 		msg->hdr.version = cpu_to_le16(6);
 		nhead->version = cpu_to_le16(CEPH_MDS_REQUEST_HEAD_VERSION);
+		nhead->struct_len = cpu_to_le32(sizeof(struct ceph_mds_request_head));
+
+		if (IS_CEPH_MDS_OP_NEWINODE(req->r_op)) {
+			owner_fsuid = from_vfsuid(req->r_mnt_idmap, &init_user_ns,
+						VFSUIDT_INIT(req->r_cred->fsuid));
+			owner_fsgid = from_vfsgid(req->r_mnt_idmap, &init_user_ns,
+						VFSGIDT_INIT(req->r_cred->fsgid));
+			nhead->owner_uid = cpu_to_le32(from_kuid(&init_user_ns, owner_fsuid));
+			nhead->owner_gid = cpu_to_le32(from_kgid(&init_user_ns, owner_fsgid));
+		} else {
+			nhead->owner_uid = cpu_to_le32(-1);
+			nhead->owner_gid = cpu_to_le32(-1);
+		}
+
 		p = msg->front.iov_base + sizeof(*nhead);
 	}
 
@@ -2993,9 +3096,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	lhead->mdsmap_epoch = cpu_to_le32(mdsc->mdsmap->m_epoch);
 	lhead->op = cpu_to_le32(req->r_op);
 	lhead->caller_uid = cpu_to_le32(from_kuid(&init_user_ns,
-						  req->r_cred->fsuid));
+						  caller_fsuid));
 	lhead->caller_gid = cpu_to_le32(from_kgid(&init_user_ns,
-						  req->r_cred->fsgid));
+						  caller_fsgid));
 	lhead->ino = cpu_to_le64(req->r_deleg_ino);
 	lhead->args = req->r_args;
 
@@ -3099,6 +3202,7 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 {
 	int mds = session->s_mds;
 	struct ceph_mds_client *mdsc = session->s_mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request_head_legacy *lhead;
 	struct ceph_mds_request_head *nhead;
 	struct ceph_msg *msg;
@@ -3117,8 +3221,8 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 	       old_max_retry = 1 << (old_max_retry * BITS_PER_BYTE);
 	       if ((old_version && req->r_attempts >= old_max_retry) ||
 		   ((uint32_t)req->r_attempts >= U32_MAX)) {
-			pr_warn_ratelimited("%s request tid %llu seq overflow\n",
-					    __func__, req->r_tid);
+			pr_warn_ratelimited_client(cl, "request tid %llu seq overflow\n",
+						   req->r_tid);
 			return -EMULTIHOP;
 	       }
 	}
@@ -3133,8 +3237,8 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 		else
 			req->r_sent_on_mseq = -1;
 	}
-	dout("%s %p tid %lld %s (attempt %d)\n", __func__, req,
-	     req->r_tid, ceph_mds_op_name(req->r_op), req->r_attempts);
+	doutc(cl, "%p tid %lld %s (attempt %d)\n", req, req->r_tid,
+	      ceph_mds_op_name(req->r_op), req->r_attempts);
 
 	if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags)) {
 		void *p;
@@ -3202,7 +3306,7 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 		nhead->ext_num_retry = cpu_to_le32(req->r_attempts - 1);
 	}
 
-	dout(" r_parent = %p\n", req->r_parent);
+	doutc(cl, " r_parent = %p\n", req->r_parent);
 	return 0;
 }
 
@@ -3230,6 +3334,7 @@ static int __send_request(struct ceph_mds_session *session,
 static void __do_request(struct ceph_mds_client *mdsc,
 			struct ceph_mds_request *req)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_session *session = NULL;
 	int mds = -1;
 	int err = 0;
@@ -3242,29 +3347,29 @@ static void __do_request(struct ceph_mds_client *mdsc,
 	}
 
 	if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO) {
-		dout("do_request metadata corrupted\n");
+		doutc(cl, "metadata corrupted\n");
 		err = -EIO;
 		goto finish;
 	}
 	if (req->r_timeout &&
 	    time_after_eq(jiffies, req->r_started + req->r_timeout)) {
-		dout("do_request timed out\n");
+		doutc(cl, "timed out\n");
 		err = -ETIMEDOUT;
 		goto finish;
 	}
 	if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
-		dout("do_request forced umount\n");
+		doutc(cl, "forced umount\n");
 		err = -EIO;
 		goto finish;
 	}
 	if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_MOUNTING) {
 		if (mdsc->mdsmap_err) {
 			err = mdsc->mdsmap_err;
-			dout("do_request mdsmap err %d\n", err);
+			doutc(cl, "mdsmap err %d\n", err);
 			goto finish;
 		}
 		if (mdsc->mdsmap->m_epoch == 0) {
-			dout("do_request no mdsmap, waiting for map\n");
+			doutc(cl, "no mdsmap, waiting for map\n");
 			list_add(&req->r_wait, &mdsc->waiting_for_map);
 			return;
 		}
@@ -3285,7 +3390,7 @@ static void __do_request(struct ceph_mds_client *mdsc,
 			err = -EJUKEBOX;
 			goto finish;
 		}
-		dout("do_request no mds or not active, waiting for map\n");
+		doutc(cl, "no mds or not active, waiting for map\n");
 		list_add(&req->r_wait, &mdsc->waiting_for_map);
 		return;
 	}
@@ -3301,8 +3406,8 @@ static void __do_request(struct ceph_mds_client *mdsc,
 	}
 	req->r_session = ceph_get_mds_session(session);
 
-	dout("do_request mds%d session %p state %s\n", mds, session,
-	     ceph_session_state_name(session->s_state));
+	doutc(cl, "mds%d session %p state %s\n", mds, session,
+	      ceph_session_state_name(session->s_state));
 
 	/*
 	 * The old ceph will crash the MDSs when see unknown OPs
@@ -3393,8 +3498,8 @@ static void __do_request(struct ceph_mds_client *mdsc,
 		spin_lock(&ci->i_ceph_lock);
 		cap = ci->i_auth_cap;
 		if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE && mds != cap->mds) {
-			dout("do_request session changed for auth cap %d -> %d\n",
-			     cap->session->s_mds, session->s_mds);
+			doutc(cl, "session changed for auth cap %d -> %d\n",
+			      cap->session->s_mds, session->s_mds);
 
 			/* Remove the auth cap from old session */
 			spin_lock(&cap->session->s_cap_lock);
@@ -3421,7 +3526,7 @@ out_session:
 	ceph_put_mds_session(session);
 finish:
 	if (err) {
-		dout("__do_request early error %d\n", err);
+		doutc(cl, "early error %d\n", err);
 		req->r_err = err;
 		complete_request(mdsc, req);
 		__unregister_request(mdsc, req);
@@ -3435,6 +3540,7 @@ finish:
 static void __wake_requests(struct ceph_mds_client *mdsc,
 			    struct list_head *head)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *req;
 	LIST_HEAD(tmp_list);
 
@@ -3444,7 +3550,8 @@ static void __wake_requests(struct ceph_mds_client *mdsc,
 		req = list_entry(tmp_list.next,
 				 struct ceph_mds_request, r_wait);
 		list_del_init(&req->r_wait);
-		dout(" wake request %p tid %llu\n", req, req->r_tid);
+		doutc(cl, " wake request %p tid %llu\n", req,
+		      req->r_tid);
 		__do_request(mdsc, req);
 	}
 }
@@ -3455,10 +3562,11 @@ static void __wake_requests(struct ceph_mds_client *mdsc,
  */
 static void kick_requests(struct ceph_mds_client *mdsc, int mds)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *req;
 	struct rb_node *p = rb_first(&mdsc->request_tree);
 
-	dout("kick_requests mds%d\n", mds);
+	doutc(cl, "kick_requests mds%d\n", mds);
 	while (p) {
 		req = rb_entry(p, struct ceph_mds_request, r_node);
 		p = rb_next(p);
@@ -3468,7 +3576,7 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds)
 			continue; /* only new requests */
 		if (req->r_session &&
 		    req->r_session->s_mds == mds) {
-			dout(" kicking tid %llu\n", req->r_tid);
+			doutc(cl, " kicking tid %llu\n", req->r_tid);
 			list_del_init(&req->r_wait);
 			__do_request(mdsc, req);
 		}
@@ -3478,6 +3586,7 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds)
 int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir,
 			      struct ceph_mds_request *req)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	int err = 0;
 
 	/* take CAP_PIN refs for r_inode, r_parent, r_old_dentry */
@@ -3499,8 +3608,7 @@ int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir,
 	if (req->r_inode) {
 		err = ceph_wait_on_async_create(req->r_inode);
 		if (err) {
-			dout("%s: wait for async create returned: %d\n",
-			     __func__, err);
+			doutc(cl, "wait for async create returned: %d\n", err);
 			return err;
 		}
 	}
@@ -3508,13 +3616,12 @@ int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir,
 	if (!err && req->r_old_inode) {
 		err = ceph_wait_on_async_create(req->r_old_inode);
 		if (err) {
-			dout("%s: wait for async create returned: %d\n",
-			     __func__, err);
+			doutc(cl, "wait for async create returned: %d\n", err);
 			return err;
 		}
 	}
 
-	dout("submit_request on %p for inode %p\n", req, dir);
+	doutc(cl, "submit_request on %p for inode %p\n", req, dir);
 	mutex_lock(&mdsc->mutex);
 	__register_request(mdsc, req, dir);
 	__do_request(mdsc, req);
@@ -3527,10 +3634,11 @@ int ceph_mdsc_wait_request(struct ceph_mds_client *mdsc,
 			   struct ceph_mds_request *req,
 			   ceph_mds_request_wait_callback_t wait_func)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	int err;
 
 	/* wait */
-	dout("do_request waiting\n");
+	doutc(cl, "do_request waiting\n");
 	if (wait_func) {
 		err = wait_func(mdsc, req);
 	} else {
@@ -3544,14 +3652,14 @@ int ceph_mdsc_wait_request(struct ceph_mds_client *mdsc,
 		else
 			err = timeleft;  /* killed */
 	}
-	dout("do_request waited, got %d\n", err);
+	doutc(cl, "do_request waited, got %d\n", err);
 	mutex_lock(&mdsc->mutex);
 
 	/* only abort if we didn't race with a real reply */
 	if (test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags)) {
 		err = le32_to_cpu(req->r_reply_info.head->result);
 	} else if (err < 0) {
-		dout("aborted request %lld with %d\n", req->r_tid, err);
+		doutc(cl, "aborted request %lld with %d\n", req->r_tid, err);
 
 		/*
 		 * ensure we aren't running concurrently with
@@ -3582,15 +3690,16 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 			 struct inode *dir,
 			 struct ceph_mds_request *req)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	int err;
 
-	dout("do_request on %p\n", req);
+	doutc(cl, "do_request on %p\n", req);
 
 	/* issue */
 	err = ceph_mdsc_submit_request(mdsc, dir, req);
 	if (!err)
 		err = ceph_mdsc_wait_request(mdsc, req, NULL);
-	dout("do_request %p done, result %d\n", req, err);
+	doutc(cl, "do_request %p done, result %d\n", req, err);
 	return err;
 }
 
@@ -3602,8 +3711,10 @@ void ceph_invalidate_dir_request(struct ceph_mds_request *req)
 {
 	struct inode *dir = req->r_parent;
 	struct inode *old_dir = req->r_old_dentry_dir;
+	struct ceph_client *cl = req->r_mdsc->fsc->client;
 
-	dout("invalidate_dir_request %p %p (complete, lease(s))\n", dir, old_dir);
+	doutc(cl, "invalidate_dir_request %p %p (complete, lease(s))\n",
+	      dir, old_dir);
 
 	ceph_dir_clear_complete(dir);
 	if (old_dir)
@@ -3624,6 +3735,7 @@ void ceph_invalidate_dir_request(struct ceph_mds_request *req)
 static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 {
 	struct ceph_mds_client *mdsc = session->s_mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *req;
 	struct ceph_mds_reply_head *head = msg->front.iov_base;
 	struct ceph_mds_reply_info_parsed *rinfo;  /* parsed reply info */
@@ -3634,7 +3746,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	bool close_sessions = false;
 
 	if (msg->front.iov_len < sizeof(*head)) {
-		pr_err("mdsc_handle_reply got corrupt (short) reply\n");
+		pr_err_client(cl, "got corrupt (short) reply\n");
 		ceph_msg_dump(msg);
 		return;
 	}
@@ -3644,17 +3756,17 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	mutex_lock(&mdsc->mutex);
 	req = lookup_get_request(mdsc, tid);
 	if (!req) {
-		dout("handle_reply on unknown tid %llu\n", tid);
+		doutc(cl, "on unknown tid %llu\n", tid);
 		mutex_unlock(&mdsc->mutex);
 		return;
 	}
-	dout("handle_reply %p\n", req);
+	doutc(cl, "handle_reply %p\n", req);
 
 	/* correct session? */
 	if (req->r_session != session) {
-		pr_err("mdsc_handle_reply got %llu on session mds%d"
-		       " not mds%d\n", tid, session->s_mds,
-		       req->r_session ? req->r_session->s_mds : -1);
+		pr_err_client(cl, "got %llu on session mds%d not mds%d\n",
+			      tid, session->s_mds,
+			      req->r_session ? req->r_session->s_mds : -1);
 		mutex_unlock(&mdsc->mutex);
 		goto out;
 	}
@@ -3662,14 +3774,14 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	/* dup? */
 	if ((test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags) && !head->safe) ||
 	    (test_bit(CEPH_MDS_R_GOT_SAFE, &req->r_req_flags) && head->safe)) {
-		pr_warn("got a dup %s reply on %llu from mds%d\n",
-			   head->safe ? "safe" : "unsafe", tid, mds);
+		pr_warn_client(cl, "got a dup %s reply on %llu from mds%d\n",
+			       head->safe ? "safe" : "unsafe", tid, mds);
 		mutex_unlock(&mdsc->mutex);
 		goto out;
 	}
 	if (test_bit(CEPH_MDS_R_GOT_SAFE, &req->r_req_flags)) {
-		pr_warn("got unsafe after safe on %llu from mds%d\n",
-			   tid, mds);
+		pr_warn_client(cl, "got unsafe after safe on %llu from mds%d\n",
+			       tid, mds);
 		mutex_unlock(&mdsc->mutex);
 		goto out;
 	}
@@ -3692,7 +3804,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 			 * response.  And even if it did, there is nothing
 			 * useful we could do with a revised return value.
 			 */
-			dout("got safe reply %llu, mds%d\n", tid, mds);
+			doutc(cl, "got safe reply %llu, mds%d\n", tid, mds);
 
 			mutex_unlock(&mdsc->mutex);
 			goto out;
@@ -3702,7 +3814,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 		list_add_tail(&req->r_unsafe_item, &req->r_session->s_unsafe);
 	}
 
-	dout("handle_reply tid %lld result %d\n", tid, result);
+	doutc(cl, "tid %lld result %d\n", tid, result);
 	if (test_bit(CEPHFS_FEATURE_REPLY_ENCODING, &session->s_features))
 		err = parse_reply_info(session, msg, req, (u64)-1);
 	else
@@ -3742,7 +3854,8 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
 	mutex_lock(&session->s_mutex);
 	if (err < 0) {
-		pr_err("mdsc_handle_reply got corrupt reply mds%d(tid:%lld)\n", mds, tid);
+		pr_err_client(cl, "got corrupt reply mds%d(tid:%lld)\n",
+			      mds, tid);
 		ceph_msg_dump(msg);
 		goto out_err;
 	}
@@ -3806,7 +3919,7 @@ out_err:
 			set_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags);
 		}
 	} else {
-		dout("reply arrived after request %lld was aborted\n", tid);
+		doutc(cl, "reply arrived after request %lld was aborted\n", tid);
 	}
 	mutex_unlock(&mdsc->mutex);
 
@@ -3835,6 +3948,7 @@ static void handle_forward(struct ceph_mds_client *mdsc,
 			   struct ceph_mds_session *session,
 			   struct ceph_msg *msg)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *req;
 	u64 tid = le64_to_cpu(msg->hdr.tid);
 	u32 next_mds;
@@ -3852,12 +3966,12 @@ static void handle_forward(struct ceph_mds_client *mdsc,
 	req = lookup_get_request(mdsc, tid);
 	if (!req) {
 		mutex_unlock(&mdsc->mutex);
-		dout("forward tid %llu to mds%d - req dne\n", tid, next_mds);
+		doutc(cl, "forward tid %llu to mds%d - req dne\n", tid, next_mds);
 		return;  /* dup reply? */
 	}
 
 	if (test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
-		dout("forward tid %llu aborted, unregistering\n", tid);
+		doutc(cl, "forward tid %llu aborted, unregistering\n", tid);
 		__unregister_request(mdsc, req);
 	} else if (fwd_seq <= req->r_num_fwd || (uint32_t)fwd_seq >= U32_MAX) {
 		/*
@@ -3873,10 +3987,11 @@ static void handle_forward(struct ceph_mds_client *mdsc,
 		set_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags);
 		mutex_unlock(&req->r_fill_mutex);
 		aborted = true;
-		pr_warn_ratelimited("forward tid %llu seq overflow\n", tid);
+		pr_warn_ratelimited_client(cl, "forward tid %llu seq overflow\n",
+					   tid);
 	} else {
 		/* resend. forward race not possible; mds would drop */
-		dout("forward tid %llu to mds%d (we resend)\n", tid, next_mds);
+		doutc(cl, "forward tid %llu to mds%d (we resend)\n", tid, next_mds);
 		BUG_ON(req->r_err);
 		BUG_ON(test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags));
 		req->r_attempts = 0;
@@ -3894,7 +4009,7 @@ static void handle_forward(struct ceph_mds_client *mdsc,
 	return;
 
 bad:
-	pr_err("mdsc_handle_forward decode error err=%d\n", err);
+	pr_err_client(cl, "decode error err=%d\n", err);
 	ceph_msg_dump(msg);
 }
 
@@ -3933,6 +4048,7 @@ static void handle_session(struct ceph_mds_session *session,
 			   struct ceph_msg *msg)
 {
 	struct ceph_mds_client *mdsc = session->s_mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	int mds = session->s_mds;
 	int msg_version = le16_to_cpu(msg->hdr.version);
 	void *p = msg->front.iov_base;
@@ -3980,7 +4096,8 @@ static void handle_session(struct ceph_mds_session *session,
 		/* version >= 5, flags   */
 		ceph_decode_32_safe(&p, end, flags, bad);
 		if (flags & CEPH_SESSION_BLOCKLISTED) {
-			pr_warn("mds%d session blocklisted\n", session->s_mds);
+			pr_warn_client(cl, "mds%d session blocklisted\n",
+				       session->s_mds);
 			blocklisted = true;
 		}
 	}
@@ -3996,22 +4113,24 @@ static void handle_session(struct ceph_mds_session *session,
 
 	mutex_lock(&session->s_mutex);
 
-	dout("handle_session mds%d %s %p state %s seq %llu\n",
-	     mds, ceph_session_op_name(op), session,
-	     ceph_session_state_name(session->s_state), seq);
+	doutc(cl, "mds%d %s %p state %s seq %llu\n", mds,
+	      ceph_session_op_name(op), session,
+	      ceph_session_state_name(session->s_state), seq);
 
 	if (session->s_state == CEPH_MDS_SESSION_HUNG) {
 		session->s_state = CEPH_MDS_SESSION_OPEN;
-		pr_info("mds%d came back\n", session->s_mds);
+		pr_info_client(cl, "mds%d came back\n", session->s_mds);
 	}
 
 	switch (op) {
 	case CEPH_SESSION_OPEN:
 		if (session->s_state == CEPH_MDS_SESSION_RECONNECTING)
-			pr_info("mds%d reconnect success\n", session->s_mds);
+			pr_info_client(cl, "mds%d reconnect success\n",
+				       session->s_mds);
 
 		if (session->s_state == CEPH_MDS_SESSION_OPEN) {
-			pr_notice("mds%d is already opened\n", session->s_mds);
+			pr_notice_client(cl, "mds%d is already opened\n",
+					 session->s_mds);
 		} else {
 			session->s_state = CEPH_MDS_SESSION_OPEN;
 			session->s_features = features;
@@ -4041,7 +4160,8 @@ static void handle_session(struct ceph_mds_session *session,
 
 	case CEPH_SESSION_CLOSE:
 		if (session->s_state == CEPH_MDS_SESSION_RECONNECTING)
-			pr_info("mds%d reconnect denied\n", session->s_mds);
+			pr_info_client(cl, "mds%d reconnect denied\n",
+				       session->s_mds);
 		session->s_state = CEPH_MDS_SESSION_CLOSED;
 		cleanup_session_requests(mdsc, session);
 		remove_session_caps(session);
@@ -4050,8 +4170,8 @@ static void handle_session(struct ceph_mds_session *session,
 		break;
 
 	case CEPH_SESSION_STALE:
-		pr_info("mds%d caps went stale, renewing\n",
-			session->s_mds);
+		pr_info_client(cl, "mds%d caps went stale, renewing\n",
+			       session->s_mds);
 		atomic_inc(&session->s_cap_gen);
 		session->s_cap_ttl = jiffies - 1;
 		send_renew_caps(mdsc, session);
@@ -4072,7 +4192,7 @@ static void handle_session(struct ceph_mds_session *session,
 		break;
 
 	case CEPH_SESSION_FORCE_RO:
-		dout("force_session_readonly %p\n", session);
+		doutc(cl, "force_session_readonly %p\n", session);
 		spin_lock(&session->s_cap_lock);
 		session->s_readonly = true;
 		spin_unlock(&session->s_cap_lock);
@@ -4081,7 +4201,8 @@ static void handle_session(struct ceph_mds_session *session,
 
 	case CEPH_SESSION_REJECT:
 		WARN_ON(session->s_state != CEPH_MDS_SESSION_OPENING);
-		pr_info("mds%d rejected session\n", session->s_mds);
+		pr_info_client(cl, "mds%d rejected session\n",
+			       session->s_mds);
 		session->s_state = CEPH_MDS_SESSION_REJECTED;
 		cleanup_session_requests(mdsc, session);
 		remove_session_caps(session);
@@ -4091,7 +4212,7 @@ static void handle_session(struct ceph_mds_session *session,
 		break;
 
 	default:
-		pr_err("mdsc_handle_session bad op %d mds%d\n", op, mds);
+		pr_err_client(cl, "bad op %d mds%d\n", op, mds);
 		WARN_ON(1);
 	}
 
@@ -4108,30 +4229,32 @@ static void handle_session(struct ceph_mds_session *session,
 	return;
 
 bad:
-	pr_err("mdsc_handle_session corrupt message mds%d len %d\n", mds,
-	       (int)msg->front.iov_len);
+	pr_err_client(cl, "corrupt message mds%d len %d\n", mds,
+		      (int)msg->front.iov_len);
 	ceph_msg_dump(msg);
 	return;
 }
 
 void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req)
 {
+	struct ceph_client *cl = req->r_mdsc->fsc->client;
 	int dcaps;
 
 	dcaps = xchg(&req->r_dir_caps, 0);
 	if (dcaps) {
-		dout("releasing r_dir_caps=%s\n", ceph_cap_string(dcaps));
+		doutc(cl, "releasing r_dir_caps=%s\n", ceph_cap_string(dcaps));
 		ceph_put_cap_refs(ceph_inode(req->r_parent), dcaps);
 	}
 }
 
 void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req)
 {
+	struct ceph_client *cl = req->r_mdsc->fsc->client;
 	int dcaps;
 
 	dcaps = xchg(&req->r_dir_caps, 0);
 	if (dcaps) {
-		dout("releasing r_dir_caps=%s\n", ceph_cap_string(dcaps));
+		doutc(cl, "releasing r_dir_caps=%s\n", ceph_cap_string(dcaps));
 		ceph_put_cap_refs_no_check_caps(ceph_inode(req->r_parent),
 						dcaps);
 	}
@@ -4146,7 +4269,7 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
 	struct ceph_mds_request *req, *nreq;
 	struct rb_node *p;
 
-	dout("replay_unsafe_requests mds%d\n", session->s_mds);
+	doutc(mdsc->fsc->client, "mds%d\n", session->s_mds);
 
 	mutex_lock(&mdsc->mutex);
 	list_for_each_entry_safe(req, nreq, &session->s_unsafe, r_unsafe_item)
@@ -4290,6 +4413,8 @@ out_unlock:
  */
 static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
 {
+	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	union {
 		struct ceph_mds_cap_reconnect v2;
 		struct ceph_mds_cap_reconnect_v1 v1;
@@ -4307,7 +4432,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
 	dentry = d_find_primary(inode);
 	if (dentry) {
 		/* set pathbase to parent dir when msg_version >= 2 */
-		path = ceph_mdsc_build_path(dentry, &pathlen, &pathbase,
+		path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase,
 					    recon_state->msg_version >= 2);
 		dput(dentry);
 		if (IS_ERR(path)) {
@@ -4326,9 +4451,9 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
 		err = 0;
 		goto out_err;
 	}
-	dout(" adding %p ino %llx.%llx cap %p %lld %s\n",
-	     inode, ceph_vinop(inode), cap, cap->cap_id,
-	     ceph_cap_string(cap->issued));
+	doutc(cl, " adding %p ino %llx.%llx cap %p %lld %s\n", inode,
+	      ceph_vinop(inode), cap, cap->cap_id,
+	      ceph_cap_string(cap->issued));
 
 	cap->seq = 0;        /* reset cap seq */
 	cap->issue_seq = 0;  /* and issue_seq */
@@ -4482,6 +4607,7 @@ static int encode_snap_realms(struct ceph_mds_client *mdsc,
 {
 	struct rb_node *p;
 	struct ceph_pagelist *pagelist = recon_state->pagelist;
+	struct ceph_client *cl = mdsc->fsc->client;
 	int err = 0;
 
 	if (recon_state->msg_version >= 4) {
@@ -4520,8 +4646,8 @@ static int encode_snap_realms(struct ceph_mds_client *mdsc,
 			ceph_pagelist_encode_32(pagelist, sizeof(sr_rec));
 		}
 
-		dout(" adding snap realm %llx seq %lld parent %llx\n",
-		     realm->ino, realm->seq, realm->parent_ino);
+		doutc(cl, " adding snap realm %llx seq %lld parent %llx\n",
+		      realm->ino, realm->seq, realm->parent_ino);
 		sr_rec.ino = cpu_to_le64(realm->ino);
 		sr_rec.seq = cpu_to_le64(realm->seq);
 		sr_rec.parent = cpu_to_le64(realm->parent_ino);
@@ -4550,6 +4676,7 @@ fail:
 static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 			       struct ceph_mds_session *session)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_msg *reply;
 	int mds = session->s_mds;
 	int err = -ENOMEM;
@@ -4558,7 +4685,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	};
 	LIST_HEAD(dispose);
 
-	pr_info("mds%d reconnect start\n", mds);
+	pr_info_client(cl, "mds%d reconnect start\n", mds);
 
 	recon_state.pagelist = ceph_pagelist_alloc(GFP_NOFS);
 	if (!recon_state.pagelist)
@@ -4574,8 +4701,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	session->s_state = CEPH_MDS_SESSION_RECONNECTING;
 	session->s_seq = 0;
 
-	dout("session %p state %s\n", session,
-	     ceph_session_state_name(session->s_state));
+	doutc(cl, "session %p state %s\n", session,
+	      ceph_session_state_name(session->s_state));
 
 	atomic_inc(&session->s_cap_gen);
 
@@ -4709,7 +4836,8 @@ fail:
 fail_nomsg:
 	ceph_pagelist_release(recon_state.pagelist);
 fail_nopagelist:
-	pr_err("error %d preparing reconnect for mds%d\n", err, mds);
+	pr_err_client(cl, "error %d preparing reconnect for mds%d\n",
+		      err, mds);
 	return;
 }
 
@@ -4728,9 +4856,9 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 	int oldstate, newstate;
 	struct ceph_mds_session *s;
 	unsigned long targets[DIV_ROUND_UP(CEPH_MAX_MDS, sizeof(unsigned long))] = {0};
+	struct ceph_client *cl = mdsc->fsc->client;
 
-	dout("check_new_map new %u old %u\n",
-	     newmap->m_epoch, oldmap->m_epoch);
+	doutc(cl, "new %u old %u\n", newmap->m_epoch, oldmap->m_epoch);
 
 	if (newmap->m_info) {
 		for (i = 0; i < newmap->possible_max_rank; i++) {
@@ -4746,12 +4874,12 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 		oldstate = ceph_mdsmap_get_state(oldmap, i);
 		newstate = ceph_mdsmap_get_state(newmap, i);
 
-		dout("check_new_map mds%d state %s%s -> %s%s (session %s)\n",
-		     i, ceph_mds_state_name(oldstate),
-		     ceph_mdsmap_is_laggy(oldmap, i) ? " (laggy)" : "",
-		     ceph_mds_state_name(newstate),
-		     ceph_mdsmap_is_laggy(newmap, i) ? " (laggy)" : "",
-		     ceph_session_state_name(s->s_state));
+		doutc(cl, "mds%d state %s%s -> %s%s (session %s)\n",
+		      i, ceph_mds_state_name(oldstate),
+		      ceph_mdsmap_is_laggy(oldmap, i) ? " (laggy)" : "",
+		      ceph_mds_state_name(newstate),
+		      ceph_mdsmap_is_laggy(newmap, i) ? " (laggy)" : "",
+		      ceph_session_state_name(s->s_state));
 
 		if (i >= newmap->possible_max_rank) {
 			/* force close session for stopped mds */
@@ -4804,7 +4932,8 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 		    newstate >= CEPH_MDS_STATE_ACTIVE) {
 			if (oldstate != CEPH_MDS_STATE_CREATING &&
 			    oldstate != CEPH_MDS_STATE_STARTING)
-				pr_info("mds%d recovery completed\n", s->s_mds);
+				pr_info_client(cl, "mds%d recovery completed\n",
+					       s->s_mds);
 			kick_requests(mdsc, i);
 			mutex_unlock(&mdsc->mutex);
 			mutex_lock(&s->s_mutex);
@@ -4848,12 +4977,13 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 			s = __open_export_target_session(mdsc, i);
 			if (IS_ERR(s)) {
 				err = PTR_ERR(s);
-				pr_err("failed to open export target session, err %d\n",
-				       err);
+				pr_err_client(cl,
+					      "failed to open export target session, err %d\n",
+					      err);
 				continue;
 			}
 		}
-		dout("send reconnect to export target mds.%d\n", i);
+		doutc(cl, "send reconnect to export target mds.%d\n", i);
 		mutex_unlock(&mdsc->mutex);
 		send_mds_reconnect(mdsc, s);
 		ceph_put_mds_session(s);
@@ -4869,8 +4999,7 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 		if (s->s_state == CEPH_MDS_SESSION_OPEN ||
 		    s->s_state == CEPH_MDS_SESSION_HUNG ||
 		    s->s_state == CEPH_MDS_SESSION_CLOSING) {
-			dout(" connecting to export targets of laggy mds%d\n",
-			     i);
+			doutc(cl, " connecting to export targets of laggy mds%d\n", i);
 			__open_export_target_sessions(mdsc, s);
 		}
 	}
@@ -4897,6 +5026,7 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 			 struct ceph_mds_session *session,
 			 struct ceph_msg *msg)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct super_block *sb = mdsc->fsc->sb;
 	struct inode *inode;
 	struct dentry *parent, *dentry;
@@ -4908,7 +5038,7 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 	struct qstr dname;
 	int release = 0;
 
-	dout("handle_lease from mds%d\n", mds);
+	doutc(cl, "from mds%d\n", mds);
 
 	if (!ceph_inc_mds_stopping_blocker(mdsc, session))
 		return;
@@ -4926,20 +5056,19 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 
 	/* lookup inode */
 	inode = ceph_find_inode(sb, vino);
-	dout("handle_lease %s, ino %llx %p %.*s\n",
-	     ceph_lease_op_name(h->action), vino.ino, inode,
-	     dname.len, dname.name);
+	doutc(cl, "%s, ino %llx %p %.*s\n", ceph_lease_op_name(h->action),
+	      vino.ino, inode, dname.len, dname.name);
 
 	mutex_lock(&session->s_mutex);
 	if (!inode) {
-		dout("handle_lease no inode %llx\n", vino.ino);
+		doutc(cl, "no inode %llx\n", vino.ino);
 		goto release;
 	}
 
 	/* dentry */
 	parent = d_find_alias(inode);
 	if (!parent) {
-		dout("no parent dentry on inode %p\n", inode);
+		doutc(cl, "no parent dentry on inode %p\n", inode);
 		WARN_ON(1);
 		goto release;  /* hrm... */
 	}
@@ -4999,7 +5128,7 @@ out:
 bad:
 	ceph_dec_mds_stopping_blocker(mdsc);
 
-	pr_err("corrupt lease message\n");
+	pr_err_client(cl, "corrupt lease message\n");
 	ceph_msg_dump(msg);
 }
 
@@ -5007,13 +5136,14 @@ void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session,
 			      struct dentry *dentry, char action,
 			      u32 seq)
 {
+	struct ceph_client *cl = session->s_mdsc->fsc->client;
 	struct ceph_msg *msg;
 	struct ceph_mds_lease *lease;
 	struct inode *dir;
 	int len = sizeof(*lease) + sizeof(u32) + NAME_MAX;
 
-	dout("lease_send_msg identry %p %s to mds%d\n",
-	     dentry, ceph_lease_op_name(action), session->s_mds);
+	doutc(cl, "identry %p %s to mds%d\n", dentry, ceph_lease_op_name(action),
+	      session->s_mds);
 
 	msg = ceph_msg_new(CEPH_MSG_CLIENT_LEASE, len, GFP_NOFS, false);
 	if (!msg)
@@ -5046,6 +5176,7 @@ static void lock_unlock_session(struct ceph_mds_session *s)
 
 static void maybe_recover_session(struct ceph_mds_client *mdsc)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_fs_client *fsc = mdsc->fsc;
 
 	if (!ceph_test_mount_opt(fsc, CLEANRECOVER))
@@ -5057,17 +5188,19 @@ static void maybe_recover_session(struct ceph_mds_client *mdsc)
 	if (!READ_ONCE(fsc->blocklisted))
 		return;
 
-	pr_info("auto reconnect after blocklisted\n");
+	pr_info_client(cl, "auto reconnect after blocklisted\n");
 	ceph_force_reconnect(fsc->sb);
 }
 
 bool check_session_state(struct ceph_mds_session *s)
 {
+	struct ceph_client *cl = s->s_mdsc->fsc->client;
+
 	switch (s->s_state) {
 	case CEPH_MDS_SESSION_OPEN:
 		if (s->s_ttl && time_after(jiffies, s->s_ttl)) {
 			s->s_state = CEPH_MDS_SESSION_HUNG;
-			pr_info("mds%d hung\n", s->s_mds);
+			pr_info_client(cl, "mds%d hung\n", s->s_mds);
 		}
 		break;
 	case CEPH_MDS_SESSION_CLOSING:
@@ -5087,6 +5220,8 @@ bool check_session_state(struct ceph_mds_session *s)
  */
 void inc_session_sequence(struct ceph_mds_session *s)
 {
+	struct ceph_client *cl = s->s_mdsc->fsc->client;
+
 	lockdep_assert_held(&s->s_mutex);
 
 	s->s_seq++;
@@ -5094,11 +5229,11 @@ void inc_session_sequence(struct ceph_mds_session *s)
 	if (s->s_state == CEPH_MDS_SESSION_CLOSING) {
 		int ret;
 
-		dout("resending session close request for mds%d\n", s->s_mds);
+		doutc(cl, "resending session close request for mds%d\n", s->s_mds);
 		ret = request_close_session(s);
 		if (ret < 0)
-			pr_err("unable to close session to mds%d: %d\n",
-			       s->s_mds, ret);
+			pr_err_client(cl, "unable to close session to mds%d: %d\n",
+				      s->s_mds, ret);
 	}
 }
 
@@ -5127,7 +5262,7 @@ static void delayed_work(struct work_struct *work)
 	int renew_caps;
 	int i;
 
-	dout("mdsc delayed_work\n");
+	doutc(mdsc->fsc->client, "mdsc delayed_work\n");
 
 	if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHED)
 		return;
@@ -5256,6 +5391,7 @@ err_mdsc:
  */
 static void wait_requests(struct ceph_mds_client *mdsc)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_options *opts = mdsc->fsc->client->options;
 	struct ceph_mds_request *req;
 
@@ -5263,25 +5399,25 @@ static void wait_requests(struct ceph_mds_client *mdsc)
 	if (__get_oldest_req(mdsc)) {
 		mutex_unlock(&mdsc->mutex);
 
-		dout("wait_requests waiting for requests\n");
+		doutc(cl, "waiting for requests\n");
 		wait_for_completion_timeout(&mdsc->safe_umount_waiters,
 				    ceph_timeout_jiffies(opts->mount_timeout));
 
 		/* tear down remaining requests */
 		mutex_lock(&mdsc->mutex);
 		while ((req = __get_oldest_req(mdsc))) {
-			dout("wait_requests timed out on tid %llu\n",
-			     req->r_tid);
+			doutc(cl, "timed out on tid %llu\n", req->r_tid);
 			list_del_init(&req->r_wait);
 			__unregister_request(mdsc, req);
 		}
 	}
 	mutex_unlock(&mdsc->mutex);
-	dout("wait_requests done\n");
+	doutc(cl, "done\n");
 }
 
 void send_flush_mdlog(struct ceph_mds_session *s)
 {
+	struct ceph_client *cl = s->s_mdsc->fsc->client;
 	struct ceph_msg *msg;
 
 	/*
@@ -5291,13 +5427,13 @@ void send_flush_mdlog(struct ceph_mds_session *s)
 		return;
 
 	mutex_lock(&s->s_mutex);
-	dout("request mdlog flush to mds%d (%s)s seq %lld\n", s->s_mds,
-	     ceph_session_state_name(s->s_state), s->s_seq);
+	doutc(cl, "request mdlog flush to mds%d (%s)s seq %lld\n",
+	      s->s_mds, ceph_session_state_name(s->s_state), s->s_seq);
 	msg = ceph_create_session_msg(CEPH_SESSION_REQUEST_FLUSH_MDLOG,
 				      s->s_seq);
 	if (!msg) {
-		pr_err("failed to request mdlog flush to mds%d (%s) seq %lld\n",
-		       s->s_mds, ceph_session_state_name(s->s_state), s->s_seq);
+		pr_err_client(cl, "failed to request mdlog flush to mds%d (%s) seq %lld\n",
+			      s->s_mds, ceph_session_state_name(s->s_state), s->s_seq);
 	} else {
 		ceph_con_send(&s->s_con, msg);
 	}
@@ -5310,7 +5446,7 @@ void send_flush_mdlog(struct ceph_mds_session *s)
  */
 void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc)
 {
-	dout("pre_umount\n");
+	doutc(mdsc->fsc->client, "begin\n");
 	mdsc->stopping = CEPH_MDSC_STOPPING_BEGIN;
 
 	ceph_mdsc_iterate_sessions(mdsc, send_flush_mdlog, true);
@@ -5325,6 +5461,7 @@ void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc)
 	ceph_msgr_flush();
 
 	ceph_cleanup_quotarealms_inodes(mdsc);
+	doutc(mdsc->fsc->client, "done\n");
 }
 
 /*
@@ -5333,12 +5470,13 @@ void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc)
 static void flush_mdlog_and_wait_mdsc_unsafe_requests(struct ceph_mds_client *mdsc,
 						 u64 want_tid)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_request *req = NULL, *nextreq;
 	struct ceph_mds_session *last_session = NULL;
 	struct rb_node *n;
 
 	mutex_lock(&mdsc->mutex);
-	dout("%s want %lld\n", __func__, want_tid);
+	doutc(cl, "want %lld\n", want_tid);
 restart:
 	req = __get_oldest_req(mdsc);
 	while (req && req->r_tid <= want_tid) {
@@ -5372,8 +5510,8 @@ restart:
 			} else {
 				ceph_put_mds_session(s);
 			}
-			dout("%s wait on %llu (want %llu)\n", __func__,
-			     req->r_tid, want_tid);
+			doutc(cl, "wait on %llu (want %llu)\n",
+			      req->r_tid, want_tid);
 			wait_for_completion(&req->r_safe_completion);
 
 			mutex_lock(&mdsc->mutex);
@@ -5391,17 +5529,18 @@ restart:
 	}
 	mutex_unlock(&mdsc->mutex);
 	ceph_put_mds_session(last_session);
-	dout("%s done\n", __func__);
+	doutc(cl, "done\n");
 }
 
 void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	u64 want_tid, want_flush;
 
 	if (READ_ONCE(mdsc->fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN)
 		return;
 
-	dout("sync\n");
+	doutc(cl, "sync\n");
 	mutex_lock(&mdsc->mutex);
 	want_tid = mdsc->last_tid;
 	mutex_unlock(&mdsc->mutex);
@@ -5417,8 +5556,7 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
 	}
 	spin_unlock(&mdsc->cap_dirty_lock);
 
-	dout("sync want tid %lld flush_seq %lld\n",
-	     want_tid, want_flush);
+	doutc(cl, "sync want tid %lld flush_seq %lld\n", want_tid, want_flush);
 
 	flush_mdlog_and_wait_mdsc_unsafe_requests(mdsc, want_tid);
 	wait_caps_flush(mdsc, want_flush);
@@ -5440,11 +5578,12 @@ static bool done_closing_sessions(struct ceph_mds_client *mdsc, int skipped)
 void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 {
 	struct ceph_options *opts = mdsc->fsc->client->options;
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_session *session;
 	int i;
 	int skipped = 0;
 
-	dout("close_sessions\n");
+	doutc(cl, "begin\n");
 
 	/* close sessions */
 	mutex_lock(&mdsc->mutex);
@@ -5462,7 +5601,7 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 	}
 	mutex_unlock(&mdsc->mutex);
 
-	dout("waiting for sessions to close\n");
+	doutc(cl, "waiting for sessions to close\n");
 	wait_event_timeout(mdsc->session_close_wq,
 			   done_closing_sessions(mdsc, skipped),
 			   ceph_timeout_jiffies(opts->mount_timeout));
@@ -5490,7 +5629,7 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 	cancel_work_sync(&mdsc->cap_reclaim_work);
 	cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */
 
-	dout("stopped\n");
+	doutc(cl, "done\n");
 }
 
 void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc)
@@ -5498,7 +5637,7 @@ void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc)
 	struct ceph_mds_session *session;
 	int mds;
 
-	dout("force umount\n");
+	doutc(mdsc->fsc->client, "force umount\n");
 
 	mutex_lock(&mdsc->mutex);
 	for (mds = 0; mds < mdsc->max_sessions; mds++) {
@@ -5529,7 +5668,7 @@ void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc)
 
 static void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
 {
-	dout("stop\n");
+	doutc(mdsc->fsc->client, "stop\n");
 	/*
 	 * Make sure the delayed work stopped before releasing
 	 * the resources.
@@ -5550,7 +5689,7 @@ static void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
 void ceph_mdsc_destroy(struct ceph_fs_client *fsc)
 {
 	struct ceph_mds_client *mdsc = fsc->mdsc;
-	dout("mdsc_destroy %p\n", mdsc);
+	doutc(fsc->client, "%p\n", mdsc);
 
 	if (!mdsc)
 		return;
@@ -5564,12 +5703,13 @@ void ceph_mdsc_destroy(struct ceph_fs_client *fsc)
 
 	fsc->mdsc = NULL;
 	kfree(mdsc);
-	dout("mdsc_destroy %p done\n", mdsc);
+	doutc(fsc->client, "%p done\n", mdsc);
 }
 
 void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 {
 	struct ceph_fs_client *fsc = mdsc->fsc;
+	struct ceph_client *cl = fsc->client;
 	const char *mds_namespace = fsc->mount_options->mds_namespace;
 	void *p = msg->front.iov_base;
 	void *end = p + msg->front.iov_len;
@@ -5581,7 +5721,7 @@ void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 	ceph_decode_need(&p, end, sizeof(u32), bad);
 	epoch = ceph_decode_32(&p);
 
-	dout("handle_fsmap epoch %u\n", epoch);
+	doutc(cl, "epoch %u\n", epoch);
 
 	/* struct_v, struct_cv, map_len, epoch, legacy_client_fscid */
 	ceph_decode_skip_n(&p, end, 2 + sizeof(u32) * 3, bad);
@@ -5626,7 +5766,8 @@ void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 	return;
 
 bad:
-	pr_err("error decoding fsmap %d. Shutting down mount.\n", err);
+	pr_err_client(cl, "error decoding fsmap %d. Shutting down mount.\n",
+		      err);
 	ceph_umount_begin(mdsc->fsc->sb);
 	ceph_msg_dump(msg);
 err_out:
@@ -5641,6 +5782,7 @@ err_out:
  */
 void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	u32 epoch;
 	u32 maplen;
 	void *p = msg->front.iov_base;
@@ -5655,18 +5797,17 @@ void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 		return;
 	epoch = ceph_decode_32(&p);
 	maplen = ceph_decode_32(&p);
-	dout("handle_map epoch %u len %d\n", epoch, (int)maplen);
+	doutc(cl, "epoch %u len %d\n", epoch, (int)maplen);
 
 	/* do we need it? */
 	mutex_lock(&mdsc->mutex);
 	if (mdsc->mdsmap && epoch <= mdsc->mdsmap->m_epoch) {
-		dout("handle_map epoch %u <= our %u\n",
-		     epoch, mdsc->mdsmap->m_epoch);
+		doutc(cl, "epoch %u <= our %u\n", epoch, mdsc->mdsmap->m_epoch);
 		mutex_unlock(&mdsc->mutex);
 		return;
 	}
 
-	newmap = ceph_mdsmap_decode(&p, end, ceph_msgr2(mdsc->fsc->client));
+	newmap = ceph_mdsmap_decode(mdsc, &p, end, ceph_msgr2(mdsc->fsc->client));
 	if (IS_ERR(newmap)) {
 		err = PTR_ERR(newmap);
 		goto bad_unlock;
@@ -5695,7 +5836,8 @@ void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 bad_unlock:
 	mutex_unlock(&mdsc->mutex);
 bad:
-	pr_err("error decoding mdsmap %d. Shutting down mount.\n", err);
+	pr_err_client(cl, "error decoding mdsmap %d. Shutting down mount.\n",
+		      err);
 	ceph_umount_begin(mdsc->fsc->sb);
 	ceph_msg_dump(msg);
 	return;
@@ -5726,7 +5868,8 @@ static void mds_peer_reset(struct ceph_connection *con)
 	struct ceph_mds_session *s = con->private;
 	struct ceph_mds_client *mdsc = s->s_mdsc;
 
-	pr_warn("mds%d closed our session\n", s->s_mds);
+	pr_warn_client(mdsc->fsc->client, "mds%d closed our session\n",
+		       s->s_mds);
 	if (READ_ONCE(mdsc->fsc->mount_state) != CEPH_MOUNT_FENCE_IO)
 		send_mds_reconnect(mdsc, s);
 }
@@ -5735,6 +5878,7 @@ static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg)
 {
 	struct ceph_mds_session *s = con->private;
 	struct ceph_mds_client *mdsc = s->s_mdsc;
+	struct ceph_client *cl = mdsc->fsc->client;
 	int type = le16_to_cpu(msg->hdr.type);
 
 	mutex_lock(&mdsc->mutex);
@@ -5774,8 +5918,8 @@ static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg)
 		break;
 
 	default:
-		pr_err("received unknown message type %d %s\n", type,
-		       ceph_msg_type_name(type));
+		pr_err_client(cl, "received unknown message type %d %s\n",
+			      type, ceph_msg_type_name(type));
 	}
 out:
 	ceph_msg_put(msg);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 5a3714bdd64a8e..2e6ddaa13d7250 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -14,9 +14,9 @@
 
 #include <linux/ceph/types.h>
 #include <linux/ceph/messenger.h>
-#include <linux/ceph/mdsmap.h>
 #include <linux/ceph/auth.h>
 
+#include "mdsmap.h"
 #include "metric.h"
 #include "super.h"
 
@@ -33,8 +33,10 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_NOTIFY_SESSION_STATE,
 	CEPHFS_FEATURE_OP_GETVXATTR,
 	CEPHFS_FEATURE_32BITS_RETRY_FWD,
+	CEPHFS_FEATURE_NEW_SNAPREALM_INFO,
+	CEPHFS_FEATURE_HAS_OWNER_UIDGID,
 
-	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_32BITS_RETRY_FWD,
+	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_HAS_OWNER_UIDGID,
 };
 
 #define CEPHFS_FEATURES_CLIENT_SUPPORTED {	\
@@ -49,6 +51,7 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_NOTIFY_SESSION_STATE,	\
 	CEPHFS_FEATURE_OP_GETVXATTR,		\
 	CEPHFS_FEATURE_32BITS_RETRY_FWD,	\
+	CEPHFS_FEATURE_HAS_OWNER_UIDGID,	\
 }
 
 /*
@@ -300,6 +303,7 @@ struct ceph_mds_request {
 	int r_fmode;        /* file mode, if expecting cap */
 	int r_request_release_offset;
 	const struct cred *r_cred;
+	struct mnt_idmap *r_mnt_idmap;
 	struct timespec64 r_stamp;
 
 	/* for choosing which mds to send this request to */
@@ -581,7 +585,8 @@ static inline void ceph_mdsc_free_path(char *path, int len)
 		__putname(path - (PATH_MAX - 1 - len));
 }
 
-extern char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base,
+extern char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc,
+				  struct dentry *dentry, int *plen, u64 *base,
 				  int for_wire);
 
 extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry);
@@ -614,4 +619,6 @@ static inline int ceph_wait_on_async_create(struct inode *inode)
 extern int ceph_wait_on_conflict_unlink(struct dentry *dentry);
 extern u64 ceph_get_deleg_ino(struct ceph_mds_session *session);
 extern int ceph_restore_deleg_ino(struct ceph_mds_session *session, u64 ino);
+
+extern bool enable_unsafe_idmap;
 #endif
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 7dac21ee6ce768..fae97c25ce58d5 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -7,10 +7,11 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 
-#include <linux/ceph/mdsmap.h>
 #include <linux/ceph/messenger.h>
 #include <linux/ceph/decode.h>
 
+#include "mdsmap.h"
+#include "mds_client.h"
 #include "super.h"
 
 #define CEPH_MDS_IS_READY(i, ignore_laggy) \
@@ -114,8 +115,10 @@ bad:
  * Ignore any fields we don't care about (there are quite a few of
  * them).
  */
-struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2)
+struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p,
+				       void *end, bool msgr2)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mdsmap *m;
 	const void *start = *p;
 	int i, j, n;
@@ -233,20 +236,18 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2)
 			*p = info_end;
 		}
 
-		dout("mdsmap_decode %d/%d %lld mds%d.%d %s %s%s\n",
-		     i+1, n, global_id, mds, inc,
-		     ceph_pr_addr(&addr),
-		     ceph_mds_state_name(state),
-		     laggy ? "(laggy)" : "");
+		doutc(cl, "%d/%d %lld mds%d.%d %s %s%s\n", i+1, n, global_id,
+		      mds, inc, ceph_pr_addr(&addr),
+		      ceph_mds_state_name(state), laggy ? "(laggy)" : "");
 
 		if (mds < 0 || mds >= m->possible_max_rank) {
-			pr_warn("mdsmap_decode got incorrect mds(%d)\n", mds);
+			pr_warn_client(cl, "got incorrect mds(%d)\n", mds);
 			continue;
 		}
 
 		if (state <= 0) {
-			dout("mdsmap_decode got incorrect state(%s)\n",
-			     ceph_mds_state_name(state));
+			doutc(cl, "got incorrect state(%s)\n",
+			      ceph_mds_state_name(state));
 			continue;
 		}
 
@@ -385,16 +386,16 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2)
 		m->m_max_xattr_size = 0;
 	}
 bad_ext:
-	dout("mdsmap_decode m_enabled: %d, m_damaged: %d, m_num_laggy: %d\n",
-	     !!m->m_enabled, !!m->m_damaged, m->m_num_laggy);
+	doutc(cl, "m_enabled: %d, m_damaged: %d, m_num_laggy: %d\n",
+	      !!m->m_enabled, !!m->m_damaged, m->m_num_laggy);
 	*p = end;
-	dout("mdsmap_decode success epoch %u\n", m->m_epoch);
+	doutc(cl, "success epoch %u\n", m->m_epoch);
 	return m;
 nomem:
 	err = -ENOMEM;
 	goto out_err;
 corrupt:
-	pr_err("corrupt mdsmap\n");
+	pr_err_client(cl, "corrupt mdsmap\n");
 	print_hex_dump(KERN_DEBUG, "mdsmap: ",
 		       DUMP_PREFIX_OFFSET, 16, 1,
 		       start, end - start, true);
diff --git a/include/linux/ceph/mdsmap.h b/fs/ceph/mdsmap.h
index 4c3e0648dc2775..89f1931f1ba6c9 100644
--- a/include/linux/ceph/mdsmap.h
+++ b/fs/ceph/mdsmap.h
@@ -5,6 +5,8 @@
 #include <linux/bug.h>
 #include <linux/ceph/types.h>
 
+struct ceph_mds_client;
+
 /*
  * mds map - describe servers in the mds cluster.
  *
@@ -65,7 +67,8 @@ static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w)
 }
 
 extern int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m);
-struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2);
+struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p,
+				       void *end, bool msgr2);
 extern void ceph_mdsmap_destroy(struct ceph_mdsmap *m);
 extern bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m);
 
diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
index 6d3584f16f9a4e..871c1090e52011 100644
--- a/fs/ceph/metric.c
+++ b/fs/ceph/metric.c
@@ -31,6 +31,7 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
 	struct ceph_client_metric *m = &mdsc->metric;
 	u64 nr_caps = atomic64_read(&m->total_caps);
 	u32 header_len = sizeof(struct ceph_metric_header);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_msg *msg;
 	s64 sum;
 	s32 items = 0;
@@ -51,8 +52,8 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
 
 	msg = ceph_msg_new(CEPH_MSG_CLIENT_METRICS, len, GFP_NOFS, true);
 	if (!msg) {
-		pr_err("send metrics to mds%d, failed to allocate message\n",
-		       s->s_mds);
+		pr_err_client(cl, "to mds%d, failed to allocate message\n",
+			      s->s_mds);
 		return false;
 	}
 
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index f7fcf7f08ec642..9d36c3532de14f 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -43,6 +43,7 @@ void ceph_handle_quota(struct ceph_mds_client *mdsc,
 {
 	struct super_block *sb = mdsc->fsc->sb;
 	struct ceph_mds_quota *h = msg->front.iov_base;
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_vino vino;
 	struct inode *inode;
 	struct ceph_inode_info *ci;
@@ -51,8 +52,8 @@ void ceph_handle_quota(struct ceph_mds_client *mdsc,
 		return;
 
 	if (msg->front.iov_len < sizeof(*h)) {
-		pr_err("%s corrupt message mds%d len %d\n", __func__,
-		       session->s_mds, (int)msg->front.iov_len);
+		pr_err_client(cl, "corrupt message mds%d len %d\n",
+			      session->s_mds, (int)msg->front.iov_len);
 		ceph_msg_dump(msg);
 		goto out;
 	}
@@ -62,7 +63,7 @@ void ceph_handle_quota(struct ceph_mds_client *mdsc,
 	vino.snap = CEPH_NOSNAP;
 	inode = ceph_find_inode(sb, vino);
 	if (!inode) {
-		pr_warn("Failed to find inode %llu\n", vino.ino);
+		pr_warn_client(cl, "failed to find inode %llx\n", vino.ino);
 		goto out;
 	}
 	ci = ceph_inode(inode);
@@ -85,6 +86,7 @@ find_quotarealm_inode(struct ceph_mds_client *mdsc, u64 ino)
 {
 	struct ceph_quotarealm_inode *qri = NULL;
 	struct rb_node **node, *parent = NULL;
+	struct ceph_client *cl = mdsc->fsc->client;
 
 	mutex_lock(&mdsc->quotarealms_inodes_mutex);
 	node = &(mdsc->quotarealms_inodes.rb_node);
@@ -110,7 +112,7 @@ find_quotarealm_inode(struct ceph_mds_client *mdsc, u64 ino)
 			rb_link_node(&qri->node, parent, node);
 			rb_insert_color(&qri->node, &mdsc->quotarealms_inodes);
 		} else
-			pr_warn("Failed to alloc quotarealms_inode\n");
+			pr_warn_client(cl, "Failed to alloc quotarealms_inode\n");
 	}
 	mutex_unlock(&mdsc->quotarealms_inodes_mutex);
 
@@ -129,6 +131,7 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc,
 					     struct super_block *sb,
 					     struct ceph_snap_realm *realm)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_quotarealm_inode *qri;
 	struct inode *in;
 
@@ -161,8 +164,8 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc,
 	}
 
 	if (IS_ERR(in)) {
-		dout("Can't lookup inode %llx (err: %ld)\n",
-		     realm->ino, PTR_ERR(in));
+		doutc(cl, "Can't lookup inode %llx (err: %ld)\n", realm->ino,
+		      PTR_ERR(in));
 		qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */
 	} else {
 		qri->timeout = 0;
@@ -213,6 +216,7 @@ static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc,
 					       enum quota_get_realm which_quota,
 					       bool retry)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_inode_info *ci = NULL;
 	struct ceph_snap_realm *realm, *next;
 	struct inode *in;
@@ -226,8 +230,9 @@ restart:
 	if (realm)
 		ceph_get_snap_realm(mdsc, realm);
 	else
-		pr_err_ratelimited("get_quota_realm: ino (%llx.%llx) "
-				   "null i_snap_realm\n", ceph_vinop(inode));
+		pr_err_ratelimited_client(cl,
+				"%p %llx.%llx null i_snap_realm\n",
+				inode, ceph_vinop(inode));
 	while (realm) {
 		bool has_inode;
 
@@ -317,6 +322,7 @@ static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op,
 				 loff_t delta)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_inode_info *ci;
 	struct ceph_snap_realm *realm, *next;
 	struct inode *in;
@@ -332,8 +338,9 @@ restart:
 	if (realm)
 		ceph_get_snap_realm(mdsc, realm);
 	else
-		pr_err_ratelimited("check_quota_exceeded: ino (%llx.%llx) "
-				   "null i_snap_realm\n", ceph_vinop(inode));
+		pr_err_ratelimited_client(cl,
+				"%p %llx.%llx null i_snap_realm\n",
+				inode, ceph_vinop(inode));
 	while (realm) {
 		bool has_inode;
 
@@ -383,7 +390,7 @@ restart:
 			break;
 		default:
 			/* Shouldn't happen */
-			pr_warn("Invalid quota check op (%d)\n", op);
+			pr_warn_client(cl, "Invalid quota check op (%d)\n", op);
 			exceeded = true; /* Just break the loop */
 		}
 		iput(in);
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 6732e1ea97d991..c65f2b202b2b3e 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -138,7 +138,7 @@ static struct ceph_snap_realm *ceph_create_snap_realm(
 	__insert_snap_realm(&mdsc->snap_realms, realm);
 	mdsc->num_snap_realms++;
 
-	dout("%s %llx %p\n", __func__, realm->ino, realm);
+	doutc(mdsc->fsc->client, "%llx %p\n", realm->ino, realm);
 	return realm;
 }
 
@@ -150,6 +150,7 @@ static struct ceph_snap_realm *ceph_create_snap_realm(
 static struct ceph_snap_realm *__lookup_snap_realm(struct ceph_mds_client *mdsc,
 						   u64 ino)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct rb_node *n = mdsc->snap_realms.rb_node;
 	struct ceph_snap_realm *r;
 
@@ -162,7 +163,7 @@ static struct ceph_snap_realm *__lookup_snap_realm(struct ceph_mds_client *mdsc,
 		else if (ino > r->ino)
 			n = n->rb_right;
 		else {
-			dout("%s %llx %p\n", __func__, r->ino, r);
+			doutc(cl, "%llx %p\n", r->ino, r);
 			return r;
 		}
 	}
@@ -188,9 +189,10 @@ static void __put_snap_realm(struct ceph_mds_client *mdsc,
 static void __destroy_snap_realm(struct ceph_mds_client *mdsc,
 				 struct ceph_snap_realm *realm)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	lockdep_assert_held_write(&mdsc->snap_rwsem);
 
-	dout("%s %p %llx\n", __func__, realm, realm->ino);
+	doutc(cl, "%p %llx\n", realm, realm->ino);
 
 	rb_erase(&realm->node, &mdsc->snap_realms);
 	mdsc->num_snap_realms--;
@@ -290,6 +292,7 @@ static int adjust_snap_realm_parent(struct ceph_mds_client *mdsc,
 				    struct ceph_snap_realm *realm,
 				    u64 parentino)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_snap_realm *parent;
 
 	lockdep_assert_held_write(&mdsc->snap_rwsem);
@@ -303,8 +306,8 @@ static int adjust_snap_realm_parent(struct ceph_mds_client *mdsc,
 		if (IS_ERR(parent))
 			return PTR_ERR(parent);
 	}
-	dout("%s %llx %p: %llx %p -> %llx %p\n", __func__, realm->ino,
-	     realm, realm->parent_ino, realm->parent, parentino, parent);
+	doutc(cl, "%llx %p: %llx %p -> %llx %p\n", realm->ino, realm,
+	      realm->parent_ino, realm->parent, parentino, parent);
 	if (realm->parent) {
 		list_del_init(&realm->child_item);
 		ceph_put_snap_realm(mdsc, realm->parent);
@@ -329,10 +332,12 @@ static int cmpu64_rev(const void *a, const void *b)
 /*
  * build the snap context for a given realm.
  */
-static int build_snap_context(struct ceph_snap_realm *realm,
+static int build_snap_context(struct ceph_mds_client *mdsc,
+			      struct ceph_snap_realm *realm,
 			      struct list_head *realm_queue,
 			      struct list_head *dirty_realms)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_snap_realm *parent = realm->parent;
 	struct ceph_snap_context *snapc;
 	int err = 0;
@@ -360,10 +365,10 @@ static int build_snap_context(struct ceph_snap_realm *realm,
 	    realm->cached_context->seq == realm->seq &&
 	    (!parent ||
 	     realm->cached_context->seq >= parent->cached_context->seq)) {
-		dout("%s %llx %p: %p seq %lld (%u snaps) (unchanged)\n",
-		     __func__, realm->ino, realm, realm->cached_context,
-		     realm->cached_context->seq,
-		     (unsigned int)realm->cached_context->num_snaps);
+		doutc(cl, "%llx %p: %p seq %lld (%u snaps) (unchanged)\n",
+		      realm->ino, realm, realm->cached_context,
+		      realm->cached_context->seq,
+		      (unsigned int)realm->cached_context->num_snaps);
 		return 0;
 	}
 
@@ -400,8 +405,8 @@ static int build_snap_context(struct ceph_snap_realm *realm,
 
 	sort(snapc->snaps, num, sizeof(u64), cmpu64_rev, NULL);
 	snapc->num_snaps = num;
-	dout("%s %llx %p: %p seq %lld (%u snaps)\n", __func__, realm->ino,
-	     realm, snapc, snapc->seq, (unsigned int) snapc->num_snaps);
+	doutc(cl, "%llx %p: %p seq %lld (%u snaps)\n", realm->ino, realm,
+	      snapc, snapc->seq, (unsigned int) snapc->num_snaps);
 
 	ceph_put_snap_context(realm->cached_context);
 	realm->cached_context = snapc;
@@ -418,16 +423,18 @@ fail:
 		ceph_put_snap_context(realm->cached_context);
 		realm->cached_context = NULL;
 	}
-	pr_err("%s %llx %p fail %d\n", __func__, realm->ino, realm, err);
+	pr_err_client(cl, "%llx %p fail %d\n", realm->ino, realm, err);
 	return err;
 }
 
 /*
  * rebuild snap context for the given realm and all of its children.
  */
-static void rebuild_snap_realms(struct ceph_snap_realm *realm,
+static void rebuild_snap_realms(struct ceph_mds_client *mdsc,
+				struct ceph_snap_realm *realm,
 				struct list_head *dirty_realms)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	LIST_HEAD(realm_queue);
 	int last = 0;
 	bool skip = false;
@@ -451,9 +458,10 @@ static void rebuild_snap_realms(struct ceph_snap_realm *realm,
 			continue;
 		}
 
-		last = build_snap_context(_realm, &realm_queue, dirty_realms);
-		dout("%s %llx %p, %s\n", __func__, _realm->ino, _realm,
-		     last > 0 ? "is deferred" : !last ? "succeeded" : "failed");
+		last = build_snap_context(mdsc, _realm, &realm_queue,
+					  dirty_realms);
+		doutc(cl, "%llx %p, %s\n", realm->ino, realm,
+		      last > 0 ? "is deferred" : !last ? "succeeded" : "failed");
 
 		/* is any child in the list ? */
 		list_for_each_entry(child, &_realm->children, child_item) {
@@ -523,6 +531,7 @@ static void ceph_queue_cap_snap(struct ceph_inode_info *ci,
 				struct ceph_cap_snap **pcapsnap)
 {
 	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_snap_context *old_snapc, *new_snapc;
 	struct ceph_cap_snap *capsnap = *pcapsnap;
 	struct ceph_buffer *old_blob = NULL;
@@ -548,14 +557,14 @@ static void ceph_queue_cap_snap(struct ceph_inode_info *ci,
 		   as no new writes are allowed to start when pending, so any
 		   writes in progress now were started before the previous
 		   cap_snap.  lucky us. */
-		dout("%s %p %llx.%llx already pending\n",
-		     __func__, inode, ceph_vinop(inode));
+		doutc(cl, "%p %llx.%llx already pending\n", inode,
+		      ceph_vinop(inode));
 		goto update_snapc;
 	}
 	if (ci->i_wrbuffer_ref_head == 0 &&
 	    !(dirty & (CEPH_CAP_ANY_EXCL|CEPH_CAP_FILE_WR))) {
-		dout("%s %p %llx.%llx nothing dirty|writing\n",
-		     __func__, inode, ceph_vinop(inode));
+		doutc(cl, "%p %llx.%llx nothing dirty|writing\n", inode,
+		      ceph_vinop(inode));
 		goto update_snapc;
 	}
 
@@ -575,15 +584,15 @@ static void ceph_queue_cap_snap(struct ceph_inode_info *ci,
 	} else {
 		if (!(used & CEPH_CAP_FILE_WR) &&
 		    ci->i_wrbuffer_ref_head == 0) {
-			dout("%s %p %llx.%llx no new_snap|dirty_page|writing\n",
-			     __func__, inode, ceph_vinop(inode));
+			doutc(cl, "%p %llx.%llx no new_snap|dirty_page|writing\n",
+			      inode, ceph_vinop(inode));
 			goto update_snapc;
 		}
 	}
 
-	dout("%s %p %llx.%llx cap_snap %p queuing under %p %s %s\n",
-	     __func__, inode, ceph_vinop(inode), capsnap, old_snapc,
-	     ceph_cap_string(dirty), capsnap->need_flush ? "" : "no_flush");
+	doutc(cl, "%p %llx.%llx cap_snap %p queuing under %p %s %s\n",
+	      inode, ceph_vinop(inode), capsnap, old_snapc,
+	      ceph_cap_string(dirty), capsnap->need_flush ? "" : "no_flush");
 	ihold(inode);
 
 	capsnap->follows = old_snapc->seq;
@@ -615,9 +624,9 @@ static void ceph_queue_cap_snap(struct ceph_inode_info *ci,
 	list_add_tail(&capsnap->ci_item, &ci->i_cap_snaps);
 
 	if (used & CEPH_CAP_FILE_WR) {
-		dout("%s %p %llx.%llx cap_snap %p snapc %p seq %llu used WR,"
-		     " now pending\n", __func__, inode, ceph_vinop(inode),
-		     capsnap, old_snapc, old_snapc->seq);
+		doutc(cl, "%p %llx.%llx cap_snap %p snapc %p seq %llu used WR,"
+		      " now pending\n", inode, ceph_vinop(inode), capsnap,
+		      old_snapc, old_snapc->seq);
 		capsnap->writing = 1;
 	} else {
 		/* note mtime, size NOW. */
@@ -634,7 +643,7 @@ update_snapc:
 		ci->i_head_snapc = NULL;
 	} else {
 		ci->i_head_snapc = ceph_get_snap_context(new_snapc);
-		dout(" new snapc is %p\n", new_snapc);
+		doutc(cl, " new snapc is %p\n", new_snapc);
 	}
 	spin_unlock(&ci->i_ceph_lock);
 
@@ -655,6 +664,7 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
 {
 	struct inode *inode = &ci->netfs.inode;
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+	struct ceph_client *cl = mdsc->fsc->client;
 
 	BUG_ON(capsnap->writing);
 	capsnap->size = i_size_read(inode);
@@ -667,11 +677,12 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
 	capsnap->truncate_size = ci->i_truncate_size;
 	capsnap->truncate_seq = ci->i_truncate_seq;
 	if (capsnap->dirty_pages) {
-		dout("%s %p %llx.%llx cap_snap %p snapc %p %llu %s s=%llu "
-		     "still has %d dirty pages\n", __func__, inode,
-		     ceph_vinop(inode), capsnap, capsnap->context,
-		     capsnap->context->seq, ceph_cap_string(capsnap->dirty),
-		     capsnap->size, capsnap->dirty_pages);
+		doutc(cl, "%p %llx.%llx cap_snap %p snapc %p %llu %s "
+		      "s=%llu still has %d dirty pages\n", inode,
+		      ceph_vinop(inode), capsnap, capsnap->context,
+		      capsnap->context->seq,
+		      ceph_cap_string(capsnap->dirty),
+		      capsnap->size, capsnap->dirty_pages);
 		return 0;
 	}
 
@@ -680,20 +691,20 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
 	 * And trigger to flush the buffer immediately.
 	 */
 	if (ci->i_wrbuffer_ref) {
-		dout("%s %p %llx.%llx cap_snap %p snapc %p %llu %s s=%llu "
-		     "used WRBUFFER, delaying\n", __func__, inode,
-		     ceph_vinop(inode), capsnap, capsnap->context,
-		     capsnap->context->seq, ceph_cap_string(capsnap->dirty),
-		     capsnap->size);
+		doutc(cl, "%p %llx.%llx cap_snap %p snapc %p %llu %s "
+		      "s=%llu used WRBUFFER, delaying\n", inode,
+		      ceph_vinop(inode), capsnap, capsnap->context,
+		      capsnap->context->seq, ceph_cap_string(capsnap->dirty),
+		      capsnap->size);
 		ceph_queue_writeback(inode);
 		return 0;
 	}
 
 	ci->i_ceph_flags |= CEPH_I_FLUSH_SNAPS;
-	dout("%s %p %llx.%llx cap_snap %p snapc %p %llu %s s=%llu\n",
-	     __func__, inode, ceph_vinop(inode), capsnap, capsnap->context,
-	     capsnap->context->seq, ceph_cap_string(capsnap->dirty),
-	     capsnap->size);
+	doutc(cl, "%p %llx.%llx cap_snap %p snapc %p %llu %s s=%llu\n",
+	      inode, ceph_vinop(inode), capsnap, capsnap->context,
+	      capsnap->context->seq, ceph_cap_string(capsnap->dirty),
+	      capsnap->size);
 
 	spin_lock(&mdsc->snap_flush_lock);
 	if (list_empty(&ci->i_snap_flush_item)) {
@@ -708,13 +719,15 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
  * Queue cap_snaps for snap writeback for this realm and its children.
  * Called under snap_rwsem, so realm topology won't change.
  */
-static void queue_realm_cap_snaps(struct ceph_snap_realm *realm)
+static void queue_realm_cap_snaps(struct ceph_mds_client *mdsc,
+				  struct ceph_snap_realm *realm)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_inode_info *ci;
 	struct inode *lastinode = NULL;
 	struct ceph_cap_snap *capsnap = NULL;
 
-	dout("%s %p %llx inode\n", __func__, realm, realm->ino);
+	doutc(cl, "%p %llx inode\n", realm, realm->ino);
 
 	spin_lock(&realm->inodes_with_caps_lock);
 	list_for_each_entry(ci, &realm->inodes_with_caps, i_snap_realm_item) {
@@ -733,8 +746,9 @@ static void queue_realm_cap_snaps(struct ceph_snap_realm *realm)
 		if (!capsnap) {
 			capsnap = kmem_cache_zalloc(ceph_cap_snap_cachep, GFP_NOFS);
 			if (!capsnap) {
-				pr_err("ENOMEM allocating ceph_cap_snap on %p\n",
-				       inode);
+				pr_err_client(cl,
+					"ENOMEM allocating ceph_cap_snap on %p\n",
+					inode);
 				return;
 			}
 		}
@@ -752,7 +766,7 @@ static void queue_realm_cap_snaps(struct ceph_snap_realm *realm)
 
 	if (capsnap)
 		kmem_cache_free(ceph_cap_snap_cachep, capsnap);
-	dout("%s %p %llx done\n", __func__, realm, realm->ino);
+	doutc(cl, "%p %llx done\n", realm, realm->ino);
 }
 
 /*
@@ -766,6 +780,7 @@ int ceph_update_snap_trace(struct ceph_mds_client *mdsc,
 			   void *p, void *e, bool deletion,
 			   struct ceph_snap_realm **realm_ret)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_mds_snap_realm *ri;    /* encoded */
 	__le64 *snaps;                     /* encoded */
 	__le64 *prior_parent_snaps;        /* encoded */
@@ -780,7 +795,7 @@ int ceph_update_snap_trace(struct ceph_mds_client *mdsc,
 
 	lockdep_assert_held_write(&mdsc->snap_rwsem);
 
-	dout("%s deletion=%d\n", __func__, deletion);
+	doutc(cl, "deletion=%d\n", deletion);
 more:
 	realm = NULL;
 	rebuild_snapcs = 0;
@@ -810,8 +825,8 @@ more:
 	rebuild_snapcs += err;
 
 	if (le64_to_cpu(ri->seq) > realm->seq) {
-		dout("%s updating %llx %p %lld -> %lld\n", __func__,
-		     realm->ino, realm, realm->seq, le64_to_cpu(ri->seq));
+		doutc(cl, "updating %llx %p %lld -> %lld\n", realm->ino,
+		      realm, realm->seq, le64_to_cpu(ri->seq));
 		/* update realm parameters, snap lists */
 		realm->seq = le64_to_cpu(ri->seq);
 		realm->created = le64_to_cpu(ri->created);
@@ -834,16 +849,16 @@ more:
 
 		rebuild_snapcs = 1;
 	} else if (!realm->cached_context) {
-		dout("%s %llx %p seq %lld new\n", __func__,
-		     realm->ino, realm, realm->seq);
+		doutc(cl, "%llx %p seq %lld new\n", realm->ino, realm,
+		      realm->seq);
 		rebuild_snapcs = 1;
 	} else {
-		dout("%s %llx %p seq %lld unchanged\n", __func__,
-		     realm->ino, realm, realm->seq);
+		doutc(cl, "%llx %p seq %lld unchanged\n", realm->ino, realm,
+		      realm->seq);
 	}
 
-	dout("done with %llx %p, rebuild_snapcs=%d, %p %p\n", realm->ino,
-	     realm, rebuild_snapcs, p, e);
+	doutc(cl, "done with %llx %p, rebuild_snapcs=%d, %p %p\n", realm->ino,
+	      realm, rebuild_snapcs, p, e);
 
 	/*
 	 * this will always track the uppest parent realm from which
@@ -855,7 +870,7 @@ more:
 
 	/* rebuild_snapcs when we reach the _end_ (root) of the trace */
 	if (realm_to_rebuild && p >= e)
-		rebuild_snap_realms(realm_to_rebuild, &dirty_realms);
+		rebuild_snap_realms(mdsc, realm_to_rebuild, &dirty_realms);
 
 	if (!first_realm)
 		first_realm = realm;
@@ -873,7 +888,7 @@ more:
 		realm = list_first_entry(&dirty_realms, struct ceph_snap_realm,
 					 dirty_item);
 		list_del_init(&realm->dirty_item);
-		queue_realm_cap_snaps(realm);
+		queue_realm_cap_snaps(mdsc, realm);
 	}
 
 	if (realm_ret)
@@ -891,7 +906,7 @@ fail:
 		ceph_put_snap_realm(mdsc, realm);
 	if (first_realm)
 		ceph_put_snap_realm(mdsc, first_realm);
-	pr_err("%s error %d\n", __func__, err);
+	pr_err_client(cl, "error %d\n", err);
 
 	/*
 	 * When receiving a corrupted snap trace we don't know what
@@ -905,11 +920,12 @@ fail:
 	WRITE_ONCE(mdsc->fsc->mount_state, CEPH_MOUNT_FENCE_IO);
 	ret = ceph_monc_blocklist_add(&client->monc, &client->msgr.inst.addr);
 	if (ret)
-		pr_err("%s failed to blocklist %s: %d\n", __func__,
-		       ceph_pr_addr(&client->msgr.inst.addr), ret);
+		pr_err_client(cl, "failed to blocklist %s: %d\n",
+			      ceph_pr_addr(&client->msgr.inst.addr), ret);
 
-	WARN(1, "%s: %s%sdo remount to continue%s",
-	     __func__, ret ? "" : ceph_pr_addr(&client->msgr.inst.addr),
+	WARN(1, "[client.%lld] %s %s%sdo remount to continue%s",
+	     client->monc.auth->global_id, __func__,
+	     ret ? "" : ceph_pr_addr(&client->msgr.inst.addr),
 	     ret ? "" : " was blocklisted, ",
 	     err == -EIO ? " after corrupted snaptrace is fixed" : "");
 
@@ -925,11 +941,12 @@ fail:
  */
 static void flush_snaps(struct ceph_mds_client *mdsc)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_inode_info *ci;
 	struct inode *inode;
 	struct ceph_mds_session *session = NULL;
 
-	dout("%s\n", __func__);
+	doutc(cl, "begin\n");
 	spin_lock(&mdsc->snap_flush_lock);
 	while (!list_empty(&mdsc->snap_flush_list)) {
 		ci = list_first_entry(&mdsc->snap_flush_list,
@@ -944,7 +961,7 @@ static void flush_snaps(struct ceph_mds_client *mdsc)
 	spin_unlock(&mdsc->snap_flush_lock);
 
 	ceph_put_mds_session(session);
-	dout("%s done\n", __func__);
+	doutc(cl, "done\n");
 }
 
 /**
@@ -960,7 +977,7 @@ static void flush_snaps(struct ceph_mds_client *mdsc)
 void ceph_change_snap_realm(struct inode *inode, struct ceph_snap_realm *realm)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc;
 	struct ceph_snap_realm *oldrealm = ci->i_snap_realm;
 
 	lockdep_assert_held(&ci->i_ceph_lock);
@@ -1000,6 +1017,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 		      struct ceph_mds_session *session,
 		      struct ceph_msg *msg)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct super_block *sb = mdsc->fsc->sb;
 	int mds = session->s_mds;
 	u64 split;
@@ -1030,8 +1048,8 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 	trace_len = le32_to_cpu(h->trace_len);
 	p += sizeof(*h);
 
-	dout("%s from mds%d op %s split %llx tracelen %d\n", __func__,
-	     mds, ceph_snap_op_name(op), split, trace_len);
+	doutc(cl, "from mds%d op %s split %llx tracelen %d\n", mds,
+	      ceph_snap_op_name(op), split, trace_len);
 
 	down_write(&mdsc->snap_rwsem);
 	locked_rwsem = 1;
@@ -1062,7 +1080,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 				goto out;
 		}
 
-		dout("splitting snap_realm %llx %p\n", realm->ino, realm);
+		doutc(cl, "splitting snap_realm %llx %p\n", realm->ino, realm);
 		for (i = 0; i < num_split_inos; i++) {
 			struct ceph_vino vino = {
 				.ino = le64_to_cpu(split_inos[i]),
@@ -1087,13 +1105,13 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 			 */
 			if (ci->i_snap_realm->created >
 			    le64_to_cpu(ri->created)) {
-				dout(" leaving %p %llx.%llx in newer realm %llx %p\n",
-				     inode, ceph_vinop(inode), ci->i_snap_realm->ino,
-				     ci->i_snap_realm);
+				doutc(cl, " leaving %p %llx.%llx in newer realm %llx %p\n",
+				      inode, ceph_vinop(inode), ci->i_snap_realm->ino,
+				      ci->i_snap_realm);
 				goto skip_inode;
 			}
-			dout(" will move %p %llx.%llx to split realm %llx %p\n",
-			     inode, ceph_vinop(inode), realm->ino, realm);
+			doutc(cl, " will move %p %llx.%llx to split realm %llx %p\n",
+			      inode, ceph_vinop(inode), realm->ino, realm);
 
 			ceph_get_snap_realm(mdsc, realm);
 			ceph_change_snap_realm(inode, realm);
@@ -1154,7 +1172,7 @@ skip_inode:
 	return;
 
 bad:
-	pr_err("%s corrupt snap message from mds%d\n", __func__, mds);
+	pr_err_client(cl, "corrupt snap message from mds%d\n", mds);
 	ceph_msg_dump(msg);
 out:
 	if (locked_rwsem)
@@ -1170,6 +1188,7 @@ out:
 struct ceph_snapid_map* ceph_get_snapid_map(struct ceph_mds_client *mdsc,
 					    u64 snap)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_snapid_map *sm, *exist;
 	struct rb_node **p, *parent;
 	int ret;
@@ -1192,8 +1211,8 @@ struct ceph_snapid_map* ceph_get_snapid_map(struct ceph_mds_client *mdsc,
 	}
 	spin_unlock(&mdsc->snapid_map_lock);
 	if (exist) {
-		dout("%s found snapid map %llx -> %x\n", __func__,
-		     exist->snap, exist->dev);
+		doutc(cl, "found snapid map %llx -> %x\n", exist->snap,
+		      exist->dev);
 		return exist;
 	}
 
@@ -1237,13 +1256,12 @@ struct ceph_snapid_map* ceph_get_snapid_map(struct ceph_mds_client *mdsc,
 	if (exist) {
 		free_anon_bdev(sm->dev);
 		kfree(sm);
-		dout("%s found snapid map %llx -> %x\n", __func__,
-		     exist->snap, exist->dev);
+		doutc(cl, "found snapid map %llx -> %x\n", exist->snap,
+		      exist->dev);
 		return exist;
 	}
 
-	dout("%s create snapid map %llx -> %x\n", __func__,
-	     sm->snap, sm->dev);
+	doutc(cl, "create snapid map %llx -> %x\n", sm->snap, sm->dev);
 	return sm;
 }
 
@@ -1268,6 +1286,7 @@ void ceph_put_snapid_map(struct ceph_mds_client* mdsc,
 
 void ceph_trim_snapid_map(struct ceph_mds_client *mdsc)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_snapid_map *sm;
 	unsigned long now;
 	LIST_HEAD(to_free);
@@ -1289,7 +1308,7 @@ void ceph_trim_snapid_map(struct ceph_mds_client *mdsc)
 	while (!list_empty(&to_free)) {
 		sm = list_first_entry(&to_free, struct ceph_snapid_map, lru);
 		list_del(&sm->lru);
-		dout("trim snapid map %llx -> %x\n", sm->snap, sm->dev);
+		doutc(cl, "trim snapid map %llx -> %x\n", sm->snap, sm->dev);
 		free_anon_bdev(sm->dev);
 		kfree(sm);
 	}
@@ -1297,6 +1316,7 @@ void ceph_trim_snapid_map(struct ceph_mds_client *mdsc)
 
 void ceph_cleanup_snapid_map(struct ceph_mds_client *mdsc)
 {
+	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_snapid_map *sm;
 	struct rb_node *p;
 	LIST_HEAD(to_free);
@@ -1315,8 +1335,8 @@ void ceph_cleanup_snapid_map(struct ceph_mds_client *mdsc)
 		list_del(&sm->lru);
 		free_anon_bdev(sm->dev);
 		if (WARN_ON_ONCE(atomic_read(&sm->ref))) {
-			pr_err("snapid map %llx -> %x still in use\n",
-			       sm->snap, sm->dev);
+			pr_err_client(cl, "snapid map %llx -> %x still in use\n",
+				      sm->snap, sm->dev);
 		}
 		kfree(sm);
 	}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 2d7f5a8d4a9260..5ec102f6b1ac51 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -44,28 +44,29 @@ static LIST_HEAD(ceph_fsc_list);
  */
 static void ceph_put_super(struct super_block *s)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(s);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(s);
 
-	dout("put_super\n");
+	doutc(fsc->client, "begin\n");
 	ceph_fscrypt_free_dummy_policy(fsc);
 	ceph_mdsc_close_sessions(fsc->mdsc);
+	doutc(fsc->client, "done\n");
 }
 
 static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
-	struct ceph_fs_client *fsc = ceph_inode_to_client(d_inode(dentry));
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(d_inode(dentry));
 	struct ceph_mon_client *monc = &fsc->client->monc;
 	struct ceph_statfs st;
 	int i, err;
 	u64 data_pool;
 
+	doutc(fsc->client, "begin\n");
 	if (fsc->mdsc->mdsmap->m_num_data_pg_pools == 1) {
 		data_pool = fsc->mdsc->mdsmap->m_data_pg_pools[0];
 	} else {
 		data_pool = CEPH_NOPOOL;
 	}
 
-	dout("statfs\n");
 	err = ceph_monc_do_statfs(monc, data_pool, &st);
 	if (err < 0)
 		return err;
@@ -113,24 +114,26 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	/* fold the fs_cluster_id into the upper bits */
 	buf->f_fsid.val[1] = monc->fs_cluster_id;
 
+	doutc(fsc->client, "done\n");
 	return 0;
 }
 
 static int ceph_sync_fs(struct super_block *sb, int wait)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb);
+	struct ceph_client *cl = fsc->client;
 
 	if (!wait) {
-		dout("sync_fs (non-blocking)\n");
+		doutc(cl, "(non-blocking)\n");
 		ceph_flush_dirty_caps(fsc->mdsc);
-		dout("sync_fs (non-blocking) done\n");
+		doutc(cl, "(non-blocking) done\n");
 		return 0;
 	}
 
-	dout("sync_fs (blocking)\n");
+	doutc(cl, "(blocking)\n");
 	ceph_osdc_sync(&fsc->client->osdc);
 	ceph_mdsc_sync(fsc->mdsc);
-	dout("sync_fs (blocking) done\n");
+	doutc(cl, "(blocking) done\n");
 	return 0;
 }
 
@@ -341,7 +344,7 @@ static int ceph_parse_source(struct fs_parameter *param, struct fs_context *fc)
 	char *dev_name = param->string, *dev_name_end;
 	int ret;
 
-	dout("%s '%s'\n", __func__, dev_name);
+	dout("'%s'\n", dev_name);
 	if (!dev_name || !*dev_name)
 		return invalfc(fc, "Empty source");
 
@@ -413,7 +416,7 @@ static int ceph_parse_mount_param(struct fs_context *fc,
 		return ret;
 
 	token = fs_parse(fc, ceph_mount_parameters, param, &result);
-	dout("%s fs_parse '%s' token %d\n", __func__, param->key, token);
+	dout("%s: fs_parse '%s' token %d\n",__func__, param->key, token);
 	if (token < 0)
 		return token;
 
@@ -684,7 +687,7 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt,
  */
 static int ceph_show_options(struct seq_file *m, struct dentry *root)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(root->d_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(root->d_sb);
 	struct ceph_mount_options *fsopt = fsc->mount_options;
 	size_t pos;
 	int ret;
@@ -881,7 +884,7 @@ static void flush_fs_workqueues(struct ceph_fs_client *fsc)
 
 static void destroy_fs_client(struct ceph_fs_client *fsc)
 {
-	dout("destroy_fs_client %p\n", fsc);
+	doutc(fsc->client, "%p\n", fsc);
 
 	spin_lock(&ceph_fsc_lock);
 	list_del(&fsc->metric_wakeup);
@@ -896,7 +899,7 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
 	ceph_destroy_client(fsc->client);
 
 	kfree(fsc);
-	dout("destroy_fs_client %p done\n", fsc);
+	dout("%s: %p done\n", __func__, fsc);
 }
 
 /*
@@ -1015,9 +1018,9 @@ static void __ceph_umount_begin(struct ceph_fs_client *fsc)
  */
 void ceph_umount_begin(struct super_block *sb)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb);
 
-	dout("ceph_umount_begin - starting forced umount\n");
+	doutc(fsc->client, "starting forced umount\n");
 	if (!fsc)
 		return;
 	fsc->mount_state = CEPH_MOUNT_SHUTDOWN;
@@ -1045,13 +1048,14 @@ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc,
 				       const char *path,
 				       unsigned long started)
 {
+	struct ceph_client *cl = fsc->client;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req = NULL;
 	int err;
 	struct dentry *root;
 
 	/* open dir */
-	dout("open_root_inode opening '%s'\n", path);
+	doutc(cl, "opening '%s'\n", path);
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, USE_ANY_MDS);
 	if (IS_ERR(req))
 		return ERR_CAST(req);
@@ -1071,13 +1075,13 @@ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc,
 	if (err == 0) {
 		struct inode *inode = req->r_target_inode;
 		req->r_target_inode = NULL;
-		dout("open_root_inode success\n");
+		doutc(cl, "success\n");
 		root = d_make_root(inode);
 		if (!root) {
 			root = ERR_PTR(-ENOMEM);
 			goto out;
 		}
-		dout("open_root_inode success, root dentry is %p\n", root);
+		doutc(cl, "success, root dentry is %p\n", root);
 	} else {
 		root = ERR_PTR(err);
 	}
@@ -1136,11 +1140,12 @@ static int ceph_apply_test_dummy_encryption(struct super_block *sb,
 static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
 				      struct fs_context *fc)
 {
+	struct ceph_client *cl = fsc->client;
 	int err;
 	unsigned long started = jiffies;  /* note the start time */
 	struct dentry *root;
 
-	dout("mount start %p\n", fsc);
+	doutc(cl, "mount start %p\n", fsc);
 	mutex_lock(&fsc->client->mount_mutex);
 
 	if (!fsc->sb->s_root) {
@@ -1163,7 +1168,7 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
 		if (err)
 			goto out;
 
-		dout("mount opening path '%s'\n", path);
+		doutc(cl, "mount opening path '%s'\n", path);
 
 		ceph_fs_debugfs_init(fsc);
 
@@ -1178,7 +1183,7 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc,
 	}
 
 	fsc->mount_state = CEPH_MOUNT_MOUNTED;
-	dout("mount success\n");
+	doutc(cl, "mount success\n");
 	mutex_unlock(&fsc->client->mount_mutex);
 	return root;
 
@@ -1191,9 +1196,10 @@ out:
 static int ceph_set_super(struct super_block *s, struct fs_context *fc)
 {
 	struct ceph_fs_client *fsc = s->s_fs_info;
+	struct ceph_client *cl = fsc->client;
 	int ret;
 
-	dout("set_super %p\n", s);
+	doutc(cl, "%p\n", s);
 
 	s->s_maxbytes = MAX_LFS_FILESIZE;
 
@@ -1226,31 +1232,32 @@ static int ceph_compare_super(struct super_block *sb, struct fs_context *fc)
 	struct ceph_fs_client *new = fc->s_fs_info;
 	struct ceph_mount_options *fsopt = new->mount_options;
 	struct ceph_options *opt = new->client->options;
-	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb);
+	struct ceph_client *cl = fsc->client;
 
-	dout("ceph_compare_super %p\n", sb);
+	doutc(cl, "%p\n", sb);
 
 	if (compare_mount_options(fsopt, opt, fsc)) {
-		dout("monitor(s)/mount options don't match\n");
+		doutc(cl, "monitor(s)/mount options don't match\n");
 		return 0;
 	}
 	if ((opt->flags & CEPH_OPT_FSID) &&
 	    ceph_fsid_compare(&opt->fsid, &fsc->client->fsid)) {
-		dout("fsid doesn't match\n");
+		doutc(cl, "fsid doesn't match\n");
 		return 0;
 	}
 	if (fc->sb_flags != (sb->s_flags & ~SB_BORN)) {
-		dout("flags differ\n");
+		doutc(cl, "flags differ\n");
 		return 0;
 	}
 
 	if (fsc->blocklisted && !ceph_test_mount_opt(fsc, CLEANRECOVER)) {
-		dout("client is blocklisted (and CLEANRECOVER is not set)\n");
+		doutc(cl, "client is blocklisted (and CLEANRECOVER is not set)\n");
 		return 0;
 	}
 
 	if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) {
-		dout("client has been forcibly unmounted\n");
+		doutc(cl, "client has been forcibly unmounted\n");
 		return 0;
 	}
 
@@ -1322,9 +1329,9 @@ static int ceph_get_tree(struct fs_context *fc)
 		goto out;
 	}
 
-	if (ceph_sb_to_client(sb) != fsc) {
+	if (ceph_sb_to_fs_client(sb) != fsc) {
 		destroy_fs_client(fsc);
-		fsc = ceph_sb_to_client(sb);
+		fsc = ceph_sb_to_fs_client(sb);
 		dout("get_sb got existing client %p\n", fsc);
 	} else {
 		dout("get_sb using new client %p\n", fsc);
@@ -1338,8 +1345,9 @@ static int ceph_get_tree(struct fs_context *fc)
 		err = PTR_ERR(res);
 		goto out_splat;
 	}
-	dout("root %p inode %p ino %llx.%llx\n", res,
-	     d_inode(res), ceph_vinop(d_inode(res)));
+
+	doutc(fsc->client, "root %p inode %p ino %llx.%llx\n", res,
+		    d_inode(res), ceph_vinop(d_inode(res)));
 	fc->root = fsc->sb->s_root;
 	return 0;
 
@@ -1377,7 +1385,7 @@ static int ceph_reconfigure_fc(struct fs_context *fc)
 	struct ceph_parse_opts_ctx *pctx = fc->fs_private;
 	struct ceph_mount_options *fsopt = pctx->opts;
 	struct super_block *sb = fc->root->d_sb;
-	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb);
 
 	err = ceph_apply_test_dummy_encryption(sb, fc, fsopt);
 	if (err)
@@ -1397,7 +1405,8 @@ static int ceph_reconfigure_fc(struct fs_context *fc)
 		kfree(fsc->mount_options->mon_addr);
 		fsc->mount_options->mon_addr = fsopt->mon_addr;
 		fsopt->mon_addr = NULL;
-		pr_notice("ceph: monitor addresses recorded, but not used for reconnection");
+		pr_notice_client(fsc->client,
+			"monitor addresses recorded, but not used for reconnection");
 	}
 
 	sync_filesystem(sb);
@@ -1516,11 +1525,12 @@ void ceph_dec_osd_stopping_blocker(struct ceph_mds_client *mdsc)
 
 static void ceph_kill_sb(struct super_block *s)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(s);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(s);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	bool wait;
 
-	dout("kill_sb %p\n", s);
+	doutc(cl, "%p\n", s);
 
 	ceph_mdsc_pre_umount(mdsc);
 	flush_fs_workqueues(fsc);
@@ -1551,9 +1561,9 @@ static void ceph_kill_sb(struct super_block *s)
 					&mdsc->stopping_waiter,
 					fsc->client->options->mount_timeout);
 		if (!timeleft) /* timed out */
-			pr_warn("umount timed out, %ld\n", timeleft);
+			pr_warn_client(cl, "umount timed out, %ld\n", timeleft);
 		else if (timeleft < 0) /* killed */
-			pr_warn("umount was killed, %ld\n", timeleft);
+			pr_warn_client(cl, "umount was killed, %ld\n", timeleft);
 	}
 
 	mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED;
@@ -1572,13 +1582,13 @@ static struct file_system_type ceph_fs_type = {
 	.name		= "ceph",
 	.init_fs_context = ceph_init_fs_context,
 	.kill_sb	= ceph_kill_sb,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE | FS_ALLOW_IDMAP,
 };
 MODULE_ALIAS_FS("ceph");
 
 int ceph_force_reconnect(struct super_block *sb)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb);
 	int err = 0;
 
 	fsc->mount_state = CEPH_MOUNT_RECOVER;
@@ -1671,6 +1681,11 @@ static const struct kernel_param_ops param_ops_mount_syntax = {
 module_param_cb(mount_syntax_v1, &param_ops_mount_syntax, &mount_support, 0444);
 module_param_cb(mount_syntax_v2, &param_ops_mount_syntax, &mount_support, 0444);
 
+bool enable_unsafe_idmap = false;
+module_param(enable_unsafe_idmap, bool, 0644);
+MODULE_PARM_DESC(enable_unsafe_idmap,
+		 "Allow to use idmapped mounts with MDS without CEPHFS_FEATURE_HAS_OWNER_UIDGID");
+
 module_init(init_ceph);
 module_exit(exit_ceph);
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 98844fc8a2f7af..fe0f64a0acb270 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -488,13 +488,13 @@ ceph_inode(const struct inode *inode)
 }
 
 static inline struct ceph_fs_client *
-ceph_inode_to_client(const struct inode *inode)
+ceph_inode_to_fs_client(const struct inode *inode)
 {
 	return (struct ceph_fs_client *)inode->i_sb->s_fs_info;
 }
 
 static inline struct ceph_fs_client *
-ceph_sb_to_client(const struct super_block *sb)
+ceph_sb_to_fs_client(const struct super_block *sb)
 {
 	return (struct ceph_fs_client *)sb->s_fs_info;
 }
@@ -502,7 +502,13 @@ ceph_sb_to_client(const struct super_block *sb)
 static inline struct ceph_mds_client *
 ceph_sb_to_mdsc(const struct super_block *sb)
 {
-	return (struct ceph_mds_client *)ceph_sb_to_client(sb)->mdsc;
+	return (struct ceph_mds_client *)ceph_sb_to_fs_client(sb)->mdsc;
+}
+
+static inline struct ceph_client *
+ceph_inode_to_client(const struct inode *inode)
+{
+	return (struct ceph_client *)ceph_inode_to_fs_client(inode)->client;
 }
 
 static inline struct ceph_vino
@@ -558,7 +564,7 @@ static inline u64 ceph_snap(struct inode *inode)
  */
 static inline u64 ceph_present_ino(struct super_block *sb, u64 ino)
 {
-	if (unlikely(ceph_test_mount_opt(ceph_sb_to_client(sb), INO32)))
+	if (unlikely(ceph_test_mount_opt(ceph_sb_to_fs_client(sb), INO32)))
 		return ceph_ino_to_ino32(ino);
 	return ino;
 }
@@ -1094,8 +1100,8 @@ struct ceph_iattr {
 	struct ceph_fscrypt_auth	*fscrypt_auth;
 };
 
-extern int __ceph_setattr(struct inode *inode, struct iattr *attr,
-			  struct ceph_iattr *cia);
+extern int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
+			  struct iattr *attr, struct ceph_iattr *cia);
 extern int ceph_setattr(struct mnt_idmap *idmap,
 			struct dentry *dentry, struct iattr *attr);
 extern int ceph_getattr(struct mnt_idmap *idmap,
@@ -1106,7 +1112,7 @@ void ceph_inode_shutdown(struct inode *inode);
 static inline bool ceph_inode_is_shutdown(struct inode *inode)
 {
 	unsigned long flags = READ_ONCE(ceph_inode(inode)->i_ceph_flags);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 	int state = READ_ONCE(fsc->mount_state);
 
 	return (flags & CEPH_I_SHUTDOWN) || state >= CEPH_MOUNT_SHUTDOWN;
@@ -1223,7 +1229,8 @@ extern void ceph_add_cap(struct inode *inode,
 			 unsigned cap, unsigned seq, u64 realmino, int flags,
 			 struct ceph_cap **new_cap);
 extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
-extern void ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
+extern void ceph_remove_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
+			    bool queue_release);
 extern void __ceph_remove_caps(struct ceph_inode_info *ci);
 extern void ceph_put_cap(struct ceph_mds_client *mdsc,
 			 struct ceph_cap *cap);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 097ce7f74073d4..e066a556eccbfe 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -57,7 +57,8 @@ static bool ceph_vxattrcb_layout_exists(struct ceph_inode_info *ci)
 static ssize_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
 				    size_t size)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(ci->netfs.inode.i_sb);
+	struct ceph_client *cl = fsc->client;
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	struct ceph_string *pool_ns;
 	s64 pool = ci->i_layout.pool_id;
@@ -69,7 +70,7 @@ static ssize_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
 
 	pool_ns = ceph_try_get_string(ci->i_layout.pool_ns);
 
-	dout("ceph_vxattrcb_layout %p\n", &ci->netfs.inode);
+	doutc(cl, "%p\n", &ci->netfs.inode);
 	down_read(&osdc->lock);
 	pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
 	if (pool_name) {
@@ -161,7 +162,7 @@ static ssize_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
 					 char *val, size_t size)
 {
 	ssize_t ret;
-	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(ci->netfs.inode.i_sb);
 	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	s64 pool = ci->i_layout.pool_id;
 	const char *pool_name;
@@ -313,7 +314,7 @@ static ssize_t ceph_vxattrcb_snap_btime(struct ceph_inode_info *ci, char *val,
 static ssize_t ceph_vxattrcb_cluster_fsid(struct ceph_inode_info *ci,
 					  char *val, size_t size)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(ci->netfs.inode.i_sb);
 
 	return ceph_fmt_xattr(val, size, "%pU", &fsc->client->fsid);
 }
@@ -321,7 +322,7 @@ static ssize_t ceph_vxattrcb_cluster_fsid(struct ceph_inode_info *ci,
 static ssize_t ceph_vxattrcb_client_id(struct ceph_inode_info *ci,
 				       char *val, size_t size)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(ci->netfs.inode.i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(ci->netfs.inode.i_sb);
 
 	return ceph_fmt_xattr(val, size, "client%lld",
 			      ceph_client_gid(fsc->client));
@@ -570,6 +571,8 @@ static int __set_xattr(struct ceph_inode_info *ci,
 			   int flags, int update_xattr,
 			   struct ceph_inode_xattr **newxattr)
 {
+	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct ceph_inode_xattr *xattr = NULL;
@@ -626,7 +629,7 @@ static int __set_xattr(struct ceph_inode_info *ci,
 		xattr->should_free_name = update_xattr;
 
 		ci->i_xattrs.count++;
-		dout("%s count=%d\n", __func__, ci->i_xattrs.count);
+		doutc(cl, "count=%d\n", ci->i_xattrs.count);
 	} else {
 		kfree(*newxattr);
 		*newxattr = NULL;
@@ -654,13 +657,13 @@ static int __set_xattr(struct ceph_inode_info *ci,
 	if (new) {
 		rb_link_node(&xattr->node, parent, p);
 		rb_insert_color(&xattr->node, &ci->i_xattrs.index);
-		dout("%s p=%p\n", __func__, p);
+		doutc(cl, "p=%p\n", p);
 	}
 
-	dout("%s added %llx.%llx xattr %p %.*s=%.*s%s\n", __func__,
-	     ceph_vinop(&ci->netfs.inode), xattr, name_len, name,
-	     min(val_len, MAX_XATTR_VAL_PRINT_LEN), val,
-	     val_len > MAX_XATTR_VAL_PRINT_LEN ? "..." : "");
+	doutc(cl, "added %p %llx.%llx xattr %p %.*s=%.*s%s\n", inode,
+	      ceph_vinop(inode), xattr, name_len, name, min(val_len,
+	      MAX_XATTR_VAL_PRINT_LEN), val,
+	      val_len > MAX_XATTR_VAL_PRINT_LEN ? "..." : "");
 
 	return 0;
 }
@@ -668,6 +671,7 @@ static int __set_xattr(struct ceph_inode_info *ci,
 static struct ceph_inode_xattr *__get_xattr(struct ceph_inode_info *ci,
 			   const char *name)
 {
+	struct ceph_client *cl = ceph_inode_to_client(&ci->netfs.inode);
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct ceph_inode_xattr *xattr = NULL;
@@ -688,13 +692,13 @@ static struct ceph_inode_xattr *__get_xattr(struct ceph_inode_info *ci,
 		else {
 			int len = min(xattr->val_len, MAX_XATTR_VAL_PRINT_LEN);
 
-			dout("%s %s: found %.*s%s\n", __func__, name, len,
-			     xattr->val, xattr->val_len > len ? "..." : "");
+			doutc(cl, "%s found %.*s%s\n", name, len, xattr->val,
+			      xattr->val_len > len ? "..." : "");
 			return xattr;
 		}
 	}
 
-	dout("%s %s: not found\n", __func__, name);
+	doutc(cl, "%s not found\n", name);
 
 	return NULL;
 }
@@ -735,19 +739,20 @@ static int __remove_xattr(struct ceph_inode_info *ci,
 static char *__copy_xattr_names(struct ceph_inode_info *ci,
 				char *dest)
 {
+	struct ceph_client *cl = ceph_inode_to_client(&ci->netfs.inode);
 	struct rb_node *p;
 	struct ceph_inode_xattr *xattr = NULL;
 
 	p = rb_first(&ci->i_xattrs.index);
-	dout("__copy_xattr_names count=%d\n", ci->i_xattrs.count);
+	doutc(cl, "count=%d\n", ci->i_xattrs.count);
 
 	while (p) {
 		xattr = rb_entry(p, struct ceph_inode_xattr, node);
 		memcpy(dest, xattr->name, xattr->name_len);
 		dest[xattr->name_len] = '\0';
 
-		dout("dest=%s %p (%s) (%d/%d)\n", dest, xattr, xattr->name,
-		     xattr->name_len, ci->i_xattrs.names_size);
+		doutc(cl, "dest=%s %p (%s) (%d/%d)\n", dest, xattr, xattr->name,
+		      xattr->name_len, ci->i_xattrs.names_size);
 
 		dest += xattr->name_len + 1;
 		p = rb_next(p);
@@ -758,19 +763,19 @@ static char *__copy_xattr_names(struct ceph_inode_info *ci,
 
 void __ceph_destroy_xattrs(struct ceph_inode_info *ci)
 {
+	struct ceph_client *cl = ceph_inode_to_client(&ci->netfs.inode);
 	struct rb_node *p, *tmp;
 	struct ceph_inode_xattr *xattr = NULL;
 
 	p = rb_first(&ci->i_xattrs.index);
 
-	dout("__ceph_destroy_xattrs p=%p\n", p);
+	doutc(cl, "p=%p\n", p);
 
 	while (p) {
 		xattr = rb_entry(p, struct ceph_inode_xattr, node);
 		tmp = p;
 		p = rb_next(tmp);
-		dout("__ceph_destroy_xattrs next p=%p (%.*s)\n", p,
-		     xattr->name_len, xattr->name);
+		doutc(cl, "next p=%p (%.*s)\n", p, xattr->name_len, xattr->name);
 		rb_erase(tmp, &ci->i_xattrs.index);
 
 		__free_xattr(xattr);
@@ -787,6 +792,7 @@ static int __build_xattrs(struct inode *inode)
 	__releases(ci->i_ceph_lock)
 	__acquires(ci->i_ceph_lock)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	u32 namelen;
 	u32 numattr = 0;
 	void *p, *end;
@@ -798,8 +804,8 @@ static int __build_xattrs(struct inode *inode)
 	int err = 0;
 	int i;
 
-	dout("__build_xattrs() len=%d\n",
-	     ci->i_xattrs.blob ? (int)ci->i_xattrs.blob->vec.iov_len : 0);
+	doutc(cl, "len=%d\n",
+	      ci->i_xattrs.blob ? (int)ci->i_xattrs.blob->vec.iov_len : 0);
 
 	if (ci->i_xattrs.index_version >= ci->i_xattrs.version)
 		return 0; /* already built */
@@ -874,6 +880,8 @@ bad:
 static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size,
 				    int val_size)
 {
+	struct ceph_client *cl = ceph_inode_to_client(&ci->netfs.inode);
+
 	/*
 	 * 4 bytes for the length, and additional 4 bytes per each xattr name,
 	 * 4 bytes per each value
@@ -881,9 +889,8 @@ static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size,
 	int size = 4 + ci->i_xattrs.count*(4 + 4) +
 			     ci->i_xattrs.names_size +
 			     ci->i_xattrs.vals_size;
-	dout("__get_required_blob_size c=%d names.size=%d vals.size=%d\n",
-	     ci->i_xattrs.count, ci->i_xattrs.names_size,
-	     ci->i_xattrs.vals_size);
+	doutc(cl, "c=%d names.size=%d vals.size=%d\n", ci->i_xattrs.count,
+	      ci->i_xattrs.names_size, ci->i_xattrs.vals_size);
 
 	if (name_size)
 		size += 4 + 4 + name_size + val_size;
@@ -899,12 +906,14 @@ static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size,
  */
 struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci)
 {
+	struct inode *inode = &ci->netfs.inode;
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct rb_node *p;
 	struct ceph_inode_xattr *xattr = NULL;
 	struct ceph_buffer *old_blob = NULL;
 	void *dest;
 
-	dout("__build_xattrs_blob %p\n", &ci->netfs.inode);
+	doutc(cl, "%p %llx.%llx\n", inode, ceph_vinop(inode));
 	if (ci->i_xattrs.dirty) {
 		int need = __get_required_blob_size(ci, 0, 0);
 
@@ -962,6 +971,7 @@ static inline int __get_request_mask(struct inode *in) {
 ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
 		      size_t size)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_inode_xattr *xattr;
 	struct ceph_vxattr *vxattr;
@@ -1000,8 +1010,9 @@ handle_non_vxattrs:
 	req_mask = __get_request_mask(inode);
 
 	spin_lock(&ci->i_ceph_lock);
-	dout("getxattr %p name '%s' ver=%lld index_ver=%lld\n", inode, name,
-	     ci->i_xattrs.version, ci->i_xattrs.index_version);
+	doutc(cl, "%p %llx.%llx name '%s' ver=%lld index_ver=%lld\n", inode,
+	      ceph_vinop(inode), name, ci->i_xattrs.version,
+	      ci->i_xattrs.index_version);
 
 	if (ci->i_xattrs.version == 0 ||
 	    !((req_mask & CEPH_CAP_XATTR_SHARED) ||
@@ -1010,8 +1021,9 @@ handle_non_vxattrs:
 
 		/* security module gets xattr while filling trace */
 		if (current->journal_info) {
-			pr_warn_ratelimited("sync getxattr %p "
-					    "during filling trace\n", inode);
+			pr_warn_ratelimited_client(cl,
+				"sync %p %llx.%llx during filling trace\n",
+				inode, ceph_vinop(inode));
 			return -EBUSY;
 		}
 
@@ -1053,14 +1065,16 @@ out:
 ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
 {
 	struct inode *inode = d_inode(dentry);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	bool len_only = (size == 0);
 	u32 namelen;
 	int err;
 
 	spin_lock(&ci->i_ceph_lock);
-	dout("listxattr %p ver=%lld index_ver=%lld\n", inode,
-	     ci->i_xattrs.version, ci->i_xattrs.index_version);
+	doutc(cl, "%p %llx.%llx ver=%lld index_ver=%lld\n", inode,
+	      ceph_vinop(inode), ci->i_xattrs.version,
+	      ci->i_xattrs.index_version);
 
 	if (ci->i_xattrs.version == 0 ||
 	    !__ceph_caps_issued_mask_metric(ci, CEPH_CAP_XATTR_SHARED, 1)) {
@@ -1094,7 +1108,8 @@ out:
 static int ceph_sync_setxattr(struct inode *inode, const char *name,
 			      const char *value, size_t size, int flags)
 {
-	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(inode->i_sb);
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_request *req;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -1119,7 +1134,7 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name,
 			flags |= CEPH_XATTR_REMOVE;
 	}
 
-	dout("setxattr value size: %zu\n", size);
+	doutc(cl, "name %s value size %zu\n", name, size);
 
 	/* do request */
 	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
@@ -1148,10 +1163,10 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name,
 	req->r_num_caps = 1;
 	req->r_inode_drop = CEPH_CAP_XATTR_SHARED;
 
-	dout("xattr.ver (before): %lld\n", ci->i_xattrs.version);
+	doutc(cl, "xattr.ver (before): %lld\n", ci->i_xattrs.version);
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	ceph_mdsc_put_request(req);
-	dout("xattr.ver (after): %lld\n", ci->i_xattrs.version);
+	doutc(cl, "xattr.ver (after): %lld\n", ci->i_xattrs.version);
 
 out:
 	if (pagelist)
@@ -1162,9 +1177,10 @@ out:
 int __ceph_setxattr(struct inode *inode, const char *name,
 			const void *value, size_t size, int flags)
 {
+	struct ceph_client *cl = ceph_inode_to_client(inode);
 	struct ceph_vxattr *vxattr;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc;
 	struct ceph_cap_flush *prealloc_cf = NULL;
 	struct ceph_buffer *old_blob = NULL;
 	int issued;
@@ -1220,9 +1236,9 @@ retry:
 	required_blob_size = __get_required_blob_size(ci, name_len, val_len);
 	if ((ci->i_xattrs.version == 0) || !(issued & CEPH_CAP_XATTR_EXCL) ||
 	    (required_blob_size > mdsc->mdsmap->m_max_xattr_size)) {
-		dout("%s do sync setxattr: version: %llu size: %d max: %llu\n",
-		     __func__, ci->i_xattrs.version, required_blob_size,
-		     mdsc->mdsmap->m_max_xattr_size);
+		doutc(cl, "sync version: %llu size: %d max: %llu\n",
+		      ci->i_xattrs.version, required_blob_size,
+		      mdsc->mdsmap->m_max_xattr_size);
 		goto do_sync;
 	}
 
@@ -1236,8 +1252,8 @@ retry:
 		}
 	}
 
-	dout("setxattr %p name '%s' issued %s\n", inode, name,
-	     ceph_cap_string(issued));
+	doutc(cl, "%p %llx.%llx name '%s' issued %s\n", inode,
+	      ceph_vinop(inode), name, ceph_cap_string(issued));
 	__build_xattrs(inode);
 
 	if (!ci->i_xattrs.prealloc_blob ||
@@ -1246,7 +1262,8 @@ retry:
 
 		spin_unlock(&ci->i_ceph_lock);
 		ceph_buffer_put(old_blob); /* Shouldn't be required */
-		dout(" pre-allocating new blob size=%d\n", required_blob_size);
+		doutc(cl, " pre-allocating new blob size=%d\n",
+		      required_blob_size);
 		blob = ceph_buffer_new(required_blob_size, GFP_NOFS);
 		if (!blob)
 			goto do_sync_unlocked;
@@ -1285,8 +1302,9 @@ do_sync_unlocked:
 
 	/* security module set xattr while filling trace */
 	if (current->journal_info) {
-		pr_warn_ratelimited("sync setxattr %p "
-				    "during filling trace\n", inode);
+		pr_warn_ratelimited_client(cl,
+				"sync %p %llx.%llx during filling trace\n",
+				inode, ceph_vinop(inode));
 		err = -EBUSY;
 	} else {
 		err = ceph_sync_setxattr(inode, name, value, size, flags);
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index c45e8c2d62e116..6d7c1a49581f7a 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -84,6 +84,14 @@ int debugfs_file_get(struct dentry *dentry)
 	struct debugfs_fsdata *fsd;
 	void *d_fsd;
 
+	/*
+	 * This could only happen if some debugfs user erroneously calls
+	 * debugfs_file_get() on a dentry that isn't even a file, let
+	 * them know about it.
+	 */
+	if (WARN_ON(!d_is_reg(dentry)))
+		return -EINVAL;
+
 	d_fsd = READ_ONCE(dentry->d_fsdata);
 	if (!((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) {
 		fsd = d_fsd;
@@ -96,7 +104,11 @@ int debugfs_file_get(struct dentry *dentry)
 					~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT);
 		refcount_set(&fsd->active_users, 1);
 		init_completion(&fsd->active_users_drained);
+		INIT_LIST_HEAD(&fsd->cancellations);
+		mutex_init(&fsd->cancellations_mtx);
+
 		if (cmpxchg(&dentry->d_fsdata, d_fsd, fsd) != d_fsd) {
+			mutex_destroy(&fsd->cancellations_mtx);
 			kfree(fsd);
 			fsd = READ_ONCE(dentry->d_fsdata);
 		}
@@ -138,6 +150,86 @@ void debugfs_file_put(struct dentry *dentry)
 }
 EXPORT_SYMBOL_GPL(debugfs_file_put);
 
+/**
+ * debugfs_enter_cancellation - enter a debugfs cancellation
+ * @file: the file being accessed
+ * @cancellation: the cancellation object, the cancel callback
+ *	inside of it must be initialized
+ *
+ * When a debugfs file is removed it needs to wait for all active
+ * operations to complete. However, the operation itself may need
+ * to wait for hardware or completion of some asynchronous process
+ * or similar. As such, it may need to be cancelled to avoid long
+ * waits or even deadlocks.
+ *
+ * This function can be used inside a debugfs handler that may
+ * need to be cancelled. As soon as this function is called, the
+ * cancellation's 'cancel' callback may be called, at which point
+ * the caller should proceed to call debugfs_leave_cancellation()
+ * and leave the debugfs handler function as soon as possible.
+ * Note that the 'cancel' callback is only ever called in the
+ * context of some kind of debugfs_remove().
+ *
+ * This function must be paired with debugfs_leave_cancellation().
+ */
+void debugfs_enter_cancellation(struct file *file,
+				struct debugfs_cancellation *cancellation)
+{
+	struct debugfs_fsdata *fsd;
+	struct dentry *dentry = F_DENTRY(file);
+
+	INIT_LIST_HEAD(&cancellation->list);
+
+	if (WARN_ON(!d_is_reg(dentry)))
+		return;
+
+	if (WARN_ON(!cancellation->cancel))
+		return;
+
+	fsd = READ_ONCE(dentry->d_fsdata);
+	if (WARN_ON(!fsd ||
+		    ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)))
+		return;
+
+	mutex_lock(&fsd->cancellations_mtx);
+	list_add(&cancellation->list, &fsd->cancellations);
+	mutex_unlock(&fsd->cancellations_mtx);
+
+	/* if we're already removing wake it up to cancel */
+	if (d_unlinked(dentry))
+		complete(&fsd->active_users_drained);
+}
+EXPORT_SYMBOL_GPL(debugfs_enter_cancellation);
+
+/**
+ * debugfs_leave_cancellation - leave cancellation section
+ * @file: the file being accessed
+ * @cancellation: the cancellation previously registered with
+ *	debugfs_enter_cancellation()
+ *
+ * See the documentation of debugfs_enter_cancellation().
+ */
+void debugfs_leave_cancellation(struct file *file,
+				struct debugfs_cancellation *cancellation)
+{
+	struct debugfs_fsdata *fsd;
+	struct dentry *dentry = F_DENTRY(file);
+
+	if (WARN_ON(!d_is_reg(dentry)))
+		return;
+
+	fsd = READ_ONCE(dentry->d_fsdata);
+	if (WARN_ON(!fsd ||
+		    ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)))
+		return;
+
+	mutex_lock(&fsd->cancellations_mtx);
+	if (!list_empty(&cancellation->list))
+		list_del(&cancellation->list);
+	mutex_unlock(&fsd->cancellations_mtx);
+}
+EXPORT_SYMBOL_GPL(debugfs_leave_cancellation);
+
 /*
  * Only permit access to world-readable files when the kernel is locked down.
  * We also need to exclude any file that has ways to write or alter it as root
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 5d41765e0c7769..034a617cb1a5e7 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -236,17 +236,25 @@ static const struct super_operations debugfs_super_operations = {
 
 static void debugfs_release_dentry(struct dentry *dentry)
 {
-	void *fsd = dentry->d_fsdata;
+	struct debugfs_fsdata *fsd = dentry->d_fsdata;
 
-	if (!((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))
-		kfree(dentry->d_fsdata);
+	if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)
+		return;
+
+	/* check it wasn't a dir (no fsdata) or automount (no real_fops) */
+	if (fsd && fsd->real_fops) {
+		WARN_ON(!list_empty(&fsd->cancellations));
+		mutex_destroy(&fsd->cancellations_mtx);
+	}
+
+	kfree(fsd);
 }
 
 static struct vfsmount *debugfs_automount(struct path *path)
 {
-	debugfs_automount_t f;
-	f = (debugfs_automount_t)path->dentry->d_fsdata;
-	return f(path->dentry, d_inode(path->dentry)->i_private);
+	struct debugfs_fsdata *fsd = path->dentry->d_fsdata;
+
+	return fsd->automount(path->dentry, d_inode(path->dentry)->i_private);
 }
 
 static const struct dentry_operations debugfs_dops = {
@@ -634,13 +642,23 @@ struct dentry *debugfs_create_automount(const char *name,
 					void *data)
 {
 	struct dentry *dentry = start_creating(name, parent);
+	struct debugfs_fsdata *fsd;
 	struct inode *inode;
 
 	if (IS_ERR(dentry))
 		return dentry;
 
+	fsd = kzalloc(sizeof(*fsd), GFP_KERNEL);
+	if (!fsd) {
+		failed_creating(dentry);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	fsd->automount = f;
+
 	if (!(debugfs_allow & DEBUGFS_ALLOW_API)) {
 		failed_creating(dentry);
+		kfree(fsd);
 		return ERR_PTR(-EPERM);
 	}
 
@@ -648,13 +666,14 @@ struct dentry *debugfs_create_automount(const char *name,
 	if (unlikely(!inode)) {
 		pr_err("out of free dentries, can not create automount '%s'\n",
 		       name);
+		kfree(fsd);
 		return failed_creating(dentry);
 	}
 
 	make_empty_dir_inode(inode);
 	inode->i_flags |= S_AUTOMOUNT;
 	inode->i_private = data;
-	dentry->d_fsdata = (void *)f;
+	dentry->d_fsdata = fsd;
 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
 	inc_nlink(inode);
 	d_instantiate(dentry, inode);
@@ -731,8 +750,37 @@ static void __debugfs_file_removed(struct dentry *dentry)
 	fsd = READ_ONCE(dentry->d_fsdata);
 	if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)
 		return;
-	if (!refcount_dec_and_test(&fsd->active_users))
+
+	/* if we hit zero, just wait for all to finish */
+	if (!refcount_dec_and_test(&fsd->active_users)) {
 		wait_for_completion(&fsd->active_users_drained);
+		return;
+	}
+
+	/* if we didn't hit zero, try to cancel any we can */
+	while (refcount_read(&fsd->active_users)) {
+		struct debugfs_cancellation *c;
+
+		/*
+		 * Lock the cancellations. Note that the cancellations
+		 * structs are meant to be on the stack, so we need to
+		 * ensure we either use them here or don't touch them,
+		 * and debugfs_leave_cancellation() will wait for this
+		 * to be finished processing before exiting one. It may
+		 * of course win and remove the cancellation, but then
+		 * chances are we never even got into this bit, we only
+		 * do if the refcount isn't zero already.
+		 */
+		mutex_lock(&fsd->cancellations_mtx);
+		while ((c = list_first_entry_or_null(&fsd->cancellations,
+						     typeof(*c), list))) {
+			list_del_init(&c->list);
+			c->cancel(dentry, c->cancel_data);
+		}
+		mutex_unlock(&fsd->cancellations_mtx);
+
+		wait_for_completion(&fsd->active_users_drained);
+	}
 }
 
 static void remove_one(struct dentry *victim)
diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h
index 92af8ae3131346..dae80c2a469ed0 100644
--- a/fs/debugfs/internal.h
+++ b/fs/debugfs/internal.h
@@ -7,6 +7,7 @@
 
 #ifndef _DEBUGFS_INTERNAL_H_
 #define _DEBUGFS_INTERNAL_H_
+#include <linux/list.h>
 
 struct file_operations;
 
@@ -17,8 +18,18 @@ extern const struct file_operations debugfs_full_proxy_file_operations;
 
 struct debugfs_fsdata {
 	const struct file_operations *real_fops;
-	refcount_t active_users;
-	struct completion active_users_drained;
+	union {
+		/* automount_fn is used when real_fops is NULL */
+		debugfs_automount_t automount;
+		struct {
+			refcount_t active_users;
+			struct completion active_users_drained;
+
+			/* protect cancellations */
+			struct mutex cancellations_mtx;
+			struct list_head cancellations;
+		};
+	};
 };
 
 /*
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index a25dd3d20008bf..b0e8774c435a4b 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -998,6 +998,14 @@ static int ecryptfs_getattr_link(struct mnt_idmap *idmap,
 	return rc;
 }
 
+static int ecryptfs_do_getattr(const struct path *path, struct kstat *stat,
+			       u32 request_mask, unsigned int flags)
+{
+	if (flags & AT_GETATTR_NOSEC)
+		return vfs_getattr_nosec(path, stat, request_mask, flags);
+	return vfs_getattr(path, stat, request_mask, flags);
+}
+
 static int ecryptfs_getattr(struct mnt_idmap *idmap,
 			    const struct path *path, struct kstat *stat,
 			    u32 request_mask, unsigned int flags)
@@ -1006,8 +1014,8 @@ static int ecryptfs_getattr(struct mnt_idmap *idmap,
 	struct kstat lower_stat;
 	int rc;
 
-	rc = vfs_getattr(ecryptfs_dentry_to_lower_path(dentry), &lower_stat,
-			 request_mask, flags);
+	rc = ecryptfs_do_getattr(ecryptfs_dentry_to_lower_path(dentry),
+				 &lower_stat, request_mask, flags);
 	if (!rc) {
 		fsstack_copy_attr_all(d_inode(dentry),
 				      ecryptfs_inode_to_lower(d_inode(dentry)));
diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig
index e540648dedc280..1d318f85232de9 100644
--- a/fs/erofs/Kconfig
+++ b/fs/erofs/Kconfig
@@ -21,7 +21,7 @@ config EROFS_FS
 	  performance under extremely memory pressure without extra cost.
 
 	  See the documentation at <file:Documentation/filesystems/erofs.rst>
-	  for more details.
+	  and the web pages at <https://erofs.docs.kernel.org> for more details.
 
 	  If unsure, say N.
 
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 029c761670bfcd..c98aeda8abb215 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -220,7 +220,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 			up_read(&devs->rwsem);
 			return 0;
 		}
-		map->m_bdev = dif->bdev_handle->bdev;
+		map->m_bdev = dif->bdev_handle ? dif->bdev_handle->bdev : NULL;
 		map->m_daxdev = dif->dax_dev;
 		map->m_dax_part_off = dif->dax_part_off;
 		map->m_fscache = dif->fscache;
@@ -238,7 +238,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 			if (map->m_pa >= startoff &&
 			    map->m_pa < startoff + length) {
 				map->m_pa -= startoff;
-				map->m_bdev = dif->bdev_handle->bdev;
+				map->m_bdev = dif->bdev_handle ?
+					      dif->bdev_handle->bdev : NULL;
 				map->m_daxdev = dif->dax_dev;
 				map->m_dax_part_off = dif->dax_part_off;
 				map->m_fscache = dif->fscache;
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index b8ad05b4509d58..14a79d3226abf4 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -15,11 +15,11 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
 	struct erofs_inode *vi = EROFS_I(inode);
 	const erofs_off_t inode_loc = erofs_iloc(inode);
-
 	erofs_blk_t blkaddr, nblks = 0;
 	void *kaddr;
 	struct erofs_inode_compact *dic;
 	struct erofs_inode_extended *die, *copied = NULL;
+	union erofs_inode_i_u iu;
 	unsigned int ifmt;
 	int err;
 
@@ -35,9 +35,8 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 
 	dic = kaddr + *ofs;
 	ifmt = le16_to_cpu(dic->i_format);
-
 	if (ifmt & ~EROFS_I_ALL) {
-		erofs_err(inode->i_sb, "unsupported i_format %u of nid %llu",
+		erofs_err(sb, "unsupported i_format %u of nid %llu",
 			  ifmt, vi->nid);
 		err = -EOPNOTSUPP;
 		goto err_out;
@@ -45,7 +44,7 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 
 	vi->datalayout = erofs_inode_datalayout(ifmt);
 	if (vi->datalayout >= EROFS_INODE_DATALAYOUT_MAX) {
-		erofs_err(inode->i_sb, "unsupported datalayout %u of nid %llu",
+		erofs_err(sb, "unsupported datalayout %u of nid %llu",
 			  vi->datalayout, vi->nid);
 		err = -EOPNOTSUPP;
 		goto err_out;
@@ -82,40 +81,15 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 		vi->xattr_isize = erofs_xattr_ibody_size(die->i_xattr_icount);
 
 		inode->i_mode = le16_to_cpu(die->i_mode);
-		switch (inode->i_mode & S_IFMT) {
-		case S_IFREG:
-		case S_IFDIR:
-		case S_IFLNK:
-			vi->raw_blkaddr = le32_to_cpu(die->i_u.raw_blkaddr);
-			break;
-		case S_IFCHR:
-		case S_IFBLK:
-			inode->i_rdev =
-				new_decode_dev(le32_to_cpu(die->i_u.rdev));
-			break;
-		case S_IFIFO:
-		case S_IFSOCK:
-			inode->i_rdev = 0;
-			break;
-		default:
-			goto bogusimode;
-		}
+		iu = die->i_u;
 		i_uid_write(inode, le32_to_cpu(die->i_uid));
 		i_gid_write(inode, le32_to_cpu(die->i_gid));
 		set_nlink(inode, le32_to_cpu(die->i_nlink));
-
-		/* extended inode has its own timestamp */
+		/* each extended inode has its own timestamp */
 		inode_set_ctime(inode, le64_to_cpu(die->i_mtime),
 				le32_to_cpu(die->i_mtime_nsec));
 
 		inode->i_size = le64_to_cpu(die->i_size);
-
-		/* total blocks for compressed files */
-		if (erofs_inode_is_data_compressed(vi->datalayout))
-			nblks = le32_to_cpu(die->i_u.compressed_blocks);
-		else if (vi->datalayout == EROFS_INODE_CHUNK_BASED)
-			/* fill chunked inode summary info */
-			vi->chunkformat = le16_to_cpu(die->i_u.c.format);
 		kfree(copied);
 		copied = NULL;
 		break;
@@ -125,49 +99,51 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 		vi->xattr_isize = erofs_xattr_ibody_size(dic->i_xattr_icount);
 
 		inode->i_mode = le16_to_cpu(dic->i_mode);
-		switch (inode->i_mode & S_IFMT) {
-		case S_IFREG:
-		case S_IFDIR:
-		case S_IFLNK:
-			vi->raw_blkaddr = le32_to_cpu(dic->i_u.raw_blkaddr);
-			break;
-		case S_IFCHR:
-		case S_IFBLK:
-			inode->i_rdev =
-				new_decode_dev(le32_to_cpu(dic->i_u.rdev));
-			break;
-		case S_IFIFO:
-		case S_IFSOCK:
-			inode->i_rdev = 0;
-			break;
-		default:
-			goto bogusimode;
-		}
+		iu = dic->i_u;
 		i_uid_write(inode, le16_to_cpu(dic->i_uid));
 		i_gid_write(inode, le16_to_cpu(dic->i_gid));
 		set_nlink(inode, le16_to_cpu(dic->i_nlink));
-
 		/* use build time for compact inodes */
 		inode_set_ctime(inode, sbi->build_time, sbi->build_time_nsec);
 
 		inode->i_size = le32_to_cpu(dic->i_size);
-		if (erofs_inode_is_data_compressed(vi->datalayout))
-			nblks = le32_to_cpu(dic->i_u.compressed_blocks);
-		else if (vi->datalayout == EROFS_INODE_CHUNK_BASED)
-			vi->chunkformat = le16_to_cpu(dic->i_u.c.format);
 		break;
 	default:
-		erofs_err(inode->i_sb,
-			  "unsupported on-disk inode version %u of nid %llu",
+		erofs_err(sb, "unsupported on-disk inode version %u of nid %llu",
 			  erofs_inode_version(ifmt), vi->nid);
 		err = -EOPNOTSUPP;
 		goto err_out;
 	}
 
-	if (vi->datalayout == EROFS_INODE_CHUNK_BASED) {
+	switch (inode->i_mode & S_IFMT) {
+	case S_IFREG:
+	case S_IFDIR:
+	case S_IFLNK:
+		vi->raw_blkaddr = le32_to_cpu(iu.raw_blkaddr);
+		break;
+	case S_IFCHR:
+	case S_IFBLK:
+		inode->i_rdev = new_decode_dev(le32_to_cpu(iu.rdev));
+		break;
+	case S_IFIFO:
+	case S_IFSOCK:
+		inode->i_rdev = 0;
+		break;
+	default:
+		erofs_err(sb, "bogus i_mode (%o) @ nid %llu", inode->i_mode,
+			  vi->nid);
+		err = -EFSCORRUPTED;
+		goto err_out;
+	}
+
+	/* total blocks for compressed files */
+	if (erofs_inode_is_data_compressed(vi->datalayout)) {
+		nblks = le32_to_cpu(iu.compressed_blocks);
+	} else if (vi->datalayout == EROFS_INODE_CHUNK_BASED) {
+		/* fill chunked inode summary info */
+		vi->chunkformat = le16_to_cpu(iu.c.format);
 		if (vi->chunkformat & ~EROFS_CHUNK_FORMAT_ALL) {
-			erofs_err(inode->i_sb,
-				  "unsupported chunk format %x of nid %llu",
+			erofs_err(sb, "unsupported chunk format %x of nid %llu",
 				  vi->chunkformat, vi->nid);
 			err = -EOPNOTSUPP;
 			goto err_out;
@@ -191,10 +167,6 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 		inode->i_blocks = nblks << (sb->s_blocksize_bits - 9);
 	return kaddr;
 
-bogusimode:
-	erofs_err(inode->i_sb, "bogus i_mode (%o) @ nid %llu",
-		  inode->i_mode, vi->nid);
-	err = -EFSCORRUPTED;
 err_out:
 	DBG_BUGON(1);
 	kfree(copied);
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 1039e5bf90afd3..4ddc36f4dbd407 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -258,7 +258,6 @@ static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			goto out_unlock;
 		}
 
-		iocb->ki_pos += status;
 		ret += status;
 		endbyte = pos + status - 1;
 		ret2 = filemap_write_and_wait_range(inode->i_mapping, pos,
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 0166bb9ca160bd..6aa15dafc67786 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -349,9 +349,10 @@ static void ext4_inode_extension_cleanup(struct inode *inode, ssize_t count)
 		return;
 	}
 	/*
-	 * If i_disksize got extended due to writeback of delalloc blocks while
-	 * the DIO was running we could fail to cleanup the orphan list in
-	 * ext4_handle_inode_extension(). Do it now.
+	 * If i_disksize got extended either due to writeback of delalloc
+	 * blocks or extending truncate while the DIO was running we could fail
+	 * to cleanup the orphan list in ext4_handle_inode_extension(). Do it
+	 * now.
 	 */
 	if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) {
 		handle_t *handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
@@ -386,10 +387,11 @@ static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size,
 	 * blocks. But the code in ext4_iomap_alloc() is careful to use
 	 * zeroed/unwritten extents if this is possible; thus we won't leave
 	 * uninitialized blocks in a file even if we didn't succeed in writing
-	 * as much as we intended.
+	 * as much as we intended. Also we can race with truncate or write
+	 * expanding the file so we have to be a bit careful here.
 	 */
-	WARN_ON_ONCE(i_size_read(inode) < READ_ONCE(EXT4_I(inode)->i_disksize));
-	if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize))
+	if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize) &&
+	    pos + size <= i_size_read(inode))
 		return size;
 	return ext4_handle_inode_extension(inode, pos, size);
 }
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 454d5612641ee3..d72b5e3c92ec40 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4478,6 +4478,10 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	start = max(start, rounddown(ac->ac_o_ex.fe_logical,
 			(ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb)));
 
+	/* avoid unnecessary preallocation that may trigger assertions */
+	if (start + size > EXT_MAX_BLOCKS)
+		size = EXT_MAX_BLOCKS - start;
+
 	/* don't cover already allocated blocks in selected range */
 	if (ar->pleft && start <= ar->lleft) {
 		size -= ar->lleft + 1 - start;
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index 23904a6a9a96f7..12ef91d170bb30 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -1222,6 +1222,7 @@ void fuse_dax_conn_free(struct fuse_conn *fc)
 	if (fc->dax) {
 		fuse_free_dax_mem_ranges(&fc->dax->free_ranges);
 		kfree(fc->dax);
+		fc->dax = NULL;
 	}
 }
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 1cdb6327511ef8..a660f1f21540ab 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1448,7 +1448,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 	if (!ia)
 		return -ENOMEM;
 
-	if (fopen_direct_io && fc->direct_io_relax) {
+	if (fopen_direct_io && fc->direct_io_allow_mmap) {
 		res = filemap_write_and_wait_range(mapping, pos, pos + count - 1);
 		if (res) {
 			fuse_io_free(ia);
@@ -1574,6 +1574,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ssize_t res;
 	bool exclusive_lock =
 		!(ff->open_flags & FOPEN_PARALLEL_DIRECT_WRITES) ||
+		get_fuse_conn(inode)->direct_io_allow_mmap ||
 		iocb->ki_flags & IOCB_APPEND ||
 		fuse_direct_write_extending_i_size(iocb, from);
 
@@ -1581,6 +1582,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	 * Take exclusive lock if
 	 * - Parallel direct writes are disabled - a user space decision
 	 * - Parallel direct writes are enabled and i_size is being extended.
+	 * - Shared mmap on direct_io file is supported (FUSE_DIRECT_IO_ALLOW_MMAP).
 	 *   This might not be needed at all, but needs further investigation.
 	 */
 	if (exclusive_lock)
@@ -2466,9 +2468,9 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	if (ff->open_flags & FOPEN_DIRECT_IO) {
 		/* Can't provide the coherency needed for MAP_SHARED
-		 * if FUSE_DIRECT_IO_RELAX isn't set.
+		 * if FUSE_DIRECT_IO_ALLOW_MMAP isn't set.
 		 */
-		if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_relax)
+		if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_allow_mmap)
 			return -ENODEV;
 
 		invalidate_inode_pages2(file->f_mapping);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 6e6e721f421b9d..1df83eebda9277 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -63,6 +63,19 @@ struct fuse_forget_link {
 	struct fuse_forget_link *next;
 };
 
+/* Submount lookup tracking */
+struct fuse_submount_lookup {
+	/** Refcount */
+	refcount_t count;
+
+	/** Unique ID, which identifies the inode between userspace
+	 * and kernel */
+	u64 nodeid;
+
+	/** The request used for sending the FORGET message */
+	struct fuse_forget_link *forget;
+};
+
 /** FUSE inode */
 struct fuse_inode {
 	/** Inode data */
@@ -158,6 +171,8 @@ struct fuse_inode {
 	 */
 	struct fuse_inode_dax *dax;
 #endif
+	/** Submount specific lookup tracking */
+	struct fuse_submount_lookup *submount_lookup;
 };
 
 /** FUSE inode state bits */
@@ -797,8 +812,8 @@ struct fuse_conn {
 	/* Is tmpfile not implemented by fs? */
 	unsigned int no_tmpfile:1;
 
-	/* relax restrictions in FOPEN_DIRECT_IO mode */
-	unsigned int direct_io_relax:1;
+	/* Relax restrictions to allow shared mmap in FOPEN_DIRECT_IO mode */
+	unsigned int direct_io_allow_mmap:1;
 
 	/* Is statx not implemented by fs? */
 	unsigned int no_statx:1;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 74d4f09d5827e8..2a6d44f91729bb 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -68,6 +68,24 @@ struct fuse_forget_link *fuse_alloc_forget(void)
 	return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL_ACCOUNT);
 }
 
+static struct fuse_submount_lookup *fuse_alloc_submount_lookup(void)
+{
+	struct fuse_submount_lookup *sl;
+
+	sl = kzalloc(sizeof(struct fuse_submount_lookup), GFP_KERNEL_ACCOUNT);
+	if (!sl)
+		return NULL;
+	sl->forget = fuse_alloc_forget();
+	if (!sl->forget)
+		goto out_free;
+
+	return sl;
+
+out_free:
+	kfree(sl);
+	return NULL;
+}
+
 static struct inode *fuse_alloc_inode(struct super_block *sb)
 {
 	struct fuse_inode *fi;
@@ -83,6 +101,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 	fi->attr_version = 0;
 	fi->orig_ino = 0;
 	fi->state = 0;
+	fi->submount_lookup = NULL;
 	mutex_init(&fi->mutex);
 	spin_lock_init(&fi->lock);
 	fi->forget = fuse_alloc_forget();
@@ -113,6 +132,17 @@ static void fuse_free_inode(struct inode *inode)
 	kmem_cache_free(fuse_inode_cachep, fi);
 }
 
+static void fuse_cleanup_submount_lookup(struct fuse_conn *fc,
+					 struct fuse_submount_lookup *sl)
+{
+	if (!refcount_dec_and_test(&sl->count))
+		return;
+
+	fuse_queue_forget(fc, sl->forget, sl->nodeid, 1);
+	sl->forget = NULL;
+	kfree(sl);
+}
+
 static void fuse_evict_inode(struct inode *inode)
 {
 	struct fuse_inode *fi = get_fuse_inode(inode);
@@ -132,6 +162,11 @@ static void fuse_evict_inode(struct inode *inode)
 					  fi->nlookup);
 			fi->forget = NULL;
 		}
+
+		if (fi->submount_lookup) {
+			fuse_cleanup_submount_lookup(fc, fi->submount_lookup);
+			fi->submount_lookup = NULL;
+		}
 	}
 	if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) {
 		WARN_ON(!list_empty(&fi->write_files));
@@ -330,6 +365,13 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
 		fuse_dax_dontcache(inode, attr->flags);
 }
 
+static void fuse_init_submount_lookup(struct fuse_submount_lookup *sl,
+				      u64 nodeid)
+{
+	sl->nodeid = nodeid;
+	refcount_set(&sl->count, 1);
+}
+
 static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr,
 			    struct fuse_conn *fc)
 {
@@ -392,12 +434,22 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 	 */
 	if (fc->auto_submounts && (attr->flags & FUSE_ATTR_SUBMOUNT) &&
 	    S_ISDIR(attr->mode)) {
+		struct fuse_inode *fi;
+
 		inode = new_inode(sb);
 		if (!inode)
 			return NULL;
 
 		fuse_init_inode(inode, attr, fc);
-		get_fuse_inode(inode)->nodeid = nodeid;
+		fi = get_fuse_inode(inode);
+		fi->nodeid = nodeid;
+		fi->submount_lookup = fuse_alloc_submount_lookup();
+		if (!fi->submount_lookup) {
+			iput(inode);
+			return NULL;
+		}
+		/* Sets nlookup = 1 on fi->submount_lookup->nlookup */
+		fuse_init_submount_lookup(fi->submount_lookup, nodeid);
 		inode->i_flags |= S_AUTOMOUNT;
 		goto done;
 	}
@@ -420,11 +472,11 @@ retry:
 		iput(inode);
 		goto retry;
 	}
-done:
 	fi = get_fuse_inode(inode);
 	spin_lock(&fi->lock);
 	fi->nlookup++;
 	spin_unlock(&fi->lock);
+done:
 	fuse_change_attributes(inode, attr, NULL, attr_valid, attr_version);
 
 	return inode;
@@ -1230,8 +1282,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 				fc->init_security = 1;
 			if (flags & FUSE_CREATE_SUPP_GROUP)
 				fc->create_supp_group = 1;
-			if (flags & FUSE_DIRECT_IO_RELAX)
-				fc->direct_io_relax = 1;
+			if (flags & FUSE_DIRECT_IO_ALLOW_MMAP)
+				fc->direct_io_allow_mmap = 1;
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
@@ -1278,7 +1330,7 @@ void fuse_send_init(struct fuse_mount *fm)
 		FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA |
 		FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT |
 		FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP |
-		FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_RELAX;
+		FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP;
 #ifdef CONFIG_FUSE_DAX
 	if (fm->fc->dax)
 		flags |= FUSE_MAP_ALIGNMENT;
@@ -1465,6 +1517,8 @@ static int fuse_fill_super_submount(struct super_block *sb,
 	struct super_block *parent_sb = parent_fi->inode.i_sb;
 	struct fuse_attr root_attr;
 	struct inode *root;
+	struct fuse_submount_lookup *sl;
+	struct fuse_inode *fi;
 
 	fuse_sb_defaults(sb);
 	fm->sb = sb;
@@ -1487,12 +1541,27 @@ static int fuse_fill_super_submount(struct super_block *sb,
 	 * its nlookup should not be incremented.  fuse_iget() does
 	 * that, though, so undo it here.
 	 */
-	get_fuse_inode(root)->nlookup--;
+	fi = get_fuse_inode(root);
+	fi->nlookup--;
+
 	sb->s_d_op = &fuse_dentry_operations;
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root)
 		return -ENOMEM;
 
+	/*
+	 * Grab the parent's submount_lookup pointer and take a
+	 * reference on the shared nlookup from the parent.  This is to
+	 * prevent the last forget for this nodeid from getting
+	 * triggered until all users have finished with it.
+	 */
+	sl = parent_fi->submount_lookup;
+	WARN_ON(!sl);
+	if (sl) {
+		refcount_inc(&sl->count);
+		fi->submount_lookup = sl;
+	}
+
 	return 0;
 }
 
diff --git a/fs/inode.c b/fs/inode.c
index edcd8a61975f34..f238d987dec901 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -215,6 +215,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	lockdep_set_class_and_name(&mapping->invalidate_lock,
 				   &sb->s_type->invalidate_lock_key,
 				   "mapping.invalidate_lock");
+	if (sb->s_iflags & SB_I_STABLE_WRITES)
+		mapping_set_stable_writes(mapping);
 	inode->i_private = NULL;
 	inode->i_mapping = mapping;
 	INIT_HLIST_HEAD(&inode->i_dentry);	/* buggered by rcu freeing */
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 8d6f934c3d9543..5e122586e06ed0 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -119,7 +119,7 @@ static int journal_submit_commit_record(journal_t *journal,
 	struct commit_header *tmp;
 	struct buffer_head *bh;
 	struct timespec64 now;
-	blk_opf_t write_flags = REQ_OP_WRITE | REQ_SYNC;
+	blk_opf_t write_flags = REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS;
 
 	*cbh = NULL;
 
@@ -270,6 +270,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 			if (!ret)
 				ret = err;
 		}
+		cond_resched();
 		spin_lock(&journal->j_list_lock);
 		jinode->i_flags &= ~JI_COMMIT_RUNNING;
 		smp_mb();
@@ -395,8 +396,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		 */
 		jbd2_journal_update_sb_log_tail(journal,
 						journal->j_tail_sequence,
-						journal->j_tail,
-						REQ_SYNC);
+						journal->j_tail, 0);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	} else {
 		jbd2_debug(3, "superblock not updated\n");
@@ -715,6 +715,7 @@ start_journal_io:
 
 			for (i = 0; i < bufs; i++) {
 				struct buffer_head *bh = wbuf[i];
+
 				/*
 				 * Compute checksum.
 				 */
@@ -727,7 +728,8 @@ start_journal_io:
 				clear_buffer_dirty(bh);
 				set_buffer_uptodate(bh);
 				bh->b_end_io = journal_end_buffer_io_sync;
-				submit_bh(REQ_OP_WRITE | REQ_SYNC, bh);
+				submit_bh(REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS,
+					  bh);
 			}
 			cond_resched();
 
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index ed53188472f9aa..206cb53ef2b068 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1100,8 +1100,7 @@ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
 	 * space and if we lose sb update during power failure we'd replay
 	 * old transaction with possibly newly overwritten data.
 	 */
-	ret = jbd2_journal_update_sb_log_tail(journal, tid, block,
-					      REQ_SYNC | REQ_FUA);
+	ret = jbd2_journal_update_sb_log_tail(journal, tid, block, REQ_FUA);
 	if (ret)
 		goto out;
 
@@ -1775,8 +1774,7 @@ static int journal_reset(journal_t *journal)
 		 */
 		jbd2_journal_update_sb_log_tail(journal,
 						journal->j_tail_sequence,
-						journal->j_tail,
-						REQ_SYNC | REQ_FUA);
+						journal->j_tail, REQ_FUA);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	}
 	return jbd2_journal_start_thread(journal);
@@ -1798,9 +1796,16 @@ static int jbd2_write_superblock(journal_t *journal, blk_opf_t write_flags)
 		return -EIO;
 	}
 
-	trace_jbd2_write_superblock(journal, write_flags);
+	/*
+	 * Always set high priority flags to exempt from block layer's
+	 * QOS policies, e.g. writeback throttle.
+	 */
+	write_flags |= JBD2_JOURNAL_REQ_FLAGS;
 	if (!(journal->j_flags & JBD2_BARRIER))
 		write_flags &= ~(REQ_FUA | REQ_PREFLUSH);
+
+	trace_jbd2_write_superblock(journal, write_flags);
+
 	if (buffer_write_io_error(bh)) {
 		/*
 		 * Oh, dear.  A previous attempt to write the journal
@@ -2050,7 +2055,7 @@ void jbd2_journal_update_sb_errno(journal_t *journal)
 	jbd2_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode);
 	sb->s_errno    = cpu_to_be32(errcode);
 
-	jbd2_write_superblock(journal, REQ_SYNC | REQ_FUA);
+	jbd2_write_superblock(journal, REQ_FUA);
 }
 EXPORT_SYMBOL(jbd2_journal_update_sb_errno);
 
@@ -2171,8 +2176,7 @@ int jbd2_journal_destroy(journal_t *journal)
 				++journal->j_transaction_sequence;
 			write_unlock(&journal->j_state_lock);
 
-			jbd2_mark_journal_empty(journal,
-					REQ_SYNC | REQ_PREFLUSH | REQ_FUA);
+			jbd2_mark_journal_empty(journal, REQ_PREFLUSH | REQ_FUA);
 			mutex_unlock(&journal->j_checkpoint_mutex);
 		} else
 			err = -EIO;
@@ -2473,7 +2477,7 @@ int jbd2_journal_flush(journal_t *journal, unsigned int flags)
 	 * the magic code for a fully-recovered superblock.  Any future
 	 * commits of data to the journal will restore the current
 	 * s_start value. */
-	jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
+	jbd2_mark_journal_empty(journal, REQ_FUA);
 
 	if (flags)
 		err = __jbd2_journal_erase(journal, flags);
@@ -2519,7 +2523,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 	if (write) {
 		/* Lock to make assertions happy... */
 		mutex_lock_io(&journal->j_checkpoint_mutex);
-		jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
+		jbd2_mark_journal_empty(journal, REQ_FUA);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	}
 
diff --git a/fs/libfs.c b/fs/libfs.c
index e9440d55073c50..c2aa6fd4795c44 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -399,6 +399,8 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
 		return -EINVAL;
 	}
 
+	/* In this case, ->private_data is protected by f_pos_lock */
+	file->private_data = NULL;
 	return vfs_setpos(file, offset, U32_MAX);
 }
 
@@ -428,7 +430,7 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry)
 			  inode->i_ino, fs_umode_to_dtype(inode->i_mode));
 }
 
-static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
+static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
 {
 	struct offset_ctx *so_ctx = inode->i_op->get_offset_ctx(inode);
 	XA_STATE(xas, &so_ctx->xa, ctx->pos);
@@ -437,7 +439,7 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
 	while (true) {
 		dentry = offset_find_next(&xas);
 		if (!dentry)
-			break;
+			return ERR_PTR(-ENOENT);
 
 		if (!offset_dir_emit(ctx, dentry)) {
 			dput(dentry);
@@ -447,6 +449,7 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
 		dput(dentry);
 		ctx->pos = xas.xa_index + 1;
 	}
+	return NULL;
 }
 
 /**
@@ -479,7 +482,12 @@ static int offset_readdir(struct file *file, struct dir_context *ctx)
 	if (!dir_emit_dots(file, ctx))
 		return 0;
 
-	offset_iterate_dir(d_inode(dir), ctx);
+	/* In this case, ->private_data is protected by f_pos_lock */
+	if (ctx->pos == 2)
+		file->private_data = NULL;
+	else if (file->private_data == ERR_PTR(-ENOENT))
+		return 0;
+	file->private_data = offset_iterate_dir(d_inode(dir), ctx);
 	return 0;
 }
 
diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c
index 4905665c47d0dc..57d1dedf3f8fa7 100644
--- a/fs/mnt_idmapping.c
+++ b/fs/mnt_idmapping.c
@@ -256,6 +256,7 @@ struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap)
 
 	return idmap;
 }
+EXPORT_SYMBOL_GPL(mnt_idmap_get);
 
 /**
  * mnt_idmap_put - put a reference to an idmapping
@@ -271,3 +272,4 @@ void mnt_idmap_put(struct mnt_idmap *idmap)
 		kfree(idmap);
 	}
 }
+EXPORT_SYMBOL_GPL(mnt_idmap_put);
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index fdf2aad7347090..e6beaaf4f1700b 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -26,8 +26,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 	int i;
 	int flags = nfsexp_flags(rqstp, exp);
 
-	validate_process_creds();
-
 	/* discard any old override before preparing the new set */
 	revert_creds(get_cred(current_real_cred()));
 	new = prepare_creds();
@@ -81,10 +79,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 	else
 		new->cap_effective = cap_raise_nfsd_set(new->cap_effective,
 							new->cap_permitted);
-	validate_process_creds();
 	put_cred(override_creds(new));
 	put_cred(new);
-	validate_process_creds();
 	return 0;
 
 oom:
diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h
index 929248c6ca84c4..4cbe0434cbb8ce 100644
--- a/fs/nfsd/cache.h
+++ b/fs/nfsd/cache.h
@@ -84,8 +84,8 @@ int	nfsd_net_reply_cache_init(struct nfsd_net *nn);
 void	nfsd_net_reply_cache_destroy(struct nfsd_net *nn);
 int	nfsd_reply_cache_init(struct nfsd_net *);
 void	nfsd_reply_cache_shutdown(struct nfsd_net *);
-int	nfsd_cache_lookup(struct svc_rqst *rqstp,
-			  struct nfsd_cacherep **cacherep);
+int	nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
+			  unsigned int len, struct nfsd_cacherep **cacherep);
 void	nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp,
 			  int cachetype, __be32 *statp);
 int	nfsd_reply_cache_stats_show(struct seq_file *m, void *v);
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 92bc109dabe638..4039ffcf90ba58 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -84,21 +84,7 @@ static void encode_uint32(struct xdr_stream *xdr, u32 n)
 static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap,
 			   size_t len)
 {
-	xdr_stream_encode_uint32_array(xdr, bitmap, len);
-}
-
-static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap,
-				struct nfs4_cb_fattr *fattr)
-{
-	fattr->ncf_cb_change = 0;
-	fattr->ncf_cb_fsize = 0;
-	if (bitmap[0] & FATTR4_WORD0_CHANGE)
-		if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_change) < 0)
-			return -NFSERR_BAD_XDR;
-	if (bitmap[0] & FATTR4_WORD0_SIZE)
-		if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_fsize) < 0)
-			return -NFSERR_BAD_XDR;
-	return 0;
+	WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0);
 }
 
 /*
@@ -372,30 +358,6 @@ encode_cb_recallany4args(struct xdr_stream *xdr,
 }
 
 /*
- * CB_GETATTR4args
- *	struct CB_GETATTR4args {
- *	   nfs_fh4 fh;
- *	   bitmap4 attr_request;
- *	};
- *
- * The size and change attributes are the only one
- * guaranteed to be serviced by the client.
- */
-static void
-encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr,
-			struct nfs4_cb_fattr *fattr)
-{
-	struct nfs4_delegation *dp =
-		container_of(fattr, struct nfs4_delegation, dl_cb_fattr);
-	struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle;
-
-	encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR);
-	encode_nfs_fh4(xdr, fh);
-	encode_bitmap4(xdr, fattr->ncf_cb_bmap, ARRAY_SIZE(fattr->ncf_cb_bmap));
-	hdr->nops++;
-}
-
-/*
  * CB_SEQUENCE4args
  *
  *	struct CB_SEQUENCE4args {
@@ -531,26 +493,6 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
 }
 
 /*
- * 20.1.  Operation 3: CB_GETATTR - Get Attributes
- */
-static void nfs4_xdr_enc_cb_getattr(struct rpc_rqst *req,
-		struct xdr_stream *xdr, const void *data)
-{
-	const struct nfsd4_callback *cb = data;
-	struct nfs4_cb_fattr *ncf =
-		container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
-	struct nfs4_cb_compound_hdr hdr = {
-		.ident = cb->cb_clp->cl_cb_ident,
-		.minorversion = cb->cb_clp->cl_minorversion,
-	};
-
-	encode_cb_compound4args(xdr, &hdr);
-	encode_cb_sequence4args(xdr, cb, &hdr);
-	encode_cb_getattr4args(xdr, &hdr, ncf);
-	encode_cb_nops(&hdr);
-}
-
-/*
  * 20.2. Operation 4: CB_RECALL - Recall a Delegation
  */
 static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr,
@@ -606,42 +548,6 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
 }
 
 /*
- * 20.1.  Operation 3: CB_GETATTR - Get Attributes
- */
-static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp,
-				  struct xdr_stream *xdr,
-				  void *data)
-{
-	struct nfsd4_callback *cb = data;
-	struct nfs4_cb_compound_hdr hdr;
-	int status;
-	u32 bitmap[3] = {0};
-	u32 attrlen;
-	struct nfs4_cb_fattr *ncf =
-		container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
-
-	status = decode_cb_compound4res(xdr, &hdr);
-	if (unlikely(status))
-		return status;
-
-	status = decode_cb_sequence4res(xdr, cb);
-	if (unlikely(status || cb->cb_seq_status))
-		return status;
-
-	status = decode_cb_op_status(xdr, OP_CB_GETATTR, &cb->cb_status);
-	if (status)
-		return status;
-	if (xdr_stream_decode_uint32_array(xdr, bitmap, 3) < 0)
-		return -NFSERR_BAD_XDR;
-	if (xdr_stream_decode_u32(xdr, &attrlen) < 0)
-		return -NFSERR_BAD_XDR;
-	if (attrlen > (sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize)))
-		return -NFSERR_BAD_XDR;
-	status = decode_cb_fattr4(xdr, bitmap, ncf);
-	return status;
-}
-
-/*
  * 20.2. Operation 4: CB_RECALL - Recall a Delegation
  */
 static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
@@ -949,7 +855,6 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = {
 	PROC(CB_NOTIFY_LOCK,	COMPOUND,	cb_notify_lock,	cb_notify_lock),
 	PROC(CB_OFFLOAD,	COMPOUND,	cb_offload,	cb_offload),
 	PROC(CB_RECALL_ANY,	COMPOUND,	cb_recall_any,	cb_recall_any),
-	PROC(CB_GETATTR,	COMPOUND,	cb_getattr,	cb_getattr),
 };
 
 static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)];
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4045c852a450e7..3edbfa0233e68a 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -127,7 +127,6 @@ static void free_session(struct nfsd4_session *);
 
 static const struct nfsd4_callback_ops nfsd4_cb_recall_ops;
 static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops;
-static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops;
 
 static struct workqueue_struct *laundry_wq;
 
@@ -1190,10 +1189,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
 	dp->dl_recalled = false;
 	nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
 		      &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
-	nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client,
-			&nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR);
-	dp->dl_cb_fattr.ncf_file_modified = false;
-	dp->dl_cb_fattr.ncf_cb_bmap[0] = FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE;
 	get_nfs4_file(fp);
 	dp->dl_stid.sc_file = fp;
 	return dp;
@@ -2804,7 +2799,7 @@ static int client_opens_release(struct inode *inode, struct file *file)
 
 	/* XXX: alternatively, we could get/drop in seq start/stop */
 	drop_client(clp);
-	return 0;
+	return seq_release(inode, file);
 }
 
 static const struct file_operations client_states_fops = {
@@ -2901,56 +2896,11 @@ nfsd4_cb_recall_any_release(struct nfsd4_callback *cb)
 	spin_unlock(&nn->client_lock);
 }
 
-static int
-nfsd4_cb_getattr_done(struct nfsd4_callback *cb, struct rpc_task *task)
-{
-	struct nfs4_cb_fattr *ncf =
-			container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
-
-	ncf->ncf_cb_status = task->tk_status;
-	switch (task->tk_status) {
-	case -NFS4ERR_DELAY:
-		rpc_delay(task, 2 * HZ);
-		return 0;
-	default:
-		return 1;
-	}
-}
-
-static void
-nfsd4_cb_getattr_release(struct nfsd4_callback *cb)
-{
-	struct nfs4_cb_fattr *ncf =
-			container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
-	struct nfs4_delegation *dp =
-			container_of(ncf, struct nfs4_delegation, dl_cb_fattr);
-
-	nfs4_put_stid(&dp->dl_stid);
-	clear_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags);
-	wake_up_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY);
-}
-
 static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = {
 	.done		= nfsd4_cb_recall_any_done,
 	.release	= nfsd4_cb_recall_any_release,
 };
 
-static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = {
-	.done		= nfsd4_cb_getattr_done,
-	.release	= nfsd4_cb_getattr_release,
-};
-
-void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf)
-{
-	struct nfs4_delegation *dp =
-			container_of(ncf, struct nfs4_delegation, dl_cb_fattr);
-
-	if (test_and_set_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags))
-		return;
-	refcount_inc(&dp->dl_stid.sc_count);
-	nfsd4_run_cb(&ncf->ncf_getattr);
-}
-
 static struct nfs4_client *create_client(struct xdr_netobj name,
 		struct svc_rqst *rqstp, nfs4_verifier *verf)
 {
@@ -5685,8 +5635,6 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	struct svc_fh *parent = NULL;
 	int cb_up;
 	int status = 0;
-	struct kstat stat;
-	struct path path;
 
 	cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client);
 	open->op_recall = false;
@@ -5724,18 +5672,6 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) {
 		open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE;
 		trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid);
-		path.mnt = currentfh->fh_export->ex_path.mnt;
-		path.dentry = currentfh->fh_dentry;
-		if (vfs_getattr(&path, &stat,
-				(STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE),
-				AT_STATX_SYNC_AS_STAT)) {
-			nfs4_put_stid(&dp->dl_stid);
-			destroy_delegation(dp);
-			goto out_no_deleg;
-		}
-		dp->dl_cb_fattr.ncf_cur_fsize = stat.size;
-		dp->dl_cb_fattr.ncf_initial_cinfo =
-			nfsd4_change_attribute(&stat, d_inode(currentfh->fh_dentry));
 	} else {
 		open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
 		trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid);
@@ -8492,8 +8428,6 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
  * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict
  * @rqstp: RPC transaction context
  * @inode: file to be checked for a conflict
- * @modified: return true if file was modified
- * @size: new size of file if modified is true
  *
  * This function is called when there is a conflict between a write
  * delegation and a change/size GETATTR from another client. The server
@@ -8502,23 +8436,21 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
  * delegation before replying to the GETATTR. See RFC 8881 section
  * 18.7.4.
  *
+ * The current implementation does not support CB_GETATTR yet. However
+ * this can avoid recalling the delegation could be added in follow up
+ * work.
+ *
  * Returns 0 if there is no conflict; otherwise an nfs_stat
  * code is returned.
  */
 __be32
-nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode,
-			     bool *modified, u64 *size)
+nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode)
 {
+	__be32 status;
 	struct file_lock_context *ctx;
-	struct nfs4_delegation *dp;
-	struct nfs4_cb_fattr *ncf;
 	struct file_lock *fl;
-	struct iattr attrs;
-	__be32 status;
-
-	might_sleep();
+	struct nfs4_delegation *dp;
 
-	*modified = false;
 	ctx = locks_inode_context(inode);
 	if (!ctx)
 		return 0;
@@ -8545,34 +8477,10 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode,
 break_lease:
 			spin_unlock(&ctx->flc_lock);
 			nfsd_stats_wdeleg_getattr_inc();
-
-			dp = fl->fl_owner;
-			ncf = &dp->dl_cb_fattr;
-			nfs4_cb_getattr(&dp->dl_cb_fattr);
-			wait_on_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY, TASK_INTERRUPTIBLE);
-			if (ncf->ncf_cb_status) {
-				status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
-				if (status != nfserr_jukebox ||
-						!nfsd_wait_for_delegreturn(rqstp, inode))
-					return status;
-			}
-			if (!ncf->ncf_file_modified &&
-					(ncf->ncf_initial_cinfo != ncf->ncf_cb_change ||
-					ncf->ncf_cur_fsize != ncf->ncf_cb_fsize))
-				ncf->ncf_file_modified = true;
-			if (ncf->ncf_file_modified) {
-				/*
-				 * The server would not update the file's metadata
-				 * with the client's modified size.
-				 */
-				attrs.ia_mtime = attrs.ia_ctime = current_time(inode);
-				attrs.ia_valid = ATTR_MTIME | ATTR_CTIME;
-				setattr_copy(&nop_mnt_idmap, inode, &attrs);
-				mark_inode_dirty(inode);
-				ncf->ncf_cur_fsize = ncf->ncf_cb_fsize;
-				*size = ncf->ncf_cur_fsize;
-				*modified = true;
-			}
+			status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
+			if (status != nfserr_jukebox ||
+					!nfsd_wait_for_delegreturn(rqstp, inode))
+				return status;
 			return 0;
 		}
 		break;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index ec4ed6206df1d1..b499fe9caa3209 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3505,9 +3505,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 		u32		attrmask[3];
 		unsigned long	mask[2];
 	} u;
-	bool file_modified;
 	unsigned long bit;
-	u64 size = 0;
 
 	WARN_ON_ONCE(bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1);
 	WARN_ON_ONCE(!nfsd_attrs_supported(minorversion, bmval));
@@ -3534,8 +3532,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	}
 	args.size = 0;
 	if (u.attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) {
-		status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry),
-						      &file_modified, &size);
+		status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry));
 		if (status)
 			goto out;
 	}
@@ -3545,7 +3542,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 			  AT_STATX_SYNC_AS_STAT);
 	if (err)
 		goto out_nfserr;
-	args.size = file_modified ? size : args.stat.size;
+	args.size = args.stat.size;
 
 	if (!(args.stat.result_mask & STATX_BTIME))
 		/* underlying FS does not offer btime so we can't share it */
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index fd56a52aa5fb67..d3273a3966598b 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -369,33 +369,52 @@ nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
 	return freed;
 }
 
-/*
- * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes
+/**
+ * nfsd_cache_csum - Checksum incoming NFS Call arguments
+ * @buf: buffer containing a whole RPC Call message
+ * @start: starting byte of the NFS Call header
+ * @remaining: size of the NFS Call header, in bytes
+ *
+ * Compute a weak checksum of the leading bytes of an NFS procedure
+ * call header to help verify that a retransmitted Call matches an
+ * entry in the duplicate reply cache.
+ *
+ * To avoid assumptions about how the RPC message is laid out in
+ * @buf and what else it might contain (eg, a GSS MIC suffix), the
+ * caller passes us the exact location and length of the NFS Call
+ * header.
+ *
+ * Returns a 32-bit checksum value, as defined in RFC 793.
  */
-static __wsum
-nfsd_cache_csum(struct svc_rqst *rqstp)
+static __wsum nfsd_cache_csum(struct xdr_buf *buf, unsigned int start,
+			      unsigned int remaining)
 {
+	unsigned int base, len;
+	struct xdr_buf subbuf;
+	__wsum csum = 0;
+	void *p;
 	int idx;
-	unsigned int base;
-	__wsum csum;
-	struct xdr_buf *buf = &rqstp->rq_arg;
-	const unsigned char *p = buf->head[0].iov_base;
-	size_t csum_len = min_t(size_t, buf->head[0].iov_len + buf->page_len,
-				RC_CSUMLEN);
-	size_t len = min(buf->head[0].iov_len, csum_len);
+
+	if (remaining > RC_CSUMLEN)
+		remaining = RC_CSUMLEN;
+	if (xdr_buf_subsegment(buf, &subbuf, start, remaining))
+		return csum;
 
 	/* rq_arg.head first */
-	csum = csum_partial(p, len, 0);
-	csum_len -= len;
+	if (subbuf.head[0].iov_len) {
+		len = min_t(unsigned int, subbuf.head[0].iov_len, remaining);
+		csum = csum_partial(subbuf.head[0].iov_base, len, csum);
+		remaining -= len;
+	}
 
 	/* Continue into page array */
-	idx = buf->page_base / PAGE_SIZE;
-	base = buf->page_base & ~PAGE_MASK;
-	while (csum_len) {
-		p = page_address(buf->pages[idx]) + base;
-		len = min_t(size_t, PAGE_SIZE - base, csum_len);
+	idx = subbuf.page_base / PAGE_SIZE;
+	base = subbuf.page_base & ~PAGE_MASK;
+	while (remaining) {
+		p = page_address(subbuf.pages[idx]) + base;
+		len = min_t(unsigned int, PAGE_SIZE - base, remaining);
 		csum = csum_partial(p, len, csum);
-		csum_len -= len;
+		remaining -= len;
 		base = 0;
 		++idx;
 	}
@@ -466,6 +485,8 @@ out:
 /**
  * nfsd_cache_lookup - Find an entry in the duplicate reply cache
  * @rqstp: Incoming Call to find
+ * @start: starting byte in @rqstp->rq_arg of the NFS Call header
+ * @len: size of the NFS Call header, in bytes
  * @cacherep: OUT: DRC entry for this request
  *
  * Try to find an entry matching the current call in the cache. When none
@@ -479,7 +500,8 @@ out:
  *   %RC_REPLY: Reply from cache
  *   %RC_DROPIT: Do not process the request further
  */
-int nfsd_cache_lookup(struct svc_rqst *rqstp, struct nfsd_cacherep **cacherep)
+int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
+		      unsigned int len, struct nfsd_cacherep **cacherep)
 {
 	struct nfsd_net		*nn;
 	struct nfsd_cacherep	*rp, *found;
@@ -495,7 +517,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, struct nfsd_cacherep **cacherep)
 		goto out;
 	}
 
-	csum = nfsd_cache_csum(rqstp);
+	csum = nfsd_cache_csum(&rqstp->rq_arg, start, len);
 
 	/*
 	 * Since the common case is a cache miss followed by an insert,
@@ -641,24 +663,17 @@ void nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp,
 	return;
 }
 
-/*
- * Copy cached reply to current reply buffer. Should always fit.
- * FIXME as reply is in a page, we should just attach the page, and
- * keep a refcount....
- */
 static int
 nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data)
 {
-	struct kvec	*vec = &rqstp->rq_res.head[0];
-
-	if (vec->iov_len + data->iov_len > PAGE_SIZE) {
-		printk(KERN_WARNING "nfsd: cached reply too large (%zd).\n",
-				data->iov_len);
-		return 0;
-	}
-	memcpy((char*)vec->iov_base + vec->iov_len, data->iov_base, data->iov_len);
-	vec->iov_len += data->iov_len;
-	return 1;
+	__be32 *p;
+
+	p = xdr_reserve_space(&rqstp->rq_res_stream, data->iov_len);
+	if (unlikely(!p))
+		return false;
+	memcpy(p, data->iov_base, data->iov_len);
+	xdr_commit_encode(&rqstp->rq_res_stream);
+	return true;
 }
 
 /*
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 3e15b72f421d4c..7cd513e59305ef 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -705,8 +705,10 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
 
 	err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
 
-	if (err >= 0 &&
-	    !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
+	if (err < 0 && !nn->nfsd_serv->sv_nrthreads && !nn->keep_active)
+		nfsd_last_thread(net);
+	else if (err >= 0 &&
+		 !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
 		svc_get(nn->nfsd_serv);
 
 	nfsd_put(net);
@@ -757,6 +759,9 @@ out_close:
 		svc_xprt_put(xprt);
 	}
 out_err:
+	if (!nn->nfsd_serv->sv_nrthreads && !nn->keep_active)
+		nfsd_last_thread(net);
+
 	nfsd_put(net);
 	return err;
 }
@@ -1510,11 +1515,10 @@ int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb)
 	int ret = -ENODEV;
 
 	mutex_lock(&nfsd_mutex);
-	if (nn->nfsd_serv) {
-		svc_get(nn->nfsd_serv);
+	if (nn->nfsd_serv)
 		ret = 0;
-	}
-	mutex_unlock(&nfsd_mutex);
+	else
+		mutex_unlock(&nfsd_mutex);
 
 	return ret;
 }
@@ -1686,8 +1690,6 @@ out:
  */
 int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb)
 {
-	mutex_lock(&nfsd_mutex);
-	nfsd_put(sock_net(cb->skb->sk));
 	mutex_unlock(&nfsd_mutex);
 
 	return 0;
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index f5ff42f41ee7fe..3286ffacbc566d 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -155,6 +155,7 @@ int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change);
 int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change);
 void nfsd_reset_versions(struct nfsd_net *nn);
 int nfsd_create_serv(struct net *net);
+void nfsd_last_thread(struct net *net);
 
 extern int nfsd_max_blksize;
 
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index d6122bb2d167b4..7a2bc8e82a637a 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -542,7 +542,7 @@ static struct notifier_block nfsd_inet6addr_notifier = {
 /* Only used under nfsd_mutex, so this atomic may be overkill: */
 static atomic_t nfsd_notifier_refcount = ATOMIC_INIT(0);
 
-static void nfsd_last_thread(struct net *net)
+void nfsd_last_thread(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	struct svc_serv *serv = nn->nfsd_serv;
@@ -955,7 +955,6 @@ nfsd(void *vrqstp)
 		rqstp->rq_server->sv_maxconn = nn->max_connections;
 
 		svc_recv(rqstp);
-		validate_process_creds();
 	}
 
 	atomic_dec(&nfsdstats.th_cnt);
@@ -981,6 +980,8 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 	const struct svc_procedure *proc = rqstp->rq_procinfo;
 	__be32 *statp = rqstp->rq_accept_statp;
 	struct nfsd_cacherep *rp;
+	unsigned int start, len;
+	__be32 *nfs_reply;
 
 	/*
 	 * Give the xdr decoder a chance to change this if it wants
@@ -988,6 +989,13 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 	 */
 	rqstp->rq_cachetype = proc->pc_cachetype;
 
+	/*
+	 * ->pc_decode advances the argument stream past the NFS
+	 * Call header, so grab the header's starting location and
+	 * size now for the call to nfsd_cache_lookup().
+	 */
+	start = xdr_stream_pos(&rqstp->rq_arg_stream);
+	len = xdr_stream_remaining(&rqstp->rq_arg_stream);
 	if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream))
 		goto out_decode_err;
 
@@ -1001,7 +1009,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 	smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter | 1);
 
 	rp = NULL;
-	switch (nfsd_cache_lookup(rqstp, &rp)) {
+	switch (nfsd_cache_lookup(rqstp, start, len, &rp)) {
 	case RC_DOIT:
 		break;
 	case RC_REPLY:
@@ -1010,6 +1018,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 		goto out_dropit;
 	}
 
+	nfs_reply = xdr_inline_decode(&rqstp->rq_res_stream, 0);
 	*statp = proc->pc_func(rqstp);
 	if (test_bit(RQ_DROPME, &rqstp->rq_flags))
 		goto out_update_drop;
@@ -1023,7 +1032,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 	 */
 	smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter + 1);
 
-	nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, statp + 1);
+	nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, nfs_reply);
 out_cached_reply:
 	return 1;
 
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index f96eaa8e9413da..41bdc913fa715b 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -117,24 +117,6 @@ struct nfs4_cpntf_state {
 	time64_t		cpntf_time;	/* last time stateid used */
 };
 
-struct nfs4_cb_fattr {
-	struct nfsd4_callback ncf_getattr;
-	u32 ncf_cb_status;
-	u32 ncf_cb_bmap[1];
-
-	/* from CB_GETATTR reply */
-	u64 ncf_cb_change;
-	u64 ncf_cb_fsize;
-
-	unsigned long ncf_cb_flags;
-	bool ncf_file_modified;
-	u64 ncf_initial_cinfo;
-	u64 ncf_cur_fsize;
-};
-
-/* bits for ncf_cb_flags */
-#define	CB_GETATTR_BUSY		0
-
 /*
  * Represents a delegation stateid. The nfs4_client holds references to these
  * and they are put when it is being destroyed or when the delegation is
@@ -168,9 +150,6 @@ struct nfs4_delegation {
 	int			dl_retries;
 	struct nfsd4_callback	dl_recall;
 	bool			dl_recalled;
-
-	/* for CB_GETATTR */
-	struct nfs4_cb_fattr    dl_cb_fattr;
 };
 
 #define cb_to_delegation(cb) \
@@ -661,7 +640,6 @@ enum nfsd4_cb_op {
 	NFSPROC4_CLNT_CB_SEQUENCE,
 	NFSPROC4_CLNT_CB_NOTIFY_LOCK,
 	NFSPROC4_CLNT_CB_RECALL_ANY,
-	NFSPROC4_CLNT_CB_GETATTR,
 };
 
 /* Returns true iff a is later than b: */
@@ -754,6 +732,5 @@ static inline bool try_to_expire_client(struct nfs4_client *clp)
 }
 
 extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp,
-		struct inode *inode, bool *file_modified, u64 *size);
-extern void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf);
+				struct inode *inode);
 #endif   /* NFSD4_STATE_H */
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index fbbea7498f02b4..e01e4e2acbd9a2 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -901,7 +901,6 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 	int host_err;
 	bool retried = false;
 
-	validate_process_creds();
 	/*
 	 * If we get here, then the client has already done an "open",
 	 * and (hopefully) checked permission - so allow OWNER_OVERRIDE
@@ -926,7 +925,6 @@ retry:
 		}
 		err = nfserrno(host_err);
 	}
-	validate_process_creds();
 	return err;
 }
 
@@ -943,12 +941,7 @@ int
 nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags,
 		   struct file **filp)
 {
-	int err;
-
-	validate_process_creds();
-	err = __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp);
-	validate_process_creds();
-	return err;
+	return __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp);
 }
 
 /*
diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h
index e8b00309c449fe..0d39af1b00a0f3 100644
--- a/fs/nfsd/xdr4cb.h
+++ b/fs/nfsd/xdr4cb.h
@@ -54,21 +54,3 @@
 #define NFS4_dec_cb_recall_any_sz	(cb_compound_dec_hdr_sz  +      \
 					cb_sequence_dec_sz +            \
 					op_dec_sz)
-
-/*
- * 1: CB_GETATTR opcode (32-bit)
- * N: file_handle
- * 1: number of entry in attribute array (32-bit)
- * 1: entry 0 in attribute array (32-bit)
- */
-#define NFS4_enc_cb_getattr_sz		(cb_compound_enc_hdr_sz +       \
-					cb_sequence_enc_sz +            \
-					1 + enc_nfs4_fh_sz + 1 + 1)
-/*
- * 4: fattr_bitmap_maxsz
- * 1: attribute array len
- * 2: change attr (64-bit)
- * 2: size (64-bit)
- */
-#define NFS4_dec_cb_getattr_sz		(cb_compound_dec_hdr_sz  +      \
-			cb_sequence_dec_sz + 4 + 1 + 2 + 2 + op_dec_sz)
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 2c6078a6b8ecb5..58ca7c936393c4 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -501,15 +501,38 @@ int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum)
 
 	down_write(&NILFS_MDT(sufile)->mi_sem);
 	ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh);
-	if (!ret) {
-		mark_buffer_dirty(bh);
-		nilfs_mdt_mark_dirty(sufile);
-		kaddr = kmap_atomic(bh->b_page);
-		su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr);
+	if (ret)
+		goto out_sem;
+
+	kaddr = kmap_atomic(bh->b_page);
+	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr);
+	if (unlikely(nilfs_segment_usage_error(su))) {
+		struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
+
+		kunmap_atomic(kaddr);
+		brelse(bh);
+		if (nilfs_segment_is_active(nilfs, segnum)) {
+			nilfs_error(sufile->i_sb,
+				    "active segment %llu is erroneous",
+				    (unsigned long long)segnum);
+		} else {
+			/*
+			 * Segments marked erroneous are never allocated by
+			 * nilfs_sufile_alloc(); only active segments, ie,
+			 * the segments indexed by ns_segnum or ns_nextnum,
+			 * can be erroneous here.
+			 */
+			WARN_ON_ONCE(1);
+		}
+		ret = -EIO;
+	} else {
 		nilfs_segment_usage_set_dirty(su);
 		kunmap_atomic(kaddr);
+		mark_buffer_dirty(bh);
+		nilfs_mdt_mark_dirty(sufile);
 		brelse(bh);
 	}
+out_sem:
 	up_write(&NILFS_MDT(sufile)->mi_sem);
 	return ret;
 }
@@ -536,9 +559,14 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
 
 	kaddr = kmap_atomic(bh->b_page);
 	su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr);
-	WARN_ON(nilfs_segment_usage_error(su));
-	if (modtime)
+	if (modtime) {
+		/*
+		 * Check segusage error and set su_lastmod only when updating
+		 * this entry with a valid timestamp, not for cancellation.
+		 */
+		WARN_ON_ONCE(nilfs_segment_usage_error(su));
 		su->su_lastmod = cpu_to_le64(modtime);
+	}
 	su->su_nblocks = cpu_to_le32(nblocks);
 	kunmap_atomic(kaddr);
 
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 0f0667957c8100..71400496ed3651 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -716,7 +716,11 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
 			goto failed_sbh;
 		}
 		nilfs_release_super_block(nilfs);
-		sb_set_blocksize(sb, blocksize);
+		if (!sb_set_blocksize(sb, blocksize)) {
+			nilfs_err(sb, "bad blocksize %d", blocksize);
+			err = -EINVAL;
+			goto out;
+		}
 
 		err = nilfs_load_super_block(nilfs, sb, blocksize, &sbp);
 		if (err)
diff --git a/fs/open.c b/fs/open.c
index 02dc608d40d81f..3494a9cd8046c4 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1088,8 +1088,6 @@ struct file *dentry_open(const struct path *path, int flags,
 	int error;
 	struct file *f;
 
-	validate_creds(cred);
-
 	/* We must always pass in a valid mount pointer. */
 	BUG_ON(!path->mnt);
 
@@ -1128,7 +1126,6 @@ struct file *dentry_create(const struct path *path, int flags, umode_t mode,
 	struct file *f;
 	int error;
 
-	validate_creds(cred);
 	f = alloc_empty_file(flags, cred);
 	if (IS_ERR(f))
 		return f;
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 4382881b070948..8bea66c9731616 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -753,15 +753,16 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c)
 	path.dentry = temp;
 	err = ovl_copy_up_data(c, &path);
 	/*
-	 * We cannot hold lock_rename() throughout this helper, because or
+	 * We cannot hold lock_rename() throughout this helper, because of
 	 * lock ordering with sb_writers, which shouldn't be held when calling
 	 * ovl_copy_up_data(), so lock workdir and destdir and make sure that
 	 * temp wasn't moved before copy up completion or cleanup.
-	 * If temp was moved, abort without the cleanup.
 	 */
 	ovl_start_write(c->dentry);
 	if (lock_rename(c->workdir, c->destdir) != NULL ||
 	    temp->d_parent != c->workdir) {
+		/* temp or workdir moved underneath us? abort without cleanup */
+		dput(temp);
 		err = -EIO;
 		goto unlock;
 	} else if (err) {
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 345b8f161ca4c3..c63b31a460befc 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -171,7 +171,7 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
 
 	type = ovl_path_real(dentry, &realpath);
 	old_cred = ovl_override_creds(dentry->d_sb);
-	err = vfs_getattr(&realpath, stat, request_mask, flags);
+	err = ovl_do_getattr(&realpath, stat, request_mask, flags);
 	if (err)
 		goto out;
 
@@ -196,8 +196,8 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
 					(!is_dir ? STATX_NLINK : 0);
 
 			ovl_path_lower(dentry, &realpath);
-			err = vfs_getattr(&realpath, &lowerstat,
-					  lowermask, flags);
+			err = ovl_do_getattr(&realpath, &lowerstat, lowermask,
+					     flags);
 			if (err)
 				goto out;
 
@@ -249,8 +249,8 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
 
 			ovl_path_lowerdata(dentry, &realpath);
 			if (realpath.dentry) {
-				err = vfs_getattr(&realpath, &lowerdatastat,
-						  lowermask, flags);
+				err = ovl_do_getattr(&realpath, &lowerdatastat,
+						     lowermask, flags);
 				if (err)
 					goto out;
 			} else {
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index ca88b2636a5729..05c3dd597fa8d9 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -408,6 +408,14 @@ static inline bool ovl_open_flags_need_copy_up(int flags)
 	return ((OPEN_FMODE(flags) & FMODE_WRITE) || (flags & O_TRUNC));
 }
 
+static inline int ovl_do_getattr(const struct path *path, struct kstat *stat,
+				 u32 request_mask, unsigned int flags)
+{
+	if (flags & AT_GETATTR_NOSEC)
+		return vfs_getattr_nosec(path, stat, request_mask, flags);
+	return vfs_getattr(path, stat, request_mask, flags);
+}
+
 /* util.c */
 int ovl_get_write_access(struct dentry *dentry);
 void ovl_put_write_access(struct dentry *dentry);
diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c
index ddab9ea267d128..3fe2dde1598f9e 100644
--- a/fs/overlayfs/params.c
+++ b/fs/overlayfs/params.c
@@ -430,7 +430,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 	struct ovl_fs_context *ctx = fc->fs_private;
 	struct ovl_fs_context_layer *l;
 	char *dup = NULL, *iter;
-	ssize_t nr_lower = 0, nr = 0, nr_data = 0;
+	ssize_t nr_lower, nr;
 	bool data_layer = false;
 
 	/*
@@ -482,6 +482,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 	iter = dup;
 	l = ctx->lower;
 	for (nr = 0; nr < nr_lower; nr++, l++) {
+		ctx->nr++;
 		memset(l, 0, sizeof(*l));
 
 		err = ovl_mount_dir(iter, &l->path);
@@ -498,10 +499,10 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 			goto out_put;
 
 		if (data_layer)
-			nr_data++;
+			ctx->nr_data++;
 
 		/* Calling strchr() again would overrun. */
-		if ((nr + 1) == nr_lower)
+		if (ctx->nr == nr_lower)
 			break;
 
 		err = -EINVAL;
@@ -511,7 +512,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 			 * This is a regular layer so we require that
 			 * there are no data layers.
 			 */
-			if ((ctx->nr_data + nr_data) > 0) {
+			if (ctx->nr_data > 0) {
 				pr_err("regular lower layers cannot follow data lower layers");
 				goto out_put;
 			}
@@ -524,8 +525,6 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
 		data_layer = true;
 		iter++;
 	}
-	ctx->nr = nr_lower;
-	ctx->nr_data += nr_data;
 	kfree(dup);
 	return 0;
 
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 50a201e9cd398a..c3f020ca13a8c7 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -978,7 +978,7 @@ int ovl_set_protattr(struct inode *inode, struct dentry *upper,
 	return 0;
 }
 
-/**
+/*
  * Caller must hold a reference to inode to prevent it from being freed while
  * it is marked inuse.
  */
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ef2eb12906da88..435b61054b5b9e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1982,15 +1982,31 @@ static int pagemap_scan_test_walk(unsigned long start, unsigned long end,
 	struct pagemap_scan_private *p = walk->private;
 	struct vm_area_struct *vma = walk->vma;
 	unsigned long vma_category = 0;
+	bool wp_allowed = userfaultfd_wp_async(vma) &&
+	    userfaultfd_wp_use_markers(vma);
 
-	if (userfaultfd_wp_async(vma) && userfaultfd_wp_use_markers(vma))
-		vma_category |= PAGE_IS_WPALLOWED;
-	else if (p->arg.flags & PM_SCAN_CHECK_WPASYNC)
-		return -EPERM;
+	if (!wp_allowed) {
+		/* User requested explicit failure over wp-async capability */
+		if (p->arg.flags & PM_SCAN_CHECK_WPASYNC)
+			return -EPERM;
+		/*
+		 * User requires wr-protect, and allows silently skipping
+		 * unsupported vmas.
+		 */
+		if (p->arg.flags & PM_SCAN_WP_MATCHING)
+			return 1;
+		/*
+		 * Then the request doesn't involve wr-protects at all,
+		 * fall through to the rest checks, and allow vma walk.
+		 */
+	}
 
 	if (vma->vm_flags & VM_PFNMAP)
 		return 1;
 
+	if (wp_allowed)
+		vma_category |= PAGE_IS_WPALLOWED;
+
 	if (!pagemap_scan_is_interesting_vma(vma_category, p))
 		return 1;
 
@@ -2140,7 +2156,7 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start,
 		return 0;
 	}
 
-	if (!p->vec_out) {
+	if ((p->arg.flags & PM_SCAN_WP_MATCHING) && !p->vec_out) {
 		/* Fast path for performing exclusive WP */
 		for (addr = start; addr != end; pte++, addr += PAGE_SIZE) {
 			if (pte_uffd_wp(ptep_get(pte)))
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index 59f6b8e32cc97a..d64a306a414be0 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -291,16 +291,23 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
 	oparms.fid->mid = le64_to_cpu(o_rsp->hdr.MessageId);
 #endif /* CIFS_DEBUG2 */
 
-	rc = -EINVAL;
+
 	if (o_rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) {
 		spin_unlock(&cfids->cfid_list_lock);
+		rc = -EINVAL;
+		goto oshr_free;
+	}
+
+	rc = smb2_parse_contexts(server, rsp_iov,
+				 &oparms.fid->epoch,
+				 oparms.fid->lease_key,
+				 &oplock, NULL, NULL);
+	if (rc) {
+		spin_unlock(&cfids->cfid_list_lock);
 		goto oshr_free;
 	}
 
-	smb2_parse_contexts(server, o_rsp,
-			    &oparms.fid->epoch,
-			    oparms.fid->lease_key, &oplock,
-			    NULL, NULL);
+	rc = -EINVAL;
 	if (!(oplock & SMB2_LEASE_READ_CACHING_HE)) {
 		spin_unlock(&cfids->cfid_list_lock);
 		goto oshr_free;
diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index 6d8804fb6535c1..60027f5aebe87f 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -40,11 +40,13 @@ void cifs_dump_detail(void *buf, struct TCP_Server_Info *server)
 #ifdef CONFIG_CIFS_DEBUG2
 	struct smb_hdr *smb = buf;
 
-	cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d\n",
-		 smb->Command, smb->Status.CifsError,
-		 smb->Flags, smb->Flags2, smb->Mid, smb->Pid);
-	cifs_dbg(VFS, "smb buf %p len %u\n", smb,
-		 server->ops->calc_smb_size(smb));
+	cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d Wct: %d\n",
+		 smb->Command, smb->Status.CifsError, smb->Flags,
+		 smb->Flags2, smb->Mid, smb->Pid, smb->WordCount);
+	if (!server->ops->check_message(buf, server->total_read, server)) {
+		cifs_dbg(VFS, "smb buf %p len %u\n", smb,
+			 server->ops->calc_smb_size(smb));
+	}
 #endif /* CONFIG_CIFS_DEBUG2 */
 }
 
@@ -136,6 +138,11 @@ cifs_dump_channel(struct seq_file *m, int i, struct cifs_chan *chan)
 {
 	struct TCP_Server_Info *server = chan->server;
 
+	if (!server) {
+		seq_printf(m, "\n\n\t\tChannel: %d DISABLED", i+1);
+		return;
+	}
+
 	seq_printf(m, "\n\n\t\tChannel: %d ConnectionId: 0x%llx"
 		   "\n\t\tNumber of credits: %d,%d,%d Dialect 0x%x"
 		   "\n\t\tTCP status: %d Instance: %d"
@@ -279,6 +286,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 	struct cifs_ses *ses;
 	struct cifs_tcon *tcon;
 	struct cifs_server_iface *iface;
+	size_t iface_weight = 0, iface_min_speed = 0;
+	struct cifs_server_iface *last_iface = NULL;
 	int c, i, j;
 
 	seq_puts(m,
@@ -544,11 +553,25 @@ skip_rdma:
 					   "\tLast updated: %lu seconds ago",
 					   ses->iface_count,
 					   (jiffies - ses->iface_last_update) / HZ);
+
+			last_iface = list_last_entry(&ses->iface_list,
+						     struct cifs_server_iface,
+						     iface_head);
+			iface_min_speed = last_iface->speed;
+
 			j = 0;
 			list_for_each_entry(iface, &ses->iface_list,
 						 iface_head) {
 				seq_printf(m, "\n\t%d)", ++j);
 				cifs_dump_iface(m, iface);
+
+				iface_weight = iface->speed / iface_min_speed;
+				seq_printf(m, "\t\tWeight (cur,total): (%zu,%zu)"
+					   "\n\t\tAllocated channels: %u\n",
+					   iface->weight_fulfilled,
+					   iface_weight,
+					   iface->num_channels);
+
 				if (is_ses_using_iface(ses, iface))
 					seq_puts(m, "\t\t[CONNECTED]\n");
 			}
@@ -746,14 +769,14 @@ static ssize_t name##_write(struct file *file, const char __user *buffer, \
 	size_t count, loff_t *ppos) \
 { \
 	int rc; \
-	rc = kstrtoint_from_user(buffer, count, 10, & name); \
+	rc = kstrtoint_from_user(buffer, count, 10, &name); \
 	if (rc) \
 		return rc; \
 	return count; \
 } \
 static int name##_proc_show(struct seq_file *m, void *v) \
 { \
-	seq_printf(m, "%d\n", name ); \
+	seq_printf(m, "%d\n", name); \
 	return 0; \
 } \
 static int name##_open(struct inode *inode, struct file *file) \
diff --git a/fs/smb/client/cifs_ioctl.h b/fs/smb/client/cifs_ioctl.h
index 332588e77c311f..26327442e383b1 100644
--- a/fs/smb/client/cifs_ioctl.h
+++ b/fs/smb/client/cifs_ioctl.h
@@ -26,6 +26,11 @@ struct smb_mnt_fs_info {
 	__u64   cifs_posix_caps;
 } __packed;
 
+struct smb_mnt_tcon_info {
+	__u32	tid;
+	__u64	session_id;
+} __packed;
+
 struct smb_snapshot_array {
 	__u32	number_of_snapshots;
 	__u32	number_of_snapshots_returned;
@@ -108,6 +113,7 @@ struct smb3_notify_info {
 #define CIFS_IOC_NOTIFY _IOW(CIFS_IOCTL_MAGIC, 9, struct smb3_notify)
 #define CIFS_DUMP_FULL_KEY _IOWR(CIFS_IOCTL_MAGIC, 10, struct smb3_full_key_debug_info)
 #define CIFS_IOC_NOTIFY_INFO _IOWR(CIFS_IOCTL_MAGIC, 11, struct smb3_notify_info)
+#define CIFS_IOC_GET_TCON_INFO _IOR(CIFS_IOCTL_MAGIC, 12, struct smb_mnt_tcon_info)
 #define CIFS_IOC_SHUTDOWN _IOR('X', 125, __u32)
 
 /*
diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c
index 6f3285f1dfee58..af7849e5974ff3 100644
--- a/fs/smb/client/cifs_spnego.c
+++ b/fs/smb/client/cifs_spnego.c
@@ -64,8 +64,8 @@ struct key_type cifs_spnego_key_type = {
  * strlen(";sec=ntlmsspi") */
 #define MAX_MECH_STR_LEN	13
 
-/* strlen of "host=" */
-#define HOST_KEY_LEN		5
+/* strlen of ";host=" */
+#define HOST_KEY_LEN		6
 
 /* strlen of ";ip4=" or ";ip6=" */
 #define IP_KEY_LEN		5
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index ea3a7a668b45f3..2131638f26d0b4 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1196,32 +1196,103 @@ const struct inode_operations cifs_symlink_inode_ops = {
 	.listxattr = cifs_listxattr,
 };
 
+/*
+ * Advance the EOF marker to after the source range.
+ */
+static int cifs_precopy_set_eof(struct inode *src_inode, struct cifsInodeInfo *src_cifsi,
+				struct cifs_tcon *src_tcon,
+				unsigned int xid, loff_t src_end)
+{
+	struct cifsFileInfo *writeable_srcfile;
+	int rc = -EINVAL;
+
+	writeable_srcfile = find_writable_file(src_cifsi, FIND_WR_FSUID_ONLY);
+	if (writeable_srcfile) {
+		if (src_tcon->ses->server->ops->set_file_size)
+			rc = src_tcon->ses->server->ops->set_file_size(
+				xid, src_tcon, writeable_srcfile,
+				src_inode->i_size, true /* no need to set sparse */);
+		else
+			rc = -ENOSYS;
+		cifsFileInfo_put(writeable_srcfile);
+		cifs_dbg(FYI, "SetFSize for copychunk rc = %d\n", rc);
+	}
+
+	if (rc < 0)
+		goto set_failed;
+
+	netfs_resize_file(&src_cifsi->netfs, src_end);
+	fscache_resize_cookie(cifs_inode_cookie(src_inode), src_end);
+	return 0;
+
+set_failed:
+	return filemap_write_and_wait(src_inode->i_mapping);
+}
+
+/*
+ * Flush out either the folio that overlaps the beginning of a range in which
+ * pos resides or the folio that overlaps the end of a range unless that folio
+ * is entirely within the range we're going to invalidate.  We extend the flush
+ * bounds to encompass the folio.
+ */
+static int cifs_flush_folio(struct inode *inode, loff_t pos, loff_t *_fstart, loff_t *_fend,
+			    bool first)
+{
+	struct folio *folio;
+	unsigned long long fpos, fend;
+	pgoff_t index = pos / PAGE_SIZE;
+	size_t size;
+	int rc = 0;
+
+	folio = filemap_get_folio(inode->i_mapping, index);
+	if (IS_ERR(folio))
+		return 0;
+
+	size = folio_size(folio);
+	fpos = folio_pos(folio);
+	fend = fpos + size - 1;
+	*_fstart = min_t(unsigned long long, *_fstart, fpos);
+	*_fend   = max_t(unsigned long long, *_fend, fend);
+	if ((first && pos == fpos) || (!first && pos == fend))
+		goto out;
+
+	rc = filemap_write_and_wait_range(inode->i_mapping, fpos, fend);
+out:
+	folio_put(folio);
+	return rc;
+}
+
 static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 		struct file *dst_file, loff_t destoff, loff_t len,
 		unsigned int remap_flags)
 {
 	struct inode *src_inode = file_inode(src_file);
 	struct inode *target_inode = file_inode(dst_file);
+	struct cifsInodeInfo *src_cifsi = CIFS_I(src_inode);
+	struct cifsInodeInfo *target_cifsi = CIFS_I(target_inode);
 	struct cifsFileInfo *smb_file_src = src_file->private_data;
-	struct cifsFileInfo *smb_file_target;
-	struct cifs_tcon *target_tcon;
+	struct cifsFileInfo *smb_file_target = dst_file->private_data;
+	struct cifs_tcon *target_tcon, *src_tcon;
+	unsigned long long destend, fstart, fend, new_size;
 	unsigned int xid;
 	int rc;
 
-	if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
+	if (remap_flags & REMAP_FILE_DEDUP)
+		return -EOPNOTSUPP;
+	if (remap_flags & ~REMAP_FILE_ADVISORY)
 		return -EINVAL;
 
 	cifs_dbg(FYI, "clone range\n");
 
 	xid = get_xid();
 
-	if (!src_file->private_data || !dst_file->private_data) {
+	if (!smb_file_src || !smb_file_target) {
 		rc = -EBADF;
 		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
 		goto out;
 	}
 
-	smb_file_target = dst_file->private_data;
+	src_tcon = tlink_tcon(smb_file_src->tlink);
 	target_tcon = tlink_tcon(smb_file_target->tlink);
 
 	/*
@@ -1234,20 +1305,63 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 	if (len == 0)
 		len = src_inode->i_size - off;
 
-	cifs_dbg(FYI, "about to flush pages\n");
-	/* should we flush first and last page first */
-	truncate_inode_pages_range(&target_inode->i_data, destoff,
-				   PAGE_ALIGN(destoff + len)-1);
+	cifs_dbg(FYI, "clone range\n");
 
-	if (target_tcon->ses->server->ops->duplicate_extents)
+	/* Flush the source buffer */
+	rc = filemap_write_and_wait_range(src_inode->i_mapping, off,
+					  off + len - 1);
+	if (rc)
+		goto unlock;
+
+	/* The server-side copy will fail if the source crosses the EOF marker.
+	 * Advance the EOF marker after the flush above to the end of the range
+	 * if it's short of that.
+	 */
+	if (src_cifsi->netfs.remote_i_size < off + len) {
+		rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len);
+		if (rc < 0)
+			goto unlock;
+	}
+
+	new_size = destoff + len;
+	destend = destoff + len - 1;
+
+	/* Flush the folios at either end of the destination range to prevent
+	 * accidental loss of dirty data outside of the range.
+	 */
+	fstart = destoff;
+	fend = destend;
+
+	rc = cifs_flush_folio(target_inode, destoff, &fstart, &fend, true);
+	if (rc)
+		goto unlock;
+	rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false);
+	if (rc)
+		goto unlock;
+
+	/* Discard all the folios that overlap the destination region. */
+	cifs_dbg(FYI, "about to discard pages %llx-%llx\n", fstart, fend);
+	truncate_inode_pages_range(&target_inode->i_data, fstart, fend);
+
+	fscache_invalidate(cifs_inode_cookie(target_inode), NULL,
+			   i_size_read(target_inode), 0);
+
+	rc = -EOPNOTSUPP;
+	if (target_tcon->ses->server->ops->duplicate_extents) {
 		rc = target_tcon->ses->server->ops->duplicate_extents(xid,
 			smb_file_src, smb_file_target, off, len, destoff);
-	else
-		rc = -EOPNOTSUPP;
+		if (rc == 0 && new_size > i_size_read(target_inode)) {
+			truncate_setsize(target_inode, new_size);
+			netfs_resize_file(&target_cifsi->netfs, new_size);
+			fscache_resize_cookie(cifs_inode_cookie(target_inode),
+					      new_size);
+		}
+	}
 
 	/* force revalidate of size and timestamps of target file now
 	   that target is updated on the server */
 	CIFS_I(target_inode)->time = 0;
+unlock:
 	/* although unlocking in the reverse order from locking is not
 	   strictly necessary here it is a little cleaner to be consistent */
 	unlock_two_nondirectories(src_inode, target_inode);
@@ -1263,10 +1377,12 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 {
 	struct inode *src_inode = file_inode(src_file);
 	struct inode *target_inode = file_inode(dst_file);
+	struct cifsInodeInfo *src_cifsi = CIFS_I(src_inode);
 	struct cifsFileInfo *smb_file_src;
 	struct cifsFileInfo *smb_file_target;
 	struct cifs_tcon *src_tcon;
 	struct cifs_tcon *target_tcon;
+	unsigned long long destend, fstart, fend;
 	ssize_t rc;
 
 	cifs_dbg(FYI, "copychunk range\n");
@@ -1306,13 +1422,41 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	if (rc)
 		goto unlock;
 
-	/* should we flush first and last page first */
-	truncate_inode_pages(&target_inode->i_data, 0);
+	/* The server-side copy will fail if the source crosses the EOF marker.
+	 * Advance the EOF marker after the flush above to the end of the range
+	 * if it's short of that.
+	 */
+	if (src_cifsi->server_eof < off + len) {
+		rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len);
+		if (rc < 0)
+			goto unlock;
+	}
+
+	destend = destoff + len - 1;
+
+	/* Flush the folios at either end of the destination range to prevent
+	 * accidental loss of dirty data outside of the range.
+	 */
+	fstart = destoff;
+	fend = destend;
+
+	rc = cifs_flush_folio(target_inode, destoff, &fstart, &fend, true);
+	if (rc)
+		goto unlock;
+	rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false);
+	if (rc)
+		goto unlock;
+
+	/* Discard all the folios that overlap the destination region. */
+	truncate_inode_pages_range(&target_inode->i_data, fstart, fend);
 
 	rc = file_modified(dst_file);
-	if (!rc)
+	if (!rc) {
 		rc = target_tcon->ses->server->ops->copychunk_range(xid,
 			smb_file_src, smb_file_target, off, len, destoff);
+		if (rc > 0 && destoff + rc > i_size_read(target_inode))
+			truncate_setsize(target_inode, destoff + rc);
+	}
 
 	file_accessed(src_file);
 
diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h
index 8ca3d7606bb49d..3adea10aa9dad6 100644
--- a/fs/smb/client/cifsfs.h
+++ b/fs/smb/client/cifsfs.h
@@ -152,6 +152,6 @@ extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
 /* when changing internal version - update following two lines at same time */
-#define SMB3_PRODUCT_BUILD 45
-#define CIFS_VERSION   "2.45"
+#define SMB3_PRODUCT_BUILD 46
+#define CIFS_VERSION   "2.46"
 #endif				/* _CIFSFS_H */
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 02082621d8e07a..55b3ce944022a0 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -191,7 +191,13 @@ struct cifs_open_info_data {
 		bool reparse_point;
 		bool symlink;
 	};
-	__u32 reparse_tag;
+	struct {
+		__u32 tag;
+		union {
+			struct reparse_data_buffer *buf;
+			struct reparse_posix_data *posix;
+		};
+	} reparse;
 	char *symlink_target;
 	union {
 		struct smb2_file_all_info fi;
@@ -395,8 +401,7 @@ struct smb_version_operations {
 			     struct cifs_tcon *tcon,
 			     struct cifs_sb_info *cifs_sb,
 			     const char *full_path,
-			     char **target_path,
-			     struct kvec *rsp_iov);
+			     char **target_path);
 	/* open a file for non-posix mounts */
 	int (*open)(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock,
 		    void *buf);
@@ -527,7 +532,8 @@ struct smb_version_operations {
 				 struct mid_q_entry **, char **, int *);
 	enum securityEnum (*select_sectype)(struct TCP_Server_Info *,
 			    enum securityEnum);
-	int (*next_header)(char *);
+	int (*next_header)(struct TCP_Server_Info *server, char *buf,
+			   unsigned int *noff);
 	/* ioctl passthrough for query_info */
 	int (*ioctl_query_info)(const unsigned int xid,
 				struct cifs_tcon *tcon,
@@ -551,6 +557,9 @@ struct smb_version_operations {
 	bool (*is_status_io_timeout)(char *buf);
 	/* Check for STATUS_NETWORK_NAME_DELETED */
 	bool (*is_network_name_deleted)(char *buf, struct TCP_Server_Info *srv);
+	int (*parse_reparse_point)(struct cifs_sb_info *cifs_sb,
+				   struct kvec *rsp_iov,
+				   struct cifs_open_info_data *data);
 };
 
 struct smb_version_values {
@@ -650,6 +659,7 @@ struct TCP_Server_Info {
 	bool noautotune;		/* do not autotune send buf sizes */
 	bool nosharesock;
 	bool tcp_nodelay;
+	bool terminate;
 	unsigned int credits;  /* send no more requests at once */
 	unsigned int max_credits; /* can override large 32000 default at mnt */
 	unsigned int in_flight;  /* number of requests on the wire to server */
@@ -969,6 +979,8 @@ struct cifs_server_iface {
 	struct list_head iface_head;
 	struct kref refcount;
 	size_t speed;
+	size_t weight_fulfilled;
+	unsigned int num_channels;
 	unsigned int rdma_capable : 1;
 	unsigned int rss_capable : 1;
 	unsigned int is_active : 1; /* unset if non existent */
@@ -1050,6 +1062,7 @@ struct cifs_ses {
 	spinlock_t chan_lock;
 	/* ========= begin: protected by chan_lock ======== */
 #define CIFS_MAX_CHANNELS 16
+#define CIFS_INVAL_CHAN_INDEX (-1)
 #define CIFS_ALL_CHANNELS_SET(ses)	\
 	((1UL << (ses)->chan_count) - 1)
 #define CIFS_ALL_CHANS_GOOD(ses)		\
@@ -2143,6 +2156,7 @@ static inline int cifs_get_num_sgs(const struct smb_rqst *rqst,
 	unsigned int len, skip;
 	unsigned int nents = 0;
 	unsigned long addr;
+	size_t data_size;
 	int i, j;
 
 	/*
@@ -2158,17 +2172,21 @@ static inline int cifs_get_num_sgs(const struct smb_rqst *rqst,
 	 * rqst[1+].rq_iov[0+] data to be encrypted/decrypted
 	 */
 	for (i = 0; i < num_rqst; i++) {
+		data_size = iov_iter_count(&rqst[i].rq_iter);
+
 		/* We really don't want a mixture of pinned and unpinned pages
 		 * in the sglist.  It's hard to keep track of which is what.
 		 * Instead, we convert to a BVEC-type iterator higher up.
 		 */
-		if (WARN_ON_ONCE(user_backed_iter(&rqst[i].rq_iter)))
+		if (data_size &&
+		    WARN_ON_ONCE(user_backed_iter(&rqst[i].rq_iter)))
 			return -EIO;
 
 		/* We also don't want to have any extra refs or pins to clean
 		 * up in the sglist.
 		 */
-		if (WARN_ON_ONCE(iov_iter_extract_will_pin(&rqst[i].rq_iter)))
+		if (data_size &&
+		    WARN_ON_ONCE(iov_iter_extract_will_pin(&rqst[i].rq_iter)))
 			return -EIO;
 
 		for (j = 0; j < rqst[i].rq_nvec; j++) {
@@ -2184,7 +2202,8 @@ static inline int cifs_get_num_sgs(const struct smb_rqst *rqst,
 			}
 			skip = 0;
 		}
-		nents += iov_iter_npages(&rqst[i].rq_iter, INT_MAX);
+		if (data_size)
+			nents += iov_iter_npages(&rqst[i].rq_iter, INT_MAX);
 	}
 	nents += DIV_ROUND_UP(offset_in_page(sig) + SMB2_SIGNATURE_SIZE, PAGE_SIZE);
 	return nents;
diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h
index a75220db5c1e18..c0513fbb8a59d4 100644
--- a/fs/smb/client/cifspdu.h
+++ b/fs/smb/client/cifspdu.h
@@ -882,11 +882,13 @@ typedef struct smb_com_open_rsp {
 	__u8 OplockLevel;
 	__u16 Fid;
 	__le32 CreateAction;
-	__le64 CreationTime;
-	__le64 LastAccessTime;
-	__le64 LastWriteTime;
-	__le64 ChangeTime;
-	__le32 FileAttributes;
+	struct_group(common_attributes,
+		__le64 CreationTime;
+		__le64 LastAccessTime;
+		__le64 LastWriteTime;
+		__le64 ChangeTime;
+		__le32 FileAttributes;
+	);
 	__le64 AllocationSize;
 	__le64 EndOfFile;
 	__le16 FileType;
@@ -1356,7 +1358,7 @@ typedef struct smb_com_transaction_ioctl_rsp {
 	__le32 DataDisplacement;
 	__u8 SetupCount;	/* 1 */
 	__le16 ReturnedDataLen;
-	__u16 ByteCount;
+	__le16 ByteCount;
 } __attribute__((packed)) TRANSACT_IOCTL_RSP;
 
 #define CIFS_ACL_OWNER 1
@@ -1509,7 +1511,7 @@ struct reparse_posix_data {
 	__le16	ReparseDataLength;
 	__u16	Reserved;
 	__le64	InodeType; /* LNK, FIFO, CHR etc. */
-	char	PathBuffer[];
+	__u8	DataBuffer[];
 } __attribute__((packed));
 
 struct cifs_quota_data {
@@ -2264,11 +2266,13 @@ typedef struct {
 /* QueryFileInfo/QueryPathinfo (also for SetPath/SetFile) data buffer formats */
 /******************************************************************************/
 typedef struct { /* data block encoding of response to level 263 QPathInfo */
-	__le64 CreationTime;
-	__le64 LastAccessTime;
-	__le64 LastWriteTime;
-	__le64 ChangeTime;
-	__le32 Attributes;
+	struct_group(common_attributes,
+		__le64 CreationTime;
+		__le64 LastAccessTime;
+		__le64 LastWriteTime;
+		__le64 ChangeTime;
+		__le32 Attributes;
+	);
 	__u32 Pad1;
 	__le64 AllocationSize;
 	__le64 EndOfFile;	/* size ie offset to first free byte in file */
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index 890ceddae07e25..46feaa0880bdf1 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -132,6 +132,7 @@ extern int SendReceiveBlockingLock(const unsigned int xid,
 			struct smb_hdr *in_buf,
 			struct smb_hdr *out_buf,
 			int *bytes_returned);
+
 void
 cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server,
 				      bool all_channels);
@@ -209,7 +210,7 @@ int cifs_get_inode_info(struct inode **inode, const char *full_path,
 			const struct cifs_fid *fid);
 bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb,
 				 struct cifs_fattr *fattr,
-				 u32 tag);
+				 struct cifs_open_info_data *data);
 extern int smb311_posix_get_inode_info(struct inode **pinode, const char *search_path,
 			struct super_block *sb, unsigned int xid);
 extern int cifs_get_inode_info_unix(struct inode **pinode,
@@ -457,6 +458,12 @@ extern int CIFSSMBUnixQuerySymLink(const unsigned int xid,
 			struct cifs_tcon *tcon,
 			const unsigned char *searchName, char **syminfo,
 			const struct nls_table *nls_codepage, int remap);
+extern int cifs_query_reparse_point(const unsigned int xid,
+				    struct cifs_tcon *tcon,
+				    struct cifs_sb_info *cifs_sb,
+				    const char *full_path,
+				    u32 *tag, struct kvec *rsp,
+				    int *rsp_buftype);
 extern int CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon,
 			       __u16 fid, char **symlinkinfo,
 			       const struct nls_table *nls_codepage);
@@ -610,13 +617,13 @@ void cifs_free_hash(struct shash_desc **sdesc);
 
 struct cifs_chan *
 cifs_ses_find_chan(struct cifs_ses *ses, struct TCP_Server_Info *server);
-int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses);
+int cifs_try_adding_channels(struct cifs_ses *ses);
 bool is_server_using_iface(struct TCP_Server_Info *server,
 			   struct cifs_server_iface *iface);
 bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface);
 void cifs_ses_mark_for_reconnect(struct cifs_ses *ses);
 
-unsigned int
+int
 cifs_ses_get_chan_index(struct cifs_ses *ses,
 			struct TCP_Server_Info *server);
 void
@@ -640,6 +647,8 @@ cifs_chan_needs_reconnect(struct cifs_ses *ses,
 bool
 cifs_chan_is_iface_active(struct cifs_ses *ses,
 			  struct TCP_Server_Info *server);
+void
+cifs_disable_secondary_channels(struct cifs_ses *ses);
 int
 cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server);
 int
@@ -656,6 +665,12 @@ void cifs_put_tcp_super(struct super_block *sb);
 int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix);
 char *extract_hostname(const char *unc);
 char *extract_sharename(const char *unc);
+int parse_reparse_point(struct reparse_data_buffer *buf,
+			u32 plen, struct cifs_sb_info *cifs_sb,
+			bool unicode, struct cifs_open_info_data *data);
+int cifs_sfu_make_node(unsigned int xid, struct inode *inode,
+		       struct dentry *dentry, struct cifs_tcon *tcon,
+		       const char *full_path, umode_t mode, dev_t dev);
 
 #ifdef CONFIG_CIFS_DFS_UPCALL
 static inline int get_dfs_path(const unsigned int xid, struct cifs_ses *ses,
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 25503f1a4fd213..9ee348e6d1069c 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1244,8 +1244,10 @@ openRetry:
 		*oplock |= CIFS_CREATE_ACTION;
 
 	if (buf) {
-		/* copy from CreationTime to Attributes */
-		memcpy((char *)buf, (char *)&rsp->CreationTime, 36);
+		/* copy commonly used attributes */
+		memcpy(&buf->common_attributes,
+		       &rsp->common_attributes,
+		       sizeof(buf->common_attributes));
 		/* the file_info buf is endian converted by caller */
 		buf->AllocationSize = rsp->AllocationSize;
 		buf->EndOfFile = rsp->EndOfFile;
@@ -2690,136 +2692,97 @@ querySymLinkRetry:
 	return rc;
 }
 
-/*
- *	Recent Windows versions now create symlinks more frequently
- *	and they use the "reparse point" mechanism below.  We can of course
- *	do symlinks nicely to Samba and other servers which support the
- *	CIFS Unix Extensions and we can also do SFU symlinks and "client only"
- *	"MF" symlinks optionally, but for recent Windows we really need to
- *	reenable the code below and fix the cifs_symlink callers to handle this.
- *	In the interim this code has been moved to its own config option so
- *	it is not compiled in by default until callers fixed up and more tested.
- */
-int
-CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon,
-		    __u16 fid, char **symlinkinfo,
-		    const struct nls_table *nls_codepage)
+int cifs_query_reparse_point(const unsigned int xid,
+			     struct cifs_tcon *tcon,
+			     struct cifs_sb_info *cifs_sb,
+			     const char *full_path,
+			     u32 *tag, struct kvec *rsp,
+			     int *rsp_buftype)
 {
-	int rc = 0;
-	int bytes_returned;
-	struct smb_com_transaction_ioctl_req *pSMB;
-	struct smb_com_transaction_ioctl_rsp *pSMBr;
-	bool is_unicode;
-	unsigned int sub_len;
-	char *sub_start;
-	struct reparse_symlink_data *reparse_buf;
-	struct reparse_posix_data *posix_buf;
+	struct cifs_open_parms oparms;
+	TRANSACT_IOCTL_REQ *io_req = NULL;
+	TRANSACT_IOCTL_RSP *io_rsp = NULL;
+	struct cifs_fid fid;
 	__u32 data_offset, data_count;
-	char *end_of_smb;
+	__u8 *start, *end;
+	int io_rsp_len;
+	int oplock = 0;
+	int rc;
 
-	cifs_dbg(FYI, "In Windows reparse style QueryLink for fid %u\n", fid);
-	rc = smb_init(SMB_COM_NT_TRANSACT, 23, tcon, (void **) &pSMB,
-		      (void **) &pSMBr);
+	cifs_tcon_dbg(FYI, "%s: path=%s\n", __func__, full_path);
+
+	if (cap_unix(tcon->ses))
+		return -EOPNOTSUPP;
+
+	oparms = (struct cifs_open_parms) {
+		.tcon = tcon,
+		.cifs_sb = cifs_sb,
+		.desired_access = FILE_READ_ATTRIBUTES,
+		.create_options = cifs_create_options(cifs_sb,
+						      OPEN_REPARSE_POINT),
+		.disposition = FILE_OPEN,
+		.path = full_path,
+		.fid = &fid,
+	};
+
+	rc = CIFS_open(xid, &oparms, &oplock, NULL);
 	if (rc)
 		return rc;
 
-	pSMB->TotalParameterCount = 0 ;
-	pSMB->TotalDataCount = 0;
-	pSMB->MaxParameterCount = cpu_to_le32(2);
-	/* BB find exact data count max from sess structure BB */
-	pSMB->MaxDataCount = cpu_to_le32(CIFSMaxBufSize & 0xFFFFFF00);
-	pSMB->MaxSetupCount = 4;
-	pSMB->Reserved = 0;
-	pSMB->ParameterOffset = 0;
-	pSMB->DataCount = 0;
-	pSMB->DataOffset = 0;
-	pSMB->SetupCount = 4;
-	pSMB->SubCommand = cpu_to_le16(NT_TRANSACT_IOCTL);
-	pSMB->ParameterCount = pSMB->TotalParameterCount;
-	pSMB->FunctionCode = cpu_to_le32(FSCTL_GET_REPARSE_POINT);
-	pSMB->IsFsctl = 1; /* FSCTL */
-	pSMB->IsRootFlag = 0;
-	pSMB->Fid = fid; /* file handle always le */
-	pSMB->ByteCount = 0;
+	rc = smb_init(SMB_COM_NT_TRANSACT, 23, tcon,
+		      (void **)&io_req, (void **)&io_rsp);
+	if (rc)
+		goto error;
 
-	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
-			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
-	if (rc) {
-		cifs_dbg(FYI, "Send error in QueryReparseLinkInfo = %d\n", rc);
-		goto qreparse_out;
-	}
+	io_req->TotalParameterCount = 0;
+	io_req->TotalDataCount = 0;
+	io_req->MaxParameterCount = cpu_to_le32(2);
+	/* BB find exact data count max from sess structure BB */
+	io_req->MaxDataCount = cpu_to_le32(CIFSMaxBufSize & 0xFFFFFF00);
+	io_req->MaxSetupCount = 4;
+	io_req->Reserved = 0;
+	io_req->ParameterOffset = 0;
+	io_req->DataCount = 0;
+	io_req->DataOffset = 0;
+	io_req->SetupCount = 4;
+	io_req->SubCommand = cpu_to_le16(NT_TRANSACT_IOCTL);
+	io_req->ParameterCount = io_req->TotalParameterCount;
+	io_req->FunctionCode = cpu_to_le32(FSCTL_GET_REPARSE_POINT);
+	io_req->IsFsctl = 1;
+	io_req->IsRootFlag = 0;
+	io_req->Fid = fid.netfid;
+	io_req->ByteCount = 0;
+
+	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *)io_req,
+			 (struct smb_hdr *)io_rsp, &io_rsp_len, 0);
+	if (rc)
+		goto error;
 
-	data_offset = le32_to_cpu(pSMBr->DataOffset);
-	data_count = le32_to_cpu(pSMBr->DataCount);
-	if (get_bcc(&pSMBr->hdr) < 2 || data_offset > 512) {
-		/* BB also check enough total bytes returned */
-		rc = -EIO;	/* bad smb */
-		goto qreparse_out;
-	}
-	if (!data_count || (data_count > 2048)) {
+	data_offset = le32_to_cpu(io_rsp->DataOffset);
+	data_count = le32_to_cpu(io_rsp->DataCount);
+	if (get_bcc(&io_rsp->hdr) < 2 || data_offset > 512 ||
+	    !data_count || data_count > 2048) {
 		rc = -EIO;
-		cifs_dbg(FYI, "Invalid return data count on get reparse info ioctl\n");
-		goto qreparse_out;
-	}
-	end_of_smb = 2 + get_bcc(&pSMBr->hdr) + (char *)&pSMBr->ByteCount;
-	reparse_buf = (struct reparse_symlink_data *)
-				((char *)&pSMBr->hdr.Protocol + data_offset);
-	if ((char *)reparse_buf >= end_of_smb) {
-		rc = -EIO;
-		goto qreparse_out;
-	}
-	if (reparse_buf->ReparseTag == cpu_to_le32(IO_REPARSE_TAG_NFS)) {
-		cifs_dbg(FYI, "NFS style reparse tag\n");
-		posix_buf =  (struct reparse_posix_data *)reparse_buf;
-
-		if (posix_buf->InodeType != cpu_to_le64(NFS_SPECFILE_LNK)) {
-			cifs_dbg(FYI, "unsupported file type 0x%llx\n",
-				 le64_to_cpu(posix_buf->InodeType));
-			rc = -EOPNOTSUPP;
-			goto qreparse_out;
-		}
-		is_unicode = true;
-		sub_len = le16_to_cpu(reparse_buf->ReparseDataLength);
-		if (posix_buf->PathBuffer + sub_len > end_of_smb) {
-			cifs_dbg(FYI, "reparse buf beyond SMB\n");
-			rc = -EIO;
-			goto qreparse_out;
-		}
-		*symlinkinfo = cifs_strndup_from_utf16(posix_buf->PathBuffer,
-				sub_len, is_unicode, nls_codepage);
-		goto qreparse_out;
-	} else if (reparse_buf->ReparseTag !=
-			cpu_to_le32(IO_REPARSE_TAG_SYMLINK)) {
-		rc = -EOPNOTSUPP;
-		goto qreparse_out;
+		goto error;
 	}
 
-	/* Reparse tag is NTFS symlink */
-	sub_start = le16_to_cpu(reparse_buf->SubstituteNameOffset) +
-				reparse_buf->PathBuffer;
-	sub_len = le16_to_cpu(reparse_buf->SubstituteNameLength);
-	if (sub_start + sub_len > end_of_smb) {
-		cifs_dbg(FYI, "reparse buf beyond SMB\n");
+	end = 2 + get_bcc(&io_rsp->hdr) + (__u8 *)&io_rsp->ByteCount;
+	start = (__u8 *)&io_rsp->hdr.Protocol + data_offset;
+	if (start >= end) {
 		rc = -EIO;
-		goto qreparse_out;
+		goto error;
 	}
-	if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE)
-		is_unicode = true;
-	else
-		is_unicode = false;
-
-	/* BB FIXME investigate remapping reserved chars here */
-	*symlinkinfo = cifs_strndup_from_utf16(sub_start, sub_len, is_unicode,
-					       nls_codepage);
-	if (!*symlinkinfo)
-		rc = -ENOMEM;
-qreparse_out:
-	cifs_buf_release(pSMB);
 
-	/*
-	 * Note: On -EAGAIN error only caller can retry on handle based calls
-	 * since file handle passed in no longer valid.
-	 */
+	*tag = le32_to_cpu(((struct reparse_data_buffer *)start)->ReparseTag);
+	rsp->iov_base = io_rsp;
+	rsp->iov_len = io_rsp_len;
+	*rsp_buftype = CIFS_LARGE_BUFFER;
+	CIFSSMBClose(xid, tcon, fid.netfid);
+	return 0;
+
+error:
+	cifs_buf_release(io_req);
+	CIFSSMBClose(xid, tcon, fid.netfid);
 	return rc;
 }
 
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 1a137b33858a1f..dd2a1fb65e7176 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -132,6 +132,9 @@ static void smb2_query_server_interfaces(struct work_struct *work)
 	free_xid(xid);
 
 	if (rc) {
+		if (rc == -EOPNOTSUPP)
+			return;
+
 		cifs_dbg(FYI, "%s: failed to query server interfaces: %d\n",
 				__func__, rc);
 	}
@@ -173,8 +176,12 @@ cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server,
 	list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
 		spin_lock(&ses->chan_lock);
 		for (i = 0; i < ses->chan_count; i++) {
+			if (!ses->chans[i].server)
+				continue;
+
 			spin_lock(&ses->chans[i].server->srv_lock);
-			ses->chans[i].server->tcpStatus = CifsNeedReconnect;
+			if (ses->chans[i].server->tcpStatus != CifsExiting)
+				ses->chans[i].server->tcpStatus = CifsNeedReconnect;
 			spin_unlock(&ses->chans[i].server->srv_lock);
 		}
 		spin_unlock(&ses->chan_lock);
@@ -212,6 +219,14 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server,
 
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) {
+		/*
+		 * if channel has been marked for termination, nothing to do
+		 * for the channel. in fact, we cannot find the channel for the
+		 * server. So safe to exit here
+		 */
+		if (server->terminate)
+			break;
+
 		/* check if iface is still active */
 		if (!cifs_chan_is_iface_active(ses, server))
 			cifs_chan_update_iface(ses, server);
@@ -246,6 +261,8 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server,
 			spin_lock(&tcon->tc_lock);
 			tcon->status = TID_NEED_RECON;
 			spin_unlock(&tcon->tc_lock);
+
+			cancel_delayed_work(&tcon->query_interfaces);
 		}
 		if (ses->tcon_ipc) {
 			ses->tcon_ipc->need_reconnect = true;
@@ -1184,7 +1201,12 @@ next_pdu:
 		server->total_read += length;
 
 		if (server->ops->next_header) {
-			next_offset = server->ops->next_header(buf);
+			if (server->ops->next_header(server, buf, &next_offset)) {
+				cifs_dbg(VFS, "%s: malformed response (next_offset=%u)\n",
+					 __func__, next_offset);
+				cifs_reconnect(server, true);
+				continue;
+			}
 			if (next_offset)
 				server->pdu_size = next_offset;
 		}
@@ -1591,10 +1613,6 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
 	list_del_init(&server->tcp_ses_list);
 	spin_unlock(&cifs_tcp_ses_lock);
 
-	/* For secondary channels, we pick up ref-count on the primary server */
-	if (SERVER_IS_CHAN(server))
-		cifs_put_tcp_session(server->primary_server, from_reconnect);
-
 	cancel_delayed_work_sync(&server->echo);
 
 	if (from_reconnect)
@@ -1608,6 +1626,10 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
 	else
 		cancel_delayed_work_sync(&server->reconnect);
 
+	/* For secondary channels, we pick up ref-count on the primary server */
+	if (SERVER_IS_CHAN(server))
+		cifs_put_tcp_session(server->primary_server, from_reconnect);
+
 	spin_lock(&server->srv_lock);
 	server->tcpStatus = CifsExiting;
 	spin_unlock(&server->srv_lock);
@@ -2033,6 +2055,12 @@ void __cifs_put_smb_ses(struct cifs_ses *ses)
 		ses->chans[i].server = NULL;
 	}
 
+	/* we now account for primary channel in iface->refcount */
+	if (ses->chans[0].iface) {
+		kref_put(&ses->chans[0].iface->refcount, release_iface);
+		ses->chans[0].server = NULL;
+	}
+
 	sesInfoFree(ses);
 	cifs_put_tcp_session(server, 0);
 }
@@ -3560,7 +3588,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
 	ctx->prepath = NULL;
 
 out:
-	cifs_try_adding_channels(cifs_sb, mnt_ctx.ses);
+	cifs_try_adding_channels(mnt_ctx.ses);
 	rc = mount_setup_tlink(cifs_sb, mnt_ctx.ses, mnt_ctx.tcon);
 	if (rc)
 		goto error;
diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c
index 81b84151450d2d..a8a1d386da6566 100644
--- a/fs/smb/client/dfs.c
+++ b/fs/smb/client/dfs.c
@@ -263,15 +263,23 @@ out:
 	return rc;
 }
 
-/* Resolve UNC hostname in @ctx->source and set ip addr in @ctx->dstaddr */
+/*
+ * If @ctx->dfs_automount, then update @ctx->dstaddr earlier with the DFS root
+ * server from where we'll start following any referrals.  Otherwise rely on the
+ * value provided by mount(2) as the user might not have dns_resolver key set up
+ * and therefore failing to upcall to resolve UNC hostname under @ctx->source.
+ */
 static int update_fs_context_dstaddr(struct smb3_fs_context *ctx)
 {
 	struct sockaddr *addr = (struct sockaddr *)&ctx->dstaddr;
-	int rc;
+	int rc = 0;
 
-	rc = dns_resolve_server_name_to_ip(ctx->source, addr, NULL);
-	if (!rc)
-		cifs_set_port(addr, ctx->port);
+	if (!ctx->nodfs && ctx->dfs_automount) {
+		rc = dns_resolve_server_name_to_ip(ctx->source, addr, NULL);
+		if (!rc)
+			cifs_set_port(addr, ctx->port);
+		ctx->dfs_automount = false;
+	}
 	return rc;
 }
 
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index cf17e3dd703e65..32a8525415d96b 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -4671,7 +4671,7 @@ static int cifs_readpage_worker(struct file *file, struct page *page,
 	/* we do not want atime to be less than mtime, it broke some apps */
 	atime = inode_set_atime_to_ts(inode, current_time(inode));
 	mtime = inode_get_mtime(inode);
-	if (timespec64_compare(&atime, &mtime))
+	if (timespec64_compare(&atime, &mtime) < 0)
 		inode_set_atime_to_ts(inode, inode_get_mtime(inode));
 
 	if (PAGE_SIZE > rc)
diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h
index 9d8d34af021147..cf46916286d029 100644
--- a/fs/smb/client/fs_context.h
+++ b/fs/smb/client/fs_context.h
@@ -268,6 +268,7 @@ struct smb3_fs_context {
 	bool witness:1; /* use witness protocol */
 	char *leaf_fullpath;
 	struct cifs_ses *dfs_root_ses;
+	bool dfs_automount:1; /* set for dfs automount only */
 };
 
 extern const struct fs_parameter_spec smb3_fs_parameters[];
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 86fbd3f847d657..09c5c0f5c96e2e 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -459,8 +459,7 @@ static int cifs_get_unix_fattr(const unsigned char *full_path,
 			return -EOPNOTSUPP;
 		rc = server->ops->query_symlink(xid, tcon,
 						cifs_sb, full_path,
-						&fattr->cf_symlink_target,
-						NULL);
+						&fattr->cf_symlink_target);
 		cifs_dbg(FYI, "%s: query_symlink: %d\n", __func__, rc);
 	}
 	return rc;
@@ -722,10 +721,51 @@ static void smb311_posix_info_to_fattr(struct cifs_fattr *fattr,
 		fattr->cf_mode, fattr->cf_uniqueid, fattr->cf_nlink);
 }
 
+static inline dev_t nfs_mkdev(struct reparse_posix_data *buf)
+{
+	u64 v = le64_to_cpu(*(__le64 *)buf->DataBuffer);
+
+	return MKDEV(v >> 32, v & 0xffffffff);
+}
+
 bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb,
 				 struct cifs_fattr *fattr,
-				 u32 tag)
+				 struct cifs_open_info_data *data)
 {
+	struct reparse_posix_data *buf = data->reparse.posix;
+	u32 tag = data->reparse.tag;
+
+	if (tag == IO_REPARSE_TAG_NFS && buf) {
+		switch (le64_to_cpu(buf->InodeType)) {
+		case NFS_SPECFILE_CHR:
+			fattr->cf_mode |= S_IFCHR | cifs_sb->ctx->file_mode;
+			fattr->cf_dtype = DT_CHR;
+			fattr->cf_rdev = nfs_mkdev(buf);
+			break;
+		case NFS_SPECFILE_BLK:
+			fattr->cf_mode |= S_IFBLK | cifs_sb->ctx->file_mode;
+			fattr->cf_dtype = DT_BLK;
+			fattr->cf_rdev = nfs_mkdev(buf);
+			break;
+		case NFS_SPECFILE_FIFO:
+			fattr->cf_mode |= S_IFIFO | cifs_sb->ctx->file_mode;
+			fattr->cf_dtype = DT_FIFO;
+			break;
+		case NFS_SPECFILE_SOCK:
+			fattr->cf_mode |= S_IFSOCK | cifs_sb->ctx->file_mode;
+			fattr->cf_dtype = DT_SOCK;
+			break;
+		case NFS_SPECFILE_LNK:
+			fattr->cf_mode = S_IFLNK | cifs_sb->ctx->file_mode;
+			fattr->cf_dtype = DT_LNK;
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			return false;
+		}
+		return true;
+	}
+
 	switch (tag) {
 	case IO_REPARSE_TAG_LX_SYMLINK:
 		fattr->cf_mode |= S_IFLNK | cifs_sb->ctx->file_mode;
@@ -750,7 +790,7 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb,
 	case 0: /* SMB1 symlink */
 	case IO_REPARSE_TAG_SYMLINK:
 	case IO_REPARSE_TAG_NFS:
-		fattr->cf_mode = S_IFLNK;
+		fattr->cf_mode = S_IFLNK | cifs_sb->ctx->file_mode;
 		fattr->cf_dtype = DT_LNK;
 		break;
 	default:
@@ -791,7 +831,7 @@ static void cifs_open_info_to_fattr(struct cifs_fattr *fattr,
 	fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks);
 
 	if (cifs_open_data_reparse(data) &&
-	    cifs_reparse_point_to_fattr(cifs_sb, fattr, data->reparse_tag))
+	    cifs_reparse_point_to_fattr(cifs_sb, fattr, data))
 		goto out_reparse;
 
 	if (fattr->cf_cifsattrs & ATTR_DIRECTORY) {
@@ -825,6 +865,8 @@ static void cifs_open_info_to_fattr(struct cifs_fattr *fattr,
 
 out_reparse:
 	if (S_ISLNK(fattr->cf_mode)) {
+		if (likely(data->symlink_target))
+			fattr->cf_eof = strnlen(data->symlink_target, PATH_MAX);
 		fattr->cf_symlink_target = data->symlink_target;
 		data->symlink_target = NULL;
 	}
@@ -856,7 +898,7 @@ cifs_get_file_info(struct file *filp)
 		data.adjust_tz = false;
 		if (data.symlink_target) {
 			data.symlink = true;
-			data.reparse_tag = IO_REPARSE_TAG_SYMLINK;
+			data.reparse.tag = IO_REPARSE_TAG_SYMLINK;
 		}
 		cifs_open_info_to_fattr(&fattr, &data, inode->i_sb);
 		break;
@@ -1025,7 +1067,7 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct kvec rsp_iov, *iov = NULL;
 	int rsp_buftype = CIFS_NO_BUFFER;
-	u32 tag = data->reparse_tag;
+	u32 tag = data->reparse.tag;
 	int rc = 0;
 
 	if (!tag && server->ops->query_reparse_point) {
@@ -1035,22 +1077,28 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
 		if (!rc)
 			iov = &rsp_iov;
 	}
-	switch ((data->reparse_tag = tag)) {
+
+	rc = -EOPNOTSUPP;
+	switch ((data->reparse.tag = tag)) {
 	case 0: /* SMB1 symlink */
-		iov = NULL;
-		fallthrough;
-	case IO_REPARSE_TAG_NFS:
-	case IO_REPARSE_TAG_SYMLINK:
-		if (!data->symlink_target && server->ops->query_symlink) {
+		if (server->ops->query_symlink) {
 			rc = server->ops->query_symlink(xid, tcon,
 							cifs_sb, full_path,
-							&data->symlink_target,
-							iov);
+							&data->symlink_target);
 		}
 		break;
 	case IO_REPARSE_TAG_MOUNT_POINT:
 		cifs_create_junction_fattr(fattr, sb);
+		rc = 0;
 		goto out;
+	default:
+		if (data->symlink_target) {
+			rc = 0;
+		} else if (server->ops->parse_reparse_point) {
+			rc = server->ops->parse_reparse_point(cifs_sb,
+							      iov, data);
+		}
+		break;
 	}
 
 	cifs_open_info_to_fattr(fattr, data, sb);
diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c
index f7160003e0ed92..e2f92c21fff502 100644
--- a/fs/smb/client/ioctl.c
+++ b/fs/smb/client/ioctl.c
@@ -117,6 +117,20 @@ out_drop_write:
 	return rc;
 }
 
+static long smb_mnt_get_tcon_info(struct cifs_tcon *tcon, void __user *arg)
+{
+	int rc = 0;
+	struct smb_mnt_tcon_info tcon_inf;
+
+	tcon_inf.tid = tcon->tid;
+	tcon_inf.session_id = tcon->ses->Suid;
+
+	if (copy_to_user(arg, &tcon_inf, sizeof(struct smb_mnt_tcon_info)))
+		rc = -EFAULT;
+
+	return rc;
+}
+
 static long smb_mnt_get_fsinfo(unsigned int xid, struct cifs_tcon *tcon,
 				void __user *arg)
 {
@@ -129,6 +143,7 @@ static long smb_mnt_get_fsinfo(unsigned int xid, struct cifs_tcon *tcon,
 
 	fsinf->version = 1;
 	fsinf->protocol_id = tcon->ses->server->vals->protocol_id;
+	fsinf->tcon_flags = tcon->Flags;
 	fsinf->device_characteristics =
 			le32_to_cpu(tcon->fsDevInfo.DeviceCharacteristics);
 	fsinf->device_type = le32_to_cpu(tcon->fsDevInfo.DeviceType);
@@ -414,6 +429,17 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 			tcon = tlink_tcon(pSMBFile->tlink);
 			rc = smb_mnt_get_fsinfo(xid, tcon, (void __user *)arg);
 			break;
+		case CIFS_IOC_GET_TCON_INFO:
+			cifs_sb = CIFS_SB(inode->i_sb);
+			tlink = cifs_sb_tlink(cifs_sb);
+			if (IS_ERR(tlink)) {
+				rc = PTR_ERR(tlink);
+				break;
+			}
+			tcon = tlink_tcon(tlink);
+			rc = smb_mnt_get_tcon_info(tcon, (void __user *)arg);
+			cifs_put_tlink(tlink);
+			break;
 		case CIFS_ENUMERATE_SNAPSHOTS:
 			if (pSMBFile == NULL)
 				break;
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index 35b176457bbed0..c2137ea3c25389 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -363,6 +363,10 @@ checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server)
 			cifs_dbg(VFS, "Length less than smb header size\n");
 		}
 		return -EIO;
+	} else if (total_read < sizeof(*smb) + 2 * smb->WordCount) {
+		cifs_dbg(VFS, "%s: can't read BCC due to invalid WordCount(%u)\n",
+			 __func__, smb->WordCount);
+		return -EIO;
 	}
 
 	/* otherwise, there is enough to get to the BCC */
diff --git a/fs/smb/client/namespace.c b/fs/smb/client/namespace.c
index c8f5ed8a69f1c1..a6968573b775e7 100644
--- a/fs/smb/client/namespace.c
+++ b/fs/smb/client/namespace.c
@@ -117,6 +117,18 @@ cifs_build_devname(char *nodename, const char *prepath)
 	return dev;
 }
 
+static bool is_dfs_mount(struct dentry *dentry)
+{
+	struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+	bool ret;
+
+	spin_lock(&tcon->tc_lock);
+	ret = !!tcon->origin_fullpath;
+	spin_unlock(&tcon->tc_lock);
+	return ret;
+}
+
 /* Return full path out of a dentry set for automount */
 static char *automount_fullpath(struct dentry *dentry, void *page)
 {
@@ -212,8 +224,9 @@ static struct vfsmount *cifs_do_automount(struct path *path)
 		ctx->source = NULL;
 		goto out;
 	}
-	cifs_dbg(FYI, "%s: ctx: source=%s UNC=%s prepath=%s\n",
-		 __func__, ctx->source, ctx->UNC, ctx->prepath);
+	ctx->dfs_automount = is_dfs_mount(mntpt);
+	cifs_dbg(FYI, "%s: ctx: source=%s UNC=%s prepath=%s dfs_automount=%d\n",
+		 __func__, ctx->source, ctx->UNC, ctx->prepath, ctx->dfs_automount);
 
 	mnt = fc_mount(fc);
 out:
diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index 47fc22de8d20c7..d30ea2005eb361 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -153,6 +153,10 @@ static bool reparse_file_needs_reval(const struct cifs_fattr *fattr)
 static void
 cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb)
 {
+	struct cifs_open_info_data data = {
+		.reparse = { .tag = fattr->cf_cifstag, },
+	};
+
 	fattr->cf_uid = cifs_sb->ctx->linux_uid;
 	fattr->cf_gid = cifs_sb->ctx->linux_gid;
 
@@ -165,7 +169,7 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb)
 	 * reasonably map some of them to directories vs. files vs. symlinks
 	 */
 	if ((fattr->cf_cifsattrs & ATTR_REPARSE) &&
-	    cifs_reparse_point_to_fattr(cifs_sb, fattr, fattr->cf_cifstag))
+	    cifs_reparse_point_to_fattr(cifs_sb, fattr, &data))
 		goto out_reparse;
 
 	if (fattr->cf_cifsattrs & ATTR_DIRECTORY) {
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index cd474cf98f30e4..2d3b332a79a164 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -24,7 +24,7 @@
 #include "fs_context.h"
 
 static int
-cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses,
+cifs_ses_add_channel(struct cifs_ses *ses,
 		     struct cifs_server_iface *iface);
 
 bool
@@ -69,7 +69,7 @@ bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface)
 
 /* channel helper functions. assumed that chan_lock is held by caller. */
 
-unsigned int
+int
 cifs_ses_get_chan_index(struct cifs_ses *ses,
 			struct TCP_Server_Info *server)
 {
@@ -85,14 +85,17 @@ cifs_ses_get_chan_index(struct cifs_ses *ses,
 		cifs_dbg(VFS, "unable to get chan index for server: 0x%llx",
 			 server->conn_id);
 	WARN_ON(1);
-	return 0;
+	return CIFS_INVAL_CHAN_INDEX;
 }
 
 void
 cifs_chan_set_in_reconnect(struct cifs_ses *ses,
 			     struct TCP_Server_Info *server)
 {
-	unsigned int chan_index = cifs_ses_get_chan_index(ses, server);
+	int chan_index = cifs_ses_get_chan_index(ses, server);
+
+	if (chan_index == CIFS_INVAL_CHAN_INDEX)
+		return;
 
 	ses->chans[chan_index].in_reconnect = true;
 }
@@ -103,6 +106,9 @@ cifs_chan_clear_in_reconnect(struct cifs_ses *ses,
 {
 	unsigned int chan_index = cifs_ses_get_chan_index(ses, server);
 
+	if (chan_index == CIFS_INVAL_CHAN_INDEX)
+		return;
+
 	ses->chans[chan_index].in_reconnect = false;
 }
 
@@ -112,6 +118,9 @@ cifs_chan_in_reconnect(struct cifs_ses *ses,
 {
 	unsigned int chan_index = cifs_ses_get_chan_index(ses, server);
 
+	if (chan_index == CIFS_INVAL_CHAN_INDEX)
+		return true;	/* err on the safer side */
+
 	return CIFS_CHAN_IN_RECONNECT(ses, chan_index);
 }
 
@@ -121,6 +130,9 @@ cifs_chan_set_need_reconnect(struct cifs_ses *ses,
 {
 	unsigned int chan_index = cifs_ses_get_chan_index(ses, server);
 
+	if (chan_index == CIFS_INVAL_CHAN_INDEX)
+		return;
+
 	set_bit(chan_index, &ses->chans_need_reconnect);
 	cifs_dbg(FYI, "Set reconnect bitmask for chan %u; now 0x%lx\n",
 		 chan_index, ses->chans_need_reconnect);
@@ -132,6 +144,9 @@ cifs_chan_clear_need_reconnect(struct cifs_ses *ses,
 {
 	unsigned int chan_index = cifs_ses_get_chan_index(ses, server);
 
+	if (chan_index == CIFS_INVAL_CHAN_INDEX)
+		return;
+
 	clear_bit(chan_index, &ses->chans_need_reconnect);
 	cifs_dbg(FYI, "Cleared reconnect bitmask for chan %u; now 0x%lx\n",
 		 chan_index, ses->chans_need_reconnect);
@@ -143,6 +158,9 @@ cifs_chan_needs_reconnect(struct cifs_ses *ses,
 {
 	unsigned int chan_index = cifs_ses_get_chan_index(ses, server);
 
+	if (chan_index == CIFS_INVAL_CHAN_INDEX)
+		return true;	/* err on the safer side */
+
 	return CIFS_CHAN_NEEDS_RECONNECT(ses, chan_index);
 }
 
@@ -152,19 +170,24 @@ cifs_chan_is_iface_active(struct cifs_ses *ses,
 {
 	unsigned int chan_index = cifs_ses_get_chan_index(ses, server);
 
+	if (chan_index == CIFS_INVAL_CHAN_INDEX)
+		return true;	/* err on the safer side */
+
 	return ses->chans[chan_index].iface &&
 		ses->chans[chan_index].iface->is_active;
 }
 
 /* returns number of channels added */
-int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
+int cifs_try_adding_channels(struct cifs_ses *ses)
 {
 	struct TCP_Server_Info *server = ses->server;
 	int old_chan_count, new_chan_count;
 	int left;
 	int rc = 0;
 	int tries = 0;
+	size_t iface_weight = 0, iface_min_speed = 0;
 	struct cifs_server_iface *iface = NULL, *niface = NULL;
+	struct cifs_server_iface *last_iface = NULL;
 
 	spin_lock(&ses->chan_lock);
 
@@ -192,21 +215,11 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
 	}
 	spin_unlock(&ses->chan_lock);
 
-	/*
-	 * Keep connecting to same, fastest, iface for all channels as
-	 * long as its RSS. Try next fastest one if not RSS or channel
-	 * creation fails.
-	 */
-	spin_lock(&ses->iface_lock);
-	iface = list_first_entry(&ses->iface_list, struct cifs_server_iface,
-				 iface_head);
-	spin_unlock(&ses->iface_lock);
-
 	while (left > 0) {
 
 		tries++;
 		if (tries > 3*ses->chan_max) {
-			cifs_dbg(FYI, "too many channel open attempts (%d channels left to open)\n",
+			cifs_dbg(VFS, "too many channel open attempts (%d channels left to open)\n",
 				 left);
 			break;
 		}
@@ -214,23 +227,41 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
 		spin_lock(&ses->iface_lock);
 		if (!ses->iface_count) {
 			spin_unlock(&ses->iface_lock);
+			cifs_dbg(VFS, "server %s does not advertise interfaces\n",
+				      ses->server->hostname);
 			break;
 		}
 
+		if (!iface)
+			iface = list_first_entry(&ses->iface_list, struct cifs_server_iface,
+						 iface_head);
+		last_iface = list_last_entry(&ses->iface_list, struct cifs_server_iface,
+					     iface_head);
+		iface_min_speed = last_iface->speed;
+
 		list_for_each_entry_safe_from(iface, niface, &ses->iface_list,
 				    iface_head) {
+			/* do not mix rdma and non-rdma interfaces */
+			if (iface->rdma_capable != ses->server->rdma)
+				continue;
+
 			/* skip ifaces that are unusable */
 			if (!iface->is_active ||
 			    (is_ses_using_iface(ses, iface) &&
-			     !iface->rss_capable)) {
+			     !iface->rss_capable))
+				continue;
+
+			/* check if we already allocated enough channels */
+			iface_weight = iface->speed / iface_min_speed;
+
+			if (iface->weight_fulfilled >= iface_weight)
 				continue;
-			}
 
 			/* take ref before unlock */
 			kref_get(&iface->refcount);
 
 			spin_unlock(&ses->iface_lock);
-			rc = cifs_ses_add_channel(cifs_sb, ses, iface);
+			rc = cifs_ses_add_channel(ses, iface);
 			spin_lock(&ses->iface_lock);
 
 			if (rc) {
@@ -241,10 +272,21 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
 				continue;
 			}
 
-			cifs_dbg(FYI, "successfully opened new channel on iface:%pIS\n",
+			iface->num_channels++;
+			iface->weight_fulfilled++;
+			cifs_dbg(VFS, "successfully opened new channel on iface:%pIS\n",
 				 &iface->sockaddr);
 			break;
 		}
+
+		/* reached end of list. reset weight_fulfilled and start over */
+		if (list_entry_is_head(iface, &ses->iface_list, iface_head)) {
+			list_for_each_entry(iface, &ses->iface_list, iface_head)
+				iface->weight_fulfilled = 0;
+			spin_unlock(&ses->iface_lock);
+			iface = NULL;
+			continue;
+		}
 		spin_unlock(&ses->iface_lock);
 
 		left--;
@@ -255,6 +297,64 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
 }
 
 /*
+ * called when multichannel is disabled by the server.
+ * this always gets called from smb2_reconnect
+ * and cannot get called in parallel threads.
+ */
+void
+cifs_disable_secondary_channels(struct cifs_ses *ses)
+{
+	int i, chan_count;
+	struct TCP_Server_Info *server;
+	struct cifs_server_iface *iface;
+
+	spin_lock(&ses->chan_lock);
+	chan_count = ses->chan_count;
+	if (chan_count == 1)
+		goto done;
+
+	ses->chan_count = 1;
+
+	/* for all secondary channels reset the need reconnect bit */
+	ses->chans_need_reconnect &= 1;
+
+	for (i = 1; i < chan_count; i++) {
+		iface = ses->chans[i].iface;
+		server = ses->chans[i].server;
+
+		/*
+		 * remove these references first, since we need to unlock
+		 * the chan_lock here, since iface_lock is a higher lock
+		 */
+		ses->chans[i].iface = NULL;
+		ses->chans[i].server = NULL;
+		spin_unlock(&ses->chan_lock);
+
+		if (iface) {
+			spin_lock(&ses->iface_lock);
+			iface->num_channels--;
+			if (iface->weight_fulfilled)
+				iface->weight_fulfilled--;
+			kref_put(&iface->refcount, release_iface);
+			spin_unlock(&ses->iface_lock);
+		}
+
+		if (server) {
+			if (!server->terminate) {
+				server->terminate = true;
+				cifs_signal_cifsd_for_reconnect(server, false);
+			}
+			cifs_put_tcp_session(server, false);
+		}
+
+		spin_lock(&ses->chan_lock);
+	}
+
+done:
+	spin_unlock(&ses->chan_lock);
+}
+
+/*
  * update the iface for the channel if necessary.
  * will return 0 when iface is updated, 1 if removed, 2 otherwise
  * Must be called with chan_lock held.
@@ -263,13 +363,16 @@ int
 cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
 {
 	unsigned int chan_index;
+	size_t iface_weight = 0, iface_min_speed = 0;
 	struct cifs_server_iface *iface = NULL;
 	struct cifs_server_iface *old_iface = NULL;
+	struct cifs_server_iface *last_iface = NULL;
+	struct sockaddr_storage ss;
 	int rc = 0;
 
 	spin_lock(&ses->chan_lock);
 	chan_index = cifs_ses_get_chan_index(ses, server);
-	if (!chan_index) {
+	if (chan_index == CIFS_INVAL_CHAN_INDEX) {
 		spin_unlock(&ses->chan_lock);
 		return 0;
 	}
@@ -283,14 +386,49 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
 	}
 	spin_unlock(&ses->chan_lock);
 
+	spin_lock(&server->srv_lock);
+	ss = server->dstaddr;
+	spin_unlock(&server->srv_lock);
+
 	spin_lock(&ses->iface_lock);
+	if (!ses->iface_count) {
+		spin_unlock(&ses->iface_lock);
+		cifs_dbg(VFS, "server %s does not advertise interfaces\n", ses->server->hostname);
+		return 0;
+	}
+
+	last_iface = list_last_entry(&ses->iface_list, struct cifs_server_iface,
+				     iface_head);
+	iface_min_speed = last_iface->speed;
+
 	/* then look for a new one */
 	list_for_each_entry(iface, &ses->iface_list, iface_head) {
+		if (!chan_index) {
+			/* if we're trying to get the updated iface for primary channel */
+			if (!cifs_match_ipaddr((struct sockaddr *) &ss,
+					       (struct sockaddr *) &iface->sockaddr))
+				continue;
+
+			kref_get(&iface->refcount);
+			break;
+		}
+
+		/* do not mix rdma and non-rdma interfaces */
+		if (iface->rdma_capable != server->rdma)
+			continue;
+
 		if (!iface->is_active ||
 		    (is_ses_using_iface(ses, iface) &&
 		     !iface->rss_capable)) {
 			continue;
 		}
+
+		/* check if we already allocated enough channels */
+		iface_weight = iface->speed / iface_min_speed;
+
+		if (iface->weight_fulfilled >= iface_weight)
+			continue;
+
 		kref_get(&iface->refcount);
 		break;
 	}
@@ -301,34 +439,52 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
 		cifs_dbg(FYI, "unable to find a suitable iface\n");
 	}
 
+	if (!iface) {
+		cifs_dbg(FYI, "unable to get the interface matching: %pIS\n",
+			 &ss);
+		spin_unlock(&ses->iface_lock);
+		return 0;
+	}
+
 	/* now drop the ref to the current iface */
-	if (old_iface && iface) {
+	if (old_iface) {
 		cifs_dbg(FYI, "replacing iface: %pIS with %pIS\n",
 			 &old_iface->sockaddr,
 			 &iface->sockaddr);
+
+		old_iface->num_channels--;
+		if (old_iface->weight_fulfilled)
+			old_iface->weight_fulfilled--;
+		iface->num_channels++;
+		iface->weight_fulfilled++;
+
 		kref_put(&old_iface->refcount, release_iface);
 	} else if (old_iface) {
-		cifs_dbg(FYI, "releasing ref to iface: %pIS\n",
+		/* if a new candidate is not found, keep things as is */
+		cifs_dbg(FYI, "could not replace iface: %pIS\n",
 			 &old_iface->sockaddr);
-		kref_put(&old_iface->refcount, release_iface);
-	} else {
-		WARN_ON(!iface);
-		cifs_dbg(FYI, "adding new iface: %pIS\n", &iface->sockaddr);
+	} else if (!chan_index) {
+		/* special case: update interface for primary channel */
+		if (iface) {
+			cifs_dbg(FYI, "referencing primary channel iface: %pIS\n",
+				 &iface->sockaddr);
+			iface->num_channels++;
+			iface->weight_fulfilled++;
+		}
 	}
 	spin_unlock(&ses->iface_lock);
 
-	spin_lock(&ses->chan_lock);
-	chan_index = cifs_ses_get_chan_index(ses, server);
-	ses->chans[chan_index].iface = iface;
-
-	/* No iface is found. if secondary chan, drop connection */
-	if (!iface && SERVER_IS_CHAN(server))
-		ses->chans[chan_index].server = NULL;
-
-	spin_unlock(&ses->chan_lock);
+	if (iface) {
+		spin_lock(&ses->chan_lock);
+		chan_index = cifs_ses_get_chan_index(ses, server);
+		if (chan_index == CIFS_INVAL_CHAN_INDEX) {
+			spin_unlock(&ses->chan_lock);
+			return 0;
+		}
 
-	if (!iface && SERVER_IS_CHAN(server))
-		cifs_put_tcp_session(server, false);
+		ses->chans[chan_index].iface = iface;
+		spin_unlock(&ses->chan_lock);
+	}
 
 	return rc;
 }
@@ -354,7 +510,7 @@ cifs_ses_find_chan(struct cifs_ses *ses, struct TCP_Server_Info *server)
 }
 
 static int
-cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses,
+cifs_ses_add_channel(struct cifs_ses *ses,
 		     struct cifs_server_iface *iface)
 {
 	struct TCP_Server_Info *chan_server;
@@ -433,7 +589,7 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses,
 	 * This will be used for encoding/decoding user/domain/pw
 	 * during sess setup auth.
 	 */
-	ctx->local_nls = cifs_sb->local_nls;
+	ctx->local_nls = ses->local_nls;
 
 	/* Use RDMA if possible */
 	ctx->rdma = iface->rdma_capable;
@@ -479,20 +635,16 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses,
 
 	rc = cifs_negotiate_protocol(xid, ses, chan->server);
 	if (!rc)
-		rc = cifs_setup_session(xid, ses, chan->server, cifs_sb->local_nls);
+		rc = cifs_setup_session(xid, ses, chan->server, ses->local_nls);
 
 	mutex_unlock(&ses->session_mutex);
 
 out:
 	if (rc && chan->server) {
-		/*
-		 * we should avoid race with these delayed works before we
-		 * remove this channel
-		 */
-		cancel_delayed_work_sync(&chan->server->echo);
-		cancel_delayed_work_sync(&chan->server->reconnect);
+		cifs_put_tcp_session(chan->server, 0);
 
 		spin_lock(&ses->chan_lock);
+
 		/* we rely on all bits beyond chan_count to be clear */
 		cifs_chan_clear_need_reconnect(ses, chan->server);
 		ses->chan_count--;
@@ -502,8 +654,6 @@ out:
 		 */
 		WARN_ON(ses->chan_count < 1);
 		spin_unlock(&ses->chan_lock);
-
-		cifs_put_tcp_session(chan->server, 0);
 	}
 
 	kfree(ctx->UNC);
@@ -535,8 +685,7 @@ static __u32 cifs_ssetup_hdr(struct cifs_ses *ses,
 
 	/* Now no need to set SMBFLG_CASELESS or obsolete CANONICAL PATH */
 
-	/* BB verify whether signing required on neg or just on auth frame
-	   (and NTLM case) */
+	/* BB verify whether signing required on neg or just auth frame (and NTLM case) */
 
 	capabilities = CAP_LARGE_FILES | CAP_NT_SMBS | CAP_LEVEL_II_OPLOCKS |
 			CAP_LARGE_WRITE_X | CAP_LARGE_READ_X;
@@ -593,8 +742,10 @@ static void unicode_domain_string(char **pbcc_area, struct cifs_ses *ses,
 
 	/* copy domain */
 	if (ses->domainName == NULL) {
-		/* Sending null domain better than using a bogus domain name (as
-		we did briefly in 2.6.18) since server will use its default */
+		/*
+		 * Sending null domain better than using a bogus domain name (as
+		 * we did briefly in 2.6.18) since server will use its default
+		 */
 		*bcc_ptr = 0;
 		*(bcc_ptr+1) = 0;
 		bytes_ret = 0;
@@ -613,8 +764,7 @@ static void unicode_ssetup_strings(char **pbcc_area, struct cifs_ses *ses,
 	char *bcc_ptr = *pbcc_area;
 	int bytes_ret = 0;
 
-	/* BB FIXME add check that strings total less
-	than 335 or will need to send them as arrays */
+	/* BB FIXME add check that strings less than 335 or will need to send as arrays */
 
 	/* copy user */
 	if (ses->user_name == NULL) {
@@ -659,8 +809,7 @@ static void ascii_ssetup_strings(char **pbcc_area, struct cifs_ses *ses,
 		if (WARN_ON_ONCE(len < 0))
 			len = CIFS_MAX_DOMAINNAME_LEN - 1;
 		bcc_ptr += len;
-	} /* else we will send a null domain name
-	     so the server will default to its own domain */
+	} /* else we send a null domain name so server will default to its own domain */
 	*bcc_ptr = 0;
 	bcc_ptr++;
 
@@ -756,11 +905,14 @@ static void decode_ascii_ssetup(char **pbcc_area, __u16 bleft,
 	if (len > bleft)
 		return;
 
-	/* No domain field in LANMAN case. Domain is
-	   returned by old servers in the SMB negprot response */
-	/* BB For newer servers which do not support Unicode,
-	   but thus do return domain here we could add parsing
-	   for it later, but it is not very important */
+	/*
+	 * No domain field in LANMAN case. Domain is
+	 * returned by old servers in the SMB negprot response
+	 *
+	 * BB For newer servers which do not support Unicode,
+	 * but thus do return domain here, we could add parsing
+	 * for it later, but it is not very important
+	 */
 	cifs_dbg(FYI, "ascii: bytes left %d\n", bleft);
 }
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
@@ -816,9 +968,12 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len,
 	ses->ntlmssp->server_flags = server_flags;
 
 	memcpy(ses->ntlmssp->cryptkey, pblob->Challenge, CIFS_CRYPTO_KEY_SIZE);
-	/* In particular we can examine sign flags */
-	/* BB spec says that if AvId field of MsvAvTimestamp is populated then
-		we must set the MIC field of the AUTHENTICATE_MESSAGE */
+	/*
+	 * In particular we can examine sign flags
+	 *
+	 * BB spec says that if AvId field of MsvAvTimestamp is populated then
+	 * we must set the MIC field of the AUTHENTICATE_MESSAGE
+	 */
 
 	tioffset = le32_to_cpu(pblob->TargetInfoArray.BufferOffset);
 	tilen = le16_to_cpu(pblob->TargetInfoArray.Length);
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index 9bf8735cdd1e8f..a9eaba8083b0d6 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -976,64 +976,37 @@ static int cifs_query_symlink(const unsigned int xid,
 			      struct cifs_tcon *tcon,
 			      struct cifs_sb_info *cifs_sb,
 			      const char *full_path,
-			      char **target_path,
-			      struct kvec *rsp_iov)
+			      char **target_path)
 {
 	int rc;
-	int oplock = 0;
-	bool is_reparse_point = !!rsp_iov;
-	struct cifs_fid fid;
-	struct cifs_open_parms oparms;
 
-	cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
+	cifs_tcon_dbg(FYI, "%s: path=%s\n", __func__, full_path);
 
-	if (is_reparse_point) {
-		cifs_dbg(VFS, "reparse points not handled for SMB1 symlinks\n");
+	if (!cap_unix(tcon->ses))
 		return -EOPNOTSUPP;
-	}
-
-	/* Check for unix extensions */
-	if (cap_unix(tcon->ses)) {
-		rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, target_path,
-					     cifs_sb->local_nls,
-					     cifs_remap(cifs_sb));
-		if (rc == -EREMOTE)
-			rc = cifs_unix_dfs_readlink(xid, tcon, full_path,
-						    target_path,
-						    cifs_sb->local_nls);
-
-		goto out;
-	}
-
-	oparms = (struct cifs_open_parms) {
-		.tcon = tcon,
-		.cifs_sb = cifs_sb,
-		.desired_access = FILE_READ_ATTRIBUTES,
-		.create_options = cifs_create_options(cifs_sb,
-						      OPEN_REPARSE_POINT),
-		.disposition = FILE_OPEN,
-		.path = full_path,
-		.fid = &fid,
-	};
-
-	rc = CIFS_open(xid, &oparms, &oplock, NULL);
-	if (rc)
-		goto out;
-
-	rc = CIFSSMBQuerySymLink(xid, tcon, fid.netfid, target_path,
-				 cifs_sb->local_nls);
-	if (rc)
-		goto out_close;
 
-	convert_delimiter(*target_path, '/');
-out_close:
-	CIFSSMBClose(xid, tcon, fid.netfid);
-out:
-	if (!rc)
-		cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path);
+	rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, target_path,
+				     cifs_sb->local_nls, cifs_remap(cifs_sb));
+	if (rc == -EREMOTE)
+		rc = cifs_unix_dfs_readlink(xid, tcon, full_path,
+					    target_path, cifs_sb->local_nls);
 	return rc;
 }
 
+static int cifs_parse_reparse_point(struct cifs_sb_info *cifs_sb,
+				    struct kvec *rsp_iov,
+				    struct cifs_open_info_data *data)
+{
+	struct reparse_data_buffer *buf;
+	TRANSACT_IOCTL_RSP *io = rsp_iov->iov_base;
+	bool unicode = !!(io->hdr.Flags2 & SMBFLG2_UNICODE);
+	u32 plen = le16_to_cpu(io->ByteCount);
+
+	buf = (struct reparse_data_buffer *)((__u8 *)&io->hdr.Protocol +
+					     le32_to_cpu(io->DataOffset));
+	return parse_reparse_point(buf, plen, cifs_sb, unicode, data);
+}
+
 static bool
 cifs_is_read_op(__u32 oplock)
 {
@@ -1068,15 +1041,7 @@ cifs_make_node(unsigned int xid, struct inode *inode,
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct inode *newinode = NULL;
-	int rc = -EPERM;
-	struct cifs_open_info_data buf = {};
-	struct cifs_io_parms io_parms;
-	__u32 oplock = 0;
-	struct cifs_fid fid;
-	struct cifs_open_parms oparms;
-	unsigned int bytes_written;
-	struct win_dev *pdev;
-	struct kvec iov[2];
+	int rc;
 
 	if (tcon->unix_ext) {
 		/*
@@ -1110,74 +1075,18 @@ cifs_make_node(unsigned int xid, struct inode *inode,
 			d_instantiate(dentry, newinode);
 		return rc;
 	}
-
 	/*
-	 * SMB1 SFU emulation: should work with all servers, but only
-	 * support block and char device (no socket & fifo)
+	 * Check if mounted with mount parm 'sfu' mount parm.
+	 * SFU emulation should work with all servers, but only
+	 * supports block and char device (no socket & fifo),
+	 * and was used by default in earlier versions of Windows
 	 */
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL))
-		return rc;
-
-	if (!S_ISCHR(mode) && !S_ISBLK(mode))
-		return rc;
-
-	cifs_dbg(FYI, "sfu compat create special file\n");
-
-	oparms = (struct cifs_open_parms) {
-		.tcon = tcon,
-		.cifs_sb = cifs_sb,
-		.desired_access = GENERIC_WRITE,
-		.create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR |
-						      CREATE_OPTION_SPECIAL),
-		.disposition = FILE_CREATE,
-		.path = full_path,
-		.fid = &fid,
-	};
-
-	if (tcon->ses->server->oplocks)
-		oplock = REQ_OPLOCK;
-	else
-		oplock = 0;
-	rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, &buf);
-	if (rc)
-		return rc;
-
-	/*
-	 * BB Do not bother to decode buf since no local inode yet to put
-	 * timestamps in, but we can reuse it safely.
-	 */
-
-	pdev = (struct win_dev *)&buf.fi;
-	io_parms.pid = current->tgid;
-	io_parms.tcon = tcon;
-	io_parms.offset = 0;
-	io_parms.length = sizeof(struct win_dev);
-	iov[1].iov_base = &buf.fi;
-	iov[1].iov_len = sizeof(struct win_dev);
-	if (S_ISCHR(mode)) {
-		memcpy(pdev->type, "IntxCHR", 8);
-		pdev->major = cpu_to_le64(MAJOR(dev));
-		pdev->minor = cpu_to_le64(MINOR(dev));
-		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
-							&bytes_written, iov, 1);
-	} else if (S_ISBLK(mode)) {
-		memcpy(pdev->type, "IntxBLK", 8);
-		pdev->major = cpu_to_le64(MAJOR(dev));
-		pdev->minor = cpu_to_le64(MINOR(dev));
-		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
-							&bytes_written, iov, 1);
-	}
-	tcon->ses->server->ops->close(xid, tcon, &fid);
-	d_drop(dentry);
-
-	/* FIXME: add code here to set EAs */
-
-	cifs_free_open_info(&buf);
-	return rc;
+		return -EPERM;
+	return cifs_sfu_make_node(xid, inode, dentry, tcon,
+				  full_path, mode, dev);
 }
 
-
-
 struct smb_version_operations smb1_operations = {
 	.send_cancel = send_nt_cancel,
 	.compare_fids = cifs_compare_fids,
@@ -1214,6 +1123,7 @@ struct smb_version_operations smb1_operations = {
 	.is_path_accessible = cifs_is_path_accessible,
 	.can_echo = cifs_can_echo,
 	.query_path_info = cifs_query_path_info,
+	.query_reparse_point = cifs_query_reparse_point,
 	.query_file_info = cifs_query_file_info,
 	.get_srv_inum = cifs_get_srv_inum,
 	.set_path_size = CIFSSMBSetEOF,
@@ -1229,6 +1139,7 @@ struct smb_version_operations smb1_operations = {
 	.rename = CIFSSMBRename,
 	.create_hardlink = CIFSCreateHardLink,
 	.query_symlink = cifs_query_symlink,
+	.parse_reparse_point = cifs_parse_reparse_point,
 	.open = cifs_open_file,
 	.set_fid = cifs_set_fid,
 	.close = cifs_close_file,
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 0b89f7008ac0f4..c94940af5d4b8d 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -555,7 +555,7 @@ static int parse_create_response(struct cifs_open_info_data *data,
 		break;
 	}
 	data->reparse_point = reparse_point;
-	data->reparse_tag = tag;
+	data->reparse.tag = tag;
 	return rc;
 }
 
diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c
index 32dfa0f7a78c30..82b84a4941dd2f 100644
--- a/fs/smb/client/smb2misc.c
+++ b/fs/smb/client/smb2misc.c
@@ -173,6 +173,21 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server)
 	}
 
 	mid = le64_to_cpu(shdr->MessageId);
+	if (check_smb2_hdr(shdr, mid))
+		return 1;
+
+	if (shdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) {
+		cifs_dbg(VFS, "Invalid structure size %u\n",
+			 le16_to_cpu(shdr->StructureSize));
+		return 1;
+	}
+
+	command = le16_to_cpu(shdr->Command);
+	if (command >= NUMBER_OF_SMB2_COMMANDS) {
+		cifs_dbg(VFS, "Invalid SMB2 command %d\n", command);
+		return 1;
+	}
+
 	if (len < pdu_size) {
 		if ((len >= hdr_size)
 		    && (shdr->Status != 0)) {
@@ -193,21 +208,6 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server)
 		return 1;
 	}
 
-	if (check_smb2_hdr(shdr, mid))
-		return 1;
-
-	if (shdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) {
-		cifs_dbg(VFS, "Invalid structure size %u\n",
-			 le16_to_cpu(shdr->StructureSize));
-		return 1;
-	}
-
-	command = le16_to_cpu(shdr->Command);
-	if (command >= NUMBER_OF_SMB2_COMMANDS) {
-		cifs_dbg(VFS, "Invalid SMB2 command %d\n", command);
-		return 1;
-	}
-
 	if (smb2_rsp_struct_sizes[command] != pdu->StructureSize2) {
 		if (command != SMB2_OPLOCK_BREAK_HE && (shdr->Status == 0 ||
 		    pdu->StructureSize2 != SMB2_ERROR_STRUCTURE_SIZE2_LE)) {
@@ -313,6 +313,9 @@ static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = {
 char *
 smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr)
 {
+	const int max_off = 4096;
+	const int max_len = 128 * 1024;
+
 	*off = 0;
 	*len = 0;
 
@@ -384,29 +387,20 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr)
 	 * Invalid length or offset probably means data area is invalid, but
 	 * we have little choice but to ignore the data area in this case.
 	 */
-	if (*off > 4096) {
-		cifs_dbg(VFS, "offset %d too large, data area ignored\n", *off);
-		*len = 0;
+	if (unlikely(*off < 0 || *off > max_off ||
+		     *len < 0 || *len > max_len)) {
+		cifs_dbg(VFS, "%s: invalid data area (off=%d len=%d)\n",
+			 __func__, *off, *len);
 		*off = 0;
-	} else if (*off < 0) {
-		cifs_dbg(VFS, "negative offset %d to data invalid ignore data area\n",
-			 *off);
-		*off = 0;
-		*len = 0;
-	} else if (*len < 0) {
-		cifs_dbg(VFS, "negative data length %d invalid, data area ignored\n",
-			 *len);
 		*len = 0;
-	} else if (*len > 128 * 1024) {
-		cifs_dbg(VFS, "data area larger than 128K: %d\n", *len);
+	} else if (*off == 0) {
 		*len = 0;
 	}
 
 	/* return pointer to beginning of data area, ie offset from SMB start */
-	if ((*off != 0) && (*len != 0))
+	if (*off > 0 && *len > 0)
 		return (char *)shdr + *off;
-	else
-		return NULL;
+	return NULL;
 }
 
 /*
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 601e7a187f8767..66b310208545bf 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -403,8 +403,10 @@ smb2_dump_detail(void *buf, struct TCP_Server_Info *server)
 	cifs_server_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Mid: %llu Pid: %d\n",
 		 shdr->Command, shdr->Status, shdr->Flags, shdr->MessageId,
 		 shdr->Id.SyncId.ProcessId);
-	cifs_server_dbg(VFS, "smb buf %p len %u\n", buf,
-		 server->ops->calc_smb_size(buf));
+	if (!server->ops->check_message(buf, server->total_read, server)) {
+		cifs_server_dbg(VFS, "smb buf %p len %u\n", buf,
+				server->ops->calc_smb_size(buf));
+	}
 #endif
 }
 
@@ -756,6 +758,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon, bool in_
 	unsigned int ret_data_len = 0;
 	struct network_interface_info_ioctl_rsp *out_buf = NULL;
 	struct cifs_ses *ses = tcon->ses;
+	struct TCP_Server_Info *pserver;
 
 	/* do not query too frequently */
 	if (ses->iface_last_update &&
@@ -780,6 +783,11 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon, bool in_
 	if (rc)
 		goto out;
 
+	/* check if iface is still active */
+	pserver = ses->chans[0].server;
+	if (pserver && !cifs_chan_is_iface_active(ses, pserver))
+		cifs_chan_update_iface(ses, pserver);
+
 out:
 	kfree(out_buf);
 	return rc;
@@ -2830,6 +2838,8 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses,
 		usleep_range(512, 2048);
 	} while (++retry_count < 5);
 
+	if (!rc && !dfs_rsp)
+		rc = -EIO;
 	if (rc) {
 		if (!is_retryable_error(rc) && rc != -ENOENT && rc != -EOPNOTSUPP)
 			cifs_tcon_dbg(VFS, "%s: ioctl error: rc=%d\n", __func__, rc);
@@ -2860,115 +2870,119 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses,
 	return rc;
 }
 
-static int
-parse_reparse_posix(struct reparse_posix_data *symlink_buf,
-		      u32 plen, char **target_path,
-		      struct cifs_sb_info *cifs_sb)
+/* See MS-FSCC 2.1.2.6 for the 'NFS' style reparse tags */
+static int parse_reparse_posix(struct reparse_posix_data *buf,
+			       struct cifs_sb_info *cifs_sb,
+			       struct cifs_open_info_data *data)
 {
 	unsigned int len;
-
-	/* See MS-FSCC 2.1.2.6 for the 'NFS' style reparse tags */
-	len = le16_to_cpu(symlink_buf->ReparseDataLength);
-
-	if (le64_to_cpu(symlink_buf->InodeType) != NFS_SPECFILE_LNK) {
-		cifs_dbg(VFS, "%lld not a supported symlink type\n",
-			le64_to_cpu(symlink_buf->InodeType));
+	u64 type;
+
+	switch ((type = le64_to_cpu(buf->InodeType))) {
+	case NFS_SPECFILE_LNK:
+		len = le16_to_cpu(buf->ReparseDataLength);
+		data->symlink_target = cifs_strndup_from_utf16(buf->DataBuffer,
+							       len, true,
+							       cifs_sb->local_nls);
+		if (!data->symlink_target)
+			return -ENOMEM;
+		convert_delimiter(data->symlink_target, '/');
+		cifs_dbg(FYI, "%s: target path: %s\n",
+			 __func__, data->symlink_target);
+		break;
+	case NFS_SPECFILE_CHR:
+	case NFS_SPECFILE_BLK:
+	case NFS_SPECFILE_FIFO:
+	case NFS_SPECFILE_SOCK:
+		break;
+	default:
+		cifs_dbg(VFS, "%s: unhandled inode type: 0x%llx\n",
+			 __func__, type);
 		return -EOPNOTSUPP;
 	}
-
-	*target_path = cifs_strndup_from_utf16(
-				symlink_buf->PathBuffer,
-				len, true, cifs_sb->local_nls);
-	if (!(*target_path))
-		return -ENOMEM;
-
-	convert_delimiter(*target_path, '/');
-	cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path);
-
 	return 0;
 }
 
-static int
-parse_reparse_symlink(struct reparse_symlink_data_buffer *symlink_buf,
-		      u32 plen, char **target_path,
-		      struct cifs_sb_info *cifs_sb)
+static int parse_reparse_symlink(struct reparse_symlink_data_buffer *sym,
+				 u32 plen, bool unicode,
+				 struct cifs_sb_info *cifs_sb,
+				 struct cifs_open_info_data *data)
 {
-	unsigned int sub_len;
-	unsigned int sub_offset;
+	unsigned int len;
+	unsigned int offs;
 
 	/* We handle Symbolic Link reparse tag here. See: MS-FSCC 2.1.2.4 */
 
-	sub_offset = le16_to_cpu(symlink_buf->SubstituteNameOffset);
-	sub_len = le16_to_cpu(symlink_buf->SubstituteNameLength);
-	if (sub_offset + 20 > plen ||
-	    sub_offset + sub_len + 20 > plen) {
+	offs = le16_to_cpu(sym->SubstituteNameOffset);
+	len = le16_to_cpu(sym->SubstituteNameLength);
+	if (offs + 20 > plen || offs + len + 20 > plen) {
 		cifs_dbg(VFS, "srv returned malformed symlink buffer\n");
 		return -EIO;
 	}
 
-	*target_path = cifs_strndup_from_utf16(
-				symlink_buf->PathBuffer + sub_offset,
-				sub_len, true, cifs_sb->local_nls);
-	if (!(*target_path))
+	data->symlink_target = cifs_strndup_from_utf16(sym->PathBuffer + offs,
+						       len, unicode,
+						       cifs_sb->local_nls);
+	if (!data->symlink_target)
 		return -ENOMEM;
 
-	convert_delimiter(*target_path, '/');
-	cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path);
+	convert_delimiter(data->symlink_target, '/');
+	cifs_dbg(FYI, "%s: target path: %s\n", __func__, data->symlink_target);
 
 	return 0;
 }
 
-static int
-parse_reparse_point(struct reparse_data_buffer *buf,
-		    u32 plen, char **target_path,
-		    struct cifs_sb_info *cifs_sb)
+int parse_reparse_point(struct reparse_data_buffer *buf,
+			u32 plen, struct cifs_sb_info *cifs_sb,
+			bool unicode, struct cifs_open_info_data *data)
 {
-	if (plen < sizeof(struct reparse_data_buffer)) {
-		cifs_dbg(VFS, "reparse buffer is too small. Must be at least 8 bytes but was %d\n",
-			 plen);
+	if (plen < sizeof(*buf)) {
+		cifs_dbg(VFS, "%s: reparse buffer is too small. Must be at least 8 bytes but was %d\n",
+			 __func__, plen);
 		return -EIO;
 	}
 
-	if (plen < le16_to_cpu(buf->ReparseDataLength) +
-	    sizeof(struct reparse_data_buffer)) {
-		cifs_dbg(VFS, "srv returned invalid reparse buf length: %d\n",
-			 plen);
+	if (plen < le16_to_cpu(buf->ReparseDataLength) + sizeof(*buf)) {
+		cifs_dbg(VFS, "%s: invalid reparse buf length: %d\n",
+			 __func__, plen);
 		return -EIO;
 	}
 
+	data->reparse.buf = buf;
+
 	/* See MS-FSCC 2.1.2 */
 	switch (le32_to_cpu(buf->ReparseTag)) {
 	case IO_REPARSE_TAG_NFS:
-		return parse_reparse_posix(
-			(struct reparse_posix_data *)buf,
-			plen, target_path, cifs_sb);
+		return parse_reparse_posix((struct reparse_posix_data *)buf,
+					   cifs_sb, data);
 	case IO_REPARSE_TAG_SYMLINK:
 		return parse_reparse_symlink(
 			(struct reparse_symlink_data_buffer *)buf,
-			plen, target_path, cifs_sb);
+			plen, unicode, cifs_sb, data);
+	case IO_REPARSE_TAG_LX_SYMLINK:
+	case IO_REPARSE_TAG_AF_UNIX:
+	case IO_REPARSE_TAG_LX_FIFO:
+	case IO_REPARSE_TAG_LX_CHR:
+	case IO_REPARSE_TAG_LX_BLK:
+		return 0;
 	default:
-		cifs_dbg(VFS, "srv returned unknown symlink buffer tag:0x%08x\n",
-			 le32_to_cpu(buf->ReparseTag));
+		cifs_dbg(VFS, "%s: unhandled reparse tag: 0x%08x\n",
+			 __func__, le32_to_cpu(buf->ReparseTag));
 		return -EOPNOTSUPP;
 	}
 }
 
-static int smb2_query_symlink(const unsigned int xid,
-			      struct cifs_tcon *tcon,
-			      struct cifs_sb_info *cifs_sb,
-			      const char *full_path,
-			      char **target_path,
-			      struct kvec *rsp_iov)
+static int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb,
+				    struct kvec *rsp_iov,
+				    struct cifs_open_info_data *data)
 {
 	struct reparse_data_buffer *buf;
 	struct smb2_ioctl_rsp *io = rsp_iov->iov_base;
 	u32 plen = le32_to_cpu(io->OutputCount);
 
-	cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
-
 	buf = (struct reparse_data_buffer *)((u8 *)io +
 					     le32_to_cpu(io->OutputOffset));
-	return parse_reparse_point(buf, plen, target_path, cifs_sb);
+	return parse_reparse_point(buf, plen, cifs_sb, true, data);
 }
 
 static int smb2_query_reparse_point(const unsigned int xid,
@@ -2991,7 +3005,7 @@ static int smb2_query_reparse_point(const unsigned int xid,
 	struct kvec *rsp_iov;
 	struct smb2_ioctl_rsp *ioctl_rsp;
 	struct reparse_data_buffer *reparse_buf;
-	u32 plen;
+	u32 off, count, len;
 
 	cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
 
@@ -3072,16 +3086,22 @@ static int smb2_query_reparse_point(const unsigned int xid,
 	 */
 	if (rc == 0) {
 		/* See MS-FSCC 2.3.23 */
+		off = le32_to_cpu(ioctl_rsp->OutputOffset);
+		count = le32_to_cpu(ioctl_rsp->OutputCount);
+		if (check_add_overflow(off, count, &len) ||
+		    len > rsp_iov[1].iov_len) {
+			cifs_tcon_dbg(VFS, "%s: invalid ioctl: off=%d count=%d\n",
+				      __func__, off, count);
+			rc = -EIO;
+			goto query_rp_exit;
+		}
 
-		reparse_buf = (struct reparse_data_buffer *)
-			((char *)ioctl_rsp +
-			 le32_to_cpu(ioctl_rsp->OutputOffset));
-		plen = le32_to_cpu(ioctl_rsp->OutputCount);
-
-		if (plen + le32_to_cpu(ioctl_rsp->OutputOffset) >
-		    rsp_iov[1].iov_len) {
-			cifs_tcon_dbg(FYI, "srv returned invalid ioctl len: %d\n",
-				 plen);
+		reparse_buf = (void *)((u8 *)ioctl_rsp + off);
+		len = sizeof(*reparse_buf);
+		if (count < len ||
+		    count < le16_to_cpu(reparse_buf->ReparseDataLength) + len) {
+			cifs_tcon_dbg(VFS, "%s: invalid ioctl: off=%d count=%d\n",
+				      __func__, off, count);
 			rc = -EIO;
 			goto query_rp_exit;
 		}
@@ -3301,6 +3321,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	struct inode *inode = file_inode(file);
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 	struct cifsFileInfo *cfile = file->private_data;
+	unsigned long long new_size;
 	long rc;
 	unsigned int xid;
 	__le64 eof;
@@ -3331,10 +3352,15 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	/*
 	 * do we also need to change the size of the file?
 	 */
-	if (keep_size == false && i_size_read(inode) < offset + len) {
-		eof = cpu_to_le64(offset + len);
+	new_size = offset + len;
+	if (keep_size == false && (unsigned long long)i_size_read(inode) < new_size) {
+		eof = cpu_to_le64(new_size);
 		rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
 				  cfile->fid.volatile_fid, cfile->pid, &eof);
+		if (rc >= 0) {
+			truncate_setsize(inode, new_size);
+			fscache_resize_cookie(cifs_inode_cookie(inode), new_size);
+		}
 	}
 
  zero_range_exit:
@@ -3729,6 +3755,9 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
 	if (rc < 0)
 		goto out_2;
 
+	truncate_setsize(inode, old_eof + len);
+	fscache_resize_cookie(cifs_inode_cookie(inode), i_size_read(inode));
+
 	rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len);
 	if (rc < 0)
 		goto out_2;
@@ -4922,6 +4951,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
 	struct smb2_hdr *shdr;
 	unsigned int pdu_length = server->pdu_size;
 	unsigned int buf_size;
+	unsigned int next_cmd;
 	struct mid_q_entry *mid_entry;
 	int next_is_large;
 	char *next_buffer = NULL;
@@ -4950,14 +4980,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
 	next_is_large = server->large_buf;
 one_more:
 	shdr = (struct smb2_hdr *)buf;
-	if (shdr->NextCommand) {
+	next_cmd = le32_to_cpu(shdr->NextCommand);
+	if (next_cmd) {
+		if (WARN_ON_ONCE(next_cmd > pdu_length))
+			return -1;
 		if (next_is_large)
 			next_buffer = (char *)cifs_buf_get();
 		else
 			next_buffer = (char *)cifs_small_buf_get();
-		memcpy(next_buffer,
-		       buf + le32_to_cpu(shdr->NextCommand),
-		       pdu_length - le32_to_cpu(shdr->NextCommand));
+		memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd);
 	}
 
 	mid_entry = smb2_find_mid(server, buf);
@@ -4981,8 +5012,8 @@ one_more:
 	else
 		ret = cifs_handle_standard(server, mid_entry);
 
-	if (ret == 0 && shdr->NextCommand) {
-		pdu_length -= le32_to_cpu(shdr->NextCommand);
+	if (ret == 0 && next_cmd) {
+		pdu_length -= next_cmd;
 		server->large_buf = next_is_large;
 		if (next_is_large)
 			server->bigbuf = buf = next_buffer;
@@ -5045,54 +5076,42 @@ smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 				NULL, 0, false);
 }
 
-static int
-smb2_next_header(char *buf)
+static int smb2_next_header(struct TCP_Server_Info *server, char *buf,
+			    unsigned int *noff)
 {
 	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
 	struct smb2_transform_hdr *t_hdr = (struct smb2_transform_hdr *)buf;
 
-	if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM)
-		return sizeof(struct smb2_transform_hdr) +
-		  le32_to_cpu(t_hdr->OriginalMessageSize);
-
-	return le32_to_cpu(hdr->NextCommand);
+	if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
+		*noff = le32_to_cpu(t_hdr->OriginalMessageSize);
+		if (unlikely(check_add_overflow(*noff, sizeof(*t_hdr), noff)))
+			return -EINVAL;
+	} else {
+		*noff = le32_to_cpu(hdr->NextCommand);
+	}
+	if (unlikely(*noff && *noff < MID_HEADER_SIZE(server)))
+		return -EINVAL;
+	return 0;
 }
 
-static int
-smb2_make_node(unsigned int xid, struct inode *inode,
-	       struct dentry *dentry, struct cifs_tcon *tcon,
-	       const char *full_path, umode_t mode, dev_t dev)
+int cifs_sfu_make_node(unsigned int xid, struct inode *inode,
+		       struct dentry *dentry, struct cifs_tcon *tcon,
+		       const char *full_path, umode_t mode, dev_t dev)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
-	int rc = -EPERM;
 	struct cifs_open_info_data buf = {};
-	struct cifs_io_parms io_parms = {0};
-	__u32 oplock = 0;
-	struct cifs_fid fid;
+	struct TCP_Server_Info *server = tcon->ses->server;
 	struct cifs_open_parms oparms;
+	struct cifs_io_parms io_parms = {};
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_fid fid;
 	unsigned int bytes_written;
 	struct win_dev *pdev;
 	struct kvec iov[2];
-
-	/*
-	 * Check if mounted with mount parm 'sfu' mount parm.
-	 * SFU emulation should work with all servers, but only
-	 * supports block and char device (no socket & fifo),
-	 * and was used by default in earlier versions of Windows
-	 */
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL))
-		return rc;
-
-	/*
-	 * TODO: Add ability to create instead via reparse point. Windows (e.g.
-	 * their current NFS server) uses this approach to expose special files
-	 * over SMB2/SMB3 and Samba will do this with SMB3.1.1 POSIX Extensions
-	 */
+	__u32 oplock = server->oplocks ? REQ_OPLOCK : 0;
+	int rc;
 
 	if (!S_ISCHR(mode) && !S_ISBLK(mode) && !S_ISFIFO(mode))
-		return rc;
-
-	cifs_dbg(FYI, "sfu compat create special file\n");
+		return -EPERM;
 
 	oparms = (struct cifs_open_parms) {
 		.tcon = tcon,
@@ -5105,11 +5124,7 @@ smb2_make_node(unsigned int xid, struct inode *inode,
 		.fid = &fid,
 	};
 
-	if (tcon->ses->server->oplocks)
-		oplock = REQ_OPLOCK;
-	else
-		oplock = 0;
-	rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, &buf);
+	rc = server->ops->open(xid, &oparms, &oplock, &buf);
 	if (rc)
 		return rc;
 
@@ -5117,42 +5132,56 @@ smb2_make_node(unsigned int xid, struct inode *inode,
 	 * BB Do not bother to decode buf since no local inode yet to put
 	 * timestamps in, but we can reuse it safely.
 	 */
-
 	pdev = (struct win_dev *)&buf.fi;
 	io_parms.pid = current->tgid;
 	io_parms.tcon = tcon;
-	io_parms.offset = 0;
-	io_parms.length = sizeof(struct win_dev);
-	iov[1].iov_base = &buf.fi;
-	iov[1].iov_len = sizeof(struct win_dev);
+	io_parms.length = sizeof(*pdev);
+	iov[1].iov_base = pdev;
+	iov[1].iov_len = sizeof(*pdev);
 	if (S_ISCHR(mode)) {
 		memcpy(pdev->type, "IntxCHR", 8);
 		pdev->major = cpu_to_le64(MAJOR(dev));
 		pdev->minor = cpu_to_le64(MINOR(dev));
-		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
-							&bytes_written, iov, 1);
 	} else if (S_ISBLK(mode)) {
 		memcpy(pdev->type, "IntxBLK", 8);
 		pdev->major = cpu_to_le64(MAJOR(dev));
 		pdev->minor = cpu_to_le64(MINOR(dev));
-		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
-							&bytes_written, iov, 1);
 	} else if (S_ISFIFO(mode)) {
 		memcpy(pdev->type, "LnxFIFO", 8);
-		pdev->major = 0;
-		pdev->minor = 0;
-		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
-							&bytes_written, iov, 1);
 	}
-	tcon->ses->server->ops->close(xid, tcon, &fid);
-	d_drop(dentry);
 
+	rc = server->ops->sync_write(xid, &fid, &io_parms,
+				     &bytes_written, iov, 1);
+	server->ops->close(xid, tcon, &fid);
+	d_drop(dentry);
 	/* FIXME: add code here to set EAs */
-
 	cifs_free_open_info(&buf);
 	return rc;
 }
 
+static int smb2_make_node(unsigned int xid, struct inode *inode,
+			  struct dentry *dentry, struct cifs_tcon *tcon,
+			  const char *full_path, umode_t mode, dev_t dev)
+{
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+
+	/*
+	 * Check if mounted with mount parm 'sfu' mount parm.
+	 * SFU emulation should work with all servers, but only
+	 * supports block and char device (no socket & fifo),
+	 * and was used by default in earlier versions of Windows
+	 */
+	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL))
+		return -EPERM;
+	/*
+	 * TODO: Add ability to create instead via reparse point. Windows (e.g.
+	 * their current NFS server) uses this approach to expose special files
+	 * over SMB2/SMB3 and Samba will do this with SMB3.1.1 POSIX Extensions
+	 */
+	return cifs_sfu_make_node(xid, inode, dentry, tcon,
+				  full_path, mode, dev);
+}
+
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 struct smb_version_operations smb20_operations = {
 	.compare_fids = smb2_compare_fids,
@@ -5203,7 +5232,7 @@ struct smb_version_operations smb20_operations = {
 	.unlink = smb2_unlink,
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
-	.query_symlink = smb2_query_symlink,
+	.parse_reparse_point = smb2_parse_reparse_point,
 	.query_mf_symlink = smb3_query_mf_symlink,
 	.create_mf_symlink = smb3_create_mf_symlink,
 	.open = smb2_open_file,
@@ -5305,7 +5334,7 @@ struct smb_version_operations smb21_operations = {
 	.unlink = smb2_unlink,
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
-	.query_symlink = smb2_query_symlink,
+	.parse_reparse_point = smb2_parse_reparse_point,
 	.query_mf_symlink = smb3_query_mf_symlink,
 	.create_mf_symlink = smb3_create_mf_symlink,
 	.open = smb2_open_file,
@@ -5410,7 +5439,7 @@ struct smb_version_operations smb30_operations = {
 	.unlink = smb2_unlink,
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
-	.query_symlink = smb2_query_symlink,
+	.parse_reparse_point = smb2_parse_reparse_point,
 	.query_mf_symlink = smb3_query_mf_symlink,
 	.create_mf_symlink = smb3_create_mf_symlink,
 	.open = smb2_open_file,
@@ -5524,7 +5553,7 @@ struct smb_version_operations smb311_operations = {
 	.unlink = smb2_unlink,
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
-	.query_symlink = smb2_query_symlink,
+	.parse_reparse_point = smb2_parse_reparse_point,
 	.query_mf_symlink = smb3_query_mf_symlink,
 	.create_mf_symlink = smb3_create_mf_symlink,
 	.open = smb2_open_file,
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index c75a80bb6d9eef..4f971c1061f0a3 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -158,11 +158,14 @@ out:
 
 static int
 smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon,
-	       struct TCP_Server_Info *server)
+	       struct TCP_Server_Info *server, bool from_reconnect)
 {
 	int rc = 0;
 	struct nls_table *nls_codepage = NULL;
 	struct cifs_ses *ses;
+	int xid;
+	struct TCP_Server_Info *pserver;
+	unsigned int chan_index;
 
 	/*
 	 * SMB2s NegProt, SessSetup, Logoff do not have tcon yet so
@@ -223,6 +226,12 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon,
 			return -EAGAIN;
 		}
 	}
+
+	/* if server is marked for termination, cifsd will cleanup */
+	if (server->terminate) {
+		spin_unlock(&server->srv_lock);
+		return -EHOSTDOWN;
+	}
 	spin_unlock(&server->srv_lock);
 
 again:
@@ -242,11 +251,23 @@ again:
 
 	mutex_lock(&ses->session_mutex);
 	/*
+	 * if this is called by delayed work, and the channel has been disabled
+	 * in parallel, the delayed work can continue to execute in parallel
+	 * there's a chance that this channel may not exist anymore
+	 */
+	spin_lock(&server->srv_lock);
+	if (server->tcpStatus == CifsExiting) {
+		spin_unlock(&server->srv_lock);
+		mutex_unlock(&ses->session_mutex);
+		rc = -EHOSTDOWN;
+		goto out;
+	}
+
+	/*
 	 * Recheck after acquire mutex. If another thread is negotiating
 	 * and the server never sends an answer the socket will be closed
 	 * and tcpStatus set to reconnect.
 	 */
-	spin_lock(&server->srv_lock);
 	if (server->tcpStatus == CifsNeedReconnect) {
 		spin_unlock(&server->srv_lock);
 		mutex_unlock(&ses->session_mutex);
@@ -283,6 +304,53 @@ again:
 
 	rc = cifs_negotiate_protocol(0, ses, server);
 	if (!rc) {
+		/*
+		 * if server stopped supporting multichannel
+		 * and the first channel reconnected, disable all the others.
+		 */
+		if (ses->chan_count > 1 &&
+		    !(server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
+			if (SERVER_IS_CHAN(server)) {
+				cifs_dbg(VFS, "server %s does not support " \
+					 "multichannel anymore. skipping secondary channel\n",
+					 ses->server->hostname);
+
+				spin_lock(&ses->chan_lock);
+				chan_index = cifs_ses_get_chan_index(ses, server);
+				if (chan_index == CIFS_INVAL_CHAN_INDEX) {
+					spin_unlock(&ses->chan_lock);
+					goto skip_terminate;
+				}
+
+				ses->chans[chan_index].server = NULL;
+				spin_unlock(&ses->chan_lock);
+
+				/*
+				 * the above reference of server by channel
+				 * needs to be dropped without holding chan_lock
+				 * as cifs_put_tcp_session takes a higher lock
+				 * i.e. cifs_tcp_ses_lock
+				 */
+				cifs_put_tcp_session(server, from_reconnect);
+
+				server->terminate = true;
+				cifs_signal_cifsd_for_reconnect(server, false);
+
+				/* mark primary server as needing reconnect */
+				pserver = server->primary_server;
+				cifs_signal_cifsd_for_reconnect(pserver, false);
+
+skip_terminate:
+				mutex_unlock(&ses->session_mutex);
+				rc = -EHOSTDOWN;
+				goto out;
+			} else {
+				cifs_server_dbg(VFS, "does not support " \
+					 "multichannel anymore. disabling all other channels\n");
+				cifs_disable_secondary_channels(ses);
+			}
+		}
+
 		rc = cifs_setup_session(0, ses, server, nls_codepage);
 		if ((rc == -EACCES) && !tcon->retry) {
 			mutex_unlock(&ses->session_mutex);
@@ -307,15 +375,41 @@ skip_sess_setup:
 		tcon->need_reopen_files = true;
 
 	rc = cifs_tree_connect(0, tcon, nls_codepage);
-	mutex_unlock(&ses->session_mutex);
 
 	cifs_dbg(FYI, "reconnect tcon rc = %d\n", rc);
 	if (rc) {
 		/* If sess reconnected but tcon didn't, something strange ... */
+		mutex_unlock(&ses->session_mutex);
 		cifs_dbg(VFS, "reconnect tcon failed rc = %d\n", rc);
 		goto out;
 	}
 
+	if (!rc &&
+	    (server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
+		mutex_unlock(&ses->session_mutex);
+
+		/*
+		 * query server network interfaces, in case they change
+		 */
+		xid = get_xid();
+		rc = SMB3_request_interfaces(xid, tcon, false);
+		free_xid(xid);
+
+		if (rc)
+			cifs_dbg(FYI, "%s: failed to query server interfaces: %d\n",
+				 __func__, rc);
+
+		if (ses->chan_max > ses->chan_count &&
+		    !SERVER_IS_CHAN(server)) {
+			if (ses->chan_count == 1)
+				cifs_server_dbg(VFS, "supports multichannel now\n");
+
+			cifs_try_adding_channels(ses);
+		}
+	} else {
+		mutex_unlock(&ses->session_mutex);
+	}
+
 	if (smb2_command != SMB2_INTERNAL_CMD)
 		mod_delayed_work(cifsiod_wq, &server->reconnect, 0);
 
@@ -376,10 +470,15 @@ static int __smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
 				 void **request_buf, unsigned int *total_len)
 {
 	/* BB eventually switch this to SMB2 specific small buf size */
-	if (smb2_command == SMB2_SET_INFO)
+	switch (smb2_command) {
+	case SMB2_SET_INFO:
+	case SMB2_QUERY_INFO:
 		*request_buf = cifs_buf_get();
-	else
+		break;
+	default:
 		*request_buf = cifs_small_buf_get();
+		break;
+	}
 	if (*request_buf == NULL) {
 		/* BB should we add a retry in here if not a writepage? */
 		return -ENOMEM;
@@ -404,7 +503,7 @@ static int smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
 {
 	int rc;
 
-	rc = smb2_reconnect(smb2_command, tcon, server);
+	rc = smb2_reconnect(smb2_command, tcon, server, false);
 	if (rc)
 		return rc;
 
@@ -2141,17 +2240,18 @@ parse_posix_ctxt(struct create_context *cc, struct smb2_file_all_info *info,
 		 posix->nlink, posix->mode, posix->reparse_tag);
 }
 
-void
-smb2_parse_contexts(struct TCP_Server_Info *server,
-		    struct smb2_create_rsp *rsp,
-		    unsigned int *epoch, char *lease_key, __u8 *oplock,
-		    struct smb2_file_all_info *buf,
-		    struct create_posix_rsp *posix)
+int smb2_parse_contexts(struct TCP_Server_Info *server,
+			struct kvec *rsp_iov,
+			unsigned int *epoch,
+			char *lease_key, __u8 *oplock,
+			struct smb2_file_all_info *buf,
+			struct create_posix_rsp *posix)
 {
-	char *data_offset;
+	struct smb2_create_rsp *rsp = rsp_iov->iov_base;
 	struct create_context *cc;
-	unsigned int next;
-	unsigned int remaining;
+	size_t rem, off, len;
+	size_t doff, dlen;
+	size_t noff, nlen;
 	char *name;
 	static const char smb3_create_tag_posix[] = {
 		0x93, 0xAD, 0x25, 0x50, 0x9C,
@@ -2160,45 +2260,63 @@ smb2_parse_contexts(struct TCP_Server_Info *server,
 	};
 
 	*oplock = 0;
-	data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset);
-	remaining = le32_to_cpu(rsp->CreateContextsLength);
-	cc = (struct create_context *)data_offset;
+
+	off = le32_to_cpu(rsp->CreateContextsOffset);
+	rem = le32_to_cpu(rsp->CreateContextsLength);
+	if (check_add_overflow(off, rem, &len) || len > rsp_iov->iov_len)
+		return -EINVAL;
+	cc = (struct create_context *)((u8 *)rsp + off);
 
 	/* Initialize inode number to 0 in case no valid data in qfid context */
 	if (buf)
 		buf->IndexNumber = 0;
 
-	while (remaining >= sizeof(struct create_context)) {
-		name = le16_to_cpu(cc->NameOffset) + (char *)cc;
-		if (le16_to_cpu(cc->NameLength) == 4 &&
-		    strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0)
-			*oplock = server->ops->parse_lease_buf(cc, epoch,
-							   lease_key);
-		else if (buf && (le16_to_cpu(cc->NameLength) == 4) &&
-		    strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0)
-			parse_query_id_ctxt(cc, buf);
-		else if ((le16_to_cpu(cc->NameLength) == 16)) {
-			if (posix &&
-			    memcmp(name, smb3_create_tag_posix, 16) == 0)
+	while (rem >= sizeof(*cc)) {
+		doff = le16_to_cpu(cc->DataOffset);
+		dlen = le32_to_cpu(cc->DataLength);
+		if (check_add_overflow(doff, dlen, &len) || len > rem)
+			return -EINVAL;
+
+		noff = le16_to_cpu(cc->NameOffset);
+		nlen = le16_to_cpu(cc->NameLength);
+		if (noff + nlen >= doff)
+			return -EINVAL;
+
+		name = (char *)cc + noff;
+		switch (nlen) {
+		case 4:
+			if (!strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4)) {
+				*oplock = server->ops->parse_lease_buf(cc, epoch,
+								       lease_key);
+			} else if (buf &&
+				   !strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4)) {
+				parse_query_id_ctxt(cc, buf);
+			}
+			break;
+		case 16:
+			if (posix && !memcmp(name, smb3_create_tag_posix, 16))
 				parse_posix_ctxt(cc, buf, posix);
+			break;
+		default:
+			cifs_dbg(FYI, "%s: unhandled context (nlen=%zu dlen=%zu)\n",
+				 __func__, nlen, dlen);
+			if (IS_ENABLED(CONFIG_CIFS_DEBUG2))
+				cifs_dump_mem("context data: ", cc, dlen);
+			break;
 		}
-		/* else {
-			cifs_dbg(FYI, "Context not matched with len %d\n",
-				le16_to_cpu(cc->NameLength));
-			cifs_dump_mem("Cctxt name: ", name, 4);
-		} */
-
-		next = le32_to_cpu(cc->Next);
-		if (!next)
+
+		off = le32_to_cpu(cc->Next);
+		if (!off)
 			break;
-		remaining -= next;
-		cc = (struct create_context *)((char *)cc + next);
+		if (check_sub_overflow(rem, off, &rem))
+			return -EINVAL;
+		cc = (struct create_context *)((u8 *)cc + off);
 	}
 
 	if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE)
 		*oplock = rsp->OplockLevel;
 
-	return;
+	return 0;
 }
 
 static int
@@ -3029,8 +3147,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	}
 
 
-	smb2_parse_contexts(server, rsp, &oparms->fid->epoch,
-			    oparms->fid->lease_key, oplock, buf, posix);
+	rc = smb2_parse_contexts(server, &rsp_iov, &oparms->fid->epoch,
+				 oparms->fid->lease_key, oplock, buf, posix);
 creat_exit:
 	SMB2_open_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
@@ -3377,12 +3495,10 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	} else {
 		trace_smb3_close_done(xid, persistent_fid, tcon->tid,
 				      ses->Suid);
-		/*
-		 * Note that have to subtract 4 since struct network_open_info
-		 * has a final 4 byte pad that close response does not have
-		 */
 		if (pbuf)
-			memcpy(pbuf, (char *)&rsp->CreationTime, sizeof(*pbuf) - 4);
+			memcpy(&pbuf->network_open_info,
+			       &rsp->network_open_info,
+			       sizeof(pbuf->network_open_info));
 	}
 
 	atomic_dec(&tcon->num_remote_opens);
@@ -3475,8 +3591,13 @@ SMB2_query_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
 	struct smb2_query_info_req *req;
 	struct kvec *iov = rqst->rq_iov;
 	unsigned int total_len;
+	size_t len;
 	int rc;
 
+	if (unlikely(check_add_overflow(input_len, sizeof(*req), &len) ||
+		     len > CIFSMaxBufSize))
+		return -EINVAL;
+
 	rc = smb2_plain_req_init(SMB2_QUERY_INFO, tcon, server,
 				 (void **) &req, &total_len);
 	if (rc)
@@ -3498,7 +3619,7 @@ SMB2_query_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
 
 	iov[0].iov_base = (char *)req;
 	/* 1 for Buffer */
-	iov[0].iov_len = total_len - 1 + input_len;
+	iov[0].iov_len = len;
 	return 0;
 }
 
@@ -3506,7 +3627,7 @@ void
 SMB2_query_info_free(struct smb_rqst *rqst)
 {
 	if (rqst && rqst->rq_iov)
-		cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
+		cifs_buf_release(rqst->rq_iov[0].iov_base); /* request */
 }
 
 static int
@@ -3802,12 +3923,28 @@ void smb2_reconnect_server(struct work_struct *work)
 	int rc;
 	bool resched = false;
 
+	/* first check if ref count has reached 0, if not inc ref count */
+	spin_lock(&cifs_tcp_ses_lock);
+	if (!server->srv_count) {
+		spin_unlock(&cifs_tcp_ses_lock);
+		return;
+	}
+	server->srv_count++;
+	spin_unlock(&cifs_tcp_ses_lock);
+
 	/* If server is a channel, select the primary channel */
 	pserver = SERVER_IS_CHAN(server) ? server->primary_server : server;
 
 	/* Prevent simultaneous reconnects that can corrupt tcon->rlist list */
 	mutex_lock(&pserver->reconnect_mutex);
 
+	/* if the server is marked for termination, drop the ref count here */
+	if (server->terminate) {
+		cifs_put_tcp_session(server, true);
+		mutex_unlock(&pserver->reconnect_mutex);
+		return;
+	}
+
 	INIT_LIST_HEAD(&tmp_list);
 	INIT_LIST_HEAD(&tmp_ses_list);
 	cifs_dbg(FYI, "Reconnecting tcons and channels\n");
@@ -3852,17 +3989,10 @@ void smb2_reconnect_server(struct work_struct *work)
 		}
 		spin_unlock(&ses->chan_lock);
 	}
-	/*
-	 * Get the reference to server struct to be sure that the last call of
-	 * cifs_put_tcon() in the loop below won't release the server pointer.
-	 */
-	if (tcon_exist || ses_exist)
-		server->srv_count++;
-
 	spin_unlock(&cifs_tcp_ses_lock);
 
 	list_for_each_entry_safe(tcon, tcon2, &tmp_list, rlist) {
-		rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon, server);
+		rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon, server, true);
 		if (!rc)
 			cifs_reopen_persistent_handles(tcon);
 		else
@@ -3895,7 +4025,7 @@ void smb2_reconnect_server(struct work_struct *work)
 	/* now reconnect sessions for necessary channels */
 	list_for_each_entry_safe(ses, ses2, &tmp_ses_list, rlist) {
 		tcon->ses = ses;
-		rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon, server);
+		rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon, server, true);
 		if (rc)
 			resched = true;
 		list_del_init(&ses->rlist);
@@ -3910,8 +4040,7 @@ done:
 	mutex_unlock(&pserver->reconnect_mutex);
 
 	/* now we can safely release srv struct */
-	if (tcon_exist || ses_exist)
-		cifs_put_tcp_session(server, 1);
+	cifs_put_tcp_session(server, true);
 }
 
 int
@@ -5373,6 +5502,11 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon,
 	return 0;
 }
 
+static inline void free_qfs_info_req(struct kvec *iov)
+{
+	cifs_buf_release(iov->iov_base);
+}
+
 int
 SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
 	      u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata)
@@ -5404,7 +5538,7 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(iov.iov_base);
+	free_qfs_info_req(&iov);
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
 		goto posix_qfsinf_exit;
@@ -5455,7 +5589,7 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(iov.iov_base);
+	free_qfs_info_req(&iov);
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
 		goto qfsinf_exit;
@@ -5522,7 +5656,7 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = cifs_send_recv(xid, ses, server,
 			    &rqst, &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(iov.iov_base);
+	free_qfs_info_req(&iov);
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
 		goto qfsattr_exit;
diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h
index 220994d0a0f7f6..db08194484e06c 100644
--- a/fs/smb/client/smb2pdu.h
+++ b/fs/smb/client/smb2pdu.h
@@ -319,13 +319,15 @@ struct smb2_file_reparse_point_info {
 } __packed;
 
 struct smb2_file_network_open_info {
-	__le64 CreationTime;
-	__le64 LastAccessTime;
-	__le64 LastWriteTime;
-	__le64 ChangeTime;
-	__le64 AllocationSize;
-	__le64 EndOfFile;
-	__le32 Attributes;
+	struct_group(network_open_info,
+		__le64 CreationTime;
+		__le64 LastAccessTime;
+		__le64 LastWriteTime;
+		__le64 ChangeTime;
+		__le64 AllocationSize;
+		__le64 EndOfFile;
+		__le32 Attributes;
+	);
 	__le32 Reserved;
 } __packed; /* level 34 Query also similar returned in close rsp and open rsp */
 
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 46eff9ec302aad..0e371f7e2854b9 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -251,11 +251,13 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *);
 
 extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *,
 					enum securityEnum);
-extern void smb2_parse_contexts(struct TCP_Server_Info *server,
-				struct smb2_create_rsp *rsp,
-				unsigned int *epoch, char *lease_key,
-				__u8 *oplock, struct smb2_file_all_info *buf,
-				struct create_posix_rsp *posix);
+int smb2_parse_contexts(struct TCP_Server_Info *server,
+			struct kvec *rsp_iov,
+			unsigned int *epoch,
+			char *lease_key, __u8 *oplock,
+			struct smb2_file_all_info *buf,
+			struct create_posix_rsp *posix);
+
 extern int smb3_encryption_required(const struct cifs_tcon *tcon);
 extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length,
 			     struct kvec *iov, unsigned int min_buf_size);
diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c
index 23c50ed7d4b590..5a3ca62d2f07f7 100644
--- a/fs/smb/client/smb2transport.c
+++ b/fs/smb/client/smb2transport.c
@@ -413,7 +413,13 @@ generate_smb3signingkey(struct cifs_ses *ses,
 		      ses->ses_status == SES_GOOD);
 
 	chan_index = cifs_ses_get_chan_index(ses, server);
-	/* TODO: introduce ref counting for channels when the can be freed */
+	if (chan_index == CIFS_INVAL_CHAN_INDEX) {
+		spin_unlock(&ses->chan_lock);
+		spin_unlock(&ses->ses_lock);
+
+		return -EINVAL;
+	}
+
 	spin_unlock(&ses->chan_lock);
 	spin_unlock(&ses->ses_lock);
 
@@ -452,6 +458,8 @@ generate_smb3signingkey(struct cifs_ses *ses,
 				  ptriplet->encryption.context,
 				  ses->smb3encryptionkey,
 				  SMB3_ENC_DEC_KEY_SIZE);
+		if (rc)
+			return rc;
 		rc = generate_key(ses, ptriplet->decryption.label,
 				  ptriplet->decryption.context,
 				  ses->smb3decryptionkey,
@@ -460,9 +468,6 @@ generate_smb3signingkey(struct cifs_ses *ses,
 			return rc;
 	}
 
-	if (rc)
-		return rc;
-
 #ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS
 	cifs_dbg(VFS, "%s: dumping generated AES session keys\n", __func__);
 	/*
diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
index d553b7a54621bc..4f717ad7c21b42 100644
--- a/fs/smb/client/transport.c
+++ b/fs/smb/client/transport.c
@@ -1023,7 +1023,7 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses)
 	spin_lock(&ses->chan_lock);
 	for (i = 0; i < ses->chan_count; i++) {
 		server = ses->chans[i].server;
-		if (!server)
+		if (!server || server->terminate)
 			continue;
 
 		/*
diff --git a/fs/smb/client/xattr.c b/fs/smb/client/xattr.c
index ac199160bce6d8..6780aa3e98a194 100644
--- a/fs/smb/client/xattr.c
+++ b/fs/smb/client/xattr.c
@@ -150,10 +150,13 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
 			goto out;
 
-		if (pTcon->ses->server->ops->set_EA)
+		if (pTcon->ses->server->ops->set_EA) {
 			rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
 				full_path, name, value, (__u16)size,
 				cifs_sb->local_nls, cifs_sb);
+			if (rc == 0)
+				inode_set_ctime_current(inode);
+		}
 		break;
 
 	case XATTR_CIFS_ACL:
diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h
index 8983f45f8430f7..57f2343164a34d 100644
--- a/fs/smb/common/smb2pdu.h
+++ b/fs/smb/common/smb2pdu.h
@@ -702,13 +702,16 @@ struct smb2_close_rsp {
 	__le16 StructureSize; /* 60 */
 	__le16 Flags;
 	__le32 Reserved;
-	__le64 CreationTime;
-	__le64 LastAccessTime;
-	__le64 LastWriteTime;
-	__le64 ChangeTime;
-	__le64 AllocationSize;	/* Beginning of FILE_STANDARD_INFO equivalent */
-	__le64 EndOfFile;
-	__le32 Attributes;
+	struct_group(network_open_info,
+		__le64 CreationTime;
+		__le64 LastAccessTime;
+		__le64 LastWriteTime;
+		__le64 ChangeTime;
+		/* Beginning of FILE_STANDARD_INFO equivalent */
+		__le64 AllocationSize;
+		__le64 EndOfFile;
+		__le32 Attributes;
+	);
 } __packed;
 
 
@@ -1142,7 +1145,7 @@ struct smb2_server_client_notification {
 #define SMB2_CREATE_SD_BUFFER			"SecD" /* security descriptor */
 #define SMB2_CREATE_DURABLE_HANDLE_REQUEST	"DHnQ"
 #define SMB2_CREATE_DURABLE_HANDLE_RECONNECT	"DHnC"
-#define SMB2_CREATE_ALLOCATION_SIZE		"AISi"
+#define SMB2_CREATE_ALLOCATION_SIZE		"AlSi"
 #define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc"
 #define SMB2_CREATE_TIMEWARP_REQUEST		"TWrp"
 #define SMB2_CREATE_QUERY_ON_DISK_ID		"QFid"
@@ -1250,6 +1253,7 @@ struct create_mxac_rsp {
 #define SMB2_LEASE_WRITE_CACHING_LE		cpu_to_le32(0x04)
 
 #define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE	cpu_to_le32(0x02)
+#define SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE	cpu_to_le32(0x04)
 
 #define SMB2_LEASE_KEY_SIZE			16
 
diff --git a/fs/smb/server/ksmbd_work.c b/fs/smb/server/ksmbd_work.c
index a2ed441e837ae4..d7c676c151e209 100644
--- a/fs/smb/server/ksmbd_work.c
+++ b/fs/smb/server/ksmbd_work.c
@@ -56,6 +56,9 @@ void ksmbd_free_work_struct(struct ksmbd_work *work)
 	kfree(work->tr_buf);
 	kvfree(work->request_buf);
 	kfree(work->iov);
+	if (!list_empty(&work->interim_entry))
+		list_del(&work->interim_entry);
+
 	if (work->async_id)
 		ksmbd_release_id(&work->conn->async_ida, work->async_id);
 	kmem_cache_free(work_cache, work);
@@ -106,7 +109,7 @@ static inline void __ksmbd_iov_pin(struct ksmbd_work *work, void *ib,
 static int __ksmbd_iov_pin_rsp(struct ksmbd_work *work, void *ib, int len,
 			       void *aux_buf, unsigned int aux_size)
 {
-	struct aux_read *ar;
+	struct aux_read *ar = NULL;
 	int need_iov_cnt = 1;
 
 	if (aux_size) {
@@ -123,8 +126,11 @@ static int __ksmbd_iov_pin_rsp(struct ksmbd_work *work, void *ib, int len,
 		new = krealloc(work->iov,
 			       sizeof(struct kvec) * work->iov_alloc_cnt,
 			       GFP_KERNEL | __GFP_ZERO);
-		if (!new)
+		if (!new) {
+			kfree(ar);
+			work->iov_alloc_cnt -= 4;
 			return -ENOMEM;
+		}
 		work->iov = new;
 	}
 
diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index 9bc0103720f57c..562b180459a1a8 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -102,9 +102,10 @@ static int alloc_lease(struct oplock_info *opinfo, struct lease_ctx_info *lctx)
 	lease->new_state = 0;
 	lease->flags = lctx->flags;
 	lease->duration = lctx->duration;
+	lease->is_dir = lctx->is_dir;
 	memcpy(lease->parent_lease_key, lctx->parent_lease_key, SMB2_LEASE_KEY_SIZE);
 	lease->version = lctx->version;
-	lease->epoch = 0;
+	lease->epoch = le16_to_cpu(lctx->epoch);
 	INIT_LIST_HEAD(&opinfo->lease_entry);
 	opinfo->o_lease = lease;
 
@@ -395,8 +396,8 @@ void close_id_del_oplock(struct ksmbd_file *fp)
 {
 	struct oplock_info *opinfo;
 
-	if (S_ISDIR(file_inode(fp->filp)->i_mode))
-		return;
+	if (fp->reserve_lease_break)
+		smb_lazy_parent_lease_break_close(fp);
 
 	opinfo = opinfo_get(fp);
 	if (!opinfo)
@@ -543,12 +544,13 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci,
 			/* upgrading lease */
 			if ((atomic_read(&ci->op_count) +
 			     atomic_read(&ci->sop_count)) == 1) {
-				if (lease->state ==
-				    (lctx->req_state & lease->state)) {
+				if (lease->state != SMB2_LEASE_NONE_LE &&
+				    lease->state == (lctx->req_state & lease->state)) {
 					lease->state |= lctx->req_state;
 					if (lctx->req_state &
 						SMB2_LEASE_WRITE_CACHING_LE)
 						lease_read_to_write(opinfo);
+
 				}
 			} else if ((atomic_read(&ci->op_count) +
 				    atomic_read(&ci->sop_count)) > 1) {
@@ -833,7 +835,8 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo)
 					     interim_entry);
 			setup_async_work(in_work, NULL, NULL);
 			smb2_send_interim_resp(in_work, STATUS_PENDING);
-			list_del(&in_work->interim_entry);
+			list_del_init(&in_work->interim_entry);
+			release_async_work(in_work);
 		}
 		INIT_WORK(&work->work, __smb2_lease_break_noti);
 		ksmbd_queue_work(work);
@@ -899,7 +902,8 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level)
 					lease->new_state =
 						SMB2_LEASE_READ_CACHING_LE;
 			} else {
-				if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE)
+				if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE &&
+						!lease->is_dir)
 					lease->new_state =
 						SMB2_LEASE_READ_CACHING_LE;
 				else
@@ -1031,6 +1035,7 @@ static void copy_lease(struct oplock_info *op1, struct oplock_info *op2)
 	       SMB2_LEASE_KEY_SIZE);
 	lease2->duration = lease1->duration;
 	lease2->flags = lease1->flags;
+	lease2->epoch = lease1->epoch++;
 }
 
 static int add_lease_global_list(struct oplock_info *opinfo)
@@ -1080,6 +1085,89 @@ static void set_oplock_level(struct oplock_info *opinfo, int level,
 	}
 }
 
+void smb_send_parent_lease_break_noti(struct ksmbd_file *fp,
+				      struct lease_ctx_info *lctx)
+{
+	struct oplock_info *opinfo;
+	struct ksmbd_inode *p_ci = NULL;
+
+	if (lctx->version != 2)
+		return;
+
+	p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent);
+	if (!p_ci)
+		return;
+
+	read_lock(&p_ci->m_lock);
+	list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) {
+		if (!opinfo->is_lease)
+			continue;
+
+		if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE &&
+		    (!(lctx->flags & SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) ||
+		     !compare_guid_key(opinfo, fp->conn->ClientGUID,
+				      lctx->parent_lease_key))) {
+			if (!atomic_inc_not_zero(&opinfo->refcount))
+				continue;
+
+			atomic_inc(&opinfo->conn->r_count);
+			if (ksmbd_conn_releasing(opinfo->conn)) {
+				atomic_dec(&opinfo->conn->r_count);
+				continue;
+			}
+
+			read_unlock(&p_ci->m_lock);
+			oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE);
+			opinfo_conn_put(opinfo);
+			read_lock(&p_ci->m_lock);
+		}
+	}
+	read_unlock(&p_ci->m_lock);
+
+	ksmbd_inode_put(p_ci);
+}
+
+void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp)
+{
+	struct oplock_info *opinfo;
+	struct ksmbd_inode *p_ci = NULL;
+
+	rcu_read_lock();
+	opinfo = rcu_dereference(fp->f_opinfo);
+	rcu_read_unlock();
+
+	if (!opinfo->is_lease || opinfo->o_lease->version != 2)
+		return;
+
+	p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent);
+	if (!p_ci)
+		return;
+
+	read_lock(&p_ci->m_lock);
+	list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) {
+		if (!opinfo->is_lease)
+			continue;
+
+		if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE) {
+			if (!atomic_inc_not_zero(&opinfo->refcount))
+				continue;
+
+			atomic_inc(&opinfo->conn->r_count);
+			if (ksmbd_conn_releasing(opinfo->conn)) {
+				atomic_dec(&opinfo->conn->r_count);
+				continue;
+			}
+			read_unlock(&p_ci->m_lock);
+			oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE);
+			opinfo_conn_put(opinfo);
+			read_lock(&p_ci->m_lock);
+		}
+	}
+	read_unlock(&p_ci->m_lock);
+
+	ksmbd_inode_put(p_ci);
+}
+
 /**
  * smb_grant_oplock() - handle oplock/lease request on file open
  * @work:		smb work
@@ -1103,10 +1191,6 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid,
 	bool prev_op_has_lease;
 	__le32 prev_op_state = 0;
 
-	/* not support directory lease */
-	if (S_ISDIR(file_inode(fp->filp)->i_mode))
-		return 0;
-
 	opinfo = alloc_opinfo(work, pid, tid);
 	if (!opinfo)
 		return -ENOMEM;
@@ -1363,6 +1447,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease)
 		memcpy(buf->lcontext.LeaseKey, lease->lease_key,
 		       SMB2_LEASE_KEY_SIZE);
 		buf->lcontext.LeaseFlags = lease->flags;
+		buf->lcontext.Epoch = cpu_to_le16(++lease->epoch);
 		buf->lcontext.LeaseState = lease->state;
 		memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key,
 		       SMB2_LEASE_KEY_SIZE);
@@ -1399,10 +1484,11 @@ void create_lease_buf(u8 *rbuf, struct lease *lease)
 /**
  * parse_lease_state() - parse lease context containted in file open request
  * @open_req:	buffer containing smb2 file open(create) request
+ * @is_dir:	whether leasing file is directory
  *
  * Return:  oplock state, -ENOENT if create lease context not found
  */
-struct lease_ctx_info *parse_lease_state(void *open_req)
+struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir)
 {
 	struct create_context *cc;
 	struct smb2_create_req *req = (struct smb2_create_req *)open_req;
@@ -1420,8 +1506,14 @@ struct lease_ctx_info *parse_lease_state(void *open_req)
 		struct create_lease_v2 *lc = (struct create_lease_v2 *)cc;
 
 		memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
-		lreq->req_state = lc->lcontext.LeaseState;
+		if (is_dir) {
+			lreq->req_state = lc->lcontext.LeaseState &
+				~SMB2_LEASE_WRITE_CACHING_LE;
+			lreq->is_dir = true;
+		} else
+			lreq->req_state = lc->lcontext.LeaseState;
 		lreq->flags = lc->lcontext.LeaseFlags;
+		lreq->epoch = lc->lcontext.Epoch;
 		lreq->duration = lc->lcontext.LeaseDuration;
 		memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey,
 				SMB2_LEASE_KEY_SIZE);
diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h
index 4b0fe6da76940f..5b93ea9196c013 100644
--- a/fs/smb/server/oplock.h
+++ b/fs/smb/server/oplock.h
@@ -34,7 +34,9 @@ struct lease_ctx_info {
 	__le32			flags;
 	__le64			duration;
 	__u8			parent_lease_key[SMB2_LEASE_KEY_SIZE];
+	__le16			epoch;
 	int			version;
+	bool			is_dir;
 };
 
 struct lease_table {
@@ -53,6 +55,7 @@ struct lease {
 	__u8			parent_lease_key[SMB2_LEASE_KEY_SIZE];
 	int			version;
 	unsigned short		epoch;
+	bool			is_dir;
 	struct lease_table	*l_lb;
 };
 
@@ -108,7 +111,7 @@ void opinfo_put(struct oplock_info *opinfo);
 
 /* Lease related functions */
 void create_lease_buf(u8 *rbuf, struct lease *lease);
-struct lease_ctx_info *parse_lease_state(void *open_req);
+struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir);
 __u8 smb2_map_lease_to_oplock(__le32 lease_state);
 int lease_read_to_write(struct oplock_info *opinfo);
 
@@ -124,4 +127,7 @@ struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn,
 int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci,
 			struct lease_ctx_info *lctx);
 void destroy_lease_table(struct ksmbd_conn *conn);
+void smb_send_parent_lease_break_noti(struct ksmbd_file *fp,
+				      struct lease_ctx_info *lctx);
+void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp);
 #endif /* __KSMBD_OPLOCK_H */
diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c
index aed7704a067286..27a9dce3e03abe 100644
--- a/fs/smb/server/smb2ops.c
+++ b/fs/smb/server/smb2ops.c
@@ -221,7 +221,8 @@ void init_smb3_0_server(struct ksmbd_conn *conn)
 	conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
-		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING;
+		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING |
+			SMB2_GLOBAL_CAP_DIRECTORY_LEASING;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION &&
 	    conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)
@@ -245,7 +246,8 @@ void init_smb3_02_server(struct ksmbd_conn *conn)
 	conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
-		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING;
+		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING |
+			SMB2_GLOBAL_CAP_DIRECTORY_LEASING;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION ||
 	    (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) &&
@@ -270,7 +272,8 @@ int init_smb3_11_server(struct ksmbd_conn *conn)
 	conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
-		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING;
+		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING |
+			SMB2_GLOBAL_CAP_DIRECTORY_LEASING;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION ||
 	    (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) &&
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 658209839729ce..652ab429bf2e9c 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -657,13 +657,9 @@ smb2_get_name(const char *src, const int maxlen, struct nls_table *local_nls)
 
 int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg)
 {
-	struct smb2_hdr *rsp_hdr;
 	struct ksmbd_conn *conn = work->conn;
 	int id;
 
-	rsp_hdr = ksmbd_resp_buf_next(work);
-	rsp_hdr->Flags |= SMB2_FLAGS_ASYNC_COMMAND;
-
 	id = ksmbd_acquire_async_msg_id(&conn->async_ida);
 	if (id < 0) {
 		pr_err("Failed to alloc async message id\n");
@@ -671,7 +667,6 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg)
 	}
 	work->asynchronous = true;
 	work->async_id = id;
-	rsp_hdr->Id.AsyncId = cpu_to_le64(id);
 
 	ksmbd_debug(SMB,
 		    "Send interim Response to inform async request id : %d\n",
@@ -723,6 +718,8 @@ void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status)
 	       __SMB2_HEADER_STRUCTURE_SIZE);
 
 	rsp_hdr = smb2_get_msg(in_work->response_buf);
+	rsp_hdr->Flags |= SMB2_FLAGS_ASYNC_COMMAND;
+	rsp_hdr->Id.AsyncId = cpu_to_le64(work->async_id);
 	smb2_set_err_rsp(in_work);
 	rsp_hdr->Status = status;
 
@@ -2380,7 +2377,8 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len,
 			rc = 0;
 		} else {
 			rc = ksmbd_vfs_setxattr(idmap, path, attr_name, value,
-						le16_to_cpu(eabuf->EaValueLength), 0);
+						le16_to_cpu(eabuf->EaValueLength),
+						0, true);
 			if (rc < 0) {
 				ksmbd_debug(SMB,
 					    "ksmbd_vfs_setxattr is failed(%d)\n",
@@ -2443,7 +2441,7 @@ static noinline int smb2_set_stream_name_xattr(const struct path *path,
 		return -EBADF;
 	}
 
-	rc = ksmbd_vfs_setxattr(idmap, path, xattr_stream_name, NULL, 0, 0);
+	rc = ksmbd_vfs_setxattr(idmap, path, xattr_stream_name, NULL, 0, 0, false);
 	if (rc < 0)
 		pr_err("Failed to store XATTR stream name :%d\n", rc);
 	return 0;
@@ -2518,7 +2516,7 @@ static void smb2_new_xattrs(struct ksmbd_tree_connect *tcon, const struct path *
 	da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME |
 		XATTR_DOSINFO_ITIME;
 
-	rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da);
+	rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da, true);
 	if (rc)
 		ksmbd_debug(SMB, "failed to store file attribute into xattr\n");
 }
@@ -2608,7 +2606,7 @@ static int smb2_create_sd_buffer(struct ksmbd_work *work,
 	    sizeof(struct create_sd_buf_req))
 		return -EINVAL;
 	return set_info_sec(work->conn, work->tcon, path, &sd_buf->ntsd,
-			    le32_to_cpu(sd_buf->ccontext.DataLength), true);
+			    le32_to_cpu(sd_buf->ccontext.DataLength), true, false);
 }
 
 static void ksmbd_acls_fattr(struct smb_fattr *fattr,
@@ -2690,7 +2688,7 @@ int smb2_open(struct ksmbd_work *work)
 		    *(char *)req->Buffer == '\\') {
 			pr_err("not allow directory name included leading slash\n");
 			rc = -EINVAL;
-			goto err_out1;
+			goto err_out2;
 		}
 
 		name = smb2_get_name(req->Buffer,
@@ -2701,7 +2699,7 @@ int smb2_open(struct ksmbd_work *work)
 			if (rc != -ENOMEM)
 				rc = -ENOENT;
 			name = NULL;
-			goto err_out1;
+			goto err_out2;
 		}
 
 		ksmbd_debug(SMB, "converted name = %s\n", name);
@@ -2709,48 +2707,44 @@ int smb2_open(struct ksmbd_work *work)
 			if (!test_share_config_flag(work->tcon->share_conf,
 						    KSMBD_SHARE_FLAG_STREAMS)) {
 				rc = -EBADF;
-				goto err_out1;
+				goto err_out2;
 			}
 			rc = parse_stream_name(name, &stream_name, &s_type);
 			if (rc < 0)
-				goto err_out1;
+				goto err_out2;
 		}
 
 		rc = ksmbd_validate_filename(name);
 		if (rc < 0)
-			goto err_out1;
+			goto err_out2;
 
 		if (ksmbd_share_veto_filename(share, name)) {
 			rc = -ENOENT;
 			ksmbd_debug(SMB, "Reject open(), vetoed file: %s\n",
 				    name);
-			goto err_out1;
+			goto err_out2;
 		}
 	} else {
 		name = kstrdup("", GFP_KERNEL);
 		if (!name) {
 			rc = -ENOMEM;
-			goto err_out1;
+			goto err_out2;
 		}
 	}
 
-	req_op_level = req->RequestedOplockLevel;
-	if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE)
-		lc = parse_lease_state(req);
-
 	if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE)) {
 		pr_err("Invalid impersonationlevel : 0x%x\n",
 		       le32_to_cpu(req->ImpersonationLevel));
 		rc = -EIO;
 		rsp->hdr.Status = STATUS_BAD_IMPERSONATION_LEVEL;
-		goto err_out1;
+		goto err_out2;
 	}
 
 	if (req->CreateOptions && !(req->CreateOptions & CREATE_OPTIONS_MASK_LE)) {
 		pr_err("Invalid create options : 0x%x\n",
 		       le32_to_cpu(req->CreateOptions));
 		rc = -EINVAL;
-		goto err_out1;
+		goto err_out2;
 	} else {
 		if (req->CreateOptions & FILE_SEQUENTIAL_ONLY_LE &&
 		    req->CreateOptions & FILE_RANDOM_ACCESS_LE)
@@ -2760,13 +2754,13 @@ int smb2_open(struct ksmbd_work *work)
 		    (FILE_OPEN_BY_FILE_ID_LE | CREATE_TREE_CONNECTION |
 		     FILE_RESERVE_OPFILTER_LE)) {
 			rc = -EOPNOTSUPP;
-			goto err_out1;
+			goto err_out2;
 		}
 
 		if (req->CreateOptions & FILE_DIRECTORY_FILE_LE) {
 			if (req->CreateOptions & FILE_NON_DIRECTORY_FILE_LE) {
 				rc = -EINVAL;
-				goto err_out1;
+				goto err_out2;
 			} else if (req->CreateOptions & FILE_NO_COMPRESSION_LE) {
 				req->CreateOptions = ~(FILE_NO_COMPRESSION_LE);
 			}
@@ -2778,21 +2772,21 @@ int smb2_open(struct ksmbd_work *work)
 		pr_err("Invalid create disposition : 0x%x\n",
 		       le32_to_cpu(req->CreateDisposition));
 		rc = -EINVAL;
-		goto err_out1;
+		goto err_out2;
 	}
 
 	if (!(req->DesiredAccess & DESIRED_ACCESS_MASK)) {
 		pr_err("Invalid desired access : 0x%x\n",
 		       le32_to_cpu(req->DesiredAccess));
 		rc = -EACCES;
-		goto err_out1;
+		goto err_out2;
 	}
 
 	if (req->FileAttributes && !(req->FileAttributes & FILE_ATTRIBUTE_MASK_LE)) {
 		pr_err("Invalid file attribute : 0x%x\n",
 		       le32_to_cpu(req->FileAttributes));
 		rc = -EINVAL;
-		goto err_out1;
+		goto err_out2;
 	}
 
 	if (req->CreateContextsOffset) {
@@ -2800,19 +2794,19 @@ int smb2_open(struct ksmbd_work *work)
 		context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER, 4);
 		if (IS_ERR(context)) {
 			rc = PTR_ERR(context);
-			goto err_out1;
+			goto err_out2;
 		} else if (context) {
 			ea_buf = (struct create_ea_buf_req *)context;
 			if (le16_to_cpu(context->DataOffset) +
 			    le32_to_cpu(context->DataLength) <
 			    sizeof(struct create_ea_buf_req)) {
 				rc = -EINVAL;
-				goto err_out1;
+				goto err_out2;
 			}
 			if (req->CreateOptions & FILE_NO_EA_KNOWLEDGE_LE) {
 				rsp->hdr.Status = STATUS_ACCESS_DENIED;
 				rc = -EACCES;
-				goto err_out1;
+				goto err_out2;
 			}
 		}
 
@@ -2820,7 +2814,7 @@ int smb2_open(struct ksmbd_work *work)
 						 SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST, 4);
 		if (IS_ERR(context)) {
 			rc = PTR_ERR(context);
-			goto err_out1;
+			goto err_out2;
 		} else if (context) {
 			ksmbd_debug(SMB,
 				    "get query maximal access context\n");
@@ -2831,11 +2825,11 @@ int smb2_open(struct ksmbd_work *work)
 						 SMB2_CREATE_TIMEWARP_REQUEST, 4);
 		if (IS_ERR(context)) {
 			rc = PTR_ERR(context);
-			goto err_out1;
+			goto err_out2;
 		} else if (context) {
 			ksmbd_debug(SMB, "get timewarp context\n");
 			rc = -EBADF;
-			goto err_out1;
+			goto err_out2;
 		}
 
 		if (tcon->posix_extensions) {
@@ -2843,7 +2837,7 @@ int smb2_open(struct ksmbd_work *work)
 							 SMB2_CREATE_TAG_POSIX, 16);
 			if (IS_ERR(context)) {
 				rc = PTR_ERR(context);
-				goto err_out1;
+				goto err_out2;
 			} else if (context) {
 				struct create_posix *posix =
 					(struct create_posix *)context;
@@ -2851,7 +2845,7 @@ int smb2_open(struct ksmbd_work *work)
 				    le32_to_cpu(context->DataLength) <
 				    sizeof(struct create_posix) - 4) {
 					rc = -EINVAL;
-					goto err_out1;
+					goto err_out2;
 				}
 				ksmbd_debug(SMB, "get posix context\n");
 
@@ -2863,7 +2857,7 @@ int smb2_open(struct ksmbd_work *work)
 
 	if (ksmbd_override_fsids(work)) {
 		rc = -ENOMEM;
-		goto err_out1;
+		goto err_out2;
 	}
 
 	rc = ksmbd_vfs_kern_path_locked(work, name, LOOKUP_NO_SYMLINKS,
@@ -3038,7 +3032,7 @@ int smb2_open(struct ksmbd_work *work)
 		}
 	}
 
-	rc = ksmbd_query_inode_status(d_inode(path.dentry->d_parent));
+	rc = ksmbd_query_inode_status(path.dentry->d_parent);
 	if (rc == KSMBD_INODE_STATUS_PENDING_DELETE) {
 		rc = -EBUSY;
 		goto err_out;
@@ -3152,7 +3146,8 @@ int smb2_open(struct ksmbd_work *work)
 								    idmap,
 								    &path,
 								    pntsd,
-								    pntsd_size);
+								    pntsd_size,
+								    false);
 					kfree(pntsd);
 					if (rc)
 						pr_err("failed to store ntacl in xattr : %d\n",
@@ -3175,11 +3170,6 @@ int smb2_open(struct ksmbd_work *work)
 
 	fp->attrib_only = !(req->DesiredAccess & ~(FILE_READ_ATTRIBUTES_LE |
 			FILE_WRITE_ATTRIBUTES_LE | FILE_SYNCHRONIZE_LE));
-	if (!S_ISDIR(file_inode(filp)->i_mode) && open_flags & O_TRUNC &&
-	    !fp->attrib_only && !stream_name) {
-		smb_break_all_oplock(work, fp);
-		need_truncate = 1;
-	}
 
 	/* fp should be searchable through ksmbd_inode.m_fp_list
 	 * after daccess, saccess, attrib_only, and stream are
@@ -3195,23 +3185,43 @@ int smb2_open(struct ksmbd_work *work)
 		goto err_out;
 	}
 
+	if (file_present || created)
+		ksmbd_vfs_kern_path_unlock(&parent_path, &path);
+
+	if (!S_ISDIR(file_inode(filp)->i_mode) && open_flags & O_TRUNC &&
+	    !fp->attrib_only && !stream_name) {
+		smb_break_all_oplock(work, fp);
+		need_truncate = 1;
+	}
+
+	req_op_level = req->RequestedOplockLevel;
+	if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE)
+		lc = parse_lease_state(req, S_ISDIR(file_inode(filp)->i_mode));
+
 	share_ret = ksmbd_smb_check_shared_mode(fp->filp, fp);
 	if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_OPLOCKS) ||
 	    (req_op_level == SMB2_OPLOCK_LEVEL_LEASE &&
 	     !(conn->vals->capabilities & SMB2_GLOBAL_CAP_LEASING))) {
 		if (share_ret < 0 && !S_ISDIR(file_inode(fp->filp)->i_mode)) {
 			rc = share_ret;
-			goto err_out;
+			goto err_out1;
 		}
 	} else {
 		if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) {
+			/*
+			 * Compare parent lease using parent key. If there is no
+			 * a lease that has same parent key, Send lease break
+			 * notification.
+			 */
+			smb_send_parent_lease_break_noti(fp, lc);
+
 			req_op_level = smb2_map_lease_to_oplock(lc->req_state);
 			ksmbd_debug(SMB,
 				    "lease req for(%s) req oplock state 0x%x, lease state 0x%x\n",
 				    name, req_op_level, lc->req_state);
 			rc = find_same_lease_key(sess, fp->f_ci, lc);
 			if (rc)
-				goto err_out;
+				goto err_out1;
 		} else if (open_flags == O_RDONLY &&
 			   (req_op_level == SMB2_OPLOCK_LEVEL_BATCH ||
 			    req_op_level == SMB2_OPLOCK_LEVEL_EXCLUSIVE))
@@ -3222,16 +3232,16 @@ int smb2_open(struct ksmbd_work *work)
 				      le32_to_cpu(req->hdr.Id.SyncId.TreeId),
 				      lc, share_ret);
 		if (rc < 0)
-			goto err_out;
+			goto err_out1;
 	}
 
 	if (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE)
 		ksmbd_fd_set_delete_on_close(fp, file_info);
 
 	if (need_truncate) {
-		rc = smb2_create_truncate(&path);
+		rc = smb2_create_truncate(&fp->filp->f_path);
 		if (rc)
-			goto err_out;
+			goto err_out1;
 	}
 
 	if (req->CreateContextsOffset) {
@@ -3241,7 +3251,7 @@ int smb2_open(struct ksmbd_work *work)
 					SMB2_CREATE_ALLOCATION_SIZE, 4);
 		if (IS_ERR(az_req)) {
 			rc = PTR_ERR(az_req);
-			goto err_out;
+			goto err_out1;
 		} else if (az_req) {
 			loff_t alloc_size;
 			int err;
@@ -3250,7 +3260,7 @@ int smb2_open(struct ksmbd_work *work)
 			    le32_to_cpu(az_req->ccontext.DataLength) <
 			    sizeof(struct create_alloc_size_req)) {
 				rc = -EINVAL;
-				goto err_out;
+				goto err_out1;
 			}
 			alloc_size = le64_to_cpu(az_req->AllocationSize);
 			ksmbd_debug(SMB,
@@ -3268,7 +3278,7 @@ int smb2_open(struct ksmbd_work *work)
 		context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID, 4);
 		if (IS_ERR(context)) {
 			rc = PTR_ERR(context);
-			goto err_out;
+			goto err_out1;
 		} else if (context) {
 			ksmbd_debug(SMB, "get query on disk id context\n");
 			query_disk_id = 1;
@@ -3277,7 +3287,7 @@ int smb2_open(struct ksmbd_work *work)
 
 	rc = ksmbd_vfs_getattr(&path, &stat);
 	if (rc)
-		goto err_out;
+		goto err_out1;
 
 	if (stat.result_mask & STATX_BTIME)
 		fp->create_time = ksmbd_UnixTimeToNT(stat.btime);
@@ -3398,13 +3408,13 @@ int smb2_open(struct ksmbd_work *work)
 	}
 
 err_out:
-	if (file_present || created) {
-		inode_unlock(d_inode(parent_path.dentry));
-		path_put(&path);
-		path_put(&parent_path);
-	}
-	ksmbd_revert_fsids(work);
+	if (rc && (file_present || created))
+		ksmbd_vfs_kern_path_unlock(&parent_path, &path);
+
 err_out1:
+	ksmbd_revert_fsids(work);
+
+err_out2:
 	if (!rc) {
 		ksmbd_update_fstate(&work->sess->file_table, fp, FP_INITED);
 		rc = ksmbd_iov_pin_rsp(work, (void *)rsp, iov_len);
@@ -5537,7 +5547,7 @@ static int smb2_rename(struct ksmbd_work *work,
 		rc = ksmbd_vfs_setxattr(file_mnt_idmap(fp->filp),
 					&fp->filp->f_path,
 					xattr_stream_name,
-					NULL, 0, 0);
+					NULL, 0, 0, true);
 		if (rc < 0) {
 			pr_err("failed to store stream name in xattr: %d\n",
 			       rc);
@@ -5630,11 +5640,9 @@ static int smb2_create_link(struct ksmbd_work *work,
 	if (rc)
 		rc = -EINVAL;
 out:
-	if (file_present) {
-		inode_unlock(d_inode(parent_path.dentry));
-		path_put(&path);
-		path_put(&parent_path);
-	}
+	if (file_present)
+		ksmbd_vfs_kern_path_unlock(&parent_path, &path);
+
 	if (!IS_ERR(link_name))
 		kfree(link_name);
 	kfree(pathname);
@@ -5701,7 +5709,8 @@ static int set_file_basic_info(struct ksmbd_file *fp,
 		da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME |
 			XATTR_DOSINFO_ITIME;
 
-		rc = ksmbd_vfs_set_dos_attrib_xattr(idmap, &filp->f_path, &da);
+		rc = ksmbd_vfs_set_dos_attrib_xattr(idmap, &filp->f_path, &da,
+				true);
 		if (rc)
 			ksmbd_debug(SMB,
 				    "failed to restore file attribute in EA\n");
@@ -6013,7 +6022,7 @@ static int smb2_set_info_sec(struct ksmbd_file *fp, int addition_info,
 	fp->saccess |= FILE_SHARE_DELETE_LE;
 
 	return set_info_sec(fp->conn, fp->tcon, &fp->filp->f_path, pntsd,
-			buf_len, false);
+			buf_len, false, true);
 }
 
 /**
@@ -7078,6 +7087,7 @@ skip:
 						      smb2_remove_blocked_lock,
 						      argv);
 				if (rc) {
+					kfree(argv);
 					err = -ENOMEM;
 					goto out;
 				}
@@ -7582,7 +7592,8 @@ static inline int fsctl_set_sparse(struct ksmbd_work *work, u64 id,
 
 		da.attr = le32_to_cpu(fp->f_ci->m_fattr);
 		ret = ksmbd_vfs_set_dos_attrib_xattr(idmap,
-						     &fp->filp->f_path, &da);
+						     &fp->filp->f_path,
+						     &da, true);
 		if (ret)
 			fp->f_ci->m_fattr = old_fattr;
 	}
@@ -8208,6 +8219,11 @@ static void smb21_lease_break_ack(struct ksmbd_work *work)
 			    le32_to_cpu(req->LeaseState));
 	}
 
+	if (ret < 0) {
+		rsp->hdr.Status = err;
+		goto err_out;
+	}
+
 	lease_state = lease->state;
 	opinfo->op_state = OPLOCK_STATE_NONE;
 	wake_up_interruptible_all(&opinfo->oplock_q);
@@ -8215,11 +8231,6 @@ static void smb21_lease_break_ack(struct ksmbd_work *work)
 	wake_up_interruptible_all(&opinfo->oplock_brk);
 	opinfo_put(opinfo);
 
-	if (ret < 0) {
-		rsp->hdr.Status = err;
-		goto err_out;
-	}
-
 	rsp->StructureSize = cpu_to_le16(36);
 	rsp->Reserved = 0;
 	rsp->Flags = 0;
@@ -8231,7 +8242,6 @@ static void smb21_lease_break_ack(struct ksmbd_work *work)
 		return;
 
 err_out:
-	opinfo->op_state = OPLOCK_STATE_NONE;
 	wake_up_interruptible_all(&opinfo->oplock_q);
 	atomic_dec(&opinfo->breaking_cnt);
 	wake_up_interruptible_all(&opinfo->oplock_brk);
diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c
index e6ba1e9b8589aa..6691ae68af0c09 100644
--- a/fs/smb/server/smb_common.c
+++ b/fs/smb/server/smb_common.c
@@ -366,11 +366,22 @@ static int smb1_allocate_rsp_buf(struct ksmbd_work *work)
 	return 0;
 }
 
+/**
+ * set_smb1_rsp_status() - set error type in smb response header
+ * @work:	smb work containing smb response header
+ * @err:	error code to set in response
+ */
+static void set_smb1_rsp_status(struct ksmbd_work *work, __le32 err)
+{
+	work->send_no_response = 1;
+}
+
 static struct smb_version_ops smb1_server_ops = {
 	.get_cmd_val = get_smb1_cmd_val,
 	.init_rsp_hdr = init_smb1_rsp_hdr,
 	.allocate_rsp_buf = smb1_allocate_rsp_buf,
 	.check_user_session = smb1_check_user_session,
+	.set_rsp_status = set_smb1_rsp_status,
 };
 
 static int smb1_negotiate(struct ksmbd_work *work)
diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c
index 6c0305be895e56..1164365533f089 100644
--- a/fs/smb/server/smbacl.c
+++ b/fs/smb/server/smbacl.c
@@ -1107,6 +1107,7 @@ pass:
 		struct smb_acl *pdacl;
 		struct smb_sid *powner_sid = NULL, *pgroup_sid = NULL;
 		int powner_sid_size = 0, pgroup_sid_size = 0, pntsd_size;
+		int pntsd_alloc_size;
 
 		if (parent_pntsd->osidoffset) {
 			powner_sid = (struct smb_sid *)((char *)parent_pntsd +
@@ -1119,9 +1120,10 @@ pass:
 			pgroup_sid_size = 1 + 1 + 6 + (pgroup_sid->num_subauth * 4);
 		}
 
-		pntsd = kzalloc(sizeof(struct smb_ntsd) + powner_sid_size +
-				pgroup_sid_size + sizeof(struct smb_acl) +
-				nt_size, GFP_KERNEL);
+		pntsd_alloc_size = sizeof(struct smb_ntsd) + powner_sid_size +
+			pgroup_sid_size + sizeof(struct smb_acl) + nt_size;
+
+		pntsd = kzalloc(pntsd_alloc_size, GFP_KERNEL);
 		if (!pntsd) {
 			rc = -ENOMEM;
 			goto free_aces_base;
@@ -1136,6 +1138,27 @@ pass:
 		pntsd->gsidoffset = parent_pntsd->gsidoffset;
 		pntsd->dacloffset = parent_pntsd->dacloffset;
 
+		if ((u64)le32_to_cpu(pntsd->osidoffset) + powner_sid_size >
+		    pntsd_alloc_size) {
+			rc = -EINVAL;
+			kfree(pntsd);
+			goto free_aces_base;
+		}
+
+		if ((u64)le32_to_cpu(pntsd->gsidoffset) + pgroup_sid_size >
+		    pntsd_alloc_size) {
+			rc = -EINVAL;
+			kfree(pntsd);
+			goto free_aces_base;
+		}
+
+		if ((u64)le32_to_cpu(pntsd->dacloffset) + sizeof(struct smb_acl) + nt_size >
+		    pntsd_alloc_size) {
+			rc = -EINVAL;
+			kfree(pntsd);
+			goto free_aces_base;
+		}
+
 		if (pntsd->osidoffset) {
 			struct smb_sid *owner_sid = (struct smb_sid *)((char *)pntsd +
 					le32_to_cpu(pntsd->osidoffset));
@@ -1162,7 +1185,7 @@ pass:
 			pntsd_size += sizeof(struct smb_acl) + nt_size;
 		}
 
-		ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, pntsd_size);
+		ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, pntsd_size, false);
 		kfree(pntsd);
 	}
 
@@ -1354,7 +1377,7 @@ err_out:
 
 int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon,
 		 const struct path *path, struct smb_ntsd *pntsd, int ntsd_len,
-		 bool type_check)
+		 bool type_check, bool get_write)
 {
 	int rc;
 	struct smb_fattr fattr = {{0}};
@@ -1414,7 +1437,8 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon,
 	if (test_share_config_flag(tcon->share_conf, KSMBD_SHARE_FLAG_ACL_XATTR)) {
 		/* Update WinACL in xattr */
 		ksmbd_vfs_remove_sd_xattrs(idmap, path);
-		ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, ntsd_len);
+		ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, ntsd_len,
+				get_write);
 	}
 
 out:
diff --git a/fs/smb/server/smbacl.h b/fs/smb/server/smbacl.h
index 49a8c292bd2e81..2b52861707d8c1 100644
--- a/fs/smb/server/smbacl.h
+++ b/fs/smb/server/smbacl.h
@@ -207,7 +207,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path,
 			__le32 *pdaccess, int uid);
 int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon,
 		 const struct path *path, struct smb_ntsd *pntsd, int ntsd_len,
-		 bool type_check);
+		 bool type_check, bool get_write);
 void id_to_sid(unsigned int cid, uint sidtype, struct smb_sid *ssid);
 void ksmbd_init_domain(u32 *sub_auth);
 
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index 1053127f71adfb..4277750a6da1b1 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -97,6 +97,13 @@ static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf,
 		return -ENOENT;
 	}
 
+	err = mnt_want_write(parent_path->mnt);
+	if (err) {
+		path_put(parent_path);
+		putname(filename);
+		return -ENOENT;
+	}
+
 	inode_lock_nested(parent_path->dentry->d_inode, I_MUTEX_PARENT);
 	d = lookup_one_qstr_excl(&last, parent_path->dentry, 0);
 	if (IS_ERR(d))
@@ -123,6 +130,7 @@ static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf,
 
 err_out:
 	inode_unlock(d_inode(parent_path->dentry));
+	mnt_drop_write(parent_path->mnt);
 	path_put(parent_path);
 	putname(filename);
 	return -ENOENT;
@@ -451,7 +459,8 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos,
 				 fp->stream.name,
 				 (void *)stream_buf,
 				 size,
-				 0);
+				 0,
+				 true);
 	if (err < 0)
 		goto out;
 
@@ -508,6 +517,9 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp,
 		}
 	}
 
+	/* Reserve lease break for parent dir at closing time */
+	fp->reserve_lease_break = true;
+
 	/* Do we need to break any of a levelII oplock? */
 	smb_break_all_levII_oplock(work, fp, 1);
 
@@ -593,10 +605,6 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path)
 		goto out_err;
 	}
 
-	err = mnt_want_write(path->mnt);
-	if (err)
-		goto out_err;
-
 	idmap = mnt_idmap(path->mnt);
 	if (S_ISDIR(d_inode(path->dentry)->i_mode)) {
 		err = vfs_rmdir(idmap, d_inode(parent), path->dentry);
@@ -607,7 +615,6 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path)
 		if (err)
 			ksmbd_debug(VFS, "unlink failed, err %d\n", err);
 	}
-	mnt_drop_write(path->mnt);
 
 out_err:
 	ksmbd_revert_fsids(work);
@@ -715,7 +722,7 @@ retry:
 		goto out3;
 	}
 
-	parent_fp = ksmbd_lookup_fd_inode(d_inode(old_child->d_parent));
+	parent_fp = ksmbd_lookup_fd_inode(old_child->d_parent);
 	if (parent_fp) {
 		if (parent_fp->daccess & FILE_DELETE_LE) {
 			pr_err("parent dir is opened with delete access\n");
@@ -907,18 +914,22 @@ ssize_t ksmbd_vfs_getxattr(struct mnt_idmap *idmap,
  * @attr_value:	xattr value to set
  * @attr_size:	size of xattr value
  * @flags:	destination buffer length
+ * @get_write:	get write access to a mount
  *
  * Return:	0 on success, otherwise error
  */
 int ksmbd_vfs_setxattr(struct mnt_idmap *idmap,
 		       const struct path *path, const char *attr_name,
-		       void *attr_value, size_t attr_size, int flags)
+		       void *attr_value, size_t attr_size, int flags,
+		       bool get_write)
 {
 	int err;
 
-	err = mnt_want_write(path->mnt);
-	if (err)
-		return err;
+	if (get_write == true) {
+		err = mnt_want_write(path->mnt);
+		if (err)
+			return err;
+	}
 
 	err = vfs_setxattr(idmap,
 			   path->dentry,
@@ -928,7 +939,8 @@ int ksmbd_vfs_setxattr(struct mnt_idmap *idmap,
 			   flags);
 	if (err)
 		ksmbd_debug(VFS, "setxattr failed, err %d\n", err);
-	mnt_drop_write(path->mnt);
+	if (get_write == true)
+		mnt_drop_write(path->mnt);
 	return err;
 }
 
@@ -1177,9 +1189,10 @@ static int ksmbd_vfs_lookup_in_dir(const struct path *dir, char *name,
 
 /**
  * ksmbd_vfs_kern_path_locked() - lookup a file and get path info
- * @name:	file path that is relative to share
- * @flags:	lookup flags
- * @path:	if lookup succeed, return path info
+ * @name:		file path that is relative to share
+ * @flags:		lookup flags
+ * @parent_path:	if lookup succeed, return parent_path info
+ * @path:		if lookup succeed, return path info
  * @caseless:	caseless filename lookup
  *
  * Return:	0 on success, otherwise error
@@ -1251,6 +1264,13 @@ out1:
 	}
 
 	if (!err) {
+		err = mnt_want_write(parent_path->mnt);
+		if (err) {
+			path_put(path);
+			path_put(parent_path);
+			return err;
+		}
+
 		err = ksmbd_vfs_lock_parent(parent_path->dentry, path->dentry);
 		if (err) {
 			path_put(path);
@@ -1260,6 +1280,14 @@ out1:
 	return err;
 }
 
+void ksmbd_vfs_kern_path_unlock(struct path *parent_path, struct path *path)
+{
+	inode_unlock(d_inode(parent_path->dentry));
+	mnt_drop_write(parent_path->mnt);
+	path_put(path);
+	path_put(parent_path);
+}
+
 struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work,
 					  const char *name,
 					  unsigned int flags,
@@ -1414,7 +1442,8 @@ out:
 int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn,
 			   struct mnt_idmap *idmap,
 			   const struct path *path,
-			   struct smb_ntsd *pntsd, int len)
+			   struct smb_ntsd *pntsd, int len,
+			   bool get_write)
 {
 	int rc;
 	struct ndr sd_ndr = {0}, acl_ndr = {0};
@@ -1474,7 +1503,7 @@ int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn,
 
 	rc = ksmbd_vfs_setxattr(idmap, path,
 				XATTR_NAME_SD, sd_ndr.data,
-				sd_ndr.offset, 0);
+				sd_ndr.offset, 0, get_write);
 	if (rc < 0)
 		pr_err("Failed to store XATTR ntacl :%d\n", rc);
 
@@ -1563,7 +1592,8 @@ free_n_data:
 
 int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap,
 				   const struct path *path,
-				   struct xattr_dos_attrib *da)
+				   struct xattr_dos_attrib *da,
+				   bool get_write)
 {
 	struct ndr n;
 	int err;
@@ -1573,7 +1603,7 @@ int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap,
 		return err;
 
 	err = ksmbd_vfs_setxattr(idmap, path, XATTR_NAME_DOS_ATTRIBUTE,
-				 (void *)n.data, n.offset, 0);
+				 (void *)n.data, n.offset, 0, get_write);
 	if (err)
 		ksmbd_debug(SMB, "failed to store dos attribute in xattr\n");
 	kfree(n.data);
@@ -1845,10 +1875,6 @@ int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap,
 	}
 	posix_state_to_acl(&acl_state, acls->a_entries);
 
-	rc = mnt_want_write(path->mnt);
-	if (rc)
-		goto out_err;
-
 	rc = set_posix_acl(idmap, dentry, ACL_TYPE_ACCESS, acls);
 	if (rc < 0)
 		ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n",
@@ -1860,9 +1886,7 @@ int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap,
 			ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n",
 				    rc);
 	}
-	mnt_drop_write(path->mnt);
 
-out_err:
 	free_acl_state(&acl_state);
 	posix_acl_release(acls);
 	return rc;
@@ -1892,10 +1916,6 @@ int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap,
 		}
 	}
 
-	rc = mnt_want_write(path->mnt);
-	if (rc)
-		goto out_err;
-
 	rc = set_posix_acl(idmap, dentry, ACL_TYPE_ACCESS, acls);
 	if (rc < 0)
 		ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n",
@@ -1907,9 +1927,7 @@ int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap,
 			ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n",
 				    rc);
 	}
-	mnt_drop_write(path->mnt);
 
-out_err:
 	posix_acl_release(acls);
 	return rc;
 }
diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h
index 00968081856e38..cfe1c8092f2302 100644
--- a/fs/smb/server/vfs.h
+++ b/fs/smb/server/vfs.h
@@ -109,7 +109,8 @@ ssize_t ksmbd_vfs_casexattr_len(struct mnt_idmap *idmap,
 				int attr_name_len);
 int ksmbd_vfs_setxattr(struct mnt_idmap *idmap,
 		       const struct path *path, const char *attr_name,
-		       void *attr_value, size_t attr_size, int flags);
+		       void *attr_value, size_t attr_size, int flags,
+		       bool get_write);
 int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name,
 				size_t *xattr_stream_name_size, int s_type);
 int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap,
@@ -117,6 +118,7 @@ int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap,
 int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name,
 			       unsigned int flags, struct path *parent_path,
 			       struct path *path, bool caseless);
+void ksmbd_vfs_kern_path_unlock(struct path *parent_path, struct path *path);
 struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work,
 					  const char *name,
 					  unsigned int flags,
@@ -144,14 +146,16 @@ int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, const struct path *path)
 int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn,
 			   struct mnt_idmap *idmap,
 			   const struct path *path,
-			   struct smb_ntsd *pntsd, int len);
+			   struct smb_ntsd *pntsd, int len,
+			   bool get_write);
 int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn,
 			   struct mnt_idmap *idmap,
 			   struct dentry *dentry,
 			   struct smb_ntsd **pntsd);
 int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap,
 				   const struct path *path,
-				   struct xattr_dos_attrib *da);
+				   struct xattr_dos_attrib *da,
+				   bool get_write);
 int ksmbd_vfs_get_dos_attrib_xattr(struct mnt_idmap *idmap,
 				   struct dentry *dentry,
 				   struct xattr_dos_attrib *da);
diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c
index c91eac6514dd95..4e82ff627d1224 100644
--- a/fs/smb/server/vfs_cache.c
+++ b/fs/smb/server/vfs_cache.c
@@ -66,14 +66,14 @@ static unsigned long inode_hash(struct super_block *sb, unsigned long hashval)
 	return tmp & inode_hash_mask;
 }
 
-static struct ksmbd_inode *__ksmbd_inode_lookup(struct inode *inode)
+static struct ksmbd_inode *__ksmbd_inode_lookup(struct dentry *de)
 {
 	struct hlist_head *head = inode_hashtable +
-		inode_hash(inode->i_sb, inode->i_ino);
+		inode_hash(d_inode(de)->i_sb, (unsigned long)de);
 	struct ksmbd_inode *ci = NULL, *ret_ci = NULL;
 
 	hlist_for_each_entry(ci, head, m_hash) {
-		if (ci->m_inode == inode) {
+		if (ci->m_de == de) {
 			if (atomic_inc_not_zero(&ci->m_count))
 				ret_ci = ci;
 			break;
@@ -84,26 +84,27 @@ static struct ksmbd_inode *__ksmbd_inode_lookup(struct inode *inode)
 
 static struct ksmbd_inode *ksmbd_inode_lookup(struct ksmbd_file *fp)
 {
-	return __ksmbd_inode_lookup(file_inode(fp->filp));
+	return __ksmbd_inode_lookup(fp->filp->f_path.dentry);
 }
 
-static struct ksmbd_inode *ksmbd_inode_lookup_by_vfsinode(struct inode *inode)
+struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d)
 {
 	struct ksmbd_inode *ci;
 
 	read_lock(&inode_hash_lock);
-	ci = __ksmbd_inode_lookup(inode);
+	ci = __ksmbd_inode_lookup(d);
 	read_unlock(&inode_hash_lock);
+
 	return ci;
 }
 
-int ksmbd_query_inode_status(struct inode *inode)
+int ksmbd_query_inode_status(struct dentry *dentry)
 {
 	struct ksmbd_inode *ci;
 	int ret = KSMBD_INODE_STATUS_UNKNOWN;
 
 	read_lock(&inode_hash_lock);
-	ci = __ksmbd_inode_lookup(inode);
+	ci = __ksmbd_inode_lookup(dentry);
 	if (ci) {
 		ret = KSMBD_INODE_STATUS_OK;
 		if (ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS))
@@ -143,7 +144,7 @@ void ksmbd_fd_set_delete_on_close(struct ksmbd_file *fp,
 static void ksmbd_inode_hash(struct ksmbd_inode *ci)
 {
 	struct hlist_head *b = inode_hashtable +
-		inode_hash(ci->m_inode->i_sb, ci->m_inode->i_ino);
+		inode_hash(d_inode(ci->m_de)->i_sb, (unsigned long)ci->m_de);
 
 	hlist_add_head(&ci->m_hash, b);
 }
@@ -157,7 +158,6 @@ static void ksmbd_inode_unhash(struct ksmbd_inode *ci)
 
 static int ksmbd_inode_init(struct ksmbd_inode *ci, struct ksmbd_file *fp)
 {
-	ci->m_inode = file_inode(fp->filp);
 	atomic_set(&ci->m_count, 1);
 	atomic_set(&ci->op_count, 0);
 	atomic_set(&ci->sop_count, 0);
@@ -166,6 +166,7 @@ static int ksmbd_inode_init(struct ksmbd_inode *ci, struct ksmbd_file *fp)
 	INIT_LIST_HEAD(&ci->m_fp_list);
 	INIT_LIST_HEAD(&ci->m_op_list);
 	rwlock_init(&ci->m_lock);
+	ci->m_de = fp->filp->f_path.dentry;
 	return 0;
 }
 
@@ -209,7 +210,7 @@ static void ksmbd_inode_free(struct ksmbd_inode *ci)
 	kfree(ci);
 }
 
-static void ksmbd_inode_put(struct ksmbd_inode *ci)
+void ksmbd_inode_put(struct ksmbd_inode *ci)
 {
 	if (atomic_dec_and_test(&ci->m_count))
 		ksmbd_inode_free(ci);
@@ -488,12 +489,15 @@ struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid)
 	return fp;
 }
 
-struct ksmbd_file *ksmbd_lookup_fd_inode(struct inode *inode)
+struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry)
 {
 	struct ksmbd_file	*lfp;
 	struct ksmbd_inode	*ci;
+	struct inode		*inode = d_inode(dentry);
 
-	ci = ksmbd_inode_lookup_by_vfsinode(inode);
+	read_lock(&inode_hash_lock);
+	ci = __ksmbd_inode_lookup(dentry);
+	read_unlock(&inode_hash_lock);
 	if (!ci)
 		return NULL;
 
diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h
index 03d0bf941216f8..a528f0cc775ae0 100644
--- a/fs/smb/server/vfs_cache.h
+++ b/fs/smb/server/vfs_cache.h
@@ -51,7 +51,7 @@ struct ksmbd_inode {
 	atomic_t			op_count;
 	/* opinfo count for streams */
 	atomic_t			sop_count;
-	struct inode			*m_inode;
+	struct dentry			*m_de;
 	unsigned int			m_flags;
 	struct hlist_node		m_hash;
 	struct list_head		m_fp_list;
@@ -105,6 +105,7 @@ struct ksmbd_file {
 	struct ksmbd_readdir_data	readdir_data;
 	int				dot_dotdot[2];
 	unsigned int			f_state;
+	bool				reserve_lease_break;
 };
 
 static inline void set_ctx_actor(struct dir_context *ctx,
@@ -138,9 +139,11 @@ struct ksmbd_file *ksmbd_lookup_foreign_fd(struct ksmbd_work *work, u64 id);
 struct ksmbd_file *ksmbd_lookup_fd_slow(struct ksmbd_work *work, u64 id,
 					u64 pid);
 void ksmbd_fd_put(struct ksmbd_work *work, struct ksmbd_file *fp);
+struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d);
+void ksmbd_inode_put(struct ksmbd_inode *ci);
 struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id);
 struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid);
-struct ksmbd_file *ksmbd_lookup_fd_inode(struct inode *inode);
+struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry);
 unsigned int ksmbd_open_durable_fd(struct ksmbd_file *fp);
 struct ksmbd_file *ksmbd_open_fd(struct ksmbd_work *work, struct file *filp);
 void ksmbd_close_tree_conn_fds(struct ksmbd_work *work);
@@ -164,7 +167,7 @@ enum KSMBD_INODE_STATUS {
 	KSMBD_INODE_STATUS_PENDING_DELETE,
 };
 
-int ksmbd_query_inode_status(struct inode *inode);
+int ksmbd_query_inode_status(struct dentry *dentry);
 bool ksmbd_inode_pending_delete(struct ksmbd_file *fp);
 void ksmbd_set_inode_pending_delete(struct ksmbd_file *fp);
 void ksmbd_clear_inode_pending_delete(struct ksmbd_file *fp);
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 581ce951933901..2dc730800f448d 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -321,7 +321,7 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length,
 		TRACE("Block @ 0x%llx, %scompressed size %d\n", index - 2,
 		      compressed ? "" : "un", length);
 	}
-	if (length < 0 || length > output->length ||
+	if (length <= 0 || length > output->length ||
 			(index + length) > msblk->bytes_used) {
 		res = -EIO;
 		goto out;
diff --git a/fs/stat.c b/fs/stat.c
index 24bb0209e4599f..f721d26ec3f7e5 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -133,7 +133,8 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
 	idmap = mnt_idmap(path->mnt);
 	if (inode->i_op->getattr)
 		return inode->i_op->getattr(idmap, path, stat,
-					    request_mask, query_flags);
+					    request_mask,
+					    query_flags | AT_GETATTR_NOSEC);
 
 	generic_fillattr(idmap, request_mask, inode, stat);
 	return 0;
@@ -166,6 +167,9 @@ int vfs_getattr(const struct path *path, struct kstat *stat,
 {
 	int retval;
 
+	if (WARN_ON_ONCE(query_flags & AT_GETATTR_NOSEC))
+		return -EPERM;
+
 	retval = security_inode_getattr(path);
 	if (retval)
 		return retval;
diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index f8a594a50ae628..2ccc849a5bda50 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -27,16 +27,16 @@
 /*
  * eventfs_mutex protects the eventfs_inode (ei) dentry. Any access
  * to the ei->dentry must be done under this mutex and after checking
- * if ei->is_freed is not set. The ei->dentry is released under the
- * mutex at the same time ei->is_freed is set. If ei->is_freed is set
- * then the ei->dentry is invalid.
+ * if ei->is_freed is not set. When ei->is_freed is set, the dentry
+ * is on its way to being freed after the last dput() is made on it.
  */
 static DEFINE_MUTEX(eventfs_mutex);
 
 /*
  * The eventfs_inode (ei) itself is protected by SRCU. It is released from
  * its parent's list and will have is_freed set (under eventfs_mutex).
- * After the SRCU grace period is over, the ei may be freed.
+ * After the SRCU grace period is over and the last dput() is called
+ * the ei is freed.
  */
 DEFINE_STATIC_SRCU(eventfs_srcu);
 
@@ -95,7 +95,7 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 	if (!(dentry->d_inode->i_mode & S_IFDIR)) {
 		if (!ei->entry_attrs) {
 			ei->entry_attrs = kzalloc(sizeof(*ei->entry_attrs) * ei->nr_entries,
-						  GFP_KERNEL);
+						  GFP_NOFS);
 			if (!ei->entry_attrs) {
 				ret = -ENOMEM;
 				goto out;
@@ -148,7 +148,8 @@ static const struct file_operations eventfs_file_operations = {
 	.release	= eventfs_release,
 };
 
-static void update_inode_attr(struct inode *inode, struct eventfs_attr *attr, umode_t mode)
+static void update_inode_attr(struct dentry *dentry, struct inode *inode,
+			      struct eventfs_attr *attr, umode_t mode)
 {
 	if (!attr) {
 		inode->i_mode = mode;
@@ -162,9 +163,13 @@ static void update_inode_attr(struct inode *inode, struct eventfs_attr *attr, um
 
 	if (attr->mode & EVENTFS_SAVE_UID)
 		inode->i_uid = attr->uid;
+	else
+		inode->i_uid = d_inode(dentry->d_parent)->i_uid;
 
 	if (attr->mode & EVENTFS_SAVE_GID)
 		inode->i_gid = attr->gid;
+	else
+		inode->i_gid = d_inode(dentry->d_parent)->i_gid;
 }
 
 /**
@@ -206,7 +211,7 @@ static struct dentry *create_file(const char *name, umode_t mode,
 		return eventfs_failed_creating(dentry);
 
 	/* If the user updated the directory's attributes, use them */
-	update_inode_attr(inode, attr, mode);
+	update_inode_attr(dentry, inode, attr, mode);
 
 	inode->i_op = &eventfs_file_inode_operations;
 	inode->i_fop = fop;
@@ -242,7 +247,8 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent
 		return eventfs_failed_creating(dentry);
 
 	/* If the user updated the directory's attributes, use them */
-	update_inode_attr(inode, &ei->attr, S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO);
+	update_inode_attr(dentry, inode, &ei->attr,
+			  S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO);
 
 	inode->i_op = &eventfs_root_dir_inode_operations;
 	inode->i_fop = &eventfs_file_operations;
@@ -326,7 +332,8 @@ create_file_dentry(struct eventfs_inode *ei, int idx,
 	struct eventfs_attr *attr = NULL;
 	struct dentry **e_dentry = &ei->d_children[idx];
 	struct dentry *dentry;
-	bool invalidate = false;
+
+	WARN_ON_ONCE(!inode_is_locked(parent->d_inode));
 
 	mutex_lock(&eventfs_mutex);
 	if (ei->is_freed) {
@@ -348,15 +355,8 @@ create_file_dentry(struct eventfs_inode *ei, int idx,
 
 	mutex_unlock(&eventfs_mutex);
 
-	/* The lookup already has the parent->d_inode locked */
-	if (!lookup)
-		inode_lock(parent->d_inode);
-
 	dentry = create_file(name, mode, attr, parent, data, fops);
 
-	if (!lookup)
-		inode_unlock(parent->d_inode);
-
 	mutex_lock(&eventfs_mutex);
 
 	if (IS_ERR_OR_NULL(dentry)) {
@@ -365,12 +365,14 @@ create_file_dentry(struct eventfs_inode *ei, int idx,
 		 * created the dentry for this e_dentry. In which case
 		 * use that one.
 		 *
-		 * Note, with the mutex held, the e_dentry cannot have content
-		 * and the ei->is_freed be true at the same time.
+		 * If ei->is_freed is set, the e_dentry is currently on its
+		 * way to being freed, don't return it. If e_dentry is NULL
+		 * it means it was already freed.
 		 */
-		dentry = *e_dentry;
-		if (WARN_ON_ONCE(dentry && ei->is_freed))
+		if (ei->is_freed)
 			dentry = NULL;
+		else
+			dentry = *e_dentry;
 		/* The lookup does not need to up the dentry refcount */
 		if (dentry && !lookup)
 			dget(dentry);
@@ -387,17 +389,14 @@ create_file_dentry(struct eventfs_inode *ei, int idx,
 		 * Otherwise it means two dentries exist with the same name.
 		 */
 		WARN_ON_ONCE(!ei->is_freed);
-		invalidate = true;
+		dentry = NULL;
 	}
 	mutex_unlock(&eventfs_mutex);
 
-	if (invalidate)
-		d_invalidate(dentry);
-
-	if (lookup || invalidate)
+	if (lookup)
 		dput(dentry);
 
-	return invalidate ? NULL : dentry;
+	return dentry;
 }
 
 /**
@@ -437,9 +436,10 @@ static struct dentry *
 create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
 		  struct dentry *parent, bool lookup)
 {
-	bool invalidate = false;
 	struct dentry *dentry = NULL;
 
+	WARN_ON_ONCE(!inode_is_locked(parent->d_inode));
+
 	mutex_lock(&eventfs_mutex);
 	if (pei->is_freed || ei->is_freed) {
 		mutex_unlock(&eventfs_mutex);
@@ -456,15 +456,8 @@ create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
 	}
 	mutex_unlock(&eventfs_mutex);
 
-	/* The lookup already has the parent->d_inode locked */
-	if (!lookup)
-		inode_lock(parent->d_inode);
-
 	dentry = create_dir(ei, parent);
 
-	if (!lookup)
-		inode_unlock(parent->d_inode);
-
 	mutex_lock(&eventfs_mutex);
 
 	if (IS_ERR_OR_NULL(dentry) && !ei->is_freed) {
@@ -473,8 +466,8 @@ create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
 		 * created the dentry for this e_dentry. In which case
 		 * use that one.
 		 *
-		 * Note, with the mutex held, the e_dentry cannot have content
-		 * and the ei->is_freed be true at the same time.
+		 * If ei->is_freed is set, the e_dentry is currently on its
+		 * way to being freed.
 		 */
 		dentry = ei->dentry;
 		if (dentry && !lookup)
@@ -493,16 +486,14 @@ create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
 		 * Otherwise it means two dentries exist with the same name.
 		 */
 		WARN_ON_ONCE(!ei->is_freed);
-		invalidate = true;
+		dentry = NULL;
 	}
 	mutex_unlock(&eventfs_mutex);
-	if (invalidate)
-		d_invalidate(dentry);
 
-	if (lookup || invalidate)
+	if (lookup)
 		dput(dentry);
 
-	return invalidate ? NULL : dentry;
+	return dentry;
 }
 
 /**
@@ -561,6 +552,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 		if (strcmp(ei_child->name, name) != 0)
 			continue;
 		ret = simple_lookup(dir, dentry, flags);
+		if (IS_ERR(ret))
+			goto out;
 		create_dir_dentry(ei, ei_child, ei_dentry, true);
 		created = true;
 		break;
@@ -583,6 +576,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 			if (r <= 0)
 				continue;
 			ret = simple_lookup(dir, dentry, flags);
+			if (IS_ERR(ret))
+				goto out;
 			create_file_dentry(ei, i, ei_dentry, name, mode, cdata,
 					   fops, true);
 			break;
@@ -632,7 +627,7 @@ static int add_dentries(struct dentry ***dentries, struct dentry *d, int cnt)
 {
 	struct dentry **tmp;
 
-	tmp = krealloc(*dentries, sizeof(d) * (cnt + 2), GFP_KERNEL);
+	tmp = krealloc(*dentries, sizeof(d) * (cnt + 2), GFP_NOFS);
 	if (!tmp)
 		return -1;
 	tmp[cnt] = d;
@@ -698,6 +693,7 @@ static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
 		return -ENOMEM;
 	}
 
+	inode_lock(parent->d_inode);
 	list_for_each_entry_srcu(ei_child, &ei->children, list,
 				 srcu_read_lock_held(&eventfs_srcu)) {
 		d = create_dir_dentry(ei, ei_child, parent, false);
@@ -730,6 +726,7 @@ static int dcache_dir_open_wrapper(struct inode *inode, struct file *file)
 			cnt++;
 		}
 	}
+	inode_unlock(parent->d_inode);
 	srcu_read_unlock(&eventfs_srcu, idx);
 	ret = dcache_dir_open(inode, file);
 
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 5b54948514fe21..ae648deed019cc 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -509,20 +509,15 @@ struct dentry *eventfs_start_creating(const char *name, struct dentry *parent)
 	struct dentry *dentry;
 	int error;
 
+	/* Must always have a parent. */
+	if (WARN_ON_ONCE(!parent))
+		return ERR_PTR(-EINVAL);
+
 	error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
 			      &tracefs_mount_count);
 	if (error)
 		return ERR_PTR(error);
 
-	/*
-	 * If the parent is not specified, we create it in the root.
-	 * We need the root dentry to do this, which is in the super
-	 * block. A pointer to that is in the struct vfsmount that we
-	 * have around.
-	 */
-	if (!parent)
-		parent = tracefs_mount->mnt_root;
-
 	if (unlikely(IS_DEADDIR(parent->d_inode)))
 		dentry = ERR_PTR(-ENOENT);
 	else
diff --git a/fs/ufs/util.c b/fs/ufs/util.c
index 13ba34e6d64ff3..2acf191eb89ede 100644
--- a/fs/ufs/util.c
+++ b/fs/ufs/util.c
@@ -245,7 +245,7 @@ struct folio *ufs_get_locked_folio(struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	struct folio *folio = filemap_lock_folio(mapping, index);
-	if (!folio) {
+	if (IS_ERR(folio)) {
 		folio = read_mapping_folio(mapping, index, NULL);
 
 		if (IS_ERR(folio)) {
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index ed0bc8cbc703d9..567fb37274d35a 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -147,7 +147,7 @@ config XFS_ONLINE_SCRUB_STATS
 	bool "XFS online metadata check usage data collection"
 	default y
 	depends on XFS_ONLINE_SCRUB
-	select XFS_DEBUG
+	select DEBUG_FS
 	help
 	  If you say Y here, the kernel will gather usage data about
 	  the online metadata check subsystem.  This includes the number
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 3069194527dd06..100ab5931b3132 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2275,16 +2275,37 @@ xfs_alloc_min_freelist(
 
 	ASSERT(mp->m_alloc_maxlevels > 0);
 
+	/*
+	 * For a btree shorter than the maximum height, the worst case is that
+	 * every level gets split and a new level is added, then while inserting
+	 * another entry to refill the AGFL, every level under the old root gets
+	 * split again. This is:
+	 *
+	 *   (full height split reservation) + (AGFL refill split height)
+	 * = (current height + 1) + (current height - 1)
+	 * = (new height) + (new height - 2)
+	 * = 2 * new height - 2
+	 *
+	 * For a btree of maximum height, the worst case is that every level
+	 * under the root gets split, then while inserting another entry to
+	 * refill the AGFL, every level under the root gets split again. This is
+	 * also:
+	 *
+	 *   2 * (current height - 1)
+	 * = 2 * (new height - 1)
+	 * = 2 * new height - 2
+	 */
+
 	/* space needed by-bno freespace btree */
 	min_free = min_t(unsigned int, levels[XFS_BTNUM_BNOi] + 1,
-				       mp->m_alloc_maxlevels);
+				       mp->m_alloc_maxlevels) * 2 - 2;
 	/* space needed by-size freespace btree */
 	min_free += min_t(unsigned int, levels[XFS_BTNUM_CNTi] + 1,
-				       mp->m_alloc_maxlevels);
+				       mp->m_alloc_maxlevels) * 2 - 2;
 	/* space needed reverse mapping used space btree */
 	if (xfs_has_rmapbt(mp))
 		min_free += min_t(unsigned int, levels[XFS_BTNUM_RMAPi] + 1,
-						mp->m_rmap_maxlevels);
+						mp->m_rmap_maxlevels) * 2 - 2;
 
 	return min_free;
 }
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index bcfb6a4203cdd9..f71679ce23b95d 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -245,21 +245,18 @@ xfs_defer_create_intents(
 	return ret;
 }
 
-/* Abort all the intents that were committed. */
 STATIC void
-xfs_defer_trans_abort(
-	struct xfs_trans		*tp,
-	struct list_head		*dop_pending)
+xfs_defer_pending_abort(
+	struct xfs_mount		*mp,
+	struct list_head		*dop_list)
 {
 	struct xfs_defer_pending	*dfp;
 	const struct xfs_defer_op_type	*ops;
 
-	trace_xfs_defer_trans_abort(tp, _RET_IP_);
-
 	/* Abort intent items that don't have a done item. */
-	list_for_each_entry(dfp, dop_pending, dfp_list) {
+	list_for_each_entry(dfp, dop_list, dfp_list) {
 		ops = defer_op_types[dfp->dfp_type];
-		trace_xfs_defer_pending_abort(tp->t_mountp, dfp);
+		trace_xfs_defer_pending_abort(mp, dfp);
 		if (dfp->dfp_intent && !dfp->dfp_done) {
 			ops->abort_intent(dfp->dfp_intent);
 			dfp->dfp_intent = NULL;
@@ -267,6 +264,16 @@ xfs_defer_trans_abort(
 	}
 }
 
+/* Abort all the intents that were committed. */
+STATIC void
+xfs_defer_trans_abort(
+	struct xfs_trans		*tp,
+	struct list_head		*dop_pending)
+{
+	trace_xfs_defer_trans_abort(tp, _RET_IP_);
+	xfs_defer_pending_abort(tp->t_mountp, dop_pending);
+}
+
 /*
  * Capture resources that the caller said not to release ("held") when the
  * transaction commits.  Caller is responsible for zero-initializing @dres.
@@ -756,12 +763,13 @@ xfs_defer_ops_capture(
 
 /* Release all resources that we used to capture deferred ops. */
 void
-xfs_defer_ops_capture_free(
+xfs_defer_ops_capture_abort(
 	struct xfs_mount		*mp,
 	struct xfs_defer_capture	*dfc)
 {
 	unsigned short			i;
 
+	xfs_defer_pending_abort(mp, &dfc->dfc_dfops);
 	xfs_defer_cancel_list(mp, &dfc->dfc_dfops);
 
 	for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
@@ -802,7 +810,7 @@ xfs_defer_ops_capture_and_commit(
 	/* Commit the transaction and add the capture structure to the list. */
 	error = xfs_trans_commit(tp);
 	if (error) {
-		xfs_defer_ops_capture_free(mp, dfc);
+		xfs_defer_ops_capture_abort(mp, dfc);
 		return error;
 	}
 
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 114a3a4930a3c4..8788ad5f6a731f 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -121,7 +121,7 @@ int xfs_defer_ops_capture_and_commit(struct xfs_trans *tp,
 		struct list_head *capture_list);
 void xfs_defer_ops_continue(struct xfs_defer_capture *d, struct xfs_trans *tp,
 		struct xfs_defer_resources *dres);
-void xfs_defer_ops_capture_free(struct xfs_mount *mp,
+void xfs_defer_ops_capture_abort(struct xfs_mount *mp,
 		struct xfs_defer_capture *d);
 void xfs_defer_resources_rele(struct xfs_defer_resources *dres);
 
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 543f3748c2a353..137a65bda95dc1 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -510,6 +510,9 @@ xfs_dinode_verify(
 	if (mode && nextents + naextents > nblocks)
 		return __this_address;
 
+	if (nextents + naextents == 0 && nblocks != 0)
+		return __this_address;
+
 	if (S_ISDIR(mode) && nextents > mp->m_dir_geo->max_extents)
 		return __this_address;
 
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index ac6ba646624df5..a013b87ab8d5e5 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -562,7 +562,8 @@ xfs_dquot_from_disk(
 	struct xfs_dquot	*dqp,
 	struct xfs_buf		*bp)
 {
-	struct xfs_disk_dquot	*ddqp = bp->b_addr + dqp->q_bufoffset;
+	struct xfs_dqblk	*dqb = xfs_buf_offset(bp, dqp->q_bufoffset);
+	struct xfs_disk_dquot	*ddqp = &dqb->dd_diskdq;
 
 	/*
 	 * Ensure that we got the type and ID we were looking for.
@@ -1250,7 +1251,7 @@ xfs_qm_dqflush(
 	}
 
 	/* Flush the incore dquot to the ondisk buffer. */
-	dqblk = bp->b_addr + dqp->q_bufoffset;
+	dqblk = xfs_buf_offset(bp, dqp->q_bufoffset);
 	xfs_dquot_to_disk(&dqblk->dd_diskdq, dqp);
 
 	/*
diff --git a/fs/xfs/xfs_dquot_item_recover.c b/fs/xfs/xfs_dquot_item_recover.c
index 8966ba842395bf..2c2720ce692382 100644
--- a/fs/xfs/xfs_dquot_item_recover.c
+++ b/fs/xfs/xfs_dquot_item_recover.c
@@ -19,6 +19,7 @@
 #include "xfs_log.h"
 #include "xfs_log_priv.h"
 #include "xfs_log_recover.h"
+#include "xfs_error.h"
 
 STATIC void
 xlog_recover_dquot_ra_pass2(
@@ -65,6 +66,7 @@ xlog_recover_dquot_commit_pass2(
 {
 	struct xfs_mount		*mp = log->l_mp;
 	struct xfs_buf			*bp;
+	struct xfs_dqblk		*dqb;
 	struct xfs_disk_dquot		*ddq, *recddq;
 	struct xfs_dq_logformat		*dq_f;
 	xfs_failaddr_t			fa;
@@ -130,14 +132,14 @@ xlog_recover_dquot_commit_pass2(
 		return error;
 
 	ASSERT(bp);
-	ddq = xfs_buf_offset(bp, dq_f->qlf_boffset);
+	dqb = xfs_buf_offset(bp, dq_f->qlf_boffset);
+	ddq = &dqb->dd_diskdq;
 
 	/*
 	 * If the dquot has an LSN in it, recover the dquot only if it's less
 	 * than the lsn of the transaction we are replaying.
 	 */
 	if (xfs_has_crc(mp)) {
-		struct xfs_dqblk *dqb = (struct xfs_dqblk *)ddq;
 		xfs_lsn_t	lsn = be64_to_cpu(dqb->dd_lsn);
 
 		if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
@@ -147,10 +149,23 @@ xlog_recover_dquot_commit_pass2(
 
 	memcpy(ddq, recddq, item->ri_buf[1].i_len);
 	if (xfs_has_crc(mp)) {
-		xfs_update_cksum((char *)ddq, sizeof(struct xfs_dqblk),
+		xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk),
 				 XFS_DQUOT_CRC_OFF);
 	}
 
+	/* Validate the recovered dquot. */
+	fa = xfs_dqblk_verify(log->l_mp, dqb, dq_f->qlf_id);
+	if (fa) {
+		XFS_CORRUPTION_ERROR("Bad dquot after recovery",
+				XFS_ERRLEVEL_LOW, mp, dqb,
+				sizeof(struct xfs_dqblk));
+		xfs_alert(mp,
+ "Metadata corruption detected at %pS, dquot 0x%x",
+				fa, dq_f->qlf_id);
+		error = -EFSCORRUPTED;
+		goto out_release;
+	}
+
 	ASSERT(dq_f->qlf_size == 2);
 	ASSERT(bp->b_mount == mp);
 	bp->b_flags |= _XBF_LOGRECOVERY;
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 3dc47937da5d17..3beb470f18920d 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -569,6 +569,14 @@ extern void xfs_setup_inode(struct xfs_inode *ip);
 extern void xfs_setup_iops(struct xfs_inode *ip);
 extern void xfs_diflags_to_iflags(struct xfs_inode *ip, bool init);
 
+static inline void xfs_update_stable_writes(struct xfs_inode *ip)
+{
+	if (bdev_stable_writes(xfs_inode_buftarg(ip)->bt_bdev))
+		mapping_set_stable_writes(VFS_I(ip)->i_mapping);
+	else
+		mapping_clear_stable_writes(VFS_I(ip)->i_mapping);
+}
+
 /*
  * When setting up a newly allocated inode, we need to call
  * xfs_finish_inode_setup() once the inode is fully instantiated at
diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c
index 0e5dba2343ea13..144198a6b2702c 100644
--- a/fs/xfs/xfs_inode_item_recover.c
+++ b/fs/xfs/xfs_inode_item_recover.c
@@ -286,6 +286,7 @@ xlog_recover_inode_commit_pass2(
 	struct xfs_log_dinode		*ldip;
 	uint				isize;
 	int				need_free = 0;
+	xfs_failaddr_t			fa;
 
 	if (item->ri_buf[0].i_len == sizeof(struct xfs_inode_log_format)) {
 		in_f = item->ri_buf[0].i_addr;
@@ -369,24 +370,26 @@ xlog_recover_inode_commit_pass2(
 	 * superblock flag to determine whether we need to look at di_flushiter
 	 * to skip replay when the on disk inode is newer than the log one
 	 */
-	if (!xfs_has_v3inodes(mp) &&
-	    ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
-		/*
-		 * Deal with the wrap case, DI_MAX_FLUSH is less
-		 * than smaller numbers
-		 */
-		if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH &&
-		    ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) {
-			/* do nothing */
-		} else {
-			trace_xfs_log_recover_inode_skip(log, in_f);
-			error = 0;
-			goto out_release;
+	if (!xfs_has_v3inodes(mp)) {
+		if (ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
+			/*
+			 * Deal with the wrap case, DI_MAX_FLUSH is less
+			 * than smaller numbers
+			 */
+			if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH &&
+			    ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) {
+				/* do nothing */
+			} else {
+				trace_xfs_log_recover_inode_skip(log, in_f);
+				error = 0;
+				goto out_release;
+			}
 		}
+
+		/* Take the opportunity to reset the flush iteration count */
+		ldip->di_flushiter = 0;
 	}
 
-	/* Take the opportunity to reset the flush iteration count */
-	ldip->di_flushiter = 0;
 
 	if (unlikely(S_ISREG(ldip->di_mode))) {
 		if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) &&
@@ -528,8 +531,19 @@ out_owner_change:
 	    (dip->di_mode != 0))
 		error = xfs_recover_inode_owner_change(mp, dip, in_f,
 						       buffer_list);
-	/* re-generate the checksum. */
+	/* re-generate the checksum and validate the recovered inode. */
 	xfs_dinode_calc_crc(log->l_mp, dip);
+	fa = xfs_dinode_verify(log->l_mp, in_f->ilf_ino, dip);
+	if (fa) {
+		XFS_CORRUPTION_ERROR(
+			"Bad dinode after recovery",
+				XFS_ERRLEVEL_LOW, mp, dip, sizeof(*dip));
+		xfs_alert(mp,
+			"Metadata corruption detected at %pS, inode 0x%llx",
+			fa, in_f->ilf_ino);
+		error = -EFSCORRUPTED;
+		goto out_release;
+	}
 
 	ASSERT(bp->b_mount == mp);
 	bp->b_flags |= _XBF_LOGRECOVERY;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index a82470e027f727..6c3919687ea6b3 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1121,23 +1121,25 @@ xfs_ioctl_setattr_xflags(
 	struct fileattr		*fa)
 {
 	struct xfs_mount	*mp = ip->i_mount;
+	bool			rtflag = (fa->fsx_xflags & FS_XFLAG_REALTIME);
 	uint64_t		i_flags2;
 
-	/* Can't change realtime flag if any extents are allocated. */
-	if ((ip->i_df.if_nextents || ip->i_delayed_blks) &&
-	    XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & FS_XFLAG_REALTIME))
-		return -EINVAL;
+	if (rtflag != XFS_IS_REALTIME_INODE(ip)) {
+		/* Can't change realtime flag if any extents are allocated. */
+		if (ip->i_df.if_nextents || ip->i_delayed_blks)
+			return -EINVAL;
+	}
 
-	/* If realtime flag is set then must have realtime device */
-	if (fa->fsx_xflags & FS_XFLAG_REALTIME) {
+	if (rtflag) {
+		/* If realtime flag is set then must have realtime device */
 		if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 ||
 		    xfs_extlen_to_rtxmod(mp, ip->i_extsize))
 			return -EINVAL;
-	}
 
-	/* Clear reflink if we are actually able to set the rt flag. */
-	if ((fa->fsx_xflags & FS_XFLAG_REALTIME) && xfs_is_reflink_inode(ip))
-		ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+		/* Clear reflink if we are actually able to set the rt flag. */
+		if (xfs_is_reflink_inode(ip))
+			ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+	}
 
 	/* diflags2 only valid for v3 inodes. */
 	i_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags);
@@ -1148,6 +1150,14 @@ xfs_ioctl_setattr_xflags(
 	ip->i_diflags2 = i_flags2;
 
 	xfs_diflags_to_iflags(ip, false);
+
+	/*
+	 * Make the stable writes flag match that of the device the inode
+	 * resides on when flipping the RT flag.
+	 */
+	if (rtflag != XFS_IS_REALTIME_INODE(ip) && S_ISREG(VFS_I(ip)->i_mode))
+		xfs_update_stable_writes(ip);
+
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	XFS_STATS_INC(mp, xs_ig_attrchg);
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index fdfda4fba12b1e..a0d77f5f512e24 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -1299,6 +1299,13 @@ xfs_setup_inode(
 	mapping_set_gfp_mask(inode->i_mapping, (gfp_mask & ~(__GFP_FS)));
 
 	/*
+	 * For real-time inodes update the stable write flags to that of the RT
+	 * device instead of the data device.
+	 */
+	if (S_ISREG(inode->i_mode) && XFS_IS_REALTIME_INODE(ip))
+		xfs_update_stable_writes(ip);
+
+	/*
 	 * If there is no attribute fork no ACL can exist on this inode,
 	 * and it can't have any file capabilities attached to it either.
 	 */
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 51c100c861770f..ee206facf0dc06 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1893,9 +1893,7 @@ xlog_write_iclog(
 		 * the buffer manually, the code needs to be kept in sync
 		 * with the I/O completion path.
 		 */
-		xlog_state_done_syncing(iclog);
-		up(&iclog->ic_sema);
-		return;
+		goto sync;
 	}
 
 	/*
@@ -1925,20 +1923,17 @@ xlog_write_iclog(
 		 * avoid shutdown re-entering this path and erroring out again.
 		 */
 		if (log->l_targ != log->l_mp->m_ddev_targp &&
-		    blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev)) {
-			xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
-			return;
-		}
+		    blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev))
+			goto shutdown;
 	}
 	if (iclog->ic_flags & XLOG_ICL_NEED_FUA)
 		iclog->ic_bio.bi_opf |= REQ_FUA;
 
 	iclog->ic_flags &= ~(XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA);
 
-	if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count)) {
-		xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
-		return;
-	}
+	if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count))
+		goto shutdown;
+
 	if (is_vmalloc_addr(iclog->ic_data))
 		flush_kernel_vmap_range(iclog->ic_data, count);
 
@@ -1959,6 +1954,12 @@ xlog_write_iclog(
 	}
 
 	submit_bio(&iclog->ic_bio);
+	return;
+shutdown:
+	xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
+sync:
+	xlog_state_done_syncing(iclog);
+	up(&iclog->ic_sema);
 }
 
 /*
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 13b94d2e605bd9..a1e18b24971a28 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2511,7 +2511,7 @@ xlog_abort_defer_ops(
 
 	list_for_each_entry_safe(dfc, next, capture_list, dfc_list) {
 		list_del_init(&dfc->dfc_list);
-		xfs_defer_ops_capture_free(mp, dfc);
+		xfs_defer_ops_capture_abort(mp, dfc);
 	}
 }
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 658edee8381dcd..e5b62dc2846644 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -784,6 +784,7 @@ xfs_reflink_end_cow_extent(
 		}
 	}
 	del = got;
+	xfs_trim_extent(&del, *offset_fsb, end_fsb - *offset_fsb);
 
 	/* Grab the corresponding mapping in the data fork. */
 	nmaps = 1;
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index afeed6e72049e4..1216d72c650fae 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -542,6 +542,7 @@ int acpi_device_set_power(struct acpi_device *device, int state);
 int acpi_bus_init_power(struct acpi_device *device);
 int acpi_device_fix_up_power(struct acpi_device *device);
 void acpi_device_fix_up_power_extended(struct acpi_device *adev);
+void acpi_device_fix_up_power_children(struct acpi_device *adev);
 int acpi_bus_update_power(acpi_handle handle, int *state_p);
 int acpi_device_update_power(struct acpi_device *device, int *state_p);
 bool acpi_bus_power_manageable(acpi_handle handle);
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 995513fa26904a..0655aa5b57b290 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -70,7 +70,7 @@ static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
  */
 static __always_inline int queued_spin_value_unlocked(struct qspinlock lock)
 {
-	return !atomic_read(&lock.val);
+	return !lock.val.counter;
 }
 
 /**
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h
index 536a0b0091c3a9..006b5c977ad772 100644
--- a/include/drm/drm_atomic_helper.h
+++ b/include/drm/drm_atomic_helper.h
@@ -97,6 +97,8 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 
 int drm_atomic_helper_prepare_planes(struct drm_device *dev,
 				     struct drm_atomic_state *state);
+void drm_atomic_helper_unprepare_planes(struct drm_device *dev,
+					struct drm_atomic_state *state);
 
 #define DRM_PLANE_COMMIT_ACTIVE_ONLY			BIT(0)
 #define DRM_PLANE_COMMIT_NO_DISABLE_AFTER_MODESET	BIT(1)
diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h
index bdfafc4a7705e1..c7a0594bdab170 100644
--- a/include/drm/drm_gpuvm.h
+++ b/include/drm/drm_gpuvm.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
 
 #ifndef __DRM_GPUVM_H__
 #define __DRM_GPUVM_H__
diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
index a7abf9f3e69729..2a1d01e5b56b8c 100644
--- a/include/drm/drm_prime.h
+++ b/include/drm/drm_prime.h
@@ -60,12 +60,19 @@ enum dma_data_direction;
 
 struct drm_device;
 struct drm_gem_object;
+struct drm_file;
 
 /* core prime functions */
 struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev,
 				      struct dma_buf_export_info *exp_info);
 void drm_gem_dmabuf_release(struct dma_buf *dma_buf);
 
+int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+			       struct drm_file *file_priv, int prime_fd, uint32_t *handle);
+int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+			       struct drm_file *file_priv, uint32_t handle, uint32_t flags,
+			       int *prime_fd);
+
 /* helper functions for exporting */
 int drm_gem_map_attach(struct dma_buf *dma_buf,
 		       struct dma_buf_attachment *attach);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 54189e0e5f419a..4db54e928b36d0 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -15,7 +15,6 @@
 #include <linux/mod_devicetable.h>
 #include <linux/property.h>
 #include <linux/uuid.h>
-#include <linux/fw_table.h>
 
 struct irq_domain;
 struct irq_domain_ops;
@@ -25,22 +24,13 @@ struct irq_domain_ops;
 #endif
 #include <acpi/acpi.h>
 
-#ifdef CONFIG_ACPI_TABLE_LIB
-#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI)
-#define __init_or_acpilib
-#define __initdata_or_acpilib
-#else
-#define EXPORT_SYMBOL_ACPI_LIB(x)
-#define __init_or_acpilib __init
-#define __initdata_or_acpilib __initdata
-#endif
-
 #ifdef	CONFIG_ACPI
 
 #include <linux/list.h>
 #include <linux/dynamic_debug.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/fw_table.h>
 
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
@@ -48,6 +38,16 @@ struct irq_domain_ops;
 #include <acpi/acpi_io.h>
 #include <asm/acpi.h>
 
+#ifdef CONFIG_ACPI_TABLE_LIB
+#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI)
+#define __init_or_acpilib
+#define __initdata_or_acpilib
+#else
+#define EXPORT_SYMBOL_ACPI_LIB(x)
+#define __init_or_acpilib __init
+#define __initdata_or_acpilib __initdata
+#endif
+
 static inline acpi_handle acpi_device_handle(struct acpi_device *adev)
 {
 	return adev ? adev->handle : NULL;
diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
index 446394f8460647..6ad02ad9c7b42d 100644
--- a/include/linux/amd-pstate.h
+++ b/include/linux/amd-pstate.h
@@ -70,6 +70,10 @@ struct amd_cpudata {
 	u32	nominal_perf;
 	u32	lowest_nonlinear_perf;
 	u32	lowest_perf;
+	u32     min_limit_perf;
+	u32     max_limit_perf;
+	u32     min_limit_freq;
+	u32     max_limit_freq;
 
 	u32	max_freq;
 	u32	min_freq;
diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index 1abedb5b2e48fa..3d0fde57ba90eb 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -209,6 +209,8 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; }
 #define module_ffa_driver(__ffa_driver)	\
 	module_driver(__ffa_driver, ffa_register, ffa_unregister)
 
+extern struct bus_type ffa_bus_type;
+
 /* FFA transport related */
 struct ffa_partition_info {
 	u16 id;
diff --git a/include/linux/blk-pm.h b/include/linux/blk-pm.h
index 2580e05a8ab672..004b38a538ffef 100644
--- a/include/linux/blk-pm.h
+++ b/include/linux/blk-pm.h
@@ -15,7 +15,6 @@ extern int blk_pre_runtime_suspend(struct request_queue *q);
 extern void blk_post_runtime_suspend(struct request_queue *q, int err);
 extern void blk_pre_runtime_resume(struct request_queue *q);
 extern void blk_post_runtime_resume(struct request_queue *q);
-extern void blk_set_runtime_active(struct request_queue *q);
 #else
 static inline void blk_pm_runtime_init(struct request_queue *q,
 				       struct device *dev) {}
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d5c5e59ddbd25a..b29ebd53417d79 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -49,9 +49,10 @@ struct block_device {
 	bool			bd_write_holder;
 	bool			bd_has_submit_bio;
 	dev_t			bd_dev;
+	struct inode		*bd_inode;	/* will die */
+
 	atomic_t		bd_openers;
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
-	struct inode *		bd_inode;	/* will die */
 	void *			bd_claiming;
 	void *			bd_holder;
 	const struct blk_holder_ops *bd_holder_ops;
@@ -69,6 +70,7 @@ struct block_device {
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	bool			bd_make_it_fail;
 #endif
+	bool			bd_ro_warned;
 	/*
 	 * keep this out-of-line as it's both big and not needed in the fast
 	 * path
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b4825d3cdb2923..cff5bb08820ecf 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -56,7 +56,7 @@ extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
 extern struct kobject *btf_kobj;
 extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma;
-extern bool bpf_global_ma_set, bpf_global_percpu_ma_set;
+extern bool bpf_global_ma_set;
 
 typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64);
 typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
@@ -909,10 +909,14 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size)
 	aux->ctx_field_size = size;
 }
 
+static bool bpf_is_ldimm64(const struct bpf_insn *insn)
+{
+	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+}
+
 static inline bool bpf_pseudo_func(const struct bpf_insn *insn)
 {
-	return insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
-	       insn->src_reg == BPF_PSEUDO_FUNC;
+	return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC;
 }
 
 struct bpf_prog_ops {
@@ -3171,6 +3175,9 @@ enum bpf_text_poke_type {
 int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		       void *addr1, void *addr2);
 
+void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+			       struct bpf_prog *new, struct bpf_prog *old);
+
 void *bpf_arch_text_copy(void *dst, void *src, size_t len);
 int bpf_arch_text_invalidate(void *dst, size_t len);
 
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index fc0d6f32c68760..94baced5a1ad64 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -142,9 +142,13 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter)
 #ifdef CONFIG_NET
 BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns)
 BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp)
+BPF_LINK_TYPE(BPF_LINK_TYPE_NETFILTER, netfilter)
+BPF_LINK_TYPE(BPF_LINK_TYPE_TCX, tcx)
+BPF_LINK_TYPE(BPF_LINK_TYPE_NETKIT, netkit)
 #endif
 #ifdef CONFIG_PERF_EVENTS
 BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf)
 #endif
 BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi)
 BPF_LINK_TYPE(BPF_LINK_TYPE_STRUCT_OPS, struct_ops)
+BPF_LINK_TYPE(BPF_LINK_TYPE_UPROBE_MULTI, uprobe_multi)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 24213a99cc79db..aa4d19d0bc94bb 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -301,6 +301,17 @@ struct bpf_func_state {
 	struct tnum callback_ret_range;
 	bool in_async_callback_fn;
 	bool in_exception_callback_fn;
+	/* For callback calling functions that limit number of possible
+	 * callback executions (e.g. bpf_loop) keeps track of current
+	 * simulated iteration number.
+	 * Value in frame N refers to number of times callback with frame
+	 * N+1 was simulated, e.g. for the following call:
+	 *
+	 *   bpf_loop(..., fn, ...); | suppose current frame is N
+	 *                           | fn would be simulated in frame N+1
+	 *                           | number of simulations is tracked in frame N
+	 */
+	u32 callback_depth;
 
 	/* The following fields should be last. See copy_func_state() */
 	int acquired_refs;
@@ -400,6 +411,7 @@ struct bpf_verifier_state {
 	struct bpf_idx_pair *jmp_history;
 	u32 jmp_history_cnt;
 	u32 dfs_depth;
+	u32 callback_unroll_depth;
 };
 
 #define bpf_get_spilled_reg(slot, frame, mask)				\
@@ -511,6 +523,10 @@ struct bpf_insn_aux_data {
 	 * this instruction, regardless of any heuristics
 	 */
 	bool force_checkpoint;
+	/* true if instruction is a call to a helper function that
+	 * accepts callback function as a parameter.
+	 */
+	bool calls_callback;
 };
 
 #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
diff --git a/include/linux/btf.h b/include/linux/btf.h
index c2231c64d60b92..59d404e22814e8 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -84,6 +84,17 @@
  */
 #define __bpf_kfunc __used noinline
 
+#define __bpf_kfunc_start_defs()					       \
+	__diag_push();							       \
+	__diag_ignore_all("-Wmissing-declarations",			       \
+			  "Global kfuncs as their definitions will be in BTF");\
+	__diag_ignore_all("-Wmissing-prototypes",			       \
+			  "Global kfuncs as their definitions will be in BTF")
+
+#define __bpf_kfunc_end_defs() __diag_pop()
+#define __bpf_hook_start() __bpf_kfunc_start_defs()
+#define __bpf_hook_end() __bpf_kfunc_end_defs()
+
 /*
  * Return the name of the passed struct, if exists, or halt the build if for
  * example the structure gets renamed. In this way, developers have to revisit
diff --git a/include/linux/ceph/ceph_debug.h b/include/linux/ceph/ceph_debug.h
index d5a5da838cafa4..11a92a946016ea 100644
--- a/include/linux/ceph/ceph_debug.h
+++ b/include/linux/ceph/ceph_debug.h
@@ -19,12 +19,25 @@
 	pr_debug("%.*s %12.12s:%-4d : " fmt,				\
 		 8 - (int)sizeof(KBUILD_MODNAME), "    ",		\
 		 kbasename(__FILE__), __LINE__, ##__VA_ARGS__)
+#  define doutc(client, fmt, ...)					\
+	pr_debug("%.*s %12.12s:%-4d : [%pU %llu] " fmt,			\
+		 8 - (int)sizeof(KBUILD_MODNAME), "    ",		\
+		 kbasename(__FILE__), __LINE__,				\
+		 &client->fsid, client->monc.auth->global_id,		\
+		 ##__VA_ARGS__)
 # else
 /* faux printk call just to see any compiler warnings. */
 #  define dout(fmt, ...)	do {				\
 		if (0)						\
 			printk(KERN_DEBUG fmt, ##__VA_ARGS__);	\
 	} while (0)
+#  define doutc(client, fmt, ...)	do {			\
+		if (0)						\
+			printk(KERN_DEBUG "[%pU %llu] " fmt,	\
+			&client->fsid,				\
+			client->monc.auth->global_id,		\
+			##__VA_ARGS__);				\
+		} while (0)
 # endif
 
 #else
@@ -33,7 +46,32 @@
  * or, just wrap pr_debug
  */
 # define dout(fmt, ...)	pr_debug(" " fmt, ##__VA_ARGS__)
+# define doutc(client, fmt, ...)					\
+	pr_debug(" [%pU %llu] %s: " fmt, &client->fsid,			\
+		 client->monc.auth->global_id, __func__, ##__VA_ARGS__)
 
 #endif
 
+#define pr_notice_client(client, fmt, ...)				\
+	pr_notice("[%pU %llu]: " fmt, &client->fsid,			\
+		  client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_info_client(client, fmt, ...)				\
+	pr_info("[%pU %llu]: " fmt, &client->fsid,			\
+		client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_warn_client(client, fmt, ...)				\
+	pr_warn("[%pU %llu]: " fmt, &client->fsid,			\
+		client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_warn_once_client(client, fmt, ...)				\
+	pr_warn_once("[%pU %llu]: " fmt, &client->fsid,			\
+		     client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_err_client(client, fmt, ...)					\
+	pr_err("[%pU %llu]: " fmt, &client->fsid,			\
+	       client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_warn_ratelimited_client(client, fmt, ...)			\
+	pr_warn_ratelimited("[%pU %llu]: " fmt, &client->fsid,		\
+			    client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_err_ratelimited_client(client, fmt, ...)			\
+	pr_err_ratelimited("[%pU %llu]: " fmt, &client->fsid,		\
+			   client->monc.auth->global_id, ##__VA_ARGS__)
+
 #endif
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index f3b3593254b975..ee1d0e5f9789f2 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -357,6 +357,11 @@ enum {
 	CEPH_MDS_OP_RENAMESNAP = 0x01403,
 };
 
+#define IS_CEPH_MDS_OP_NEWINODE(op) (op == CEPH_MDS_OP_CREATE     || \
+				     op == CEPH_MDS_OP_MKNOD      || \
+				     op == CEPH_MDS_OP_MKDIR      || \
+				     op == CEPH_MDS_OP_SYMLINK)
+
 extern const char *ceph_mds_op_name(int op);
 
 #define CEPH_SETATTR_MODE              (1 << 0)
@@ -497,7 +502,7 @@ struct ceph_mds_request_head_legacy {
 	union ceph_mds_request_args args;
 } __attribute__ ((packed));
 
-#define CEPH_MDS_REQUEST_HEAD_VERSION  2
+#define CEPH_MDS_REQUEST_HEAD_VERSION  3
 
 struct ceph_mds_request_head_old {
 	__le16 version;                /* struct version */
@@ -528,6 +533,9 @@ struct ceph_mds_request_head {
 
 	__le32 ext_num_retry;          /* new count retry attempts */
 	__le32 ext_num_fwd;            /* new count fwd attempts */
+
+	__le32 struct_len;             /* to store size of struct ceph_mds_request_head */
+	__le32 owner_uid, owner_gid;   /* used for OPs which create inodes */
 } __attribute__ ((packed));
 
 /* cap/lease release record */
diff --git a/include/linux/closure.h b/include/linux/closure.h
index de7bb47d8a46ac..c554c6a08768ad 100644
--- a/include/linux/closure.h
+++ b/include/linux/closure.h
@@ -104,7 +104,7 @@
 
 struct closure;
 struct closure_syncer;
-typedef void (closure_fn) (struct closure *);
+typedef void (closure_fn) (struct work_struct *);
 extern struct dentry *bcache_debug;
 
 struct closure_waitlist {
@@ -254,7 +254,7 @@ static inline void closure_queue(struct closure *cl)
 		INIT_WORK(&cl->work, cl->work.func);
 		BUG_ON(!queue_work(wq, &cl->work));
 	} else
-		cl->fn(cl);
+		cl->fn(&cl->work);
 }
 
 /**
@@ -309,6 +309,11 @@ static inline void closure_wake_up(struct closure_waitlist *list)
 	__closure_wake_up(list);
 }
 
+#define CLOSURE_CALLBACK(name)	void name(struct work_struct *ws)
+#define closure_type(name, type, member)				\
+	struct closure *cl = container_of(ws, struct closure, work);	\
+	type *name = container_of(cl, type, member)
+
 /**
  * continue_at - jump to another function with barrier
  *
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index d305db70674bb5..efc0c0b07efb41 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -195,6 +195,7 @@ enum cpuhp_state {
 	CPUHP_AP_ARM_CORESIGHT_CTI_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,
+	CPUHP_AP_HRTIMERS_DYING,
 	CPUHP_AP_X86_TBOOT_DYING,
 	CPUHP_AP_ARM_CACHE_B15_RAC_DYING,
 	CPUHP_AP_ONLINE,
diff --git a/include/linux/cred.h b/include/linux/cred.h
index af8d353a4b86af..2976f534a7a32f 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -109,14 +109,7 @@ static inline int groups_search(const struct group_info *group_info, kgid_t grp)
  * same context as task->real_cred.
  */
 struct cred {
-	atomic_t	usage;
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	atomic_t	subscribers;	/* number of processes subscribed */
-	void		*put_addr;
-	unsigned	magic;
-#define CRED_MAGIC	0x43736564
-#define CRED_MAGIC_DEAD	0x44656144
-#endif
+	atomic_long_t	usage;
 	kuid_t		uid;		/* real UID of the task */
 	kgid_t		gid;		/* real GID of the task */
 	kuid_t		suid;		/* saved UID of the task */
@@ -172,46 +165,6 @@ extern int cred_fscmp(const struct cred *, const struct cred *);
 extern void __init cred_init(void);
 extern int set_cred_ucounts(struct cred *);
 
-/*
- * check for validity of credentials
- */
-#ifdef CONFIG_DEBUG_CREDENTIALS
-extern void __noreturn __invalid_creds(const struct cred *, const char *, unsigned);
-extern void __validate_process_creds(struct task_struct *,
-				     const char *, unsigned);
-
-extern bool creds_are_invalid(const struct cred *cred);
-
-static inline void __validate_creds(const struct cred *cred,
-				    const char *file, unsigned line)
-{
-	if (unlikely(creds_are_invalid(cred)))
-		__invalid_creds(cred, file, line);
-}
-
-#define validate_creds(cred)				\
-do {							\
-	__validate_creds((cred), __FILE__, __LINE__);	\
-} while(0)
-
-#define validate_process_creds()				\
-do {								\
-	__validate_process_creds(current, __FILE__, __LINE__);	\
-} while(0)
-
-extern void validate_creds_for_do_exit(struct task_struct *);
-#else
-static inline void validate_creds(const struct cred *cred)
-{
-}
-static inline void validate_creds_for_do_exit(struct task_struct *tsk)
-{
-}
-static inline void validate_process_creds(void)
-{
-}
-#endif
-
 static inline bool cap_ambient_invariant_ok(const struct cred *cred)
 {
 	return cap_issubset(cred->cap_ambient,
@@ -229,7 +182,7 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred)
  */
 static inline struct cred *get_new_cred_many(struct cred *cred, int nr)
 {
-	atomic_add(nr, &cred->usage);
+	atomic_long_add(nr, &cred->usage);
 	return cred;
 }
 
@@ -264,7 +217,6 @@ static inline const struct cred *get_cred_many(const struct cred *cred, int nr)
 	struct cred *nonconst_cred = (struct cred *) cred;
 	if (!cred)
 		return cred;
-	validate_creds(cred);
 	nonconst_cred->non_rcu = 0;
 	return get_new_cred_many(nonconst_cred, nr);
 }
@@ -288,9 +240,8 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred)
 	struct cred *nonconst_cred = (struct cred *) cred;
 	if (!cred)
 		return NULL;
-	if (!atomic_inc_not_zero(&nonconst_cred->usage))
+	if (!atomic_long_inc_not_zero(&nonconst_cred->usage))
 		return NULL;
-	validate_creds(cred);
 	nonconst_cred->non_rcu = 0;
 	return cred;
 }
@@ -312,8 +263,7 @@ static inline void put_cred_many(const struct cred *_cred, int nr)
 	struct cred *cred = (struct cred *) _cred;
 
 	if (cred) {
-		validate_creds(cred);
-		if (atomic_sub_and_test(nr, &cred->usage))
+		if (atomic_long_sub_and_test(nr, &cred->usage))
 			__put_cred(cred);
 	}
 }
diff --git a/include/linux/damon.h b/include/linux/damon.h
index ab2f17d9926b59..e00ddf1ed39c05 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -559,6 +559,8 @@ struct damon_ctx {
 	 * update
 	 */
 	unsigned long next_ops_update_sis;
+	/* for waiting until the execution of the kdamond_fn is started */
+	struct completion kdamond_started;
 
 /* public: */
 	struct task_struct *kdamond;
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index ea2d919fd9c799..c9c65b132c0fd7 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -171,6 +171,25 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf,
 ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf,
 			      size_t count, loff_t *ppos);
 
+/**
+ * struct debugfs_cancellation - cancellation data
+ * @list: internal, for keeping track
+ * @cancel: callback to call
+ * @cancel_data: extra data for the callback to call
+ */
+struct debugfs_cancellation {
+	struct list_head list;
+	void (*cancel)(struct dentry *, void *);
+	void *cancel_data;
+};
+
+void __acquires(cancellation)
+debugfs_enter_cancellation(struct file *file,
+			   struct debugfs_cancellation *cancellation);
+void __releases(cancellation)
+debugfs_leave_cancellation(struct file *file,
+			   struct debugfs_cancellation *cancellation);
+
 #else
 
 #include <linux/err.h>
diff --git a/include/linux/device.h b/include/linux/device.h
index d7a72a8749ea03..6c83294395ac08 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1007,6 +1007,8 @@ static inline void device_unlock(struct device *dev)
 	mutex_unlock(&dev->mutex);
 }
 
+DEFINE_GUARD(device, struct device *, device_lock(_T), device_unlock(_T))
+
 static inline void device_lock_assert(struct device *dev)
 {
 	lockdep_assert_held(&dev->mutex);
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index ebe78bd3d121dd..b3772edca2e6e0 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -499,6 +499,21 @@ static inline bool dma_fence_is_later(struct dma_fence *f1,
 }
 
 /**
+ * dma_fence_is_later_or_same - return true if f1 is later or same as f2
+ * @f1: the first fence from the same context
+ * @f2: the second fence from the same context
+ *
+ * Returns true if f1 is chronologically later than f2 or the same fence. Both
+ * fences must be from the same context, since a seqno is not re-used across
+ * contexts.
+ */
+static inline bool dma_fence_is_later_or_same(struct dma_fence *f1,
+					      struct dma_fence *f2)
+{
+	return f1 == f2 || dma_fence_is_later(f1, f2);
+}
+
+/**
  * dma_fence_later - return the chronologically later fence
  * @f1:	the first fence from the same context
  * @f2:	the second fence from the same context
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index f0ccca16a0aca1..4a658de44ee92e 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -144,6 +144,7 @@ bool dma_pci_p2pdma_supported(struct device *dev);
 int dma_set_mask(struct device *dev, u64 mask);
 int dma_set_coherent_mask(struct device *dev, u64 mask);
 u64 dma_get_required_mask(struct device *dev);
+bool dma_addressing_limited(struct device *dev);
 size_t dma_max_mapping_size(struct device *dev);
 size_t dma_opt_mapping_size(struct device *dev);
 bool dma_need_sync(struct device *dev, dma_addr_t dma_addr);
@@ -264,6 +265,10 @@ static inline u64 dma_get_required_mask(struct device *dev)
 {
 	return 0;
 }
+static inline bool dma_addressing_limited(struct device *dev)
+{
+	return false;
+}
 static inline size_t dma_max_mapping_size(struct device *dev)
 {
 	return 0;
@@ -465,20 +470,6 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask)
 	return dma_set_mask_and_coherent(dev, mask);
 }
 
-/**
- * dma_addressing_limited - return if the device is addressing limited
- * @dev:	device to check
- *
- * Return %true if the devices DMA mask is too small to address all memory in
- * the system, else %false.  Lack of addressing bits is the prime reason for
- * bounce buffering, but might not be the only one.
- */
-static inline bool dma_addressing_limited(struct device *dev)
-{
-	return min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
-			    dma_get_required_mask(dev);
-}
-
 static inline unsigned int dma_get_max_seg_size(struct device *dev)
 {
 	if (dev->dma_parms && dev->dma_parms->max_segment_size)
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 226a36ed5aa1fc..689028257fccbd 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -1045,10 +1045,10 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add,
 
 /**
  * ethtool_sprintf - Write formatted string to ethtool string data
- * @data: Pointer to start of string to update
+ * @data: Pointer to a pointer to the start of string to update
  * @fmt: Format of string to write
  *
- * Write formatted string to data. Update data to point at start of
+ * Write formatted string to *data. Update *data to point at start of
  * next string.
  */
 extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...);
diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h
index 45fca09b231943..69501e0ec239f9 100644
--- a/include/linux/export-internal.h
+++ b/include/linux/export-internal.h
@@ -50,9 +50,7 @@
 	    "	.previous"						"\n"	\
 	)
 
-#ifdef CONFIG_IA64
-#define KSYM_FUNC(name)		@fptr(name)
-#elif defined(CONFIG_PARISC) && defined(CONFIG_64BIT)
+#if defined(CONFIG_PARISC) && defined(CONFIG_64BIT)
 #define KSYM_FUNC(name)		P%name
 #else
 #define KSYM_FUNC(name)		name
diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h
index ff8fa58d5818b3..ca49947f0a775a 100644
--- a/include/linux/fw_table.h
+++ b/include/linux/fw_table.h
@@ -25,9 +25,6 @@ struct acpi_subtable_proc {
 	int count;
 };
 
-#include <linux/acpi.h>
-#include <acpi/acpi.h>
-
 union acpi_subtable_headers {
 	struct acpi_subtable_header common;
 	struct acpi_hmat_structure hmat;
diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h
index 6730ee900ee1c9..13b1e65fbdccb7 100644
--- a/include/linux/hid-sensor-ids.h
+++ b/include/linux/hid-sensor-ids.h
@@ -21,10 +21,6 @@
 #define HID_USAGE_SENSOR_ALS					0x200041
 #define HID_USAGE_SENSOR_DATA_LIGHT				0x2004d0
 #define HID_USAGE_SENSOR_LIGHT_ILLUM				0x2004d1
-#define HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE		0x2004d2
-#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY			0x2004d3
-#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X			0x2004d4
-#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y			0x2004d5
 
 /* PROX (200011) */
 #define HID_USAGE_SENSOR_PROX                                   0x200011
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 5a8387a4a71263..bf43f3ff666400 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -679,6 +679,7 @@ struct hid_device {							/* device report descriptor */
 	struct list_head debug_list;
 	spinlock_t  debug_list_lock;
 	wait_queue_head_t debug_wait;
+	struct kref			ref;
 
 	unsigned int id;						/* system unique id */
 
@@ -687,6 +688,8 @@ struct hid_device {							/* device report descriptor */
 #endif /* CONFIG_BPF */
 };
 
+void hiddev_free(struct kref *ref);
+
 #define to_hid_device(pdev) \
 	container_of(pdev, struct hid_device, dev)
 
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 4cacc0e43b5139..be20cff4ba7370 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -454,7 +454,7 @@ static inline void memcpy_from_folio(char *to, struct folio *folio,
 		memcpy(to, from, chunk);
 		kunmap_local(from);
 
-		from += chunk;
+		to += chunk;
 		offset += chunk;
 		len -= chunk;
 	} while (len > 0);
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 0ee140176f102f..f2044d5a652b5c 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -531,9 +531,9 @@ extern void sysrq_timer_list_show(void);
 
 int hrtimers_prepare_cpu(unsigned int cpu);
 #ifdef CONFIG_HOTPLUG_CPU
-int hrtimers_dead_cpu(unsigned int cpu);
+int hrtimers_cpu_dying(unsigned int cpu);
 #else
-#define hrtimers_dead_cpu	NULL
+#define hrtimers_cpu_dying	NULL
 #endif
 
 #endif
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d3acecc5db4b33..236ec7b63c5413 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -1268,10 +1268,7 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
 	return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
 }
 
-static inline bool __vma_private_lock(struct vm_area_struct *vma)
-{
-	return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data;
-}
+bool __vma_private_lock(struct vm_area_struct *vma);
 
 /*
  * Safe version of huge_pte_offset() to check the locks.  See comments
diff --git a/include/linux/idr.h b/include/linux/idr.h
index a0dce14090a9e1..da5f5fa4a3a6ae 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -200,7 +200,7 @@ static inline void idr_preload_end(void)
  */
 #define idr_for_each_entry_ul(idr, entry, tmp, id)			\
 	for (tmp = 0, id = 0;						\
-	     tmp <= id && ((entry) = idr_get_next_ul(idr, &(id))) != NULL; \
+	     ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \
 	     tmp = id, ++id)
 
 /**
@@ -224,10 +224,12 @@ static inline void idr_preload_end(void)
  * @id: Entry ID.
  *
  * Continue to iterate over entries, continuing after the current position.
+ * After normal termination @entry is left with the value NULL.  This
+ * is convenient for a "not found" value.
  */
 #define idr_for_each_entry_continue_ul(idr, entry, tmp, id)		\
 	for (tmp = id;							\
-	     tmp <= id && ((entry) = idr_get_next_ul(idr, &(id))) != NULL; \
+	     ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \
 	     tmp = id, ++id)
 
 /*
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 958771bac9c029..2b5e500bf0930f 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2830,12 +2830,14 @@ ieee80211_he_oper_size(const u8 *he_oper_ie)
 static inline const struct ieee80211_he_6ghz_oper *
 ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper)
 {
-	const u8 *ret = (const void *)&he_oper->optional;
+	const u8 *ret;
 	u32 he_oper_params;
 
 	if (!he_oper)
 		return NULL;
 
+	ret = (const void *)&he_oper->optional;
+
 	he_oper_params = le32_to_cpu(he_oper->he_oper_params);
 
 	if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO))
@@ -4445,7 +4447,8 @@ ieee80211_is_protected_dual_of_public_action(struct sk_buff *skb)
 		action != WLAN_PUB_ACTION_LOC_TRACK_NOTI &&
 		action != WLAN_PUB_ACTION_FTM_REQUEST &&
 		action != WLAN_PUB_ACTION_FTM_RESPONSE &&
-		action != WLAN_PUB_ACTION_FILS_DISCOVERY;
+		action != WLAN_PUB_ACTION_FILS_DISCOVERY &&
+		action != WLAN_PUB_ACTION_VENDOR_SPECIFIC;
 }
 
 /**
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index d3009d56af0ba3..239a4f68801bb5 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -340,6 +340,9 @@ struct io_ring_ctx {
 
 	struct list_head	io_buffers_cache;
 
+	/* deferred free list, protected by ->uring_lock */
+	struct hlist_head	io_buf_list;
+
 	/* Keep this last, we don't need it for the fast path */
 	struct wait_queue_head		poll_wq;
 	struct io_restriction		restrictions;
@@ -431,6 +434,7 @@ enum {
 	/* keep async read/write and isreg together and in order */
 	REQ_F_SUPPORT_NOWAIT_BIT,
 	REQ_F_ISREG_BIT,
+	REQ_F_POLL_NO_LAZY_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -498,6 +502,8 @@ enum {
 	REQ_F_CLEAR_POLLIN	= BIT(REQ_F_CLEAR_POLLIN_BIT),
 	/* hashed into ->cancel_hash_locked, protected by ->uring_lock */
 	REQ_F_HASH_LOCKED	= BIT(REQ_F_HASH_LOCKED_BIT),
+	/* don't use lazy poll wake for this request */
+	REQ_F_POLL_NO_LAZY	= BIT(REQ_F_POLL_NO_LAZY_BIT),
 };
 
 typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index ec289c1016f5f2..6291aa7b079b0d 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -845,6 +845,7 @@ static inline void dev_iommu_priv_set(struct device *dev, void *priv)
 	dev->iommu->priv = priv;
 }
 
+extern struct mutex iommu_probe_device_lock;
 int iommu_probe_device(struct device *dev);
 
 int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 6dcbb4eb80fb20..beb30719ee161b 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1374,6 +1374,9 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum2,		CSUM_V2)
 JBD2_FEATURE_INCOMPAT_FUNCS(csum3,		CSUM_V3)
 JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 
+/* Journal high priority write IO operation flags */
+#define JBD2_JOURNAL_REQ_FLAGS		(REQ_META | REQ_SYNC | REQ_IDLE)
+
 /*
  * Journal flag definitions
  */
diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index 7d985a1dfe4af9..5caf3ce823733a 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -73,6 +73,7 @@ struct key_type {
 
 	unsigned int flags;
 #define KEY_TYPE_NET_DOMAIN	0x00000001 /* Keys of this type have a net namespace domain */
+#define KEY_TYPE_INSTANT_REAP	0x00000002 /* Keys of this type don't have a delay after expiring */
 
 	/* vet a description */
 	int (*vet_description)(const char *description);
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 365eb092e9c4e9..0ff44d6633e339 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -139,7 +139,7 @@ static inline bool kprobe_ftrace(struct kprobe *p)
  *
  */
 struct kretprobe_holder {
-	struct kretprobe	*rp;
+	struct kretprobe __rcu *rp;
 	struct objpool_head	pool;
 };
 
@@ -197,10 +197,8 @@ extern int arch_trampoline_kprobe(struct kprobe *p);
 #ifdef CONFIG_KRETPROBE_ON_RETHOOK
 static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri)
 {
-	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(),
-		"Kretprobe is accessed from instance under preemptive context");
-
-	return (struct kretprobe *)READ_ONCE(ri->node.rethook->data);
+	/* rethook::data is non-changed field, so that you can access it freely. */
+	return (struct kretprobe *)ri->node.rethook->data;
 }
 static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri)
 {
@@ -245,10 +243,7 @@ unsigned long kretprobe_trampoline_handler(struct pt_regs *regs,
 
 static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri)
 {
-	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(),
-		"Kretprobe is accessed from instance under preemptive context");
-
-	return READ_ONCE(ri->rph->rp);
+	return rcu_dereference_check(ri->rph->rp, rcu_read_lock_any_held());
 }
 
 static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri)
@@ -445,6 +440,10 @@ int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 
 int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
 			    char *type, char *sym);
+
+int kprobe_exceptions_notify(struct notifier_block *self,
+			     unsigned long val, void *data);
+
 #else /* !CONFIG_KPROBES: */
 
 static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 99b8176c3738d1..ff217a5ce55214 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -48,7 +48,7 @@ LSM_HOOK(int, 0, quota_on, struct dentry *dentry)
 LSM_HOOK(int, 0, syslog, int type)
 LSM_HOOK(int, 0, settime, const struct timespec64 *ts,
 	 const struct timezone *tz)
-LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages)
+LSM_HOOK(int, 1, vm_enough_memory, struct mm_struct *mm, long pages)
 LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm)
 LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, const struct file *file)
 LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm)
@@ -273,7 +273,7 @@ LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen)
 LSM_HOOK(void, LSM_RET_VOID, inode_invalidate_secctx, struct inode *inode)
 LSM_HOOK(int, 0, inode_notifysecctx, struct inode *inode, void *ctx, u32 ctxlen)
 LSM_HOOK(int, 0, inode_setsecctx, struct dentry *dentry, void *ctx, u32 ctxlen)
-LSM_HOOK(int, 0, inode_getsecctx, struct inode *inode, void **ctx,
+LSM_HOOK(int, -EOPNOTSUPP, inode_getsecctx, struct inode *inode, void **ctx,
 	 u32 *ctxlen)
 
 #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE)
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 8fa23bdcedbf98..007fd9c3e4b62c 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -420,7 +420,7 @@ static inline u32 linkmode_adv_to_mii_t1_adv_m_t(unsigned long *advertising)
  * A function that translates value of following registers to the linkmode:
  * IEEE 802.3-2018 45.2.3.10 "EEE control and capability 1" register (3.20)
  * IEEE 802.3-2018 45.2.7.13 "EEE advertisement 1" register (7.60)
- * IEEE 802.3-2018 45.2.7.14 "EEE "link partner ability 1 register (7.61)
+ * IEEE 802.3-2018 45.2.7.14 "EEE link partner ability 1" register (7.61)
  */
 static inline void mii_eee_cap1_mod_linkmode_t(unsigned long *adv, u32 val)
 {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6f3631425f386d..3f7b664d625b94 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -621,7 +621,7 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 
 	u8         reserved_at_140[0x8];
 	u8         bth_dst_qp[0x18];
-	u8	   reserved_at_160[0x20];
+	u8	   inner_esp_spi[0x20];
 	u8	   outer_esp_spi[0x20];
 	u8         reserved_at_1a0[0x60];
 };
@@ -12001,6 +12001,13 @@ enum {
 	MLX5_IPSEC_ASO_INC_SN            = 0x2,
 };
 
+enum {
+	MLX5_IPSEC_ASO_REPLAY_WIN_32BIT  = 0x0,
+	MLX5_IPSEC_ASO_REPLAY_WIN_64BIT  = 0x1,
+	MLX5_IPSEC_ASO_REPLAY_WIN_128BIT = 0x2,
+	MLX5_IPSEC_ASO_REPLAY_WIN_256BIT = 0x3,
+};
+
 struct mlx5_ifc_ipsec_aso_bits {
 	u8         valid[0x1];
 	u8         reserved_at_201[0x1];
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 418d26608ece70..da5219b48d5229 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -886,8 +886,8 @@ static inline bool vma_is_anonymous(struct vm_area_struct *vma)
  */
 static inline bool vma_is_initial_heap(const struct vm_area_struct *vma)
 {
-       return vma->vm_start <= vma->vm_mm->brk &&
-		vma->vm_end >= vma->vm_mm->start_brk;
+	return vma->vm_start < vma->vm_mm->brk &&
+		vma->vm_end > vma->vm_mm->start_brk;
 }
 
 /*
@@ -901,8 +901,8 @@ static inline bool vma_is_initial_stack(const struct vm_area_struct *vma)
 	 * its "stack".  It's not even well-defined for programs written
 	 * languages like Go.
 	 */
-       return vma->vm_start <= vma->vm_mm->start_stack &&
-	       vma->vm_end >= vma->vm_mm->start_stack;
+	return vma->vm_start <= vma->vm_mm->start_stack &&
+		vma->vm_end >= vma->vm_mm->start_stack;
 }
 
 static inline bool vma_is_temporary_stack(struct vm_area_struct *vma)
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 9ae7def16cb2a9..f4fe593c1400e6 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -232,22 +232,27 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio,
 	if (folio_test_unevictable(folio) || !lrugen->enabled)
 		return false;
 	/*
-	 * There are three common cases for this page:
-	 * 1. If it's hot, e.g., freshly faulted in or previously hot and
-	 *    migrated, add it to the youngest generation.
-	 * 2. If it's cold but can't be evicted immediately, i.e., an anon page
-	 *    not in swapcache or a dirty page pending writeback, add it to the
-	 *    second oldest generation.
-	 * 3. Everything else (clean, cold) is added to the oldest generation.
+	 * There are four common cases for this page:
+	 * 1. If it's hot, i.e., freshly faulted in, add it to the youngest
+	 *    generation, and it's protected over the rest below.
+	 * 2. If it can't be evicted immediately, i.e., a dirty page pending
+	 *    writeback, add it to the second youngest generation.
+	 * 3. If it should be evicted first, e.g., cold and clean from
+	 *    folio_rotate_reclaimable(), add it to the oldest generation.
+	 * 4. Everything else falls between 2 & 3 above and is added to the
+	 *    second oldest generation if it's considered inactive, or the
+	 *    oldest generation otherwise. See lru_gen_is_active().
 	 */
 	if (folio_test_active(folio))
 		seq = lrugen->max_seq;
 	else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) ||
 		 (folio_test_reclaim(folio) &&
 		  (folio_test_dirty(folio) || folio_test_writeback(folio))))
-		seq = lrugen->min_seq[type] + 1;
-	else
+		seq = lrugen->max_seq - 1;
+	else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq)
 		seq = lrugen->min_seq[type];
+	else
+		seq = lrugen->min_seq[type] + 1;
 
 	gen = lru_gen_from_seq(seq);
 	flags = (gen + 1UL) << LRU_GEN_PGOFF;
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index daa2f40d9ce65f..7b12eebc5586dc 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -295,7 +295,9 @@ struct mmc_card {
 #define MMC_QUIRK_BROKEN_HPI	(1<<13)		/* Disable broken HPI support */
 #define MMC_QUIRK_BROKEN_SD_DISCARD	(1<<14)	/* Disable broken SD discard support */
 #define MMC_QUIRK_BROKEN_SD_CACHE	(1<<15)	/* Disable broken SD cache support */
+#define MMC_QUIRK_BROKEN_CACHE_FLUSH	(1<<16)	/* Don't flush cache until the write has occurred */
 
+	bool			written_flag;	/* Indicates eMMC has been written since power on */
 	bool			reenable_cmdq;	/* Re-enable Command Queue */
 
 	unsigned int		erase_size;	/* erase size in sectors */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3c25226beeed47..9db36e1977125b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -505,33 +505,37 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
  * the old generation, is incremented when all its bins become empty.
  *
  * There are four operations:
- * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its
+ * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its
  *    current generation (old or young) and updates its "seg" to "head";
- * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its
+ * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its
  *    current generation (old or young) and updates its "seg" to "tail";
- * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old
+ * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old
  *    generation, updates its "gen" to "old" and resets its "seg" to "default";
- * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the
+ * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the
  *    young generation, updates its "gen" to "young" and resets its "seg" to
  *    "default".
  *
  * The events that trigger the above operations are:
  * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD;
- * 2. The first attempt to reclaim an memcg below low, which triggers
+ * 2. The first attempt to reclaim a memcg below low, which triggers
  *    MEMCG_LRU_TAIL;
- * 3. The first attempt to reclaim an memcg below reclaimable size threshold,
- *    which triggers MEMCG_LRU_TAIL;
- * 4. The second attempt to reclaim an memcg below reclaimable size threshold,
- *    which triggers MEMCG_LRU_YOUNG;
- * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG;
+ * 3. The first attempt to reclaim a memcg offlined or below reclaimable size
+ *    threshold, which triggers MEMCG_LRU_TAIL;
+ * 4. The second attempt to reclaim a memcg offlined or below reclaimable size
+ *    threshold, which triggers MEMCG_LRU_YOUNG;
+ * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG;
  * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG;
- * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD.
+ * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD.
  *
- * Note that memcg LRU only applies to global reclaim, and the round-robin
- * incrementing of their max_seq counters ensures the eventual fairness to all
- * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
+ * Notes:
+ * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing
+ *    of their max_seq counters ensures the eventual fairness to all eligible
+ *    memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
+ * 2. There are only two valid generations: old (seq) and young (seq+1).
+ *    MEMCG_NR_GENS is set to three so that when reading the generation counter
+ *    locklessly, a stale value (seq-1) does not wraparound to young.
  */
-#define MEMCG_NR_GENS	2
+#define MEMCG_NR_GENS	3
 #define MEMCG_NR_BINS	8
 
 struct lru_gen_memcg {
diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h
index 057c89867aa2f3..b8da2db4ecd295 100644
--- a/include/linux/mnt_idmapping.h
+++ b/include/linux/mnt_idmapping.h
@@ -115,6 +115,9 @@ static inline bool vfsgid_eq_kgid(vfsgid_t vfsgid, kgid_t kgid)
 
 int vfsgid_in_group_p(vfsgid_t vfsgid);
 
+struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap);
+void mnt_idmap_put(struct mnt_idmap *idmap);
+
 vfsuid_t make_vfsuid(struct mnt_idmap *idmap,
 		     struct user_namespace *fs_userns, kuid_t kuid);
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a16c9cc063fe0e..2564e209465ea8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1797,6 +1797,13 @@ enum netdev_ml_priv_type {
 	ML_PRIV_CAN,
 };
 
+enum netdev_stat_type {
+	NETDEV_PCPU_STAT_NONE,
+	NETDEV_PCPU_STAT_LSTATS, /* struct pcpu_lstats */
+	NETDEV_PCPU_STAT_TSTATS, /* struct pcpu_sw_netstats */
+	NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */
+};
+
 /**
  *	struct net_device - The DEVICE structure.
  *
@@ -1991,10 +1998,14 @@ enum netdev_ml_priv_type {
  *
  * 	@ml_priv:	Mid-layer private
  *	@ml_priv_type:  Mid-layer private type
- * 	@lstats:	Loopback statistics
- * 	@tstats:	Tunnel statistics
- * 	@dstats:	Dummy statistics
- * 	@vstats:	Virtual ethernet statistics
+ *
+ *	@pcpu_stat_type:	Type of device statistics which the core should
+ *				allocate/free: none, lstats, tstats, dstats. none
+ *				means the driver is handling statistics allocation/
+ *				freeing internally.
+ *	@lstats:		Loopback statistics: packets, bytes
+ *	@tstats:		Tunnel statistics: RX/TX packets, RX/TX bytes
+ *	@dstats:		Dummy statistics: RX/TX/drop packets, RX/TX bytes
  *
  *	@garp_port:	GARP
  *	@mrp_port:	MRP
@@ -2354,6 +2365,7 @@ struct net_device {
 	void				*ml_priv;
 	enum netdev_ml_priv_type	ml_priv_type;
 
+	enum netdev_stat_type		pcpu_stat_type:8;
 	union {
 		struct pcpu_lstats __percpu		*lstats;
 		struct pcpu_sw_netstats __percpu	*tstats;
@@ -2755,6 +2767,16 @@ struct pcpu_sw_netstats {
 	struct u64_stats_sync   syncp;
 } __aligned(4 * sizeof(u64));
 
+struct pcpu_dstats {
+	u64			rx_packets;
+	u64			rx_bytes;
+	u64			rx_drops;
+	u64			tx_packets;
+	u64			tx_bytes;
+	u64			tx_drops;
+	struct u64_stats_sync	syncp;
+} __aligned(8 * sizeof(u64));
+
 struct pcpu_lstats {
 	u64_stats_t packets;
 	u64_stats_t bytes;
diff --git a/include/linux/nvme-keyring.h b/include/linux/nvme-keyring.h
index 4efea9dd967c1b..e10333d78dbbe5 100644
--- a/include/linux/nvme-keyring.h
+++ b/include/linux/nvme-keyring.h
@@ -6,14 +6,12 @@
 #ifndef _NVME_KEYRING_H
 #define _NVME_KEYRING_H
 
-#ifdef CONFIG_NVME_KEYRING
+#if IS_ENABLED(CONFIG_NVME_KEYRING)
 
 key_serial_t nvme_tls_psk_default(struct key *keyring,
 		const char *hostnqn, const char *subnqn);
 
 key_serial_t nvme_keyring_id(void);
-int nvme_keyring_init(void);
-void nvme_keyring_exit(void);
 
 #else
 
@@ -26,11 +24,5 @@ static inline key_serial_t nvme_keyring_id(void)
 {
 	return 0;
 }
-static inline int nvme_keyring_init(void)
-{
-	return 0;
-}
-static inline void nvme_keyring_exit(void) {}
-
 #endif /* !CONFIG_NVME_KEYRING */
 #endif /* _NVME_KEYRING_H */
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index a7ba74babad73a..44325c068b6a01 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -1732,7 +1732,7 @@ struct nvmf_auth_dhchap_success1_data {
 	__u8		rsvd2;
 	__u8		rvalid;
 	__u8		rsvd3[7];
-	/* 'hl' bytes of response value if 'rvalid' is set */
+	/* 'hl' bytes of response value */
 	__u8		rval[];
 };
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index bcc1ea44b4e854..06142ff7f9ce0e 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -204,6 +204,8 @@ enum mapping_flags {
 	AS_NO_WRITEBACK_TAGS = 5,
 	AS_LARGE_FOLIO_SUPPORT = 6,
 	AS_RELEASE_ALWAYS,	/* Call ->release_folio(), even if no private data */
+	AS_STABLE_WRITES,	/* must wait for writeback before modifying
+				   folio contents */
 };
 
 /**
@@ -289,6 +291,21 @@ static inline void mapping_clear_release_always(struct address_space *mapping)
 	clear_bit(AS_RELEASE_ALWAYS, &mapping->flags);
 }
 
+static inline bool mapping_stable_writes(const struct address_space *mapping)
+{
+	return test_bit(AS_STABLE_WRITES, &mapping->flags);
+}
+
+static inline void mapping_set_stable_writes(struct address_space *mapping)
+{
+	set_bit(AS_STABLE_WRITES, &mapping->flags);
+}
+
+static inline void mapping_clear_stable_writes(struct address_space *mapping)
+{
+	clear_bit(AS_STABLE_WRITES, &mapping->flags);
+}
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
 	return mapping->gfp_mask;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 60ca768bc8679f..dea043bc1e383a 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1829,6 +1829,7 @@ extern bool pcie_ports_native;
 int pci_disable_link_state(struct pci_dev *pdev, int state);
 int pci_disable_link_state_locked(struct pci_dev *pdev, int state);
 int pci_enable_link_state(struct pci_dev *pdev, int state);
+int pci_enable_link_state_locked(struct pci_dev *pdev, int state);
 void pcie_no_aspm(void);
 bool pcie_aspm_support_enabled(void);
 bool pcie_aspm_enabled(struct pci_dev *pdev);
@@ -1839,6 +1840,8 @@ static inline int pci_disable_link_state_locked(struct pci_dev *pdev, int state)
 { return 0; }
 static inline int pci_enable_link_state(struct pci_dev *pdev, int state)
 { return 0; }
+static inline int pci_enable_link_state_locked(struct pci_dev *pdev, int state)
+{ return 0; }
 static inline void pcie_no_aspm(void) { }
 static inline bool pcie_aspm_support_enabled(void) { return false; }
 static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index afb028c54f3397..5547ba68e6e47d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -843,11 +843,11 @@ struct perf_event {
 };
 
 /*
- *           ,-----------------------[1:n]----------------------.
- *           V                                                  V
- * perf_event_context <-[1:n]-> perf_event_pmu_context <--- perf_event
- *           ^                      ^     |                     |
- *           `--------[1:n]---------'     `-[n:1]-> pmu <-[1:n]-'
+ *           ,-----------------------[1:n]------------------------.
+ *           V                                                    V
+ * perf_event_context <-[1:n]-> perf_event_pmu_context <-[1:n]- perf_event
+ *                                        |                       |
+ *                                        `--[n:1]-> pmu <-[1:n]--'
  *
  *
  * struct perf_event_pmu_context  lifetime is refcount based and RCU freed
@@ -865,6 +865,9 @@ struct perf_event {
  * ctx->mutex pinning the configuration. Since we hold a reference on
  * group_leader (through the filedesc) it can't go away, therefore it's
  * associated pmu_ctx must exist and cannot change due to ctx->mutex.
+ *
+ * perf_event holds a refcount on perf_event_context
+ * perf_event holds a refcount on perf_event_pmu_context
  */
 struct perf_event_pmu_context {
 	struct pmu			*pmu;
diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h
index 63e630276499f8..ab1c7deff118f3 100644
--- a/include/linux/platform_data/x86/asus-wmi.h
+++ b/include/linux/platform_data/x86/asus-wmi.h
@@ -114,6 +114,9 @@
 /* Charging mode - 1=Barrel, 2=USB */
 #define ASUS_WMI_DEVID_CHARGE_MODE	0x0012006C
 
+/* MCU powersave mode */
+#define ASUS_WMI_DEVID_MCU_POWERSAVE   0x001200E2
+
 /* epu is connected? 1 == true */
 #define ASUS_WMI_DEVID_EGPU_CONNECTED	0x00090018
 /* egpu on/off */
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index e3b437587b32d7..cda3597b84f2c3 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -41,8 +41,8 @@ struct pwm_args {
 };
 
 enum {
-	PWMF_REQUESTED = 1 << 0,
-	PWMF_EXPORTED = 1 << 1,
+	PWMF_REQUESTED = 0,
+	PWMF_EXPORTED = 1,
 };
 
 /*
diff --git a/include/linux/rethook.h b/include/linux/rethook.h
index ce69b2b7bc3586..ba60962805f6d7 100644
--- a/include/linux/rethook.h
+++ b/include/linux/rethook.h
@@ -28,7 +28,12 @@ typedef void (*rethook_handler_t) (struct rethook_node *, void *, unsigned long,
  */
 struct rethook {
 	void			*data;
-	rethook_handler_t	handler;
+	/*
+	 * To avoid sparse warnings, this uses a raw function pointer with
+	 * __rcu, instead of rethook_handler_t. But this must be same as
+	 * rethook_handler_t.
+	 */
+	void (__rcu *handler) (struct rethook_node *, void *, unsigned long, struct pt_regs *);
 	struct objpool_head	pool;
 	struct rcu_head		rcu;
 };
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index c1637515a8a416..c953b8c0d2f433 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -106,6 +106,7 @@ struct sk_psock {
 	struct mutex			work_mutex;
 	struct sk_psock_work_state	work_state;
 	struct delayed_work		work;
+	struct sock			*sk_pair;
 	struct rcu_work			rwork;
 };
 
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 86825c88b5767a..255a0562aea5a8 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -566,6 +566,7 @@ struct spi_controller {
 #define SPI_CONTROLLER_MUST_RX		BIT(3)	/* Requires rx */
 #define SPI_CONTROLLER_MUST_TX		BIT(4)	/* Requires tx */
 #define SPI_CONTROLLER_GPIO_SS		BIT(5)	/* GPIO CS must select slave */
+#define SPI_CONTROLLER_SUSPENDED	BIT(6)	/* Currently suspended */
 
 	/* Flag indicating if the allocation of this struct is devres-managed */
 	bool			devm_allocated;
diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h
index c36e7a3b45e7e7..3be2cb564710b5 100644
--- a/include/linux/stackleak.h
+++ b/include/linux/stackleak.h
@@ -14,6 +14,7 @@
 
 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK
 #include <asm/stacktrace.h>
+#include <linux/linkage.h>
 
 /*
  * The lowest address on tsk's stack which we can plausibly erase.
@@ -76,6 +77,11 @@ static inline void stackleak_task_init(struct task_struct *t)
 # endif
 }
 
+asmlinkage void noinstr stackleak_erase(void);
+asmlinkage void noinstr stackleak_erase_on_task_stack(void);
+asmlinkage void noinstr stackleak_erase_off_task_stack(void);
+void __no_caller_saved_registers noinstr stackleak_track_stack(void);
+
 #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */
 static inline void stackleak_task_init(struct task_struct *t) { }
 #endif
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 0b4658a7eceb62..dee5ad6e48c5a0 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -175,6 +175,7 @@ struct stmmac_fpe_cfg {
 	bool hs_enable;				/* FPE handshake enable */
 	enum stmmac_fpe_state lp_fpe_state;	/* Link Partner FPE state */
 	enum stmmac_fpe_state lo_fpe_state;	/* Local station FPE state */
+	u32 fpe_csr;				/* MAC_FPE_CTRL_STS reg cache */
 };
 
 struct stmmac_safety_feature_cfg {
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index ec4e9367f5b03b..b646b574b060d6 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -152,7 +152,7 @@ struct tcp_request_sock {
 	u64				snt_synack; /* first SYNACK sent time */
 	bool				tfo_listener;
 	bool				is_mptcp;
-	s8				req_usec_ts;
+	bool				req_usec_ts;
 #if IS_ENABLED(CONFIG_MPTCP)
 	bool				drop_req;
 #endif
@@ -169,7 +169,7 @@ struct tcp_request_sock {
 #ifdef CONFIG_TCP_AO
 	u8				ao_keyid;
 	u8				ao_rcv_next;
-	u8				maclen;
+	bool				used_tcp_ao;
 #endif
 };
 
@@ -180,14 +180,10 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
 
 static inline bool tcp_rsk_used_ao(const struct request_sock *req)
 {
-	/* The real length of MAC is saved in the request socket,
-	 * signing anything with zero-length makes no sense, so here is
-	 * a little hack..
-	 */
 #ifndef CONFIG_TCP_AO
 	return false;
 #else
-	return tcp_rsk(req)->maclen != 0;
+	return tcp_rsk(req)->used_tcp_ao;
 #endif
 }
 
diff --git a/include/linux/units.h b/include/linux/units.h
index ff1bd6b5f5b372..45110daaf8d326 100644
--- a/include/linux/units.h
+++ b/include/linux/units.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_UNITS_H
 #define _LINUX_UNITS_H
 
+#include <linux/bits.h>
 #include <linux/math.h>
 
 /* Metric prefixes in accordance with Système international (d'unités) */
diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h
index b513749582d775..e4de6bc1f69b62 100644
--- a/include/linux/usb/phy.h
+++ b/include/linux/usb/phy.h
@@ -144,10 +144,6 @@ struct usb_phy {
 	 */
 	int	(*set_wakeup)(struct usb_phy *x, bool enabled);
 
-	/* notify phy port status change */
-	int	(*notify_port_status)(struct usb_phy *x, int port,
-				      u16 portstatus, u16 portchange);
-
 	/* notify phy connect status change */
 	int	(*notify_connect)(struct usb_phy *x,
 			enum usb_device_speed speed);
@@ -321,15 +317,6 @@ usb_phy_set_wakeup(struct usb_phy *x, bool enabled)
 }
 
 static inline int
-usb_phy_notify_port_status(struct usb_phy *x, int port, u16 portstatus, u16 portchange)
-{
-	if (x && x->notify_port_status)
-		return x->notify_port_status(x, port, portstatus, portchange);
-	else
-		return 0;
-}
-
-static inline int
 usb_phy_notify_connect(struct usb_phy *x, enum usb_device_speed speed)
 {
 	if (x && x->notify_connect)
diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h
index 287e9d83fb8bc3..33a4c146dc19c4 100644
--- a/include/linux/usb/r8152.h
+++ b/include/linux/usb/r8152.h
@@ -30,6 +30,7 @@
 #define VENDOR_ID_NVIDIA		0x0955
 #define VENDOR_ID_TPLINK		0x2357
 #define VENDOR_ID_DLINK			0x2001
+#define VENDOR_ID_ASUS			0x0b05
 
 #if IS_REACHABLE(CONFIG_USB_RTL8152)
 extern u8 rtl8152_get_version(struct usb_interface *intf);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 454e9295970c49..a65b2513f8cdcb 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -289,16 +289,12 @@ void vfio_combine_iova_ranges(struct rb_root_cached *root, u32 cur_nodes,
 /*
  * External user API
  */
-#if IS_ENABLED(CONFIG_VFIO_GROUP)
 struct iommu_group *vfio_file_iommu_group(struct file *file);
+
+#if IS_ENABLED(CONFIG_VFIO_GROUP)
 bool vfio_file_is_group(struct file *file);
 bool vfio_file_has_dev(struct file *file, struct vfio_device *device);
 #else
-static inline struct iommu_group *vfio_file_iommu_group(struct file *file)
-{
-	return NULL;
-}
-
 static inline bool vfio_file_is_group(struct file *file)
 {
 	return false;
diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
index d0f2797420f704..a09e13a577a99a 100644
--- a/include/linux/virtio_pci_modern.h
+++ b/include/linux/virtio_pci_modern.h
@@ -5,13 +5,6 @@
 #include <linux/pci.h>
 #include <linux/virtio_pci.h>
 
-struct virtio_pci_modern_common_cfg {
-	struct virtio_pci_common_cfg cfg;
-
-	__le16 queue_notify_data;	/* read-write */
-	__le16 queue_reset;		/* read-write */
-};
-
 /**
  * struct virtio_pci_modern_device - info for modern PCI virtio
  * @pci_dev:	    Ptr to the PCI device struct
diff --git a/include/linux/vlynq.h b/include/linux/vlynq.h
deleted file mode 100644
index e9c0cd36c48aea..00000000000000
--- a/include/linux/vlynq.h
+++ /dev/null
@@ -1,149 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2006, 2007 Eugene Konev <ejka@openwrt.org>
- */
-
-#ifndef __VLYNQ_H__
-#define __VLYNQ_H__
-
-#include <linux/device.h>
-#include <linux/types.h>
-
-struct module;
-
-#define VLYNQ_NUM_IRQS 32
-
-struct vlynq_mapping {
-	u32 size;
-	u32 offset;
-};
-
-enum vlynq_divisor {
-	vlynq_div_auto = 0,
-	vlynq_ldiv1,
-	vlynq_ldiv2,
-	vlynq_ldiv3,
-	vlynq_ldiv4,
-	vlynq_ldiv5,
-	vlynq_ldiv6,
-	vlynq_ldiv7,
-	vlynq_ldiv8,
-	vlynq_rdiv1,
-	vlynq_rdiv2,
-	vlynq_rdiv3,
-	vlynq_rdiv4,
-	vlynq_rdiv5,
-	vlynq_rdiv6,
-	vlynq_rdiv7,
-	vlynq_rdiv8,
-	vlynq_div_external
-};
-
-struct vlynq_device_id {
-	u32 id;
-	enum vlynq_divisor divisor;
-	unsigned long driver_data;
-};
-
-struct vlynq_regs;
-struct vlynq_device {
-	u32 id, dev_id;
-	int local_irq;
-	int remote_irq;
-	enum vlynq_divisor divisor;
-	u32 regs_start, regs_end;
-	u32 mem_start, mem_end;
-	u32 irq_start, irq_end;
-	int irq;
-	int enabled;
-	struct vlynq_regs *local;
-	struct vlynq_regs *remote;
-	struct device dev;
-};
-
-struct vlynq_driver {
-	char *name;
-	struct vlynq_device_id *id_table;
-	int (*probe)(struct vlynq_device *dev, struct vlynq_device_id *id);
-	void (*remove)(struct vlynq_device *dev);
-	struct device_driver driver;
-};
-
-struct plat_vlynq_ops {
-	int (*on)(struct vlynq_device *dev);
-	void (*off)(struct vlynq_device *dev);
-};
-
-static inline struct vlynq_driver *to_vlynq_driver(struct device_driver *drv)
-{
-	return container_of(drv, struct vlynq_driver, driver);
-}
-
-static inline struct vlynq_device *to_vlynq_device(struct device *device)
-{
-	return container_of(device, struct vlynq_device, dev);
-}
-
-extern struct bus_type vlynq_bus_type;
-
-extern int __vlynq_register_driver(struct vlynq_driver *driver,
-				   struct module *owner);
-
-static inline int vlynq_register_driver(struct vlynq_driver *driver)
-{
-	return __vlynq_register_driver(driver, THIS_MODULE);
-}
-
-static inline void *vlynq_get_drvdata(struct vlynq_device *dev)
-{
-	return dev_get_drvdata(&dev->dev);
-}
-
-static inline void vlynq_set_drvdata(struct vlynq_device *dev, void *data)
-{
-	dev_set_drvdata(&dev->dev, data);
-}
-
-static inline u32 vlynq_mem_start(struct vlynq_device *dev)
-{
-	return dev->mem_start;
-}
-
-static inline u32 vlynq_mem_end(struct vlynq_device *dev)
-{
-	return dev->mem_end;
-}
-
-static inline u32 vlynq_mem_len(struct vlynq_device *dev)
-{
-	return dev->mem_end - dev->mem_start + 1;
-}
-
-static inline int vlynq_virq_to_irq(struct vlynq_device *dev, int virq)
-{
-	int irq = dev->irq_start + virq;
-	if ((irq < dev->irq_start) || (irq > dev->irq_end))
-		return -EINVAL;
-
-	return irq;
-}
-
-static inline int vlynq_irq_to_virq(struct vlynq_device *dev, int irq)
-{
-	if ((irq < dev->irq_start) || (irq > dev->irq_end))
-		return -EINVAL;
-
-	return irq - dev->irq_start;
-}
-
-extern void vlynq_unregister_driver(struct vlynq_driver *driver);
-extern int vlynq_enable_device(struct vlynq_device *dev);
-extern void vlynq_disable_device(struct vlynq_device *dev);
-extern int vlynq_set_local_mapping(struct vlynq_device *dev, u32 tx_offset,
-				   struct vlynq_mapping *mapping);
-extern int vlynq_set_remote_mapping(struct vlynq_device *dev, u32 tx_offset,
-				    struct vlynq_mapping *mapping);
-extern int vlynq_set_local_irq(struct vlynq_device *dev, int virq);
-extern int vlynq_set_remote_irq(struct vlynq_device *dev, int virq);
-
-#endif /* __VLYNQ_H__ */
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 82da55101b5a30..61ebe723ee4d50 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -31,17 +31,22 @@ struct prefix_info {
 	__u8			length;
 	__u8			prefix_len;
 
+	union __packed {
+		__u8		flags;
+		struct __packed {
 #if defined(__BIG_ENDIAN_BITFIELD)
-	__u8			onlink : 1,
+			__u8	onlink : 1,
 			 	autoconf : 1,
 				reserved : 6;
 #elif defined(__LITTLE_ENDIAN_BITFIELD)
-	__u8			reserved : 6,
+			__u8	reserved : 6,
 				autoconf : 1,
 				onlink : 1;
 #else
 #error "Please fix <asm/byteorder.h>"
 #endif
+		};
+	};
 	__be32			valid;
 	__be32			prefered;
 	__be32			reserved2;
@@ -49,6 +54,9 @@ struct prefix_info {
 	struct in6_addr		prefix;
 };
 
+/* rfc4861 4.6.2: IPv6 PIO is 32 bytes in size */
+static_assert(sizeof(struct prefix_info) == 32);
+
 #include <linux/ipv6.h>
 #include <linux/netdevice.h>
 #include <net/if_inet6.h>
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 824c258143a3ab..49c4640027d8a6 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -75,6 +75,7 @@ struct unix_sock {
 };
 
 #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk)
+#define unix_peer(sk) (unix_sk(sk)->peer)
 
 #define peer_wait peer_wq.wait
 
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 20988623c5cc27..a3a1ea2696a804 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -189,6 +189,7 @@ struct blocked_key {
 struct smp_csrk {
 	bdaddr_t bdaddr;
 	u8 bdaddr_type;
+	u8 link_type;
 	u8 type;
 	u8 val[16];
 };
@@ -198,6 +199,7 @@ struct smp_ltk {
 	struct rcu_head rcu;
 	bdaddr_t bdaddr;
 	u8 bdaddr_type;
+	u8 link_type;
 	u8 authenticated;
 	u8 type;
 	u8 enc_size;
@@ -212,6 +214,7 @@ struct smp_irk {
 	bdaddr_t rpa;
 	bdaddr_t bdaddr;
 	u8 addr_type;
+	u8 link_type;
 	u8 val[16];
 };
 
@@ -219,6 +222,8 @@ struct link_key {
 	struct list_head list;
 	struct rcu_head rcu;
 	bdaddr_t bdaddr;
+	u8 bdaddr_type;
+	u8 link_type;
 	u8 type;
 	u8 val[HCI_LINK_KEY_SIZE];
 	u8 pin_len;
@@ -1227,11 +1232,11 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev,
 			continue;
 
 		/* Match CIG ID if set */
-		if (cig != BT_ISO_QOS_CIG_UNSET && cig != c->iso_qos.ucast.cig)
+		if (cig != c->iso_qos.ucast.cig)
 			continue;
 
 		/* Match CIS ID if set */
-		if (id != BT_ISO_QOS_CIS_UNSET && id != c->iso_qos.ucast.cis)
+		if (id != c->iso_qos.ucast.cis)
 			continue;
 
 		/* Match destination address if set */
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index b137a33a1b6892..4ecfb06c413dbf 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -9299,4 +9299,50 @@ bool cfg80211_valid_disable_subchannel_bitmap(u16 *bitmap,
  */
 void cfg80211_links_removed(struct net_device *dev, u16 link_mask);
 
+#ifdef CONFIG_CFG80211_DEBUGFS
+/**
+ * wiphy_locked_debugfs_read - do a locked read in debugfs
+ * @wiphy: the wiphy to use
+ * @file: the file being read
+ * @buf: the buffer to fill and then read from
+ * @bufsize: size of the buffer
+ * @userbuf: the user buffer to copy to
+ * @count: read count
+ * @ppos: read position
+ * @handler: the read handler to call (under wiphy lock)
+ * @data: additional data to pass to the read handler
+ */
+ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file,
+				  char *buf, size_t bufsize,
+				  char __user *userbuf, size_t count,
+				  loff_t *ppos,
+				  ssize_t (*handler)(struct wiphy *wiphy,
+						     struct file *file,
+						     char *buf,
+						     size_t bufsize,
+						     void *data),
+				  void *data);
+
+/**
+ * wiphy_locked_debugfs_write - do a locked write in debugfs
+ * @wiphy: the wiphy to use
+ * @file: the file being written to
+ * @buf: the buffer to copy the user data to
+ * @bufsize: size of the buffer
+ * @userbuf: the user buffer to copy from
+ * @count: read count
+ * @handler: the write handler to call (under wiphy lock)
+ * @data: additional data to pass to the write handler
+ */
+ssize_t wiphy_locked_debugfs_write(struct wiphy *wiphy, struct file *file,
+				   char *buf, size_t bufsize,
+				   const char __user *userbuf, size_t count,
+				   ssize_t (*handler)(struct wiphy *wiphy,
+						      struct file *file,
+						      char *buf,
+						      size_t count,
+						      void *data),
+				   void *data);
+#endif
+
 #endif /* __NET_CFG80211_H */
diff --git a/include/net/flow.h b/include/net/flow.h
index 7f0adda3bf2fed..335bbc52171c10 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -40,8 +40,8 @@ struct flowi_common {
 #define FLOWI_FLAG_KNOWN_NH		0x02
 	__u32	flowic_secid;
 	kuid_t  flowic_uid;
-	struct flowi_tunnel flowic_tun_key;
 	__u32		flowic_multipath_hash;
+	struct flowi_tunnel flowic_tun_key;
 };
 
 union flowi_uli {
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index e18a4c0d69eedc..c53244f2043704 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -12,10 +12,12 @@
  * struct genl_multicast_group - generic netlink multicast group
  * @name: name of the multicast group, names are per-family
  * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM)
+ * @cap_sys_admin: whether %CAP_SYS_ADMIN is required for binding
  */
 struct genl_multicast_group {
 	char			name[GENL_NAMSIZ];
 	u8			flags;
+	u8			cap_sys_admin:1;
 };
 
 struct genl_split_ops;
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 3e454c4d7ba623..f07642264c1eb6 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -22,10 +22,6 @@
 #define IF_RS_SENT	0x10
 #define IF_READY	0x80000000
 
-/* prefix flags */
-#define IF_PREFIX_ONLINK	0x01
-#define IF_PREFIX_AUTOCONF	0x02
-
 enum {
 	INET6_IFADDR_STATE_PREDAD,
 	INET6_IFADDR_STATE_DAD,
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 1ba9f4ddf2f6db..9ba6413fd2e3ea 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -179,9 +179,6 @@ struct fib6_info {
 
 	refcount_t			fib6_ref;
 	unsigned long			expires;
-
-	struct hlist_node		gc_link;
-
 	struct dst_metrics		*fib6_metrics;
 #define fib6_pmtu		fib6_metrics->metrics[RTAX_MTU-1]
 
@@ -250,6 +247,19 @@ static inline bool fib6_requires_src(const struct fib6_info *rt)
 	return rt->fib6_src.plen > 0;
 }
 
+static inline void fib6_clean_expires(struct fib6_info *f6i)
+{
+	f6i->fib6_flags &= ~RTF_EXPIRES;
+	f6i->expires = 0;
+}
+
+static inline void fib6_set_expires(struct fib6_info *f6i,
+				    unsigned long expires)
+{
+	f6i->expires = expires;
+	f6i->fib6_flags |= RTF_EXPIRES;
+}
+
 static inline bool fib6_check_expired(const struct fib6_info *f6i)
 {
 	if (f6i->fib6_flags & RTF_EXPIRES)
@@ -257,11 +267,6 @@ static inline bool fib6_check_expired(const struct fib6_info *f6i)
 	return false;
 }
 
-static inline bool fib6_has_expires(const struct fib6_info *f6i)
-{
-	return f6i->fib6_flags & RTF_EXPIRES;
-}
-
 /* Function to safely get fn->fn_sernum for passed in rt
  * and store result in passed in cookie.
  * Return true if we can get cookie safely
@@ -383,7 +388,6 @@ struct fib6_table {
 	struct inet_peer_base	tb6_peers;
 	unsigned int		flags;
 	unsigned int		fib_seq;
-	struct hlist_head       tb6_gc_hlist;	/* GC candidates */
 #define RT6_TABLE_HAS_DFLT_ROUTER	BIT(0)
 };
 
@@ -500,48 +504,6 @@ void fib6_gc_cleanup(void);
 
 int fib6_init(void);
 
-/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be
- * NULL.
- */
-static inline void fib6_set_expires_locked(struct fib6_info *f6i,
-					   unsigned long expires)
-{
-	struct fib6_table *tb6;
-
-	tb6 = f6i->fib6_table;
-	f6i->expires = expires;
-	if (tb6 && !fib6_has_expires(f6i))
-		hlist_add_head(&f6i->gc_link, &tb6->tb6_gc_hlist);
-	f6i->fib6_flags |= RTF_EXPIRES;
-}
-
-/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be
- * NULL.  If fib6_table is NULL, the fib6_info will no be inserted into the
- * list of GC candidates until it is inserted into a table.
- */
-static inline void fib6_set_expires(struct fib6_info *f6i,
-				    unsigned long expires)
-{
-	spin_lock_bh(&f6i->fib6_table->tb6_lock);
-	fib6_set_expires_locked(f6i, expires);
-	spin_unlock_bh(&f6i->fib6_table->tb6_lock);
-}
-
-static inline void fib6_clean_expires_locked(struct fib6_info *f6i)
-{
-	if (fib6_has_expires(f6i))
-		hlist_del_init(&f6i->gc_link);
-	f6i->fib6_flags &= ~RTF_EXPIRES;
-	f6i->expires = 0;
-}
-
-static inline void fib6_clean_expires(struct fib6_info *f6i)
-{
-	spin_lock_bh(&f6i->fib6_table->tb6_lock);
-	fib6_clean_expires_locked(f6i);
-	spin_unlock_bh(&f6i->fib6_table->tb6_lock);
-}
-
 struct ipv6_route_iter {
 	struct seq_net_private p;
 	struct fib6_walker w;
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 07022bb0d44d4b..0d28172193fa63 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -162,7 +162,7 @@ struct neighbour {
 	struct rcu_head		rcu;
 	struct net_device	*dev;
 	netdevice_tracker	dev_tracker;
-	u8			primary_key[0];
+	u8			primary_key[];
 } __randomize_layout;
 
 struct neigh_ops {
diff --git a/include/net/netfilter/nf_conntrack_act_ct.h b/include/net/netfilter/nf_conntrack_act_ct.h
index 078d3c52c03f98..e5f2f0b73a9a0d 100644
--- a/include/net/netfilter/nf_conntrack_act_ct.h
+++ b/include/net/netfilter/nf_conntrack_act_ct.h
@@ -20,7 +20,22 @@ static inline struct nf_conn_act_ct_ext *nf_conn_act_ct_ext_find(const struct nf
 #endif
 }
 
-static inline struct nf_conn_act_ct_ext *nf_conn_act_ct_ext_add(struct nf_conn *ct)
+static inline void nf_conn_act_ct_ext_fill(struct sk_buff *skb, struct nf_conn *ct,
+					   enum ip_conntrack_info ctinfo)
+{
+#if IS_ENABLED(CONFIG_NET_ACT_CT)
+	struct nf_conn_act_ct_ext *act_ct_ext;
+
+	act_ct_ext = nf_conn_act_ct_ext_find(ct);
+	if (dev_net(skb->dev) == &init_net && act_ct_ext)
+		act_ct_ext->ifindex[CTINFO2DIR(ctinfo)] = skb->dev->ifindex;
+#endif
+}
+
+static inline struct
+nf_conn_act_ct_ext *nf_conn_act_ct_ext_add(struct sk_buff *skb,
+					   struct nf_conn *ct,
+					   enum ip_conntrack_info ctinfo)
 {
 #if IS_ENABLED(CONFIG_NET_ACT_CT)
 	struct nf_conn_act_ct_ext *act_ct = nf_ct_ext_find(ct, NF_CT_EXT_ACT_CT);
@@ -29,22 +44,11 @@ static inline struct nf_conn_act_ct_ext *nf_conn_act_ct_ext_add(struct nf_conn *
 		return act_ct;
 
 	act_ct = nf_ct_ext_add(ct, NF_CT_EXT_ACT_CT, GFP_ATOMIC);
+	nf_conn_act_ct_ext_fill(skb, ct, ctinfo);
 	return act_ct;
 #else
 	return NULL;
 #endif
 }
 
-static inline void nf_conn_act_ct_ext_fill(struct sk_buff *skb, struct nf_conn *ct,
-					   enum ip_conntrack_info ctinfo)
-{
-#if IS_ENABLED(CONFIG_NET_ACT_CT)
-	struct nf_conn_act_ct_ext *act_ct_ext;
-
-	act_ct_ext = nf_conn_act_ct_ext_find(ct);
-	if (dev_net(skb->dev) == &init_net && act_ct_ext)
-		act_ct_ext->ifindex[CTINFO2DIR(ctinfo)] = skb->dev->ifindex;
-#endif
-}
-
 #endif /* _NF_CONNTRACK_ACT_CT_H */
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index fe1507c1db828b..692d5955911c7d 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -62,6 +62,8 @@ struct nf_flowtable_type {
 						  enum flow_offload_tuple_dir dir,
 						  struct nf_flow_rule *flow_rule);
 	void				(*free)(struct nf_flowtable *ft);
+	void				(*get)(struct nf_flowtable *ft);
+	void				(*put)(struct nf_flowtable *ft);
 	nf_hookfn			*hook;
 	struct module			*owner;
 };
@@ -240,6 +242,11 @@ nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table,
 	}
 
 	list_add_tail(&block_cb->list, &block->cb_list);
+	up_write(&flow_table->flow_block_lock);
+
+	if (flow_table->type->get)
+		flow_table->type->get(flow_table);
+	return 0;
 
 unlock:
 	up_write(&flow_table->flow_block_lock);
@@ -262,6 +269,9 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
 		WARN_ON(true);
 	}
 	up_write(&flow_table->flow_block_lock);
+
+	if (flow_table->type->put)
+		flow_table->type->put(flow_table);
 }
 
 void flow_offload_route_init(struct flow_offload *flow,
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 3bbd13ab1ecf59..b157c5cafd14cf 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -178,9 +178,9 @@ static inline __be32 nft_reg_load_be32(const u32 *sreg)
 	return *(__force __be32 *)sreg;
 }
 
-static inline void nft_reg_store64(u32 *dreg, u64 val)
+static inline void nft_reg_store64(u64 *dreg, u64 val)
 {
-	put_unaligned(val, (u64 *)dreg);
+	put_unaligned(val, dreg);
 }
 
 static inline u64 nft_reg_load64(const u32 *sreg)
diff --git a/include/net/netkit.h b/include/net/netkit.h
index 0ba2e6b847ca53..9ec0163739f451 100644
--- a/include/net/netkit.h
+++ b/include/net/netkit.h
@@ -10,6 +10,7 @@ int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog);
 int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr);
+INDIRECT_CALLABLE_DECLARE(struct net_device *netkit_peer_dev(struct net_device *dev));
 #else
 static inline int netkit_prog_attach(const union bpf_attr *attr,
 				     struct bpf_prog *prog)
@@ -34,5 +35,10 @@ static inline int netkit_prog_query(const union bpf_attr *attr,
 {
 	return -EINVAL;
 }
+
+static inline struct net_device *netkit_peer_dev(struct net_device *dev)
+{
+	return NULL;
+}
 #endif /* CONFIG_NETKIT */
 #endif /* __NET_NETKIT_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 1d6931caf0c3c1..0201136b0b9caf 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2799,6 +2799,11 @@ static inline bool sk_is_tcp(const struct sock *sk)
 	return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP;
 }
 
+static inline bool sk_is_stream_unix(const struct sock *sk)
+{
+	return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM;
+}
+
 /**
  * sk_eat_skb - Release a skb if it is no longer needed
  * @sk: socket to eat this skb from
diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h
index 8a6dbfb233362b..77f87c622a2ef4 100644
--- a/include/net/tc_act/tc_ct.h
+++ b/include/net/tc_act/tc_ct.h
@@ -58,6 +58,11 @@ static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a)
 	return to_ct_params(a)->nf_ft;
 }
 
+static inline struct nf_conntrack_helper *tcf_ct_helper(const struct tc_action *a)
+{
+	return to_ct_params(a)->helper;
+}
+
 #else
 static inline uint16_t tcf_ct_zone(const struct tc_action *a) { return 0; }
 static inline int tcf_ct_action(const struct tc_action *a) { return 0; }
@@ -65,6 +70,10 @@ static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a)
 {
 	return NULL;
 }
+static inline struct nf_conntrack_helper *tcf_ct_helper(const struct tc_action *a)
+{
+	return NULL;
+}
 #endif /* CONFIG_NF_CONNTRACK */
 
 #if IS_ENABLED(CONFIG_NET_ACT_CT)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d2f0736b76b8b2..144ba48bb07bb9 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1514,17 +1514,22 @@ static inline int tcp_full_space(const struct sock *sk)
 	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
-static inline void tcp_adjust_rcv_ssthresh(struct sock *sk)
+static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh)
 {
 	int unused_mem = sk_unused_reserved_mem(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
+	tp->rcv_ssthresh = min(tp->rcv_ssthresh, new_ssthresh);
 	if (unused_mem)
 		tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh,
 					 tcp_win_from_space(sk, unused_mem));
 }
 
+static inline void tcp_adjust_rcv_ssthresh(struct sock *sk)
+{
+	__tcp_adjust_rcv_ssthresh(sk, 4U * tcp_sk(sk)->advmss);
+}
+
 void tcp_cleanup_rbuf(struct sock *sk, int copied);
 void __tcp_cleanup_rbuf(struct sock *sk, int copied);
 
diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h
index a375a171ef3cb3..6477810806137d 100644
--- a/include/net/tcp_ao.h
+++ b/include/net/tcp_ao.h
@@ -62,11 +62,17 @@ static inline int tcp_ao_maclen(const struct tcp_ao_key *key)
 	return key->maclen;
 }
 
+/* Use tcp_ao_len_aligned() for TCP header calculations */
 static inline int tcp_ao_len(const struct tcp_ao_key *key)
 {
 	return tcp_ao_maclen(key) + sizeof(struct tcp_ao_hdr);
 }
 
+static inline int tcp_ao_len_aligned(const struct tcp_ao_key *key)
+{
+	return round_up(tcp_ao_len(key), 4);
+}
+
 static inline unsigned int tcp_ao_digest_size(struct tcp_ao_key *key)
 {
 	return key->digest_size;
@@ -124,7 +130,7 @@ struct tcp_ao_info {
 #define tcp_hash_fail(msg, family, skb, fmt, ...)			\
 do {									\
 	const struct tcphdr *th = tcp_hdr(skb);				\
-	char hdr_flags[5] = {};						\
+	char hdr_flags[6];						\
 	char *f = hdr_flags;						\
 									\
 	if (th->fin)							\
@@ -133,17 +139,18 @@ do {									\
 		*f++ = 'S';						\
 	if (th->rst)							\
 		*f++ = 'R';						\
+	if (th->psh)							\
+		*f++ = 'P';						\
 	if (th->ack)							\
-		*f++ = 'A';						\
-	if (f != hdr_flags)						\
-		*f = ' ';						\
+		*f++ = '.';						\
+	*f = 0;								\
 	if ((family) == AF_INET) {					\
-		net_info_ratelimited("%s for (%pI4, %d)->(%pI4, %d) %s" fmt "\n", \
+		net_info_ratelimited("%s for %pI4.%d->%pI4.%d [%s] " fmt "\n", \
 				msg, &ip_hdr(skb)->saddr, ntohs(th->source), \
 				&ip_hdr(skb)->daddr, ntohs(th->dest),	\
 				hdr_flags, ##__VA_ARGS__);		\
 	} else {							\
-		net_info_ratelimited("%s for [%pI6c]:%u->[%pI6c]:%u %s" fmt "\n", \
+		net_info_ratelimited("%s for [%pI6c].%d->[%pI6c].%d [%s]" fmt "\n", \
 				msg, &ipv6_hdr(skb)->saddr, ntohs(th->source), \
 				&ipv6_hdr(skb)->daddr, ntohs(th->dest),	\
 				hdr_flags, ##__VA_ARGS__);		\
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 95896472a82bfb..565a850445414d 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -77,6 +77,13 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
 {
 	__rdma_block_iter_start(biter, umem->sgt_append.sgt.sgl,
 				umem->sgt_append.sgt.nents, pgsz);
+	biter->__sg_advance = ib_umem_offset(umem) & ~(pgsz - 1);
+	biter->__sg_numblocks = ib_umem_num_dma_blocks(umem, pgsz);
+}
+
+static inline bool __rdma_umem_block_iter_next(struct ib_block_iter *biter)
+{
+	return __rdma_block_iter_next(biter) && biter->__sg_numblocks--;
 }
 
 /**
@@ -92,7 +99,7 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
  */
 #define rdma_umem_for_each_dma_block(umem, biter, pgsz)                        \
 	for (__rdma_umem_block_iter_start(biter, umem, pgsz);                  \
-	     __rdma_block_iter_next(biter);)
+	     __rdma_umem_block_iter_next(biter);)
 
 #ifdef CONFIG_INFINIBAND_USER_MEM
 
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index fb1a2d6b196900..b7b6b58dd3486d 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2850,6 +2850,7 @@ struct ib_block_iter {
 	/* internal states */
 	struct scatterlist *__sg;	/* sg holding the current aligned block */
 	dma_addr_t __dma_addr;		/* unaligned DMA address of this block */
+	size_t __sg_numblocks;		/* ib_umem_num_dma_blocks() */
 	unsigned int __sg_nents;	/* number of SG entries */
 	unsigned int __sg_advance;	/* number of bytes to advance in sg in next step */
 	unsigned int __pg_bit;		/* alignment of current block */
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 10480eb582b2a6..5ec1e71a09de76 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -167,19 +167,25 @@ struct scsi_device {
 	 * power state for system suspend/resume (suspend to RAM and
 	 * hibernation) operations.
 	 */
-	bool manage_system_start_stop;
+	unsigned manage_system_start_stop:1;
 
 	/*
 	 * If true, let the high-level device driver (sd) manage the device
 	 * power state for runtime device suspand and resume operations.
 	 */
-	bool manage_runtime_start_stop;
+	unsigned manage_runtime_start_stop:1;
 
 	/*
 	 * If true, let the high-level device driver (sd) manage the device
 	 * power state for system shutdown (power off) operations.
 	 */
-	bool manage_shutdown;
+	unsigned manage_shutdown:1;
+
+	/*
+	 * If set and if the device is runtime suspended, ask the high-level
+	 * device driver (sd) to force a runtime resume of the device.
+	 */
+	unsigned force_runtime_start_on_system_start:1;
 
 	unsigned removable:1;
 	unsigned changed:1;	/* Data invalid due to media change */
diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h
index 043f8ac65dbf69..68e053fe73403d 100644
--- a/include/sound/cs35l41.h
+++ b/include/sound/cs35l41.h
@@ -906,6 +906,6 @@ int cs35l41_init_boost(struct device *dev, struct regmap *regmap,
 bool cs35l41_safe_reset(struct regmap *regmap, enum cs35l41_boost_type b_type);
 int cs35l41_mdsync_up(struct regmap *regmap);
 int cs35l41_global_enable(struct device *dev, struct regmap *regmap, enum cs35l41_boost_type b_type,
-			  int enable, bool firmware_running);
+			  int enable, struct cs_dsp *dsp);
 
 #endif /* __CS35L41_H */
diff --git a/include/trace/events/9p.h b/include/trace/events/9p.h
index 4dfa6d7f83baa9..cd104a1343e2d6 100644
--- a/include/trace/events/9p.h
+++ b/include/trace/events/9p.h
@@ -178,18 +178,21 @@ TRACE_EVENT(9p_protocol_dump,
 		    __field(	void *,		clnt				)
 		    __field(	__u8,		type				)
 		    __field(	__u16,		tag				)
-		    __array(	unsigned char,	line,	P9_PROTO_DUMP_SZ	)
+		    __dynamic_array(unsigned char, line,
+				min_t(size_t, pdu->capacity, P9_PROTO_DUMP_SZ))
 		    ),
 
 	    TP_fast_assign(
 		    __entry->clnt   =  clnt;
 		    __entry->type   =  pdu->id;
 		    __entry->tag    =  pdu->tag;
-		    memcpy(__entry->line, pdu->sdata, P9_PROTO_DUMP_SZ);
+		    memcpy(__get_dynamic_array(line), pdu->sdata,
+				__get_dynamic_array_len(line));
 		    ),
-	    TP_printk("clnt %lu %s(tag = %d)\n%.3x: %16ph\n%.3x: %16ph\n",
+	    TP_printk("clnt %lu %s(tag = %d)\n%*ph\n",
 		      (unsigned long)__entry->clnt, show_9p_op(__entry->type),
-		      __entry->tag, 0, __entry->line, 16, __entry->line + 16)
+		      __entry->tag, __get_dynamic_array_len(line),
+		      __get_dynamic_array(line))
  );
 
 
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 4c53a5ef6257b8..f7e537f64db457 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -328,7 +328,7 @@
 	E_(rxrpc_rtt_tx_ping,			"PING")
 
 #define rxrpc_rtt_rx_traces \
-	EM(rxrpc_rtt_rx_cancel,			"CNCL") \
+	EM(rxrpc_rtt_rx_other_ack,		"OACK") \
 	EM(rxrpc_rtt_rx_obsolete,		"OBSL") \
 	EM(rxrpc_rtt_rx_lost,			"LOST") \
 	EM(rxrpc_rtt_rx_ping_response,		"PONG") \
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index c25fc96145947e..d24e8e121507bb 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -219,6 +219,22 @@
  */
 #define BTRFS_METADATA_ITEM_KEY	169
 
+/*
+ * Special inline ref key which stores the id of the subvolume which originally
+ * created the extent. This subvolume owns the extent permanently from the
+ * perspective of simple quotas. Needed to know which subvolume to free quota
+ * usage from when the extent is deleted.
+ *
+ * Stored as an inline ref rather to avoid wasting space on a separate item on
+ * top of the existing extent item. However, unlike the other inline refs,
+ * there is one one owner ref per extent rather than one per extent.
+ *
+ * Because of this, it goes at the front of the list of inline refs, and thus
+ * must have a lower type value than any other inline ref type (to satisfy the
+ * disk format rule that inline refs have non-decreasing type).
+ */
+#define BTRFS_EXTENT_OWNER_REF_KEY	172
+
 #define BTRFS_TREE_BLOCK_REF_KEY	176
 
 #define BTRFS_EXTENT_DATA_REF_KEY	178
@@ -234,14 +250,6 @@
 #define BTRFS_SHARED_DATA_REF_KEY	184
 
 /*
- * Special inline ref key which stores the id of the subvolume which originally
- * created the extent. This subvolume owns the extent permanently from the
- * perspective of simple quotas. Needed to know which subvolume to free quota
- * usage from when the extent is deleted.
- */
-#define BTRFS_EXTENT_OWNER_REF_KEY	188
-
-/*
  * block groups give us hints into the extent allocation trees.  Which
  * blocks are free etc etc
  */
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index 6c80f96049bd07..282e90aeb163c0 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -116,5 +116,8 @@
 #define AT_HANDLE_FID		AT_REMOVEDIR	/* file handle is needed to
 					compare object identity and may not
 					be usable to open_by_handle_at(2) */
+#if defined(__KERNEL__)
+#define AT_GETATTR_NOSEC	0x80000000
+#endif
 
 #endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index db92a7202b342b..e7418d15fe3906 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -209,7 +209,7 @@
  *  - add FUSE_HAS_EXPIRE_ONLY
  *
  *  7.39
- *  - add FUSE_DIRECT_IO_RELAX
+ *  - add FUSE_DIRECT_IO_ALLOW_MMAP
  *  - add FUSE_STATX and related structures
  */
 
@@ -409,8 +409,7 @@ struct fuse_file_lock {
  * FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir,
  *			symlink and mknod (single group that matches parent)
  * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation
- * FUSE_DIRECT_IO_RELAX: relax restrictions in FOPEN_DIRECT_IO mode, for now
- *                       allow shared mmap
+ * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode.
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -449,7 +448,10 @@ struct fuse_file_lock {
 #define FUSE_HAS_INODE_DAX	(1ULL << 33)
 #define FUSE_CREATE_SUPP_GROUP	(1ULL << 34)
 #define FUSE_HAS_EXPIRE_ONLY	(1ULL << 35)
-#define FUSE_DIRECT_IO_RELAX	(1ULL << 36)
+#define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36)
+
+/* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */
+#define FUSE_DIRECT_IO_RELAX	FUSE_DIRECT_IO_ALLOW_MMAP
 
 /**
  * CUSE INIT request/reply flags
diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h
index c8ae72466ee644..3cd044edee5d89 100644
--- a/include/uapi/linux/nfsd_netlink.h
+++ b/include/uapi/linux/nfsd_netlink.h
@@ -3,8 +3,8 @@
 /*	Documentation/netlink/specs/nfsd.yaml */
 /* YNL-GEN uapi header */
 
-#ifndef _UAPI_LINUX_NFSD_H
-#define _UAPI_LINUX_NFSD_H
+#ifndef _UAPI_LINUX_NFSD_NETLINK_H
+#define _UAPI_LINUX_NFSD_NETLINK_H
 
 #define NFSD_FAMILY_NAME	"nfsd"
 #define NFSD_FAMILY_VERSION	1
@@ -36,4 +36,4 @@ enum {
 	NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1)
 };
 
-#endif /* _UAPI_LINUX_NFSD_H */
+#endif /* _UAPI_LINUX_NFSD_NETLINK_H */
diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h
index 5c6c4269f7efe4..2ec6f35cda32e9 100644
--- a/include/uapi/linux/stddef.h
+++ b/include/uapi/linux/stddef.h
@@ -27,7 +27,7 @@
 	union { \
 		struct { MEMBERS } ATTRS; \
 		struct TAG { MEMBERS } ATTRS NAME; \
-	}
+	} ATTRS
 
 #ifdef __cplusplus
 /* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */
diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h
index 4a195b68f28f6d..b383c2fe0cf354 100644
--- a/include/uapi/linux/v4l2-subdev.h
+++ b/include/uapi/linux/v4l2-subdev.h
@@ -239,7 +239,7 @@ struct v4l2_subdev_routing {
  * set (which is the default), the 'stream' fields will be forced to 0 by the
  * kernel.
  */
- #define V4L2_SUBDEV_CLIENT_CAP_STREAMS		(1U << 0)
+ #define V4L2_SUBDEV_CLIENT_CAP_STREAMS		(1ULL << 0)
 
 /**
  * struct v4l2_subdev_client_capability - Capabilities of the client accessing
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index f703afc7ad31ba..44f4dd2add1880 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -166,6 +166,17 @@ struct virtio_pci_common_cfg {
 	__le32 queue_used_hi;		/* read-write */
 };
 
+/*
+ * Warning: do not use sizeof on this: use offsetofend for
+ * specific fields you need.
+ */
+struct virtio_pci_modern_common_cfg {
+	struct virtio_pci_common_cfg cfg;
+
+	__le16 queue_notify_data;	/* read-write */
+	__le16 queue_reset;		/* read-write */
+};
+
 /* Fields in VIRTIO_PCI_CAP_PCI_CFG: */
 struct virtio_pci_cfg_cap {
 	struct virtio_pci_cap cap;
diff --git a/include/xen/events.h b/include/xen/events.h
index 23932b0673dc74..3b07409f80320e 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -88,7 +88,6 @@ void xen_irq_resume(void);
 
 /* Clear an irq's pending state, in preparation for polling on it */
 void xen_clear_irq_pending(int irq);
-void xen_set_irq_pending(int irq);
 bool xen_test_irq_pending(int irq);
 
 /* Poll waiting for an irq to become pending.  In the usual case, the
@@ -101,8 +100,8 @@ void xen_poll_irq_timeout(int irq, u64 timeout);
 
 /* Determine the IRQ which is bound to an event channel */
 unsigned int irq_from_evtchn(evtchn_port_t evtchn);
-int irq_from_virq(unsigned int cpu, unsigned int virq);
-evtchn_port_t evtchn_from_irq(unsigned irq);
+int irq_evtchn_from_virq(unsigned int cpu, unsigned int virq,
+			 evtchn_port_t *evtchn);
 
 int xen_set_callback_via(uint64_t via);
 int xen_evtchn_do_upcall(void);
@@ -122,9 +121,6 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 /* De-allocates the above mentioned physical interrupt. */
 int xen_destroy_irq(int irq);
 
-/* Return irq from pirq */
-int xen_irq_from_pirq(unsigned pirq);
-
 /* Return the pirq allocated to the irq. */
 int xen_pirq_from_irq(unsigned irq);
 
diff --git a/io_uring/cancel.c b/io_uring/cancel.c
index 3c19cccb1aecf9..8a8b07dfc444cd 100644
--- a/io_uring/cancel.c
+++ b/io_uring/cancel.c
@@ -273,7 +273,7 @@ int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg)
 	};
 	ktime_t timeout = KTIME_MAX;
 	struct io_uring_sync_cancel_reg sc;
-	struct fd f = { };
+	struct file *file = NULL;
 	DEFINE_WAIT(wait);
 	int ret, i;
 
@@ -295,10 +295,10 @@ int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg)
 	/* we can grab a normal file descriptor upfront */
 	if ((cd.flags & IORING_ASYNC_CANCEL_FD) &&
 	   !(cd.flags & IORING_ASYNC_CANCEL_FD_FIXED)) {
-		f = fdget(sc.fd);
-		if (!f.file)
+		file = fget(sc.fd);
+		if (!file)
 			return -EBADF;
-		cd.file = f.file;
+		cd.file = file;
 	}
 
 	ret = __io_sync_cancel(current->io_uring, &cd, sc.fd);
@@ -348,6 +348,7 @@ int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg)
 	if (ret == -ENOENT || ret > 0)
 		ret = 0;
 out:
-	fdput(f);
+	if (file)
+		fput(file);
 	return ret;
 }
diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index f04a43044d917c..976e9500f6518c 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -145,13 +145,8 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 	if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) {
 		struct io_sq_data *sq = ctx->sq_data;
 
-		if (mutex_trylock(&sq->lock)) {
-			if (sq->thread) {
-				sq_pid = task_pid_nr(sq->thread);
-				sq_cpu = task_cpu(sq->thread);
-			}
-			mutex_unlock(&sq->lock);
-		}
+		sq_pid = sq->task_pid;
+		sq_cpu = sq->sq_cpu;
 	}
 
 	seq_printf(m, "SqThread:\t%d\n", sq_pid);
diff --git a/io_uring/fs.c b/io_uring/fs.c
index 08e3b175469c68..eccea851dd5a28 100644
--- a/io_uring/fs.c
+++ b/io_uring/fs.c
@@ -254,7 +254,7 @@ int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	newf = u64_to_user_ptr(READ_ONCE(sqe->addr2));
 	lnk->flags = READ_ONCE(sqe->hardlink_flags);
 
-	lnk->oldpath = getname(oldf);
+	lnk->oldpath = getname_uflags(oldf, lnk->flags);
 	if (IS_ERR(lnk->oldpath))
 		return PTR_ERR(lnk->oldpath);
 
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index ed254076c72333..9626a363f12136 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -271,6 +271,7 @@ static __cold void io_fallback_req_func(struct work_struct *work)
 	struct io_kiocb *req, *tmp;
 	struct io_tw_state ts = { .locked = true, };
 
+	percpu_ref_get(&ctx->refs);
 	mutex_lock(&ctx->uring_lock);
 	llist_for_each_entry_safe(req, tmp, node, io_task_work.node)
 		req->io_task_work.func(req, &ts);
@@ -278,6 +279,7 @@ static __cold void io_fallback_req_func(struct work_struct *work)
 		return;
 	io_submit_flush_completions(ctx);
 	mutex_unlock(&ctx->uring_lock);
+	percpu_ref_put(&ctx->refs);
 }
 
 static int io_alloc_hash_table(struct io_hash_table *table, unsigned bits)
@@ -325,6 +327,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	INIT_LIST_HEAD(&ctx->sqd_list);
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
 	INIT_LIST_HEAD(&ctx->io_buffers_cache);
+	INIT_HLIST_HEAD(&ctx->io_buf_list);
 	io_alloc_cache_init(&ctx->rsrc_node_cache, IO_NODE_ALLOC_CACHE_MAX,
 			    sizeof(struct io_rsrc_node));
 	io_alloc_cache_init(&ctx->apoll_cache, IO_ALLOC_CACHE_MAX,
@@ -2666,7 +2669,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0;
 }
 
-static void io_mem_free(void *ptr)
+void io_mem_free(void *ptr)
 {
 	if (!ptr)
 		return;
@@ -2697,6 +2700,7 @@ static void *__io_uaddr_map(struct page ***pages, unsigned short *npages,
 {
 	struct page **page_array;
 	unsigned int nr_pages;
+	void *page_addr;
 	int ret, i;
 
 	*npages = 0;
@@ -2718,27 +2722,29 @@ err:
 		io_pages_free(&page_array, ret > 0 ? ret : 0);
 		return ret < 0 ? ERR_PTR(ret) : ERR_PTR(-EFAULT);
 	}
-	/*
-	 * Should be a single page. If the ring is small enough that we can
-	 * use a normal page, that is fine. If we need multiple pages, then
-	 * userspace should use a huge page. That's the only way to guarantee
-	 * that we get contigious memory, outside of just being lucky or
-	 * (currently) having low memory fragmentation.
-	 */
-	if (page_array[0] != page_array[ret - 1])
-		goto err;
 
-	/*
-	 * Can't support mapping user allocated ring memory on 32-bit archs
-	 * where it could potentially reside in highmem. Just fail those with
-	 * -EINVAL, just like we did on kernels that didn't support this
-	 * feature.
-	 */
+	page_addr = page_address(page_array[0]);
 	for (i = 0; i < nr_pages; i++) {
-		if (PageHighMem(page_array[i])) {
-			ret = -EINVAL;
+		ret = -EINVAL;
+
+		/*
+		 * Can't support mapping user allocated ring memory on 32-bit
+		 * archs where it could potentially reside in highmem. Just
+		 * fail those with -EINVAL, just like we did on kernels that
+		 * didn't support this feature.
+		 */
+		if (PageHighMem(page_array[i]))
 			goto err;
-		}
+
+		/*
+		 * No support for discontig pages for now, should either be a
+		 * single normal page, or a huge page. Later on we can add
+		 * support for remapping discontig pages, for now we will
+		 * just fail them with EINVAL.
+		 */
+		if (page_address(page_array[i]) != page_addr)
+			goto err;
+		page_addr += PAGE_SIZE;
 	}
 
 	*pages = page_array;
@@ -2775,7 +2781,7 @@ static void io_rings_free(struct io_ring_ctx *ctx)
 	}
 }
 
-static void *io_mem_alloc(size_t size)
+void *io_mem_alloc(size_t size)
 {
 	gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP;
 	void *ret;
@@ -2947,6 +2953,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 		ctx->mm_account = NULL;
 	}
 	io_rings_free(ctx);
+	io_kbuf_mmap_list_free(ctx);
 
 	percpu_ref_exit(&ctx->refs);
 	free_uid(ctx->user);
@@ -3141,12 +3148,7 @@ static __cold void io_ring_exit_work(struct work_struct *work)
 	init_completion(&exit.completion);
 	init_task_work(&exit.task_work, io_tctx_exit_cb);
 	exit.ctx = ctx;
-	/*
-	 * Some may use context even when all refs and requests have been put,
-	 * and they are free to do so while still holding uring_lock or
-	 * completion_lock, see io_req_task_submit(). Apart from other work,
-	 * this lock/unlock section also waits them to finish.
-	 */
+
 	mutex_lock(&ctx->uring_lock);
 	while (!list_empty(&ctx->tctx_list)) {
 		WARN_ON_ONCE(time_after(jiffies, timeout));
@@ -3475,25 +3477,27 @@ static void *io_uring_validate_mmap_request(struct file *file,
 	struct page *page;
 	void *ptr;
 
-	/* Don't allow mmap if the ring was setup without it */
-	if (ctx->flags & IORING_SETUP_NO_MMAP)
-		return ERR_PTR(-EINVAL);
-
 	switch (offset & IORING_OFF_MMAP_MASK) {
 	case IORING_OFF_SQ_RING:
 	case IORING_OFF_CQ_RING:
+		/* Don't allow mmap if the ring was setup without it */
+		if (ctx->flags & IORING_SETUP_NO_MMAP)
+			return ERR_PTR(-EINVAL);
 		ptr = ctx->rings;
 		break;
 	case IORING_OFF_SQES:
+		/* Don't allow mmap if the ring was setup without it */
+		if (ctx->flags & IORING_SETUP_NO_MMAP)
+			return ERR_PTR(-EINVAL);
 		ptr = ctx->sq_sqes;
 		break;
 	case IORING_OFF_PBUF_RING: {
 		unsigned int bgid;
 
 		bgid = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT;
-		mutex_lock(&ctx->uring_lock);
+		rcu_read_lock();
 		ptr = io_pbuf_get_address(ctx, bgid);
-		mutex_unlock(&ctx->uring_lock);
+		rcu_read_unlock();
 		if (!ptr)
 			return ERR_PTR(-EINVAL);
 		break;
@@ -3645,7 +3649,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		size_t, argsz)
 {
 	struct io_ring_ctx *ctx;
-	struct fd f;
+	struct file *file;
 	long ret;
 
 	if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP |
@@ -3663,20 +3667,19 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		if (unlikely(!tctx || fd >= IO_RINGFD_REG_MAX))
 			return -EINVAL;
 		fd = array_index_nospec(fd, IO_RINGFD_REG_MAX);
-		f.file = tctx->registered_rings[fd];
-		f.flags = 0;
-		if (unlikely(!f.file))
+		file = tctx->registered_rings[fd];
+		if (unlikely(!file))
 			return -EBADF;
 	} else {
-		f = fdget(fd);
-		if (unlikely(!f.file))
+		file = fget(fd);
+		if (unlikely(!file))
 			return -EBADF;
 		ret = -EOPNOTSUPP;
-		if (unlikely(!io_is_uring_fops(f.file)))
+		if (unlikely(!io_is_uring_fops(file)))
 			goto out;
 	}
 
-	ctx = f.file->private_data;
+	ctx = file->private_data;
 	ret = -EBADFD;
 	if (unlikely(ctx->flags & IORING_SETUP_R_DISABLED))
 		goto out;
@@ -3770,7 +3773,8 @@ iopoll_locked:
 		}
 	}
 out:
-	fdput(f);
+	if (!(flags & IORING_ENTER_REGISTERED_RING))
+		fput(file);
 	return ret;
 }
 
@@ -4611,7 +4615,7 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
 {
 	struct io_ring_ctx *ctx;
 	long ret = -EBADF;
-	struct fd f;
+	struct file *file;
 	bool use_registered_ring;
 
 	use_registered_ring = !!(opcode & IORING_REGISTER_USE_REGISTERED_RING);
@@ -4630,27 +4634,27 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
 		if (unlikely(!tctx || fd >= IO_RINGFD_REG_MAX))
 			return -EINVAL;
 		fd = array_index_nospec(fd, IO_RINGFD_REG_MAX);
-		f.file = tctx->registered_rings[fd];
-		f.flags = 0;
-		if (unlikely(!f.file))
+		file = tctx->registered_rings[fd];
+		if (unlikely(!file))
 			return -EBADF;
 	} else {
-		f = fdget(fd);
-		if (unlikely(!f.file))
+		file = fget(fd);
+		if (unlikely(!file))
 			return -EBADF;
 		ret = -EOPNOTSUPP;
-		if (!io_is_uring_fops(f.file))
+		if (!io_is_uring_fops(file))
 			goto out_fput;
 	}
 
-	ctx = f.file->private_data;
+	ctx = file->private_data;
 
 	mutex_lock(&ctx->uring_lock);
 	ret = __io_uring_register(ctx, opcode, arg, nr_args);
 	mutex_unlock(&ctx->uring_lock);
 	trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs, ret);
 out_fput:
-	fdput(f);
+	if (!use_registered_ring)
+		fput(file);
 	return ret;
 }
 
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index dc6d779b452b9b..ed84f2737b3a3f 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -86,6 +86,9 @@ bool __io_alloc_req_refill(struct io_ring_ctx *ctx);
 bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
 			bool cancel_all);
 
+void *io_mem_alloc(size_t size);
+void io_mem_free(void *ptr);
+
 #if defined(CONFIG_PROVE_LOCKING)
 static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx)
 {
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index fea06810b43dbb..72b6af1d2ed3b0 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -33,26 +33,49 @@ struct io_provide_buf {
 	__u16				bid;
 };
 
+struct io_buf_free {
+	struct hlist_node		list;
+	void				*mem;
+	size_t				size;
+	int				inuse;
+};
+
+static struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx,
+						   struct io_buffer_list *bl,
+						   unsigned int bgid)
+{
+	if (bl && bgid < BGID_ARRAY)
+		return &bl[bgid];
+
+	return xa_load(&ctx->io_bl_xa, bgid);
+}
+
 static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx,
 							unsigned int bgid)
 {
-	if (ctx->io_bl && bgid < BGID_ARRAY)
-		return &ctx->io_bl[bgid];
+	lockdep_assert_held(&ctx->uring_lock);
 
-	return xa_load(&ctx->io_bl_xa, bgid);
+	return __io_buffer_get_list(ctx, ctx->io_bl, bgid);
 }
 
 static int io_buffer_add_list(struct io_ring_ctx *ctx,
 			      struct io_buffer_list *bl, unsigned int bgid)
 {
+	/*
+	 * Store buffer group ID and finally mark the list as visible.
+	 * The normal lookup doesn't care about the visibility as we're
+	 * always under the ->uring_lock, but the RCU lookup from mmap does.
+	 */
 	bl->bgid = bgid;
+	smp_store_release(&bl->is_ready, 1);
+
 	if (bgid < BGID_ARRAY)
 		return 0;
 
 	return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL));
 }
 
-void io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
+bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_buffer_list *bl;
@@ -65,7 +88,7 @@ void io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
 	 * multiple use.
 	 */
 	if (req->flags & REQ_F_PARTIAL_IO)
-		return;
+		return false;
 
 	io_ring_submit_lock(ctx, issue_flags);
 
@@ -76,7 +99,7 @@ void io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
 	req->buf_index = buf->bgid;
 
 	io_ring_submit_unlock(ctx, issue_flags);
-	return;
+	return true;
 }
 
 unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags)
@@ -196,21 +219,40 @@ void __user *io_buffer_select(struct io_kiocb *req, size_t *len,
 
 static __cold int io_init_bl_list(struct io_ring_ctx *ctx)
 {
+	struct io_buffer_list *bl;
 	int i;
 
-	ctx->io_bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list),
-				GFP_KERNEL);
-	if (!ctx->io_bl)
+	bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), GFP_KERNEL);
+	if (!bl)
 		return -ENOMEM;
 
 	for (i = 0; i < BGID_ARRAY; i++) {
-		INIT_LIST_HEAD(&ctx->io_bl[i].buf_list);
-		ctx->io_bl[i].bgid = i;
+		INIT_LIST_HEAD(&bl[i].buf_list);
+		bl[i].bgid = i;
 	}
 
+	smp_store_release(&ctx->io_bl, bl);
 	return 0;
 }
 
+/*
+ * Mark the given mapped range as free for reuse
+ */
+static void io_kbuf_mark_free(struct io_ring_ctx *ctx, struct io_buffer_list *bl)
+{
+	struct io_buf_free *ibf;
+
+	hlist_for_each_entry(ibf, &ctx->io_buf_list, list) {
+		if (bl->buf_ring == ibf->mem) {
+			ibf->inuse = 0;
+			return;
+		}
+	}
+
+	/* can't happen... */
+	WARN_ON_ONCE(1);
+}
+
 static int __io_remove_buffers(struct io_ring_ctx *ctx,
 			       struct io_buffer_list *bl, unsigned nbufs)
 {
@@ -223,7 +265,11 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx,
 	if (bl->is_mapped) {
 		i = bl->buf_ring->tail - bl->head;
 		if (bl->is_mmap) {
-			folio_put(virt_to_folio(bl->buf_ring));
+			/*
+			 * io_kbuf_list_free() will free the page(s) at
+			 * ->release() time.
+			 */
+			io_kbuf_mark_free(ctx, bl);
 			bl->buf_ring = NULL;
 			bl->is_mmap = 0;
 		} else if (bl->buf_nr_pages) {
@@ -274,9 +320,17 @@ void io_destroy_buffers(struct io_ring_ctx *ctx)
 	xa_for_each(&ctx->io_bl_xa, index, bl) {
 		xa_erase(&ctx->io_bl_xa, bl->bgid);
 		__io_remove_buffers(ctx, bl, -1U);
-		kfree(bl);
+		kfree_rcu(bl, rcu);
 	}
 
+	/*
+	 * Move deferred locked entries to cache before pruning
+	 */
+	spin_lock(&ctx->completion_lock);
+	if (!list_empty(&ctx->io_buffers_comp))
+		list_splice_init(&ctx->io_buffers_comp, &ctx->io_buffers_cache);
+	spin_unlock(&ctx->completion_lock);
+
 	list_for_each_safe(item, tmp, &ctx->io_buffers_cache) {
 		buf = list_entry(item, struct io_buffer, list);
 		kmem_cache_free(io_buf_cachep, buf);
@@ -460,7 +514,16 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
 		INIT_LIST_HEAD(&bl->buf_list);
 		ret = io_buffer_add_list(ctx, bl, p->bgid);
 		if (ret) {
-			kfree(bl);
+			/*
+			 * Doesn't need rcu free as it was never visible, but
+			 * let's keep it consistent throughout. Also can't
+			 * be a lower indexed array group, as adding one
+			 * where lookup failed cannot happen.
+			 */
+			if (p->bgid >= BGID_ARRAY)
+				kfree_rcu(bl, rcu);
+			else
+				WARN_ON_ONCE(1);
 			goto err;
 		}
 	}
@@ -531,19 +594,63 @@ error_unpin:
 	return -EINVAL;
 }
 
-static int io_alloc_pbuf_ring(struct io_uring_buf_reg *reg,
+/*
+ * See if we have a suitable region that we can reuse, rather than allocate
+ * both a new io_buf_free and mem region again. We leave it on the list as
+ * even a reused entry will need freeing at ring release.
+ */
+static struct io_buf_free *io_lookup_buf_free_entry(struct io_ring_ctx *ctx,
+						    size_t ring_size)
+{
+	struct io_buf_free *ibf, *best = NULL;
+	size_t best_dist;
+
+	hlist_for_each_entry(ibf, &ctx->io_buf_list, list) {
+		size_t dist;
+
+		if (ibf->inuse || ibf->size < ring_size)
+			continue;
+		dist = ibf->size - ring_size;
+		if (!best || dist < best_dist) {
+			best = ibf;
+			if (!dist)
+				break;
+			best_dist = dist;
+		}
+	}
+
+	return best;
+}
+
+static int io_alloc_pbuf_ring(struct io_ring_ctx *ctx,
+			      struct io_uring_buf_reg *reg,
 			      struct io_buffer_list *bl)
 {
-	gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP;
+	struct io_buf_free *ibf;
 	size_t ring_size;
 	void *ptr;
 
 	ring_size = reg->ring_entries * sizeof(struct io_uring_buf_ring);
-	ptr = (void *) __get_free_pages(gfp, get_order(ring_size));
-	if (!ptr)
-		return -ENOMEM;
 
-	bl->buf_ring = ptr;
+	/* Reuse existing entry, if we can */
+	ibf = io_lookup_buf_free_entry(ctx, ring_size);
+	if (!ibf) {
+		ptr = io_mem_alloc(ring_size);
+		if (IS_ERR(ptr))
+			return PTR_ERR(ptr);
+
+		/* Allocate and store deferred free entry */
+		ibf = kmalloc(sizeof(*ibf), GFP_KERNEL_ACCOUNT);
+		if (!ibf) {
+			io_mem_free(ptr);
+			return -ENOMEM;
+		}
+		ibf->mem = ptr;
+		ibf->size = ring_size;
+		hlist_add_head(&ibf->list, &ctx->io_buf_list);
+	}
+	ibf->inuse = 1;
+	bl->buf_ring = ibf->mem;
 	bl->is_mapped = 1;
 	bl->is_mmap = 1;
 	return 0;
@@ -555,6 +662,8 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	struct io_buffer_list *bl, *free_bl = NULL;
 	int ret;
 
+	lockdep_assert_held(&ctx->uring_lock);
+
 	if (copy_from_user(&reg, arg, sizeof(reg)))
 		return -EFAULT;
 
@@ -599,7 +708,7 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	if (!(reg.flags & IOU_PBUF_RING_MMAP))
 		ret = io_pin_pbuf_ring(&reg, bl);
 	else
-		ret = io_alloc_pbuf_ring(&reg, bl);
+		ret = io_alloc_pbuf_ring(ctx, &reg, bl);
 
 	if (!ret) {
 		bl->nr_entries = reg.ring_entries;
@@ -609,7 +718,7 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 		return 0;
 	}
 
-	kfree(free_bl);
+	kfree_rcu(free_bl, rcu);
 	return ret;
 }
 
@@ -618,6 +727,8 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	struct io_uring_buf_reg reg;
 	struct io_buffer_list *bl;
 
+	lockdep_assert_held(&ctx->uring_lock);
+
 	if (copy_from_user(&reg, arg, sizeof(reg)))
 		return -EFAULT;
 	if (reg.resv[0] || reg.resv[1] || reg.resv[2])
@@ -634,7 +745,7 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	__io_remove_buffers(ctx, bl, -1U);
 	if (bl->bgid >= BGID_ARRAY) {
 		xa_erase(&ctx->io_bl_xa, bl->bgid);
-		kfree(bl);
+		kfree_rcu(bl, rcu);
 	}
 	return 0;
 }
@@ -643,9 +754,33 @@ void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid)
 {
 	struct io_buffer_list *bl;
 
-	bl = io_buffer_get_list(ctx, bgid);
+	bl = __io_buffer_get_list(ctx, smp_load_acquire(&ctx->io_bl), bgid);
+
 	if (!bl || !bl->is_mmap)
 		return NULL;
+	/*
+	 * Ensure the list is fully setup. Only strictly needed for RCU lookup
+	 * via mmap, and in that case only for the array indexed groups. For
+	 * the xarray lookups, it's either visible and ready, or not at all.
+	 */
+	if (!smp_load_acquire(&bl->is_ready))
+		return NULL;
 
 	return bl->buf_ring;
 }
+
+/*
+ * Called at or after ->release(), free the mmap'ed buffers that we used
+ * for memory mapped provided buffer rings.
+ */
+void io_kbuf_mmap_list_free(struct io_ring_ctx *ctx)
+{
+	struct io_buf_free *ibf;
+	struct hlist_node *tmp;
+
+	hlist_for_each_entry_safe(ibf, tmp, &ctx->io_buf_list, list) {
+		hlist_del(&ibf->list);
+		io_mem_free(ibf->mem);
+		kfree(ibf);
+	}
+}
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index d14345ef61fc8d..9be5960817ea1c 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -15,6 +15,7 @@ struct io_buffer_list {
 			struct page **buf_pages;
 			struct io_uring_buf_ring *buf_ring;
 		};
+		struct rcu_head rcu;
 	};
 	__u16 bgid;
 
@@ -28,6 +29,8 @@ struct io_buffer_list {
 	__u8 is_mapped;
 	/* ring mapped provided buffers, but mmap'ed by application */
 	__u8 is_mmap;
+	/* bl is visible from an RCU point of view for lookup */
+	__u8 is_ready;
 };
 
 struct io_buffer {
@@ -51,13 +54,15 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags);
 int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
 int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
 
+void io_kbuf_mmap_list_free(struct io_ring_ctx *ctx);
+
 unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags);
 
-void io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags);
+bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags);
 
 void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid);
 
-static inline void io_kbuf_recycle_ring(struct io_kiocb *req)
+static inline bool io_kbuf_recycle_ring(struct io_kiocb *req)
 {
 	/*
 	 * We don't need to recycle for REQ_F_BUFFER_RING, we can just clear
@@ -80,8 +85,10 @@ static inline void io_kbuf_recycle_ring(struct io_kiocb *req)
 		} else {
 			req->buf_index = req->buf_list->bgid;
 			req->flags &= ~REQ_F_BUFFER_RING;
+			return true;
 		}
 	}
+	return false;
 }
 
 static inline bool io_do_buffer_select(struct io_kiocb *req)
@@ -91,12 +98,13 @@ static inline bool io_do_buffer_select(struct io_kiocb *req)
 	return !(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING));
 }
 
-static inline void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
+static inline bool io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
 {
 	if (req->flags & REQ_F_BUFFER_SELECTED)
-		io_kbuf_recycle_legacy(req, issue_flags);
+		return io_kbuf_recycle_legacy(req, issue_flags);
 	if (req->flags & REQ_F_BUFFER_RING)
-		io_kbuf_recycle_ring(req);
+		return io_kbuf_recycle_ring(req);
+	return false;
 }
 
 static inline unsigned int __io_put_kbuf_list(struct io_kiocb *req,
diff --git a/io_uring/net.c b/io_uring/net.c
index 7a8e298af81b3b..75d494dad7e2c7 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -1461,16 +1461,6 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags)
 	int ret;
 	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
 
-	if (connect->in_progress) {
-		struct socket *socket;
-
-		ret = -ENOTSOCK;
-		socket = sock_from_file(req->file);
-		if (socket)
-			ret = sock_error(socket->sk);
-		goto out;
-	}
-
 	if (req_has_async_data(req)) {
 		io = req->async_data;
 	} else {
@@ -1490,9 +1480,7 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags)
 	    && force_nonblock) {
 		if (ret == -EINPROGRESS) {
 			connect->in_progress = true;
-			return -EAGAIN;
-		}
-		if (ret == -ECONNABORTED) {
+		} else if (ret == -ECONNABORTED) {
 			if (connect->seen_econnaborted)
 				goto out;
 			connect->seen_econnaborted = true;
@@ -1506,6 +1494,16 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags)
 		memcpy(req->async_data, &__io, sizeof(__io));
 		return -EAGAIN;
 	}
+	if (connect->in_progress) {
+		/*
+		 * At least bluetooth will return -EBADFD on a re-connect
+		 * attempt, and it's (supposedly) also valid to get -EISCONN
+		 * which means the previous result is good. For both of these,
+		 * grab the sock_error() and use that for the completion.
+		 */
+		if (ret == -EBADFD || ret == -EISCONN)
+			ret = sock_error(sock_from_file(req->file)->sk);
+	}
 	if (ret == -ERESTARTSYS)
 		ret = -EINTR;
 out:
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 25a3515a177c7a..799db44283c7e3 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -66,7 +66,7 @@ const struct io_issue_def io_issue_defs[] = {
 		.iopoll			= 1,
 		.iopoll_queue		= 1,
 		.vectored		= 1,
-		.prep			= io_prep_rw,
+		.prep			= io_prep_rwv,
 		.issue			= io_read,
 	},
 	[IORING_OP_WRITEV] = {
@@ -80,7 +80,7 @@ const struct io_issue_def io_issue_defs[] = {
 		.iopoll			= 1,
 		.iopoll_queue		= 1,
 		.vectored		= 1,
-		.prep			= io_prep_rw,
+		.prep			= io_prep_rwv,
 		.issue			= io_write,
 	},
 	[IORING_OP_FSYNC] = {
@@ -98,7 +98,7 @@ const struct io_issue_def io_issue_defs[] = {
 		.ioprio			= 1,
 		.iopoll			= 1,
 		.iopoll_queue		= 1,
-		.prep			= io_prep_rw,
+		.prep			= io_prep_rw_fixed,
 		.issue			= io_read,
 	},
 	[IORING_OP_WRITE_FIXED] = {
@@ -111,7 +111,7 @@ const struct io_issue_def io_issue_defs[] = {
 		.ioprio			= 1,
 		.iopoll			= 1,
 		.iopoll_queue		= 1,
-		.prep			= io_prep_rw,
+		.prep			= io_prep_rw_fixed,
 		.issue			= io_write,
 	},
 	[IORING_OP_POLL_ADD] = {
diff --git a/io_uring/poll.c b/io_uring/poll.c
index d38d05edb4fa26..d59b74a99d4e4b 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -366,11 +366,16 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
 
 static void __io_poll_execute(struct io_kiocb *req, int mask)
 {
+	unsigned flags = 0;
+
 	io_req_set_res(req, mask, 0);
 	req->io_task_work.func = io_poll_task_func;
 
 	trace_io_uring_task_add(req, mask);
-	__io_req_task_work_add(req, IOU_F_TWQ_LAZY_WAKE);
+
+	if (!(req->flags & REQ_F_POLL_NO_LAZY))
+		flags = IOU_F_TWQ_LAZY_WAKE;
+	__io_req_task_work_add(req, flags);
 }
 
 static inline void io_poll_execute(struct io_kiocb *req, int res)
@@ -526,10 +531,19 @@ static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt,
 	poll->head = head;
 	poll->wait.private = (void *) wqe_private;
 
-	if (poll->events & EPOLLEXCLUSIVE)
+	if (poll->events & EPOLLEXCLUSIVE) {
+		/*
+		 * Exclusive waits may only wake a limited amount of entries
+		 * rather than all of them, this may interfere with lazy
+		 * wake if someone does wait(events > 1). Ensure we don't do
+		 * lazy wake for those, as we need to process each one as they
+		 * come in.
+		 */
+		req->flags |= REQ_F_POLL_NO_LAZY;
 		add_wait_queue_exclusive(head, &poll->wait);
-	else
+	} else {
 		add_wait_queue(head, &poll->wait);
+	}
 }
 
 static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 7034be555334d2..f521c5965a9331 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1258,7 +1258,7 @@ int io_import_fixed(int ddir, struct iov_iter *iter,
 		 */
 		const struct bio_vec *bvec = imu->bvec;
 
-		if (offset <= bvec->bv_len) {
+		if (offset < bvec->bv_len) {
 			/*
 			 * Note, huge pages buffers consists of one large
 			 * bvec entry and should always go this way. The other
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index 8625181fb87acf..08ac0d8e07ef84 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -77,17 +77,10 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 
 int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file);
 
-#if defined(CONFIG_UNIX)
-static inline bool io_file_need_scm(struct file *filp)
-{
-	return !!unix_get_socket(filp);
-}
-#else
 static inline bool io_file_need_scm(struct file *filp)
 {
 	return false;
 }
-#endif
 
 static inline int io_scm_file_account(struct io_ring_ctx *ctx,
 				      struct file *file)
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 3398e1d944c261..64390d4e20c187 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -83,18 +83,6 @@ int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	/* used for fixed read/write too - just read unconditionally */
 	req->buf_index = READ_ONCE(sqe->buf_index);
 
-	if (req->opcode == IORING_OP_READ_FIXED ||
-	    req->opcode == IORING_OP_WRITE_FIXED) {
-		struct io_ring_ctx *ctx = req->ctx;
-		u16 index;
-
-		if (unlikely(req->buf_index >= ctx->nr_user_bufs))
-			return -EFAULT;
-		index = array_index_nospec(req->buf_index, ctx->nr_user_bufs);
-		req->imu = ctx->user_bufs[index];
-		io_req_set_rsrc_node(req, ctx, 0);
-	}
-
 	ioprio = READ_ONCE(sqe->ioprio);
 	if (ioprio) {
 		ret = ioprio_check_cap(ioprio);
@@ -110,16 +98,42 @@ int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	rw->addr = READ_ONCE(sqe->addr);
 	rw->len = READ_ONCE(sqe->len);
 	rw->flags = READ_ONCE(sqe->rw_flags);
+	return 0;
+}
+
+int io_prep_rwv(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	int ret;
+
+	ret = io_prep_rw(req, sqe);
+	if (unlikely(ret))
+		return ret;
 
-	/* Have to do this validation here, as this is in io_read() rw->len might
-	 * have chanaged due to buffer selection
+	/*
+	 * Have to do this validation here, as this is in io_read() rw->len
+	 * might have chanaged due to buffer selection
 	 */
-	if (req->opcode == IORING_OP_READV && req->flags & REQ_F_BUFFER_SELECT) {
-		ret = io_iov_buffer_select_prep(req);
-		if (ret)
-			return ret;
-	}
+	if (req->flags & REQ_F_BUFFER_SELECT)
+		return io_iov_buffer_select_prep(req);
+
+	return 0;
+}
 
+int io_prep_rw_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	u16 index;
+	int ret;
+
+	ret = io_prep_rw(req, sqe);
+	if (unlikely(ret))
+		return ret;
+
+	if (unlikely(req->buf_index >= ctx->nr_user_bufs))
+		return -EFAULT;
+	index = array_index_nospec(req->buf_index, ctx->nr_user_bufs);
+	req->imu = ctx->user_bufs[index];
+	io_req_set_rsrc_node(req, ctx, 0);
 	return 0;
 }
 
@@ -129,12 +143,20 @@ int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
  */
 int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
+	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
 	int ret;
 
+	/* must be used with provided buffers */
+	if (!(req->flags & REQ_F_BUFFER_SELECT))
+		return -EINVAL;
+
 	ret = io_prep_rw(req, sqe);
 	if (unlikely(ret))
 		return ret;
 
+	if (rw->addr || rw->len)
+		return -EINVAL;
+
 	req->flags |= REQ_F_APOLL_MULTISHOT;
 	return 0;
 }
@@ -542,6 +564,9 @@ static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
 {
 	if (!force && !io_cold_defs[req->opcode].prep_async)
 		return 0;
+	/* opcode type doesn't need async data */
+	if (!io_cold_defs[req->opcode].async_size)
+		return 0;
 	if (!req_has_async_data(req)) {
 		struct io_async_rw *iorw;
 
@@ -887,6 +912,7 @@ int io_read(struct io_kiocb *req, unsigned int issue_flags)
 
 int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 {
+	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
 	unsigned int cflags = 0;
 	int ret;
 
@@ -903,7 +929,12 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 	 * handling arm it.
 	 */
 	if (ret == -EAGAIN) {
-		io_kbuf_recycle(req, issue_flags);
+		/*
+		 * Reset rw->len to 0 again to avoid clamping future mshot
+		 * reads, in case the buffer size varies.
+		 */
+		if (io_kbuf_recycle(req, issue_flags))
+			rw->len = 0;
 		return -EAGAIN;
 	}
 
@@ -916,6 +947,7 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 		 * jump to the termination path. This request is then done.
 		 */
 		cflags = io_put_kbuf(req, issue_flags);
+		rw->len = 0; /* similarly to above, reset len to 0 */
 
 		if (io_fill_cqe_req_aux(req,
 					issue_flags & IO_URING_F_COMPLETE_DEFER,
diff --git a/io_uring/rw.h b/io_uring/rw.h
index c5aed03d42a4d1..f9e89b4fe4da91 100644
--- a/io_uring/rw.h
+++ b/io_uring/rw.h
@@ -16,6 +16,8 @@ struct io_async_rw {
 };
 
 int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_prep_rwv(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_prep_rw_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_read(struct io_kiocb *req, unsigned int issue_flags);
 int io_readv_prep_async(struct io_kiocb *req);
 int io_write(struct io_kiocb *req, unsigned int issue_flags);
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index bd6c2c7959a5bf..65b5dbe3c850ed 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -214,6 +214,7 @@ static bool io_sqd_handle_event(struct io_sq_data *sqd)
 			did_sig = get_signal(&ksig);
 		cond_resched();
 		mutex_lock(&sqd->lock);
+		sqd->sq_cpu = raw_smp_processor_id();
 	}
 	return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
 }
@@ -229,10 +230,15 @@ static int io_sq_thread(void *data)
 	snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
 	set_task_comm(current, buf);
 
-	if (sqd->sq_cpu != -1)
+	/* reset to our pid after we've set task_comm, for fdinfo */
+	sqd->task_pid = current->pid;
+
+	if (sqd->sq_cpu != -1) {
 		set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu));
-	else
+	} else {
 		set_cpus_allowed_ptr(current, cpu_online_mask);
+		sqd->sq_cpu = raw_smp_processor_id();
+	}
 
 	mutex_lock(&sqd->lock);
 	while (1) {
@@ -261,6 +267,7 @@ static int io_sq_thread(void *data)
 				mutex_unlock(&sqd->lock);
 				cond_resched();
 				mutex_lock(&sqd->lock);
+				sqd->sq_cpu = raw_smp_processor_id();
 			}
 			continue;
 		}
@@ -294,6 +301,7 @@ static int io_sq_thread(void *data)
 				mutex_unlock(&sqd->lock);
 				schedule();
 				mutex_lock(&sqd->lock);
+				sqd->sq_cpu = raw_smp_processor_id();
 			}
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 				atomic_andnot(IORING_SQ_NEED_WAKEUP,
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index acbc2924ecd211..7d3ef62e620a58 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -7,7 +7,7 @@
 #include <linux/nospec.h>
 
 #include <uapi/linux/io_uring.h>
-#include <uapi/asm-generic/ioctls.h>
+#include <asm/ioctls.h>
 
 #include "io_uring.h"
 #include "rsrc.h"
diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 7aff28ded2f48f..2fd510256604e9 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -94,10 +94,8 @@ config KEXEC_JUMP
 config CRASH_DUMP
 	bool "kernel crash dumps"
 	depends on ARCH_SUPPORTS_CRASH_DUMP
-	depends on ARCH_SUPPORTS_KEXEC
 	select CRASH_CORE
 	select KEXEC_CORE
-	select KEXEC
 	help
 	  Generate crash dump after being started by kexec.
 	  This should be normally only set in special crash dump kernels
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 91e82e34b51e32..7a98cd176a127d 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -531,7 +531,7 @@ int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark)
 	if (tsk != current)
 		return 0;
 
-	if (WARN_ON_ONCE(!current->mm))
+	if (!current->mm)
 		return 0;
 	exe_file = get_mm_exe_file(current->mm);
 	if (!exe_file)
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 2058e89b5ddd00..c85ff9162a5cd4 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1012,11 +1012,16 @@ static void prog_array_map_poke_untrack(struct bpf_map *map,
 	mutex_unlock(&aux->poke_mutex);
 }
 
+void __weak bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+				      struct bpf_prog *new, struct bpf_prog *old)
+{
+	WARN_ON_ONCE(1);
+}
+
 static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 				    struct bpf_prog *old,
 				    struct bpf_prog *new)
 {
-	u8 *old_addr, *new_addr, *old_bypass_addr;
 	struct prog_poke_elem *elem;
 	struct bpf_array_aux *aux;
 
@@ -1025,7 +1030,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 
 	list_for_each_entry(elem, &aux->poke_progs, list) {
 		struct bpf_jit_poke_descriptor *poke;
-		int i, ret;
+		int i;
 
 		for (i = 0; i < elem->aux->size_poke_tab; i++) {
 			poke = &elem->aux->poke_tab[i];
@@ -1044,21 +1049,10 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			 *    activated, so tail call updates can arrive from here
 			 *    while JIT is still finishing its final fixup for
 			 *    non-activated poke entries.
-			 * 3) On program teardown, the program's kallsym entry gets
-			 *    removed out of RCU callback, but we can only untrack
-			 *    from sleepable context, therefore bpf_arch_text_poke()
-			 *    might not see that this is in BPF text section and
-			 *    bails out with -EINVAL. As these are unreachable since
-			 *    RCU grace period already passed, we simply skip them.
-			 * 4) Also programs reaching refcount of zero while patching
+			 * 3) Also programs reaching refcount of zero while patching
 			 *    is in progress is okay since we're protected under
 			 *    poke_mutex and untrack the programs before the JIT
-			 *    buffer is freed. When we're still in the middle of
-			 *    patching and suddenly kallsyms entry of the program
-			 *    gets evicted, we just skip the rest which is fine due
-			 *    to point 3).
-			 * 5) Any other error happening below from bpf_arch_text_poke()
-			 *    is a unexpected bug.
+			 *    buffer is freed.
 			 */
 			if (!READ_ONCE(poke->tailcall_target_stable))
 				continue;
@@ -1068,39 +1062,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			    poke->tail_call.key != key)
 				continue;
 
-			old_bypass_addr = old ? NULL : poke->bypass_addr;
-			old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
-			new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
-
-			if (new) {
-				ret = bpf_arch_text_poke(poke->tailcall_target,
-							 BPF_MOD_JUMP,
-							 old_addr, new_addr);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-				if (!old) {
-					ret = bpf_arch_text_poke(poke->tailcall_bypass,
-								 BPF_MOD_JUMP,
-								 poke->bypass_addr,
-								 NULL);
-					BUG_ON(ret < 0 && ret != -EINVAL);
-				}
-			} else {
-				ret = bpf_arch_text_poke(poke->tailcall_bypass,
-							 BPF_MOD_JUMP,
-							 old_bypass_addr,
-							 poke->bypass_addr);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-				/* let other CPUs finish the execution of program
-				 * so that it will not possible to expose them
-				 * to invalid nop, stack unwind, nop state
-				 */
-				if (!ret)
-					synchronize_rcu();
-				ret = bpf_arch_text_poke(poke->tailcall_target,
-							 BPF_MOD_JUMP,
-							 old_addr, NULL);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-			}
+			bpf_arch_poke_desc_update(poke, new, old);
 		}
 	}
 }
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 833faa04461bc2..0fae7916418709 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -782,9 +782,7 @@ struct bpf_iter_num_kern {
 	int end; /* final value, exclusive */
 } __aligned(8);
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end)
 {
@@ -843,4 +841,4 @@ __bpf_kfunc void bpf_iter_num_destroy(struct bpf_iter_num *it)
 	s->cur = s->end = 0;
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c
index 209e5135f9fbc5..f04a468cf6a726 100644
--- a/kernel/bpf/cgroup_iter.c
+++ b/kernel/bpf/cgroup_iter.c
@@ -282,7 +282,7 @@ static struct bpf_iter_reg bpf_cgroup_reg_info = {
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__cgroup, cgroup),
-		  PTR_TO_BTF_ID_OR_NULL },
+		  PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
 	},
 	.seq_info		= &cgroup_iter_seq_info,
 };
@@ -305,9 +305,7 @@ struct bpf_iter_css_kern {
 	unsigned int flags;
 } __attribute__((aligned(8)));
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		"Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_css_new(struct bpf_iter_css *it,
 		struct cgroup_subsys_state *start, unsigned int flags)
@@ -358,4 +356,4 @@ __bpf_kfunc void bpf_iter_css_destroy(struct bpf_iter_css *it)
 {
 }
 
-__diag_pop();
\ No newline at end of file
+__bpf_kfunc_end_defs();
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 08626b519ce23f..fe254ae035fe49 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -64,8 +64,8 @@
 #define OFF	insn->off
 #define IMM	insn->imm
 
-struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma;
-bool bpf_global_ma_set, bpf_global_percpu_ma_set;
+struct bpf_mem_alloc bpf_global_ma;
+bool bpf_global_ma_set;
 
 /* No hurry in this branch
  *
@@ -371,14 +371,18 @@ static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old,
 static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
 				s32 end_new, s32 curr, const bool probe_pass)
 {
-	const s32 off_min = S16_MIN, off_max = S16_MAX;
+	s64 off_min, off_max, off;
 	s32 delta = end_new - end_old;
-	s32 off;
 
-	if (insn->code == (BPF_JMP32 | BPF_JA))
+	if (insn->code == (BPF_JMP32 | BPF_JA)) {
 		off = insn->imm;
-	else
+		off_min = S32_MIN;
+		off_max = S32_MAX;
+	} else {
 		off = insn->off;
+		off_min = S16_MIN;
+		off_max = S16_MAX;
+	}
 
 	if (curr < pos && curr + off + 1 >= end_old)
 		off += delta;
@@ -2934,9 +2938,7 @@ static int __init bpf_global_ma_init(void)
 
 	ret = bpf_mem_alloc_init(&bpf_global_ma, 0, false);
 	bpf_global_ma_set = !ret;
-	ret = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true);
-	bpf_global_percpu_ma_set = !ret;
-	return !bpf_global_ma_set || !bpf_global_percpu_ma_set;
+	return ret;
 }
 late_initcall(bpf_global_ma_init);
 #endif
diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c
index 6983af8e093c4b..e01c741e54e7b8 100644
--- a/kernel/bpf/cpumask.c
+++ b/kernel/bpf/cpumask.c
@@ -34,9 +34,7 @@ static bool cpu_valid(u32 cpu)
 	return cpu < nr_cpu_ids;
 }
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global kfuncs as their definitions will be in BTF");
+__bpf_kfunc_start_defs();
 
 /**
  * bpf_cpumask_create() - Create a mutable BPF cpumask.
@@ -407,7 +405,7 @@ __bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
 	return cpumask_any_and_distribute(src1, src2);
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(cpumask_kfunc_btf_ids)
 BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index e46ac288a1080b..56b0c1f678ee75 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1177,13 +1177,6 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map
 		ret = -EBUSY;
 		goto out;
 	}
-	if (!atomic64_read(&map->usercnt)) {
-		/* maps with timers must be either held by user space
-		 * or pinned in bpffs.
-		 */
-		ret = -EPERM;
-		goto out;
-	}
 	/* allocate hrtimer via map_kmalloc to use memcg accounting */
 	t = bpf_map_kmalloc_node(map, sizeof(*t), GFP_ATOMIC, map->numa_node);
 	if (!t) {
@@ -1196,7 +1189,21 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map
 	rcu_assign_pointer(t->callback_fn, NULL);
 	hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT);
 	t->timer.function = bpf_timer_cb;
-	timer->timer = t;
+	WRITE_ONCE(timer->timer, t);
+	/* Guarantee the order between timer->timer and map->usercnt. So
+	 * when there are concurrent uref release and bpf timer init, either
+	 * bpf_timer_cancel_and_free() called by uref release reads a no-NULL
+	 * timer or atomic64_read() below returns a zero usercnt.
+	 */
+	smp_mb();
+	if (!atomic64_read(&map->usercnt)) {
+		/* maps with timers must be either held by user space
+		 * or pinned in bpffs.
+		 */
+		WRITE_ONCE(timer->timer, NULL);
+		kfree(t);
+		ret = -EPERM;
+	}
 out:
 	__bpf_spin_unlock_irqrestore(&timer->lock);
 	return ret;
@@ -1374,7 +1381,7 @@ void bpf_timer_cancel_and_free(void *val)
 	/* The subsequent bpf_timer_start/cancel() helpers won't be able to use
 	 * this timer, since it won't be initialized.
 	 */
-	timer->timer = NULL;
+	WRITE_ONCE(timer->timer, NULL);
 out:
 	__bpf_spin_unlock_irqrestore(&timer->lock);
 	if (!t)
@@ -1886,9 +1893,7 @@ void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
 	}
 }
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign)
 {
@@ -2505,7 +2510,7 @@ __bpf_kfunc void bpf_throw(u64 cookie)
 	WARN(1, "A call to BPF exception callback should never return\n");
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(generic_btf_ids)
 #ifdef CONFIG_KEXEC_CORE
@@ -2564,15 +2569,17 @@ BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY)
+#ifdef CONFIG_CGROUPS
 BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
-BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
-BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
-BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
 BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY)
+#endif
+BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_dynptr_adjust)
 BTF_ID_FLAGS(func, bpf_dynptr_is_null)
 BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index 6fc9dae9edc81c..6abd7c5df4b39e 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -193,9 +193,7 @@ static int __init bpf_map_iter_init(void)
 
 late_initcall(bpf_map_iter_init);
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map)
 {
@@ -213,7 +211,7 @@ __bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map)
 	return ret;
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(bpf_map_iter_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_map_sum_elem_count, KF_TRUSTED_ARGS)
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 63b909d277d479..6a51cfe4c2d63f 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -978,6 +978,8 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
 		memcg = get_memcg(c);
 		old_memcg = set_active_memcg(memcg);
 		ret = __alloc(c, NUMA_NO_NODE, GFP_KERNEL | __GFP_NOWARN | __GFP_ACCOUNT);
+		if (ret)
+			*(struct bpf_mem_cache **)ret = c;
 		set_active_memcg(old_memcg);
 		mem_cgroup_put(memcg);
 	}
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 654601dd6b493d..26082b97894d3c 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -704,7 +704,7 @@ static struct bpf_iter_reg task_reg_info = {
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__task, task),
-		  PTR_TO_BTF_ID_OR_NULL },
+		  PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
 	},
 	.seq_info		= &task_seq_info,
 	.fill_link_info		= bpf_iter_fill_link_info,
@@ -822,9 +822,7 @@ struct bpf_iter_task_vma_kern {
 	struct bpf_iter_task_vma_kern_data *data;
 } __attribute__((aligned(8)));
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
 				      struct task_struct *task, u64 addr)
@@ -890,7 +888,9 @@ __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it)
 	}
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
+
+#ifdef CONFIG_CGROUPS
 
 struct bpf_iter_css_task {
 	__u64 __opaque[1];
@@ -900,9 +900,7 @@ struct bpf_iter_css_task_kern {
 	struct css_task_iter *css_it;
 } __attribute__((aligned(8)));
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_css_task_new(struct bpf_iter_css_task *it,
 		struct cgroup_subsys_state *css, unsigned int flags)
@@ -948,7 +946,9 @@ __bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it)
 	bpf_mem_free(&bpf_global_ma, kit->css_it);
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
+
+#endif /* CONFIG_CGROUPS */
 
 struct bpf_iter_task {
 	__u64 __opaque[3];
@@ -969,9 +969,7 @@ enum {
 	BPF_TASK_ITER_PROC_THREADS
 };
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
 		struct task_struct *task__nullable, unsigned int flags)
@@ -1041,7 +1039,7 @@ __bpf_kfunc void bpf_iter_task_destroy(struct bpf_iter_task *it)
 {
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 857d7669451712..af2819d5c8ee7c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -26,6 +26,7 @@
 #include <linux/poison.h>
 #include <linux/module.h>
 #include <linux/cpumask.h>
+#include <linux/bpf_mem_alloc.h>
 #include <net/xdp.h>
 
 #include "disasm.h"
@@ -41,6 +42,9 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
 #undef BPF_LINK_TYPE
 };
 
+struct bpf_mem_alloc bpf_global_percpu_ma;
+static bool bpf_global_percpu_ma_set;
+
 /* bpf_check() is a static code analyzer that walks eBPF program
  * instruction by instruction and updates register/stack state.
  * All paths of conditional branches are analyzed until 'bpf_exit' insn.
@@ -336,6 +340,7 @@ struct bpf_kfunc_call_arg_meta {
 struct btf *btf_vmlinux;
 
 static DEFINE_MUTEX(bpf_verifier_lock);
+static DEFINE_MUTEX(bpf_percpu_ma_lock);
 
 static const struct bpf_line_info *
 find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
@@ -542,13 +547,12 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id)
 	return func_id == BPF_FUNC_dynptr_data;
 }
 
-static bool is_callback_calling_kfunc(u32 btf_id);
+static bool is_sync_callback_calling_kfunc(u32 btf_id);
 static bool is_bpf_throw_kfunc(struct bpf_insn *insn);
 
-static bool is_callback_calling_function(enum bpf_func_id func_id)
+static bool is_sync_callback_calling_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_for_each_map_elem ||
-	       func_id == BPF_FUNC_timer_set_callback ||
 	       func_id == BPF_FUNC_find_vma ||
 	       func_id == BPF_FUNC_loop ||
 	       func_id == BPF_FUNC_user_ringbuf_drain;
@@ -559,6 +563,18 @@ static bool is_async_callback_calling_function(enum bpf_func_id func_id)
 	return func_id == BPF_FUNC_timer_set_callback;
 }
 
+static bool is_callback_calling_function(enum bpf_func_id func_id)
+{
+	return is_sync_callback_calling_function(func_id) ||
+	       is_async_callback_calling_function(func_id);
+}
+
+static bool is_sync_callback_calling_insn(struct bpf_insn *insn)
+{
+	return (bpf_helper_call(insn) && is_sync_callback_calling_function(insn->imm)) ||
+	       (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm));
+}
+
 static bool is_storage_get_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_sk_storage_get ||
@@ -1803,6 +1819,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 	dst_state->first_insn_idx = src->first_insn_idx;
 	dst_state->last_insn_idx = src->last_insn_idx;
 	dst_state->dfs_depth = src->dfs_depth;
+	dst_state->callback_unroll_depth = src->callback_unroll_depth;
 	dst_state->used_as_loop_entry = src->used_as_loop_entry;
 	for (i = 0; i <= src->curframe; i++) {
 		dst = dst_state->frame[i];
@@ -3434,13 +3451,11 @@ static void mark_insn_zext(struct bpf_verifier_env *env,
 	reg->subreg_def = DEF_NOT_SUBREG;
 }
 
-static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
-			 enum reg_arg_type t)
+static int __check_reg_arg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno,
+			   enum reg_arg_type t)
 {
-	struct bpf_verifier_state *vstate = env->cur_state;
-	struct bpf_func_state *state = vstate->frame[vstate->curframe];
 	struct bpf_insn *insn = env->prog->insnsi + env->insn_idx;
-	struct bpf_reg_state *reg, *regs = state->regs;
+	struct bpf_reg_state *reg;
 	bool rw64;
 
 	if (regno >= MAX_BPF_REG) {
@@ -3481,6 +3496,15 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
 	return 0;
 }
 
+static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
+			 enum reg_arg_type t)
+{
+	struct bpf_verifier_state *vstate = env->cur_state;
+	struct bpf_func_state *state = vstate->frame[vstate->curframe];
+
+	return __check_reg_arg(env, state->regs, regno, t);
+}
+
 static void mark_jmp_point(struct bpf_verifier_env *env, int idx)
 {
 	env->insn_aux_data[idx].jmp_point = true;
@@ -3516,12 +3540,29 @@ static int push_jmp_history(struct bpf_verifier_env *env,
 
 /* Backtrack one insn at a time. If idx is not at the top of recorded
  * history then previous instruction came from straight line execution.
+ * Return -ENOENT if we exhausted all instructions within given state.
+ *
+ * It's legal to have a bit of a looping with the same starting and ending
+ * insn index within the same state, e.g.: 3->4->5->3, so just because current
+ * instruction index is the same as state's first_idx doesn't mean we are
+ * done. If there is still some jump history left, we should keep going. We
+ * need to take into account that we might have a jump history between given
+ * state's parent and itself, due to checkpointing. In this case, we'll have
+ * history entry recording a jump from last instruction of parent state and
+ * first instruction of given state.
  */
 static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
 			     u32 *history)
 {
 	u32 cnt = *history;
 
+	if (i == st->first_insn_idx) {
+		if (cnt == 0)
+			return -ENOENT;
+		if (cnt == 1 && st->jmp_history[0].idx == i)
+			return -ENOENT;
+	}
+
 	if (cnt && st->jmp_history[cnt - 1].idx == i) {
 		i = st->jmp_history[cnt - 1].prev_idx;
 		(*history)--;
@@ -3702,6 +3743,8 @@ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask)
 	}
 }
 
+static bool calls_callback(struct bpf_verifier_env *env, int insn_idx);
+
 /* For given verifier state backtrack_insn() is called from the last insn to
  * the first insn. Its purpose is to compute a bitmask of registers and
  * stack slots that needs precision in the parent verifier state.
@@ -3742,7 +3785,12 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 	if (class == BPF_ALU || class == BPF_ALU64) {
 		if (!bt_is_reg_set(bt, dreg))
 			return 0;
-		if (opcode == BPF_MOV) {
+		if (opcode == BPF_END || opcode == BPF_NEG) {
+			/* sreg is reserved and unused
+			 * dreg still need precision before this insn
+			 */
+			return 0;
+		} else if (opcode == BPF_MOV) {
 			if (BPF_SRC(insn->code) == BPF_X) {
 				/* dreg = sreg or dreg = (s8, s16, s32)sreg
 				 * dreg needs precision after this insn
@@ -3872,16 +3920,13 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 					return -EFAULT;
 				return 0;
 			}
-		} else if ((bpf_helper_call(insn) &&
-			    is_callback_calling_function(insn->imm) &&
-			    !is_async_callback_calling_function(insn->imm)) ||
-			   (bpf_pseudo_kfunc_call(insn) && is_callback_calling_kfunc(insn->imm))) {
-			/* callback-calling helper or kfunc call, which means
-			 * we are exiting from subprog, but unlike the subprog
-			 * call handling above, we shouldn't propagate
-			 * precision of r1-r5 (if any requested), as they are
-			 * not actually arguments passed directly to callback
-			 * subprogs
+		} else if (is_sync_callback_calling_insn(insn) && idx != subseq_idx - 1) {
+			/* exit from callback subprog to callback-calling helper or
+			 * kfunc call. Use idx/subseq_idx check to discern it from
+			 * straight line code backtracking.
+			 * Unlike the subprog call handling above, we shouldn't
+			 * propagate precision of r1-r5 (if any requested), as they are
+			 * not actually arguments passed directly to callback subprogs
 			 */
 			if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) {
 				verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
@@ -3916,10 +3961,18 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 		} else if (opcode == BPF_EXIT) {
 			bool r0_precise;
 
+			/* Backtracking to a nested function call, 'idx' is a part of
+			 * the inner frame 'subseq_idx' is a part of the outer frame.
+			 * In case of a regular function call, instructions giving
+			 * precision to registers R1-R5 should have been found already.
+			 * In case of a callback, it is ok to have R1-R5 marked for
+			 * backtracking, as these registers are set by the function
+			 * invoking callback.
+			 */
+			if (subseq_idx >= 0 && calls_callback(env, subseq_idx))
+				for (i = BPF_REG_1; i <= BPF_REG_5; i++)
+					bt_clear_reg(bt, i);
 			if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
-				/* if backtracing was looking for registers R1-R5
-				 * they should have been found already.
-				 */
 				verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
 				WARN_ONCE(1, "verifier backtracking bug");
 				return -EFAULT;
@@ -4396,10 +4449,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 				 * Nothing to be tracked further in the parent state.
 				 */
 				return 0;
-			if (i == first_idx)
-				break;
 			subseq_idx = i;
 			i = get_prev_insn_idx(st, i, &history);
+			if (i == -ENOENT)
+				break;
 			if (i >= env->prog->len) {
 				/* This can happen if backtracking reached insn 0
 				 * and there are still reg_mask or stack_mask
@@ -4674,7 +4727,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 		   insn->imm != 0 && env->bpf_capable) {
 		struct bpf_reg_state fake_reg = {};
 
-		__mark_reg_known(&fake_reg, (u32)insn->imm);
+		__mark_reg_known(&fake_reg, insn->imm);
 		fake_reg.type = SCALAR_VALUE;
 		save_register_state(state, spi, &fake_reg, size);
 	} else if (reg && is_spillable_regtype(reg->type)) {
@@ -5388,7 +5441,9 @@ static bool in_rcu_cs(struct bpf_verifier_env *env)
 /* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */
 BTF_SET_START(rcu_protected_types)
 BTF_ID(struct, prog_test_ref_kfunc)
+#ifdef CONFIG_CGROUPS
 BTF_ID(struct, cgroup)
+#endif
 BTF_ID(struct, bpf_cpumask)
 BTF_ID(struct, task_struct)
 BTF_SET_END(rcu_protected_types)
@@ -9321,7 +9376,7 @@ static void clear_caller_saved_regs(struct bpf_verifier_env *env,
 	/* after the call registers r0 - r5 were scratched */
 	for (i = 0; i < CALLER_SAVED_REGS; i++) {
 		mark_reg_not_init(env, regs, caller_saved[i]);
-		check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
+		__check_reg_arg(env, regs, caller_saved[i], DST_OP_NO_MARK);
 	}
 }
 
@@ -9334,11 +9389,10 @@ static int set_callee_state(struct bpf_verifier_env *env,
 			    struct bpf_func_state *caller,
 			    struct bpf_func_state *callee, int insn_idx);
 
-static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
-			     int *insn_idx, int subprog,
-			     set_callee_state_fn set_callee_state_cb)
+static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int callsite,
+			    set_callee_state_fn set_callee_state_cb,
+			    struct bpf_verifier_state *state)
 {
-	struct bpf_verifier_state *state = env->cur_state;
 	struct bpf_func_state *caller, *callee;
 	int err;
 
@@ -9348,54 +9402,72 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		return -E2BIG;
 	}
 
-	caller = state->frame[state->curframe];
 	if (state->frame[state->curframe + 1]) {
 		verbose(env, "verifier bug. Frame %d already allocated\n",
 			state->curframe + 1);
 		return -EFAULT;
 	}
 
+	caller = state->frame[state->curframe];
+	callee = kzalloc(sizeof(*callee), GFP_KERNEL);
+	if (!callee)
+		return -ENOMEM;
+	state->frame[state->curframe + 1] = callee;
+
+	/* callee cannot access r0, r6 - r9 for reading and has to write
+	 * into its own stack before reading from it.
+	 * callee can read/write into caller's stack
+	 */
+	init_func_state(env, callee,
+			/* remember the callsite, it will be used by bpf_exit */
+			callsite,
+			state->curframe + 1 /* frameno within this callchain */,
+			subprog /* subprog number within this prog */);
+	/* Transfer references to the callee */
+	err = copy_reference_state(callee, caller);
+	err = err ?: set_callee_state_cb(env, caller, callee, callsite);
+	if (err)
+		goto err_out;
+
+	/* only increment it after check_reg_arg() finished */
+	state->curframe++;
+
+	return 0;
+
+err_out:
+	free_func_state(callee);
+	state->frame[state->curframe + 1] = NULL;
+	return err;
+}
+
+static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+			      int insn_idx, int subprog,
+			      set_callee_state_fn set_callee_state_cb)
+{
+	struct bpf_verifier_state *state = env->cur_state, *callback_state;
+	struct bpf_func_state *caller, *callee;
+	int err;
+
+	caller = state->frame[state->curframe];
 	err = btf_check_subprog_call(env, subprog, caller->regs);
 	if (err == -EFAULT)
 		return err;
-	if (subprog_is_global(env, subprog)) {
-		if (err) {
-			verbose(env, "Caller passes invalid args into func#%d\n",
-				subprog);
-			return err;
-		} else {
-			if (env->log.level & BPF_LOG_LEVEL)
-				verbose(env,
-					"Func#%d is global and valid. Skipping.\n",
-					subprog);
-			clear_caller_saved_regs(env, caller->regs);
-
-			/* All global functions return a 64-bit SCALAR_VALUE */
-			mark_reg_unknown(env, caller->regs, BPF_REG_0);
-			caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
-
-			/* continue with next insn after call */
-			return 0;
-		}
-	}
 
 	/* set_callee_state is used for direct subprog calls, but we are
 	 * interested in validating only BPF helpers that can call subprogs as
 	 * callbacks
 	 */
-	if (set_callee_state_cb != set_callee_state) {
-		env->subprog_info[subprog].is_cb = true;
-		if (bpf_pseudo_kfunc_call(insn) &&
-		    !is_callback_calling_kfunc(insn->imm)) {
-			verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n",
-				func_id_name(insn->imm), insn->imm);
-			return -EFAULT;
-		} else if (!bpf_pseudo_kfunc_call(insn) &&
-			   !is_callback_calling_function(insn->imm)) { /* helper */
-			verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n",
-				func_id_name(insn->imm), insn->imm);
-			return -EFAULT;
-		}
+	env->subprog_info[subprog].is_cb = true;
+	if (bpf_pseudo_kfunc_call(insn) &&
+	    !is_sync_callback_calling_kfunc(insn->imm)) {
+		verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n",
+			func_id_name(insn->imm), insn->imm);
+		return -EFAULT;
+	} else if (!bpf_pseudo_kfunc_call(insn) &&
+		   !is_callback_calling_function(insn->imm)) { /* helper */
+		verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n",
+			func_id_name(insn->imm), insn->imm);
+		return -EFAULT;
 	}
 
 	if (insn->code == (BPF_JMP | BPF_CALL) &&
@@ -9406,53 +9478,83 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		/* there is no real recursion here. timer callbacks are async */
 		env->subprog_info[subprog].is_async_cb = true;
 		async_cb = push_async_cb(env, env->subprog_info[subprog].start,
-					 *insn_idx, subprog);
+					 insn_idx, subprog);
 		if (!async_cb)
 			return -EFAULT;
 		callee = async_cb->frame[0];
 		callee->async_entry_cnt = caller->async_entry_cnt + 1;
 
 		/* Convert bpf_timer_set_callback() args into timer callback args */
-		err = set_callee_state_cb(env, caller, callee, *insn_idx);
+		err = set_callee_state_cb(env, caller, callee, insn_idx);
 		if (err)
 			return err;
 
+		return 0;
+	}
+
+	/* for callback functions enqueue entry to callback and
+	 * proceed with next instruction within current frame.
+	 */
+	callback_state = push_stack(env, env->subprog_info[subprog].start, insn_idx, false);
+	if (!callback_state)
+		return -ENOMEM;
+
+	err = setup_func_entry(env, subprog, insn_idx, set_callee_state_cb,
+			       callback_state);
+	if (err)
+		return err;
+
+	callback_state->callback_unroll_depth++;
+	callback_state->frame[callback_state->curframe - 1]->callback_depth++;
+	caller->callback_depth = 0;
+	return 0;
+}
+
+static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+			   int *insn_idx)
+{
+	struct bpf_verifier_state *state = env->cur_state;
+	struct bpf_func_state *caller;
+	int err, subprog, target_insn;
+
+	target_insn = *insn_idx + insn->imm + 1;
+	subprog = find_subprog(env, target_insn);
+	if (subprog < 0) {
+		verbose(env, "verifier bug. No program starts at insn %d\n", target_insn);
+		return -EFAULT;
+	}
+
+	caller = state->frame[state->curframe];
+	err = btf_check_subprog_call(env, subprog, caller->regs);
+	if (err == -EFAULT)
+		return err;
+	if (subprog_is_global(env, subprog)) {
+		if (err) {
+			verbose(env, "Caller passes invalid args into func#%d\n", subprog);
+			return err;
+		}
+
+		if (env->log.level & BPF_LOG_LEVEL)
+			verbose(env, "Func#%d is global and valid. Skipping.\n", subprog);
 		clear_caller_saved_regs(env, caller->regs);
+
+		/* All global functions return a 64-bit SCALAR_VALUE */
 		mark_reg_unknown(env, caller->regs, BPF_REG_0);
 		caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
+
 		/* continue with next insn after call */
 		return 0;
 	}
 
-	callee = kzalloc(sizeof(*callee), GFP_KERNEL);
-	if (!callee)
-		return -ENOMEM;
-	state->frame[state->curframe + 1] = callee;
-
-	/* callee cannot access r0, r6 - r9 for reading and has to write
-	 * into its own stack before reading from it.
-	 * callee can read/write into caller's stack
+	/* for regular function entry setup new frame and continue
+	 * from that frame.
 	 */
-	init_func_state(env, callee,
-			/* remember the callsite, it will be used by bpf_exit */
-			*insn_idx /* callsite */,
-			state->curframe + 1 /* frameno within this callchain */,
-			subprog /* subprog number within this prog */);
-
-	/* Transfer references to the callee */
-	err = copy_reference_state(callee, caller);
-	if (err)
-		goto err_out;
-
-	err = set_callee_state_cb(env, caller, callee, *insn_idx);
+	err = setup_func_entry(env, subprog, *insn_idx, set_callee_state, state);
 	if (err)
-		goto err_out;
+		return err;
 
 	clear_caller_saved_regs(env, caller->regs);
 
-	/* only increment it after check_reg_arg() finished */
-	state->curframe++;
-
 	/* and go analyze first insn of the callee */
 	*insn_idx = env->subprog_info[subprog].start - 1;
 
@@ -9460,14 +9562,10 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		verbose(env, "caller:\n");
 		print_verifier_state(env, caller, true);
 		verbose(env, "callee:\n");
-		print_verifier_state(env, callee, true);
+		print_verifier_state(env, state->frame[state->curframe], true);
 	}
-	return 0;
 
-err_out:
-	free_func_state(callee);
-	state->frame[state->curframe + 1] = NULL;
-	return err;
+	return 0;
 }
 
 int map_set_for_each_callback_args(struct bpf_verifier_env *env,
@@ -9511,22 +9609,6 @@ static int set_callee_state(struct bpf_verifier_env *env,
 	return 0;
 }
 
-static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
-			   int *insn_idx)
-{
-	int subprog, target_insn;
-
-	target_insn = *insn_idx + insn->imm + 1;
-	subprog = find_subprog(env, target_insn);
-	if (subprog < 0) {
-		verbose(env, "verifier bug. No program starts at insn %d\n",
-			target_insn);
-		return -EFAULT;
-	}
-
-	return __check_func_call(env, insn, insn_idx, subprog, set_callee_state);
-}
-
 static int set_map_elem_callback_state(struct bpf_verifier_env *env,
 				       struct bpf_func_state *caller,
 				       struct bpf_func_state *callee,
@@ -9719,9 +9801,10 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env)
 
 static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 {
-	struct bpf_verifier_state *state = env->cur_state;
+	struct bpf_verifier_state *state = env->cur_state, *prev_st;
 	struct bpf_func_state *caller, *callee;
 	struct bpf_reg_state *r0;
+	bool in_callback_fn;
 	int err;
 
 	callee = state->frame[state->curframe];
@@ -9750,6 +9833,11 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 			verbose_invalid_scalar(env, r0, &range, "callback return", "R0");
 			return -EINVAL;
 		}
+		if (!calls_callback(env, callee->callsite)) {
+			verbose(env, "BUG: in callback at %d, callsite %d !calls_callback\n",
+				*insn_idx, callee->callsite);
+			return -EFAULT;
+		}
 	} else {
 		/* return to the caller whatever r0 had in the callee */
 		caller->regs[BPF_REG_0] = *r0;
@@ -9767,7 +9855,16 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 			return err;
 	}
 
-	*insn_idx = callee->callsite + 1;
+	/* for callbacks like bpf_loop or bpf_for_each_map_elem go back to callsite,
+	 * there function call logic would reschedule callback visit. If iteration
+	 * converges is_state_visited() would prune that visit eventually.
+	 */
+	in_callback_fn = callee->in_callback_fn;
+	if (in_callback_fn)
+		*insn_idx = callee->callsite;
+	else
+		*insn_idx = callee->callsite + 1;
+
 	if (env->log.level & BPF_LOG_LEVEL) {
 		verbose(env, "returning from callee:\n");
 		print_verifier_state(env, callee, true);
@@ -9778,6 +9875,24 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 	 * bpf_throw, this will be done by copy_verifier_state for extra frames. */
 	free_func_state(callee);
 	state->frame[state->curframe--] = NULL;
+
+	/* for callbacks widen imprecise scalars to make programs like below verify:
+	 *
+	 *   struct ctx { int i; }
+	 *   void cb(int idx, struct ctx *ctx) { ctx->i++; ... }
+	 *   ...
+	 *   struct ctx = { .i = 0; }
+	 *   bpf_loop(100, cb, &ctx, 0);
+	 *
+	 * This is similar to what is done in process_iter_next_call() for open
+	 * coded iterators.
+	 */
+	prev_st = in_callback_fn ? find_prev_entry(env, state, *insn_idx) : NULL;
+	if (prev_st) {
+		err = widen_imprecise_scalars(env, prev_st, state);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -10180,24 +10295,37 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		}
 		break;
 	case BPF_FUNC_for_each_map_elem:
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_map_elem_callback_state);
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_map_elem_callback_state);
 		break;
 	case BPF_FUNC_timer_set_callback:
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_timer_callback_state);
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_timer_callback_state);
 		break;
 	case BPF_FUNC_find_vma:
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_find_vma_callback_state);
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_find_vma_callback_state);
 		break;
 	case BPF_FUNC_snprintf:
 		err = check_bpf_snprintf_call(env, regs);
 		break;
 	case BPF_FUNC_loop:
 		update_loop_inline_state(env, meta.subprogno);
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_loop_callback_state);
+		/* Verifier relies on R1 value to determine if bpf_loop() iteration
+		 * is finished, thus mark it precise.
+		 */
+		err = mark_chain_precision(env, BPF_REG_1);
+		if (err)
+			return err;
+		if (cur_func(env)->callback_depth < regs[BPF_REG_1].umax_value) {
+			err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+						 set_loop_callback_state);
+		} else {
+			cur_func(env)->callback_depth = 0;
+			if (env->log.level & BPF_LOG_LEVEL2)
+				verbose(env, "frame%d bpf_loop iteration limit reached\n",
+					env->cur_state->curframe);
+		}
 		break;
 	case BPF_FUNC_dynptr_from_mem:
 		if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) {
@@ -10293,8 +10421,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		break;
 	}
 	case BPF_FUNC_user_ringbuf_drain:
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_user_ringbuf_callback_state);
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_user_ringbuf_callback_state);
 		break;
 	}
 
@@ -10835,7 +10963,9 @@ BTF_ID(func, bpf_dynptr_clone)
 BTF_ID(func, bpf_percpu_obj_new_impl)
 BTF_ID(func, bpf_percpu_obj_drop_impl)
 BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
 BTF_ID(func, bpf_iter_css_task_new)
+#endif
 BTF_SET_END(special_kfunc_set)
 
 BTF_ID_LIST(special_kfunc_list)
@@ -10861,7 +10991,11 @@ BTF_ID(func, bpf_dynptr_clone)
 BTF_ID(func, bpf_percpu_obj_new_impl)
 BTF_ID(func, bpf_percpu_obj_drop_impl)
 BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
 BTF_ID(func, bpf_iter_css_task_new)
+#else
+BTF_ID_UNUSED
+#endif
 
 static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
 {
@@ -11176,7 +11310,7 @@ static bool is_bpf_graph_api_kfunc(u32 btf_id)
 	       btf_id == special_kfunc_list[KF_bpf_refcount_acquire_impl];
 }
 
-static bool is_callback_calling_kfunc(u32 btf_id)
+static bool is_sync_callback_calling_kfunc(u32 btf_id)
 {
 	return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl];
 }
@@ -11394,6 +11528,12 @@ static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env,
 						  &meta->arg_rbtree_root.field);
 }
 
+/*
+ * css_task iter allowlist is needed to avoid dead locking on css_set_lock.
+ * LSM hooks and iters (both sleepable and non-sleepable) are safe.
+ * Any sleepable progs are also safe since bpf_check_attach_target() enforce
+ * them can only be attached to some specific hook points.
+ */
 static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env)
 {
 	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
@@ -11401,10 +11541,12 @@ static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env)
 	switch (prog_type) {
 	case BPF_PROG_TYPE_LSM:
 		return true;
-	case BPF_TRACE_ITER:
-		return env->prog->aux->sleepable;
+	case BPF_PROG_TYPE_TRACING:
+		if (env->prog->expected_attach_type == BPF_TRACE_ITER)
+			return true;
+		fallthrough;
 	default:
-		return false;
+		return env->prog->aux->sleepable;
 	}
 }
 
@@ -11663,7 +11805,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 		case KF_ARG_PTR_TO_ITER:
 			if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) {
 				if (!check_css_task_iter_allowlist(env)) {
-					verbose(env, "css_task_iter is only allowed in bpf_lsm and bpf iter-s\n");
+					verbose(env, "css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs\n");
 					return -EINVAL;
 				}
 			}
@@ -11920,6 +12062,21 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		return -EACCES;
 	}
 
+	/* Check the arguments */
+	err = check_kfunc_args(env, &meta, insn_idx);
+	if (err < 0)
+		return err;
+
+	if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
+		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
+					 set_rbtree_add_callback_state);
+		if (err) {
+			verbose(env, "kfunc %s#%d failed callback verification\n",
+				func_name, meta.func_id);
+			return err;
+		}
+	}
+
 	rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta);
 	rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta);
 
@@ -11955,10 +12112,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		return -EINVAL;
 	}
 
-	/* Check the arguments */
-	err = check_kfunc_args(env, &meta, insn_idx);
-	if (err < 0)
-		return err;
 	/* In case of release function, we get register number of refcounted
 	 * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now.
 	 */
@@ -11992,16 +12145,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		}
 	}
 
-	if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
-		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
-					set_rbtree_add_callback_state);
-		if (err) {
-			verbose(env, "kfunc %s#%d failed callback verification\n",
-				func_name, meta.func_id);
-			return err;
-		}
-	}
-
 	if (meta.func_id == special_kfunc_list[KF_bpf_throw]) {
 		if (!bpf_jit_supports_exceptions()) {
 			verbose(env, "JIT does not support calling kfunc %s#%d\n",
@@ -12053,8 +12196,19 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 				if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set)
 					return -ENOMEM;
 
-				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl] && !bpf_global_percpu_ma_set)
-					return -ENOMEM;
+				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+					if (!bpf_global_percpu_ma_set) {
+						mutex_lock(&bpf_percpu_ma_lock);
+						if (!bpf_global_percpu_ma_set) {
+							err = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true);
+							if (!err)
+								bpf_global_percpu_ma_set = true;
+						}
+						mutex_unlock(&bpf_percpu_ma_lock);
+						if (err)
+							return err;
+					}
+				}
 
 				if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) {
 					verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
@@ -15354,6 +15508,15 @@ static bool is_force_checkpoint(struct bpf_verifier_env *env, int insn_idx)
 	return env->insn_aux_data[insn_idx].force_checkpoint;
 }
 
+static void mark_calls_callback(struct bpf_verifier_env *env, int idx)
+{
+	env->insn_aux_data[idx].calls_callback = true;
+}
+
+static bool calls_callback(struct bpf_verifier_env *env, int insn_idx)
+{
+	return env->insn_aux_data[insn_idx].calls_callback;
+}
 
 enum {
 	DONE_EXPLORING = 0,
@@ -15365,8 +15528,7 @@ enum {
  * w - next instruction
  * e - edge
  */
-static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
-		     bool loop_ok)
+static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
 {
 	int *insn_stack = env->cfg.insn_stack;
 	int *insn_state = env->cfg.insn_state;
@@ -15398,7 +15560,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
 		insn_stack[env->cfg.cur_stack++] = w;
 		return KEEP_EXPLORING;
 	} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
-		if (loop_ok && env->bpf_capable)
+		if (env->bpf_capable)
 			return DONE_EXPLORING;
 		verbose_linfo(env, t, "%d: ", t);
 		verbose_linfo(env, w, "%d: ", w);
@@ -15418,24 +15580,20 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
 				struct bpf_verifier_env *env,
 				bool visit_callee)
 {
-	int ret;
+	int ret, insn_sz;
 
-	ret = push_insn(t, t + 1, FALLTHROUGH, env, false);
+	insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1;
+	ret = push_insn(t, t + insn_sz, FALLTHROUGH, env);
 	if (ret)
 		return ret;
 
-	mark_prune_point(env, t + 1);
+	mark_prune_point(env, t + insn_sz);
 	/* when we exit from subprog, we need to record non-linear history */
-	mark_jmp_point(env, t + 1);
+	mark_jmp_point(env, t + insn_sz);
 
 	if (visit_callee) {
 		mark_prune_point(env, t);
-		ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env,
-				/* It's ok to allow recursion from CFG point of
-				 * view. __check_func_call() will do the actual
-				 * check.
-				 */
-				bpf_pseudo_func(insns + t));
+		ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
 	}
 	return ret;
 }
@@ -15448,15 +15606,17 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
 static int visit_insn(int t, struct bpf_verifier_env *env)
 {
 	struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t];
-	int ret, off;
+	int ret, off, insn_sz;
 
 	if (bpf_pseudo_func(insn))
 		return visit_func_call_insn(t, insns, env, true);
 
 	/* All non-branch instructions have a single fall-through edge. */
 	if (BPF_CLASS(insn->code) != BPF_JMP &&
-	    BPF_CLASS(insn->code) != BPF_JMP32)
-		return push_insn(t, t + 1, FALLTHROUGH, env, false);
+	    BPF_CLASS(insn->code) != BPF_JMP32) {
+		insn_sz = bpf_is_ldimm64(insn) ? 2 : 1;
+		return push_insn(t, t + insn_sz, FALLTHROUGH, env);
+	}
 
 	switch (BPF_OP(insn->code)) {
 	case BPF_EXIT:
@@ -15470,6 +15630,21 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
 			 * async state will be pushed for further exploration.
 			 */
 			mark_prune_point(env, t);
+		/* For functions that invoke callbacks it is not known how many times
+		 * callback would be called. Verifier models callback calling functions
+		 * by repeatedly visiting callback bodies and returning to origin call
+		 * instruction.
+		 * In order to stop such iteration verifier needs to identify when a
+		 * state identical some state from a previous iteration is reached.
+		 * Check below forces creation of checkpoint before callback calling
+		 * instruction to allow search for such identical states.
+		 */
+		if (is_sync_callback_calling_insn(insn)) {
+			mark_calls_callback(env, t);
+			mark_force_checkpoint(env, t);
+			mark_prune_point(env, t);
+			mark_jmp_point(env, t);
+		}
 		if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
 			struct bpf_kfunc_call_arg_meta meta;
 
@@ -15502,8 +15677,7 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
 			off = insn->imm;
 
 		/* unconditional jump with single edge */
-		ret = push_insn(t, t + off + 1, FALLTHROUGH, env,
-				true);
+		ret = push_insn(t, t + off + 1, FALLTHROUGH, env);
 		if (ret)
 			return ret;
 
@@ -15516,11 +15690,11 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
 		/* conditional jump with two edges */
 		mark_prune_point(env, t);
 
-		ret = push_insn(t, t + 1, FALLTHROUGH, env, true);
+		ret = push_insn(t, t + 1, FALLTHROUGH, env);
 		if (ret)
 			return ret;
 
-		return push_insn(t, t + insn->off + 1, BRANCH, env, true);
+		return push_insn(t, t + insn->off + 1, BRANCH, env);
 	}
 }
 
@@ -15586,11 +15760,21 @@ walk_cfg:
 	}
 
 	for (i = 0; i < insn_cnt; i++) {
+		struct bpf_insn *insn = &env->prog->insnsi[i];
+
 		if (insn_state[i] != EXPLORED) {
 			verbose(env, "unreachable insn %d\n", i);
 			ret = -EINVAL;
 			goto err_free;
 		}
+		if (bpf_is_ldimm64(insn)) {
+			if (insn_state[i + 1] != 0) {
+				verbose(env, "jump into the middle of ldimm64 insn %d\n", i);
+				ret = -EINVAL;
+				goto err_free;
+			}
+			i++; /* skip second half of ldimm64 */
+		}
 	}
 	ret = 0; /* cfg looks good */
 
@@ -16930,10 +17114,16 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 				}
 				goto skip_inf_loop_check;
 			}
+			if (calls_callback(env, insn_idx)) {
+				if (states_equal(env, &sl->state, cur, true))
+					goto hit;
+				goto skip_inf_loop_check;
+			}
 			/* attempt to detect infinite loop to avoid unnecessary doomed work */
 			if (states_maybe_looping(&sl->state, cur) &&
 			    states_equal(env, &sl->state, cur, false) &&
-			    !iter_active_depths_differ(&sl->state, cur)) {
+			    !iter_active_depths_differ(&sl->state, cur) &&
+			    sl->state.callback_unroll_depth == cur->callback_unroll_depth) {
 				verbose_linfo(env, insn_idx, "; ");
 				verbose(env, "infinite loop detected at insn %d\n", insn_idx);
 				verbose(env, "cur state:");
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 4e610863cc3771..8f3cef1a4d8a74 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3898,14 +3898,6 @@ static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
 	return psi_trigger_poll(&ctx->psi.trigger, of->file, pt);
 }
 
-static int cgroup_pressure_open(struct kernfs_open_file *of)
-{
-	if (of->file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE))
-		return -EPERM;
-
-	return 0;
-}
-
 static void cgroup_pressure_release(struct kernfs_open_file *of)
 {
 	struct cgroup_file_ctx *ctx = of->priv;
@@ -5312,7 +5304,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "io.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_IO]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_io_pressure_show,
 		.write = cgroup_io_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5321,7 +5312,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "memory.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_memory_pressure_show,
 		.write = cgroup_memory_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5330,7 +5320,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "cpu.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_cpu_pressure_show,
 		.write = cgroup_cpu_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5340,7 +5329,6 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "irq.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]),
-		.open = cgroup_pressure_open,
 		.seq_show = cgroup_irq_pressure_show,
 		.write = cgroup_irq_pressure_write,
 		.poll = cgroup_pressure_poll,
diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c
index 122dacb3a44390..66d1708042a72b 100644
--- a/kernel/cgroup/legacy_freezer.c
+++ b/kernel/cgroup/legacy_freezer.c
@@ -66,9 +66,15 @@ static struct freezer *parent_freezer(struct freezer *freezer)
 bool cgroup_freezing(struct task_struct *task)
 {
 	bool ret;
+	unsigned int state;
 
 	rcu_read_lock();
-	ret = task_freezer(task)->state & CGROUP_FREEZING;
+	/* Check if the cgroup is still FREEZING, but not FROZEN. The extra
+	 * !FROZEN check is required, because the FREEZING bit is not cleared
+	 * when the state FROZEN is reached.
+	 */
+	state = task_freezer(task)->state;
+	ret = (state & CGROUP_FREEZING) && !(state & CGROUP_FROZEN);
 	rcu_read_unlock();
 
 	return ret;
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 4ec29e6b1d8dce..a8350d2d63e6b1 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -211,19 +211,16 @@ unlock_ret:
  * optimize away the callsite. Therefore, __weak is needed to ensure that the
  * call is still emitted, by telling the compiler that we don't know what the
  * function might eventually be.
- *
- * __diag_* below are needed to dismiss the missing prototype warning.
  */
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "kfuncs which will be used in BPF programs");
+
+__bpf_hook_start();
 
 __weak noinline void bpf_rstat_flush(struct cgroup *cgrp,
 				     struct cgroup *parent, int cpu)
 {
 }
 
-__diag_pop();
+__bpf_hook_end();
 
 /* see cgroup_rstat_flush() */
 static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9e4c6780adde8f..a86972a9199158 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2113,7 +2113,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 	[CPUHP_HRTIMERS_PREPARE] = {
 		.name			= "hrtimers:prepare",
 		.startup.single		= hrtimers_prepare_cpu,
-		.teardown.single	= hrtimers_dead_cpu,
+		.teardown.single	= NULL,
 	},
 	[CPUHP_SMPCFD_PREPARE] = {
 		.name			= "smpcfd:prepare",
@@ -2205,6 +2205,12 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.startup.single		= NULL,
 		.teardown.single	= smpcfd_dying_cpu,
 	},
+	[CPUHP_AP_HRTIMERS_DYING] = {
+		.name			= "hrtimers:dying",
+		.startup.single		= NULL,
+		.teardown.single	= hrtimers_cpu_dying,
+	},
+
 	/* Entry state on starting. Interrupts enabled from here on. Transient
 	 * state for synchronsization */
 	[CPUHP_AP_ONLINE] = {
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index efe87d501c8c3c..d4313b53837e3d 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -199,7 +199,7 @@ static __initdata char *suffix_tbl[] = {
  * It returns 0 on success and -EINVAL on failure.
  */
 static int __init parse_crashkernel_suffix(char *cmdline,
-					   unsigned long long	*crash_size,
+					   unsigned long long *crash_size,
 					   const char *suffix)
 {
 	char *cur = cmdline;
@@ -268,9 +268,9 @@ static int __init __parse_crashkernel(char *cmdline,
 			     unsigned long long *crash_base,
 			     const char *suffix)
 {
-	char	*first_colon, *first_space;
-	char	*ck_cmdline;
-	char	*name = "crashkernel=";
+	char *first_colon, *first_space;
+	char *ck_cmdline;
+	char *name = "crashkernel=";
 
 	BUG_ON(!crash_size || !crash_base);
 	*crash_size = 0;
@@ -440,7 +440,7 @@ retry:
 		return;
 	}
 
-	if ((crash_base > CRASH_ADDR_LOW_MAX) &&
+	if ((crash_base >= CRASH_ADDR_LOW_MAX) &&
 	     crash_low_size && reserve_crashkernel_low(crash_low_size)) {
 		memblock_phys_free(crash_base, crash_size);
 		return;
diff --git a/kernel/cred.c b/kernel/cred.c
index 3c714cb31660d9..c033a201c808e5 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -43,10 +43,6 @@ static struct group_info init_groups = { .usage = REFCOUNT_INIT(2) };
  */
 struct cred init_cred = {
 	.usage			= ATOMIC_INIT(4),
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	.subscribers		= ATOMIC_INIT(2),
-	.magic			= CRED_MAGIC,
-#endif
 	.uid			= GLOBAL_ROOT_UID,
 	.gid			= GLOBAL_ROOT_GID,
 	.suid			= GLOBAL_ROOT_UID,
@@ -66,31 +62,6 @@ struct cred init_cred = {
 	.ucounts		= &init_ucounts,
 };
 
-static inline void set_cred_subscribers(struct cred *cred, int n)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	atomic_set(&cred->subscribers, n);
-#endif
-}
-
-static inline int read_cred_subscribers(const struct cred *cred)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	return atomic_read(&cred->subscribers);
-#else
-	return 0;
-#endif
-}
-
-static inline void alter_cred_subscribers(const struct cred *_cred, int n)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	struct cred *cred = (struct cred *) _cred;
-
-	atomic_add(n, &cred->subscribers);
-#endif
-}
-
 /*
  * The RCU callback to actually dispose of a set of credentials
  */
@@ -100,20 +71,9 @@ static void put_cred_rcu(struct rcu_head *rcu)
 
 	kdebug("put_cred_rcu(%p)", cred);
 
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	if (cred->magic != CRED_MAGIC_DEAD ||
-	    atomic_read(&cred->usage) != 0 ||
-	    read_cred_subscribers(cred) != 0)
-		panic("CRED: put_cred_rcu() sees %p with"
-		      " mag %x, put %p, usage %d, subscr %d\n",
-		      cred, cred->magic, cred->put_addr,
-		      atomic_read(&cred->usage),
-		      read_cred_subscribers(cred));
-#else
-	if (atomic_read(&cred->usage) != 0)
-		panic("CRED: put_cred_rcu() sees %p with usage %d\n",
-		      cred, atomic_read(&cred->usage));
-#endif
+	if (atomic_long_read(&cred->usage) != 0)
+		panic("CRED: put_cred_rcu() sees %p with usage %ld\n",
+		      cred, atomic_long_read(&cred->usage));
 
 	security_cred_free(cred);
 	key_put(cred->session_keyring);
@@ -137,16 +97,10 @@ static void put_cred_rcu(struct rcu_head *rcu)
  */
 void __put_cred(struct cred *cred)
 {
-	kdebug("__put_cred(%p{%d,%d})", cred,
-	       atomic_read(&cred->usage),
-	       read_cred_subscribers(cred));
-
-	BUG_ON(atomic_read(&cred->usage) != 0);
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	BUG_ON(read_cred_subscribers(cred) != 0);
-	cred->magic = CRED_MAGIC_DEAD;
-	cred->put_addr = __builtin_return_address(0);
-#endif
+	kdebug("__put_cred(%p{%ld})", cred,
+	       atomic_long_read(&cred->usage));
+
+	BUG_ON(atomic_long_read(&cred->usage) != 0);
 	BUG_ON(cred == current->cred);
 	BUG_ON(cred == current->real_cred);
 
@@ -164,9 +118,8 @@ void exit_creds(struct task_struct *tsk)
 {
 	struct cred *real_cred, *cred;
 
-	kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred,
-	       atomic_read(&tsk->cred->usage),
-	       read_cred_subscribers(tsk->cred));
+	kdebug("exit_creds(%u,%p,%p,{%ld})", tsk->pid, tsk->real_cred, tsk->cred,
+	       atomic_long_read(&tsk->cred->usage));
 
 	real_cred = (struct cred *) tsk->real_cred;
 	tsk->real_cred = NULL;
@@ -174,15 +127,10 @@ void exit_creds(struct task_struct *tsk)
 	cred = (struct cred *) tsk->cred;
 	tsk->cred = NULL;
 
-	validate_creds(cred);
 	if (real_cred == cred) {
-		alter_cred_subscribers(cred, -2);
 		put_cred_many(cred, 2);
 	} else {
-		validate_creds(real_cred);
-		alter_cred_subscribers(real_cred, -1);
 		put_cred(real_cred);
-		alter_cred_subscribers(cred, -1);
 		put_cred(cred);
 	}
 
@@ -230,10 +178,7 @@ struct cred *cred_alloc_blank(void)
 	if (!new)
 		return NULL;
 
-	atomic_set(&new->usage, 1);
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	new->magic = CRED_MAGIC;
-#endif
+	atomic_long_set(&new->usage, 1);
 	if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
@@ -264,8 +209,6 @@ struct cred *prepare_creds(void)
 	const struct cred *old;
 	struct cred *new;
 
-	validate_process_creds();
-
 	new = kmem_cache_alloc(cred_jar, GFP_KERNEL);
 	if (!new)
 		return NULL;
@@ -276,8 +219,7 @@ struct cred *prepare_creds(void)
 	memcpy(new, old, sizeof(struct cred));
 
 	new->non_rcu = 0;
-	atomic_set(&new->usage, 1);
-	set_cred_subscribers(new, 0);
+	atomic_long_set(&new->usage, 1);
 	get_group_info(new->group_info);
 	get_uid(new->user);
 	get_user_ns(new->user_ns);
@@ -300,7 +242,6 @@ struct cred *prepare_creds(void)
 	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
-	validate_creds(new);
 	return new;
 
 error:
@@ -362,10 +303,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 		clone_flags & CLONE_THREAD
 	    ) {
 		p->real_cred = get_cred_many(p->cred, 2);
-		alter_cred_subscribers(p->cred, 2);
-		kdebug("share_creds(%p{%d,%d})",
-		       p->cred, atomic_read(&p->cred->usage),
-		       read_cred_subscribers(p->cred));
+		kdebug("share_creds(%p{%ld})",
+		       p->cred, atomic_long_read(&p->cred->usage));
 		inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
 		return 0;
 	}
@@ -404,8 +343,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 
 	p->cred = p->real_cred = get_cred(new);
 	inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
-	alter_cred_subscribers(new, 2);
-	validate_creds(new);
 	return 0;
 
 error_put:
@@ -457,17 +394,11 @@ int commit_creds(struct cred *new)
 	struct task_struct *task = current;
 	const struct cred *old = task->real_cred;
 
-	kdebug("commit_creds(%p{%d,%d})", new,
-	       atomic_read(&new->usage),
-	       read_cred_subscribers(new));
+	kdebug("commit_creds(%p{%ld})", new,
+	       atomic_long_read(&new->usage));
 
 	BUG_ON(task->cred != old);
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	BUG_ON(read_cred_subscribers(old) < 2);
-	validate_creds(old);
-	validate_creds(new);
-#endif
-	BUG_ON(atomic_read(&new->usage) < 1);
+	BUG_ON(atomic_long_read(&new->usage) < 1);
 
 	get_cred(new); /* we will require a ref for the subj creds too */
 
@@ -502,14 +433,12 @@ int commit_creds(struct cred *new)
 	 * RLIMIT_NPROC limits on user->processes have already been checked
 	 * in set_user().
 	 */
-	alter_cred_subscribers(new, 2);
 	if (new->user != old->user || new->user_ns != old->user_ns)
 		inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1);
 	rcu_assign_pointer(task->real_cred, new);
 	rcu_assign_pointer(task->cred, new);
 	if (new->user != old->user || new->user_ns != old->user_ns)
 		dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1);
-	alter_cred_subscribers(old, -2);
 
 	/* send notifications */
 	if (!uid_eq(new->uid,   old->uid)  ||
@@ -539,14 +468,10 @@ EXPORT_SYMBOL(commit_creds);
  */
 void abort_creds(struct cred *new)
 {
-	kdebug("abort_creds(%p{%d,%d})", new,
-	       atomic_read(&new->usage),
-	       read_cred_subscribers(new));
+	kdebug("abort_creds(%p{%ld})", new,
+	       atomic_long_read(&new->usage));
 
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	BUG_ON(read_cred_subscribers(new) != 0);
-#endif
-	BUG_ON(atomic_read(&new->usage) < 1);
+	BUG_ON(atomic_long_read(&new->usage) < 1);
 	put_cred(new);
 }
 EXPORT_SYMBOL(abort_creds);
@@ -562,12 +487,8 @@ const struct cred *override_creds(const struct cred *new)
 {
 	const struct cred *old = current->cred;
 
-	kdebug("override_creds(%p{%d,%d})", new,
-	       atomic_read(&new->usage),
-	       read_cred_subscribers(new));
-
-	validate_creds(old);
-	validate_creds(new);
+	kdebug("override_creds(%p{%ld})", new,
+	       atomic_long_read(&new->usage));
 
 	/*
 	 * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'.
@@ -576,18 +497,12 @@ const struct cred *override_creds(const struct cred *new)
 	 * we are only installing the cred into the thread-synchronous
 	 * '->cred' pointer, not the '->real_cred' pointer that is
 	 * visible to other threads under RCU.
-	 *
-	 * Also note that we did validate_creds() manually, not depending
-	 * on the validation in 'get_cred()'.
 	 */
 	get_new_cred((struct cred *)new);
-	alter_cred_subscribers(new, 1);
 	rcu_assign_pointer(current->cred, new);
-	alter_cred_subscribers(old, -1);
 
-	kdebug("override_creds() = %p{%d,%d}", old,
-	       atomic_read(&old->usage),
-	       read_cred_subscribers(old));
+	kdebug("override_creds() = %p{%ld}", old,
+	       atomic_long_read(&old->usage));
 	return old;
 }
 EXPORT_SYMBOL(override_creds);
@@ -603,15 +518,10 @@ void revert_creds(const struct cred *old)
 {
 	const struct cred *override = current->cred;
 
-	kdebug("revert_creds(%p{%d,%d})", old,
-	       atomic_read(&old->usage),
-	       read_cred_subscribers(old));
+	kdebug("revert_creds(%p{%ld})", old,
+	       atomic_long_read(&old->usage));
 
-	validate_creds(old);
-	validate_creds(override);
-	alter_cred_subscribers(old, 1);
 	rcu_assign_pointer(current->cred, old);
-	alter_cred_subscribers(override, -1);
 	put_cred(override);
 }
 EXPORT_SYMBOL(revert_creds);
@@ -731,12 +641,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	kdebug("prepare_kernel_cred() alloc %p", new);
 
 	old = get_task_cred(daemon);
-	validate_creds(old);
 
 	*new = *old;
 	new->non_rcu = 0;
-	atomic_set(&new->usage, 1);
-	set_cred_subscribers(new, 0);
+	atomic_long_set(&new->usage, 1);
 	get_uid(new->user);
 	get_user_ns(new->user_ns);
 	get_group_info(new->group_info);
@@ -760,7 +668,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 		goto error;
 
 	put_cred(old);
-	validate_creds(new);
 	return new;
 
 error:
@@ -825,109 +732,3 @@ int set_create_files_as(struct cred *new, struct inode *inode)
 	return security_kernel_create_files_as(new, inode);
 }
 EXPORT_SYMBOL(set_create_files_as);
-
-#ifdef CONFIG_DEBUG_CREDENTIALS
-
-bool creds_are_invalid(const struct cred *cred)
-{
-	if (cred->magic != CRED_MAGIC)
-		return true;
-	return false;
-}
-EXPORT_SYMBOL(creds_are_invalid);
-
-/*
- * dump invalid credentials
- */
-static void dump_invalid_creds(const struct cred *cred, const char *label,
-			       const struct task_struct *tsk)
-{
-	pr_err("%s credentials: %p %s%s%s\n",
-	       label, cred,
-	       cred == &init_cred ? "[init]" : "",
-	       cred == tsk->real_cred ? "[real]" : "",
-	       cred == tsk->cred ? "[eff]" : "");
-	pr_err("->magic=%x, put_addr=%p\n",
-	       cred->magic, cred->put_addr);
-	pr_err("->usage=%d, subscr=%d\n",
-	       atomic_read(&cred->usage),
-	       read_cred_subscribers(cred));
-	pr_err("->*uid = { %d,%d,%d,%d }\n",
-		from_kuid_munged(&init_user_ns, cred->uid),
-		from_kuid_munged(&init_user_ns, cred->euid),
-		from_kuid_munged(&init_user_ns, cred->suid),
-		from_kuid_munged(&init_user_ns, cred->fsuid));
-	pr_err("->*gid = { %d,%d,%d,%d }\n",
-		from_kgid_munged(&init_user_ns, cred->gid),
-		from_kgid_munged(&init_user_ns, cred->egid),
-		from_kgid_munged(&init_user_ns, cred->sgid),
-		from_kgid_munged(&init_user_ns, cred->fsgid));
-#ifdef CONFIG_SECURITY
-	pr_err("->security is %p\n", cred->security);
-	if ((unsigned long) cred->security >= PAGE_SIZE &&
-	    (((unsigned long) cred->security & 0xffffff00) !=
-	     (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8)))
-		pr_err("->security {%x, %x}\n",
-		       ((u32*)cred->security)[0],
-		       ((u32*)cred->security)[1]);
-#endif
-}
-
-/*
- * report use of invalid credentials
- */
-void __noreturn __invalid_creds(const struct cred *cred, const char *file, unsigned line)
-{
-	pr_err("Invalid credentials\n");
-	pr_err("At %s:%u\n", file, line);
-	dump_invalid_creds(cred, "Specified", current);
-	BUG();
-}
-EXPORT_SYMBOL(__invalid_creds);
-
-/*
- * check the credentials on a process
- */
-void __validate_process_creds(struct task_struct *tsk,
-			      const char *file, unsigned line)
-{
-	if (tsk->cred == tsk->real_cred) {
-		if (unlikely(read_cred_subscribers(tsk->cred) < 2 ||
-			     creds_are_invalid(tsk->cred)))
-			goto invalid_creds;
-	} else {
-		if (unlikely(read_cred_subscribers(tsk->real_cred) < 1 ||
-			     read_cred_subscribers(tsk->cred) < 1 ||
-			     creds_are_invalid(tsk->real_cred) ||
-			     creds_are_invalid(tsk->cred)))
-			goto invalid_creds;
-	}
-	return;
-
-invalid_creds:
-	pr_err("Invalid process credentials\n");
-	pr_err("At %s:%u\n", file, line);
-
-	dump_invalid_creds(tsk->real_cred, "Real", tsk);
-	if (tsk->cred != tsk->real_cred)
-		dump_invalid_creds(tsk->cred, "Effective", tsk);
-	else
-		pr_err("Effective creds == Real creds\n");
-	BUG();
-}
-EXPORT_SYMBOL(__validate_process_creds);
-
-/*
- * check creds for do_exit()
- */
-void validate_creds_for_do_exit(struct task_struct *tsk)
-{
-	kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})",
-	       tsk->real_cred, tsk->cred,
-	       atomic_read(&tsk->cred->usage),
-	       read_cred_subscribers(tsk->cred));
-
-	__validate_process_creds(tsk, __FILE__, __LINE__);
-}
-
-#endif /* CONFIG_DEBUG_CREDENTIALS */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index ed3056eb20b8bd..73c95815789a0f 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -587,6 +587,46 @@ int dma_direct_supported(struct device *dev, u64 mask)
 	return mask >= phys_to_dma_unencrypted(dev, min_mask);
 }
 
+/*
+ * To check whether all ram resource ranges are covered by dma range map
+ * Returns 0 when further check is needed
+ * Returns 1 if there is some RAM range can't be covered by dma_range_map
+ */
+static int check_ram_in_range_map(unsigned long start_pfn,
+				  unsigned long nr_pages, void *data)
+{
+	unsigned long end_pfn = start_pfn + nr_pages;
+	const struct bus_dma_region *bdr = NULL;
+	const struct bus_dma_region *m;
+	struct device *dev = data;
+
+	while (start_pfn < end_pfn) {
+		for (m = dev->dma_range_map; PFN_DOWN(m->size); m++) {
+			unsigned long cpu_start_pfn = PFN_DOWN(m->cpu_start);
+
+			if (start_pfn >= cpu_start_pfn &&
+			    start_pfn - cpu_start_pfn < PFN_DOWN(m->size)) {
+				bdr = m;
+				break;
+			}
+		}
+		if (!bdr)
+			return 1;
+
+		start_pfn = PFN_DOWN(bdr->cpu_start) + PFN_DOWN(bdr->size);
+	}
+
+	return 0;
+}
+
+bool dma_direct_all_ram_mapped(struct device *dev)
+{
+	if (!dev->dma_range_map)
+		return true;
+	return !walk_system_ram_range(0, PFN_DOWN(ULONG_MAX) + 1, dev,
+				      check_ram_in_range_map);
+}
+
 size_t dma_direct_max_mapping_size(struct device *dev)
 {
 	/* If SWIOTLB is active, use its maximum mapping size */
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index 97ec892ea0b5ac..18d346118fe8eb 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -20,6 +20,7 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
 int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs);
+bool dma_direct_all_ram_mapped(struct device *dev);
 size_t dma_direct_max_mapping_size(struct device *dev);
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index e323ca48f7f2a4..58db8fd70471a1 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -793,6 +793,28 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_set_coherent_mask);
 
+/**
+ * dma_addressing_limited - return if the device is addressing limited
+ * @dev:	device to check
+ *
+ * Return %true if the devices DMA mask is too small to address all memory in
+ * the system, else %false.  Lack of addressing bits is the prime reason for
+ * bounce buffering, but might not be the only one.
+ */
+bool dma_addressing_limited(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
+			 dma_get_required_mask(dev))
+		return true;
+
+	if (unlikely(ops))
+		return false;
+	return !dma_direct_all_ram_mapped(dev);
+}
+EXPORT_SYMBOL_GPL(dma_addressing_limited);
+
 size_t dma_max_mapping_size(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 26202274784f03..33d942615be54c 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -283,7 +283,8 @@ static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start,
 	}
 
 	for (i = 0; i < mem->nslabs; i++) {
-		mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i);
+		mem->slots[i].list = min(IO_TLB_SEGSIZE - io_tlb_offset(i),
+					 mem->nslabs - i);
 		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
 		mem->slots[i].alloc_size = 0;
 	}
@@ -558,29 +559,40 @@ void __init swiotlb_exit(void)
  * alloc_dma_pages() - allocate pages to be used for DMA
  * @gfp:	GFP flags for the allocation.
  * @bytes:	Size of the buffer.
+ * @phys_limit:	Maximum allowed physical address of the buffer.
  *
  * Allocate pages from the buddy allocator. If successful, make the allocated
  * pages decrypted that they can be used for DMA.
  *
- * Return: Decrypted pages, or %NULL on failure.
+ * Return: Decrypted pages, %NULL on allocation failure, or ERR_PTR(-EAGAIN)
+ * if the allocated physical address was above @phys_limit.
  */
-static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes)
+static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes, u64 phys_limit)
 {
 	unsigned int order = get_order(bytes);
 	struct page *page;
+	phys_addr_t paddr;
 	void *vaddr;
 
 	page = alloc_pages(gfp, order);
 	if (!page)
 		return NULL;
 
-	vaddr = page_address(page);
+	paddr = page_to_phys(page);
+	if (paddr + bytes - 1 > phys_limit) {
+		__free_pages(page, order);
+		return ERR_PTR(-EAGAIN);
+	}
+
+	vaddr = phys_to_virt(paddr);
 	if (set_memory_decrypted((unsigned long)vaddr, PFN_UP(bytes)))
 		goto error;
 	return page;
 
 error:
-	__free_pages(page, order);
+	/* Intentional leak if pages cannot be encrypted again. */
+	if (!set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes)))
+		__free_pages(page, order);
 	return NULL;
 }
 
@@ -618,11 +630,7 @@ static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes,
 	else if (phys_limit <= DMA_BIT_MASK(32))
 		gfp |= __GFP_DMA32;
 
-	while ((page = alloc_dma_pages(gfp, bytes)) &&
-	       page_to_phys(page) + bytes - 1 > phys_limit) {
-		/* allocated, but too high */
-		__free_pages(page, get_order(bytes));
-
+	while (IS_ERR(page = alloc_dma_pages(gfp, bytes, phys_limit))) {
 		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
 		    phys_limit < DMA_BIT_MASK(64) &&
 		    !(gfp & (__GFP_DMA32 | __GFP_DMA)))
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 683dc086ef10a5..9efd0d7775e7ce 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1814,31 +1814,34 @@ static inline void perf_event__state_init(struct perf_event *event)
 					      PERF_EVENT_STATE_INACTIVE;
 }
 
-static void __perf_event_read_size(struct perf_event *event, int nr_siblings)
+static int __perf_event_read_size(u64 read_format, int nr_siblings)
 {
 	int entry = sizeof(u64); /* value */
 	int size = 0;
 	int nr = 1;
 
-	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
 		size += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
 		size += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_ID)
+	if (read_format & PERF_FORMAT_ID)
 		entry += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_LOST)
+	if (read_format & PERF_FORMAT_LOST)
 		entry += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_GROUP) {
+	if (read_format & PERF_FORMAT_GROUP) {
 		nr += nr_siblings;
 		size += sizeof(u64);
 	}
 
-	size += entry * nr;
-	event->read_size = size;
+	/*
+	 * Since perf_event_validate_size() limits this to 16k and inhibits
+	 * adding more siblings, this will never overflow.
+	 */
+	return size + nr * entry;
 }
 
 static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
@@ -1888,8 +1891,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
  */
 static void perf_event__header_size(struct perf_event *event)
 {
-	__perf_event_read_size(event,
-			       event->group_leader->nr_siblings);
+	event->read_size =
+		__perf_event_read_size(event->attr.read_format,
+				       event->group_leader->nr_siblings);
 	__perf_event_header_size(event, event->attr.sample_type);
 }
 
@@ -1920,23 +1924,44 @@ static void perf_event__id_header_size(struct perf_event *event)
 	event->id_header_size = size;
 }
 
+/*
+ * Check that adding an event to the group does not result in anybody
+ * overflowing the 64k event limit imposed by the output buffer.
+ *
+ * Specifically, check that the read_size for the event does not exceed 16k,
+ * read_size being the one term that grows with groups size. Since read_size
+ * depends on per-event read_format, also (re)check the existing events.
+ *
+ * This leaves 48k for the constant size fields and things like callchains,
+ * branch stacks and register sets.
+ */
 static bool perf_event_validate_size(struct perf_event *event)
 {
-	/*
-	 * The values computed here will be over-written when we actually
-	 * attach the event.
-	 */
-	__perf_event_read_size(event, event->group_leader->nr_siblings + 1);
-	__perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ);
-	perf_event__id_header_size(event);
+	struct perf_event *sibling, *group_leader = event->group_leader;
+
+	if (__perf_event_read_size(event->attr.read_format,
+				   group_leader->nr_siblings + 1) > 16*1024)
+		return false;
+
+	if (__perf_event_read_size(group_leader->attr.read_format,
+				   group_leader->nr_siblings + 1) > 16*1024)
+		return false;
 
 	/*
-	 * Sum the lot; should not exceed the 64k limit we have on records.
-	 * Conservative limit to allow for callchains and other variable fields.
+	 * When creating a new group leader, group_leader->ctx is initialized
+	 * after the size has been validated, but we cannot safely use
+	 * for_each_sibling_event() until group_leader->ctx is set. A new group
+	 * leader cannot have any siblings yet, so we can safely skip checking
+	 * the non-existent siblings.
 	 */
-	if (event->read_size + event->header_size +
-	    event->id_header_size + sizeof(struct perf_event_header) >= 16*1024)
-		return false;
+	if (event == group_leader)
+		return true;
+
+	for_each_sibling_event(sibling, group_leader) {
+		if (__perf_event_read_size(sibling->attr.read_format,
+					   group_leader->nr_siblings + 1) > 16*1024)
+			return false;
+	}
 
 	return true;
 }
@@ -4828,6 +4853,11 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 	void *task_ctx_data = NULL;
 
 	if (!ctx->task) {
+		/*
+		 * perf_pmu_migrate_context() / __perf_pmu_install_event()
+		 * relies on the fact that find_get_pmu_context() cannot fail
+		 * for CPU contexts.
+		 */
 		struct perf_cpu_pmu_context *cpc;
 
 		cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu);
@@ -12889,6 +12919,9 @@ static void __perf_pmu_install_event(struct pmu *pmu,
 				     int cpu, struct perf_event *event)
 {
 	struct perf_event_pmu_context *epc;
+	struct perf_event_context *old_ctx = event->ctx;
+
+	get_ctx(ctx); /* normally find_get_context() */
 
 	event->cpu = cpu;
 	epc = find_get_pmu_context(pmu, ctx, event);
@@ -12897,6 +12930,11 @@ static void __perf_pmu_install_event(struct pmu *pmu,
 	if (event->state >= PERF_EVENT_STATE_OFF)
 		event->state = PERF_EVENT_STATE_INACTIVE;
 	perf_install_in_context(ctx, event, cpu);
+
+	/*
+	 * Now that event->ctx is updated and visible, put the old ctx.
+	 */
+	put_ctx(old_ctx);
 }
 
 static void __perf_pmu_install(struct perf_event_context *ctx,
@@ -12935,6 +12973,10 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	struct perf_event_context *src_ctx, *dst_ctx;
 	LIST_HEAD(events);
 
+	/*
+	 * Since per-cpu context is persistent, no need to grab an extra
+	 * reference.
+	 */
 	src_ctx = &per_cpu_ptr(&perf_cpu_context, src_cpu)->ctx;
 	dst_ctx = &per_cpu_ptr(&perf_cpu_context, dst_cpu)->ctx;
 
diff --git a/kernel/exit.c b/kernel/exit.c
index ee9f43bed49a24..aedc0832c9f4de 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -824,8 +824,6 @@ void __noreturn do_exit(long code)
 	ptrace_event(PTRACE_EVENT_EXIT, code);
 	user_events_exit(tsk);
 
-	validate_creds_for_do_exit(tsk);
-
 	io_uring_files_cancel();
 	exit_signals(tsk);  /* sets PF_EXITING */
 
@@ -909,7 +907,6 @@ void __noreturn do_exit(long code)
 	if (tsk->task_frag.page)
 		put_page(tsk->task_frag.page);
 
-	validate_creds_for_do_exit(tsk);
 	exit_task_stack_account(tsk);
 
 	check_stack_usage();
diff --git a/kernel/freezer.c b/kernel/freezer.c
index c450fa8b8b5ef4..759006a9a91026 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -201,7 +201,7 @@ void __thaw_task(struct task_struct *p)
 	if (WARN_ON_ONCE(freezing(p)))
 		goto unlock;
 
-	if (task_call_func(p, __restore_freezer_state, NULL))
+	if (!frozen(p) || task_call_func(p, __restore_freezer_state, NULL))
 		goto unlock;
 
 	wake_up_state(p, TASK_FROZEN);
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 52695c59d04114..dad981a865b841 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -700,7 +700,8 @@ retry:
 	owner = uval & FUTEX_TID_MASK;
 
 	if (pending_op && !pi && !owner) {
-		futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+		futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
+			   FUTEX_BITSET_MATCH_ANY);
 		return 0;
 	}
 
@@ -752,8 +753,10 @@ retry:
 	 * Wake robust non-PI futexes here. The wakeup of
 	 * PI futexes happens in exit_pi_state():
 	 */
-	if (!pi && (uval & FUTEX_WAITERS))
-		futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+	if (!pi && (uval & FUTEX_WAITERS)) {
+		futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
+			   FUTEX_BITSET_MATCH_ANY);
+	}
 
 	return 0;
 }
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 075a632e6c7c3f..d5a0ee40bf66c5 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2252,7 +2252,7 @@ int register_kretprobe(struct kretprobe *rp)
 		rp->rph = NULL;
 		return -ENOMEM;
 	}
-	rp->rph->rp = rp;
+	rcu_assign_pointer(rp->rph->rp, rp);
 	rp->nmissed = 0;
 	/* Establish function entry probe point */
 	ret = register_kprobe(&rp->kp);
@@ -2300,7 +2300,7 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
 #ifdef CONFIG_KRETPROBE_ON_RETHOOK
 		rethook_free(rps[i]->rh);
 #else
-		rps[i]->rph->rp = NULL;
+		rcu_assign_pointer(rps[i]->rph->rp, NULL);
 #endif
 	}
 	mutex_unlock(&kprobe_mutex);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index e85b5ad3e20698..151bd3de59363a 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3497,7 +3497,8 @@ static int alloc_chain_hlocks(int req)
 		size = chain_block_size(curr);
 		if (likely(size >= req)) {
 			del_chain_block(0, size, chain_block_next(curr));
-			add_chain_block(curr + req, size - req);
+			if (size > req)
+				add_chain_block(curr + req, size - req);
 			return curr;
 		}
 	}
diff --git a/kernel/resource.c b/kernel/resource.c
index 866ef3663a0b65..91be1bc50b60e9 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1844,8 +1844,8 @@ get_free_mem_region(struct device *dev, struct resource *base,
 
 	write_lock(&resource_lock);
 	for (addr = gfr_start(base, size, align, flags);
-	     gfr_continue(base, addr, size, flags);
-	     addr = gfr_next(addr, size, flags)) {
+	     gfr_continue(base, addr, align, flags);
+	     addr = gfr_next(addr, align, flags)) {
 		if (__region_intersects(base, addr, size, 0, IORES_DESC_NONE) !=
 		    REGION_DISJOINT)
 			continue;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2048138ce54b57..d7a3c63a2171a8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3666,41 +3666,140 @@ static inline void
 dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
 #endif
 
+static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se,
+			   unsigned long weight)
+{
+	unsigned long old_weight = se->load.weight;
+	u64 avruntime = avg_vruntime(cfs_rq);
+	s64 vlag, vslice;
+
+	/*
+	 * VRUNTIME
+	 * ========
+	 *
+	 * COROLLARY #1: The virtual runtime of the entity needs to be
+	 * adjusted if re-weight at !0-lag point.
+	 *
+	 * Proof: For contradiction assume this is not true, so we can
+	 * re-weight without changing vruntime at !0-lag point.
+	 *
+	 *             Weight	VRuntime   Avg-VRuntime
+	 *     before    w          v            V
+	 *      after    w'         v'           V'
+	 *
+	 * Since lag needs to be preserved through re-weight:
+	 *
+	 *	lag = (V - v)*w = (V'- v')*w', where v = v'
+	 *	==>	V' = (V - v)*w/w' + v		(1)
+	 *
+	 * Let W be the total weight of the entities before reweight,
+	 * since V' is the new weighted average of entities:
+	 *
+	 *	V' = (WV + w'v - wv) / (W + w' - w)	(2)
+	 *
+	 * by using (1) & (2) we obtain:
+	 *
+	 *	(WV + w'v - wv) / (W + w' - w) = (V - v)*w/w' + v
+	 *	==> (WV-Wv+Wv+w'v-wv)/(W+w'-w) = (V - v)*w/w' + v
+	 *	==> (WV - Wv)/(W + w' - w) + v = (V - v)*w/w' + v
+	 *	==>	(V - v)*W/(W + w' - w) = (V - v)*w/w' (3)
+	 *
+	 * Since we are doing at !0-lag point which means V != v, we
+	 * can simplify (3):
+	 *
+	 *	==>	W / (W + w' - w) = w / w'
+	 *	==>	Ww' = Ww + ww' - ww
+	 *	==>	W * (w' - w) = w * (w' - w)
+	 *	==>	W = w	(re-weight indicates w' != w)
+	 *
+	 * So the cfs_rq contains only one entity, hence vruntime of
+	 * the entity @v should always equal to the cfs_rq's weighted
+	 * average vruntime @V, which means we will always re-weight
+	 * at 0-lag point, thus breach assumption. Proof completed.
+	 *
+	 *
+	 * COROLLARY #2: Re-weight does NOT affect weighted average
+	 * vruntime of all the entities.
+	 *
+	 * Proof: According to corollary #1, Eq. (1) should be:
+	 *
+	 *	(V - v)*w = (V' - v')*w'
+	 *	==>    v' = V' - (V - v)*w/w'		(4)
+	 *
+	 * According to the weighted average formula, we have:
+	 *
+	 *	V' = (WV - wv + w'v') / (W - w + w')
+	 *	   = (WV - wv + w'(V' - (V - v)w/w')) / (W - w + w')
+	 *	   = (WV - wv + w'V' - Vw + wv) / (W - w + w')
+	 *	   = (WV + w'V' - Vw) / (W - w + w')
+	 *
+	 *	==>  V'*(W - w + w') = WV + w'V' - Vw
+	 *	==>	V' * (W - w) = (W - w) * V	(5)
+	 *
+	 * If the entity is the only one in the cfs_rq, then reweight
+	 * always occurs at 0-lag point, so V won't change. Or else
+	 * there are other entities, hence W != w, then Eq. (5) turns
+	 * into V' = V. So V won't change in either case, proof done.
+	 *
+	 *
+	 * So according to corollary #1 & #2, the effect of re-weight
+	 * on vruntime should be:
+	 *
+	 *	v' = V' - (V - v) * w / w'		(4)
+	 *	   = V  - (V - v) * w / w'
+	 *	   = V  - vl * w / w'
+	 *	   = V  - vl'
+	 */
+	if (avruntime != se->vruntime) {
+		vlag = (s64)(avruntime - se->vruntime);
+		vlag = div_s64(vlag * old_weight, weight);
+		se->vruntime = avruntime - vlag;
+	}
+
+	/*
+	 * DEADLINE
+	 * ========
+	 *
+	 * When the weight changes, the virtual time slope changes and
+	 * we should adjust the relative virtual deadline accordingly.
+	 *
+	 *	d' = v' + (d - v)*w/w'
+	 *	   = V' - (V - v)*w/w' + (d - v)*w/w'
+	 *	   = V  - (V - v)*w/w' + (d - v)*w/w'
+	 *	   = V  + (d - V)*w/w'
+	 */
+	vslice = (s64)(se->deadline - avruntime);
+	vslice = div_s64(vslice * old_weight, weight);
+	se->deadline = avruntime + vslice;
+}
+
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
 {
-	unsigned long old_weight = se->load.weight;
+	bool curr = cfs_rq->curr == se;
 
 	if (se->on_rq) {
 		/* commit outstanding execution time */
-		if (cfs_rq->curr == se)
+		if (curr)
 			update_curr(cfs_rq);
 		else
-			avg_vruntime_sub(cfs_rq, se);
+			__dequeue_entity(cfs_rq, se);
 		update_load_sub(&cfs_rq->load, se->load.weight);
 	}
 	dequeue_load_avg(cfs_rq, se);
 
-	update_load_set(&se->load, weight);
-
 	if (!se->on_rq) {
 		/*
 		 * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i),
 		 * we need to scale se->vlag when w_i changes.
 		 */
-		se->vlag = div_s64(se->vlag * old_weight, weight);
+		se->vlag = div_s64(se->vlag * se->load.weight, weight);
 	} else {
-		s64 deadline = se->deadline - se->vruntime;
-		/*
-		 * When the weight changes, the virtual time slope changes and
-		 * we should adjust the relative virtual deadline accordingly.
-		 */
-		deadline = div_s64(deadline * old_weight, weight);
-		se->deadline = se->vruntime + deadline;
-		if (se != cfs_rq->curr)
-			min_deadline_cb_propagate(&se->run_node, NULL);
+		reweight_eevdf(cfs_rq, se, weight);
 	}
 
+	update_load_set(&se->load, weight);
+
 #ifdef CONFIG_SMP
 	do {
 		u32 divider = get_pelt_divider(&se->avg);
@@ -3712,8 +3811,17 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	enqueue_load_avg(cfs_rq, se);
 	if (se->on_rq) {
 		update_load_add(&cfs_rq->load, se->load.weight);
-		if (cfs_rq->curr != se)
-			avg_vruntime_add(cfs_rq, se);
+		if (!curr) {
+			/*
+			 * The entity's vruntime has been adjusted, so let's check
+			 * whether the rq-wide min_vruntime needs updated too. Since
+			 * the calculations above require stable min_vruntime rather
+			 * than up-to-date one, we do the update at the end of the
+			 * reweight process.
+			 */
+			__enqueue_entity(cfs_rq, se);
+			update_min_vruntime(cfs_rq);
+		}
 	}
 }
 
@@ -3857,14 +3965,11 @@ static void update_cfs_group(struct sched_entity *se)
 
 #ifndef CONFIG_SMP
 	shares = READ_ONCE(gcfs_rq->tg->shares);
-
-	if (likely(se->load.weight == shares))
-		return;
 #else
-	shares   = calc_group_shares(gcfs_rq);
+	shares = calc_group_shares(gcfs_rq);
 #endif
-
-	reweight_entity(cfs_rq_of(se), se, shares);
+	if (unlikely(se->load.weight != shares))
+		reweight_entity(cfs_rq_of(se), se, shares);
 }
 
 #else /* CONFIG_FAIR_GROUP_SCHED */
@@ -11079,12 +11184,16 @@ static int should_we_balance(struct lb_env *env)
 			continue;
 		}
 
-		/* Are we the first idle CPU? */
+		/*
+		 * Are we the first idle core in a non-SMT domain or higher,
+		 * or the first idle CPU in a SMT domain?
+		 */
 		return cpu == env->dst_cpu;
 	}
 
-	if (idle_smt == env->dst_cpu)
-		return true;
+	/* Are we the first idle CPU with busy siblings? */
+	if (idle_smt != -1)
+		return idle_smt == env->dst_cpu;
 
 	/* Are we the first CPU of this group ? */
 	return group_balance_cpu(sg) == env->dst_cpu;
diff --git a/kernel/sys.c b/kernel/sys.c
index 420d9cb9cc8e20..e219fcfa112d86 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2394,6 +2394,10 @@ static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3,
 	if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN))
 		return -EINVAL;
 
+	/* PARISC cannot allow mdwe as it needs writable stacks */
+	if (IS_ENABLED(CONFIG_PARISC))
+		return -EINVAL;
+
 	current_bits = get_current_mdwe();
 	if (current_bits && current_bits != bits)
 		return -EPERM; /* Cannot unset the flags */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index e1a6e3c675c0e8..9a846439b36a0f 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -201,6 +201,20 @@ COND_SYSCALL(recvmmsg_time32);
 COND_SYSCALL_COMPAT(recvmmsg_time32);
 COND_SYSCALL_COMPAT(recvmmsg_time64);
 
+/* Posix timer syscalls may be configured out */
+COND_SYSCALL(timer_create);
+COND_SYSCALL(timer_gettime);
+COND_SYSCALL(timer_getoverrun);
+COND_SYSCALL(timer_settime);
+COND_SYSCALL(timer_delete);
+COND_SYSCALL(clock_adjtime);
+COND_SYSCALL(getitimer);
+COND_SYSCALL(setitimer);
+COND_SYSCALL(alarm);
+COND_SYSCALL_COMPAT(timer_create);
+COND_SYSCALL_COMPAT(getitimer);
+COND_SYSCALL_COMPAT(setitimer);
+
 /*
  * Architecture specific syscalls: see further below
  */
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 238262e4aba7e2..760793998cdd70 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -2219,29 +2219,22 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 	}
 }
 
-int hrtimers_dead_cpu(unsigned int scpu)
+int hrtimers_cpu_dying(unsigned int dying_cpu)
 {
 	struct hrtimer_cpu_base *old_base, *new_base;
-	int i;
+	int i, ncpu = cpumask_first(cpu_active_mask);
 
-	BUG_ON(cpu_online(scpu));
-	tick_cancel_sched_timer(scpu);
+	tick_cancel_sched_timer(dying_cpu);
+
+	old_base = this_cpu_ptr(&hrtimer_bases);
+	new_base = &per_cpu(hrtimer_bases, ncpu);
 
-	/*
-	 * this BH disable ensures that raise_softirq_irqoff() does
-	 * not wakeup ksoftirqd (and acquire the pi-lock) while
-	 * holding the cpu_base lock
-	 */
-	local_bh_disable();
-	local_irq_disable();
-	old_base = &per_cpu(hrtimer_bases, scpu);
-	new_base = this_cpu_ptr(&hrtimer_bases);
 	/*
 	 * The caller is globally serialized and nobody else
 	 * takes two locks at once, deadlock is not possible.
 	 */
-	raw_spin_lock(&new_base->lock);
-	raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
+	raw_spin_lock(&old_base->lock);
+	raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING);
 
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
 		migrate_hrtimer_list(&old_base->clock_base[i],
@@ -2252,15 +2245,13 @@ int hrtimers_dead_cpu(unsigned int scpu)
 	 * The migration might have changed the first expiring softirq
 	 * timer on this CPU. Update it.
 	 */
-	hrtimer_update_softirq_timer(new_base, false);
+	__hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT);
+	/* Tell the other CPU to retrigger the next event */
+	smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
 
-	raw_spin_unlock(&old_base->lock);
 	raw_spin_unlock(&new_base->lock);
+	raw_spin_unlock(&old_base->lock);
 
-	/* Check, if we got expired work to do */
-	__hrtimer_peek_ahead_timers();
-	local_irq_enable();
-	local_bh_enable();
 	return 0;
 }
 
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 828aeecbd1e8a9..9b6fcb8d85e78d 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -17,40 +17,6 @@
 #include <linux/time_namespace.h>
 #include <linux/compat.h>
 
-#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
-/* Architectures may override SYS_NI and COMPAT_SYS_NI */
-#include <asm/syscall_wrapper.h>
-#endif
-
-asmlinkage long sys_ni_posix_timers(void)
-{
-	pr_err_once("process %d (%s) attempted a POSIX timer syscall "
-		    "while CONFIG_POSIX_TIMERS is not set\n",
-		    current->pid, current->comm);
-	return -ENOSYS;
-}
-
-#ifndef SYS_NI
-#define SYS_NI(name)  SYSCALL_ALIAS(sys_##name, sys_ni_posix_timers)
-#endif
-
-#ifndef COMPAT_SYS_NI
-#define COMPAT_SYS_NI(name)  SYSCALL_ALIAS(compat_sys_##name, sys_ni_posix_timers)
-#endif
-
-SYS_NI(timer_create);
-SYS_NI(timer_gettime);
-SYS_NI(timer_getoverrun);
-SYS_NI(timer_settime);
-SYS_NI(timer_delete);
-SYS_NI(clock_adjtime);
-SYS_NI(getitimer);
-SYS_NI(setitimer);
-SYS_NI(clock_adjtime32);
-#ifdef __ARCH_WANT_SYS_ALARM
-SYS_NI(alarm);
-#endif
-
 /*
  * We preserve minimal support for CLOCK_REALTIME and CLOCK_MONOTONIC
  * as it is easy to remain compatible with little code. CLOCK_BOOTTIME
@@ -158,18 +124,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 				 which_clock);
 }
 
-#ifdef CONFIG_COMPAT
-COMPAT_SYS_NI(timer_create);
-#endif
-
-#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA)
-COMPAT_SYS_NI(getitimer);
-COMPAT_SYS_NI(setitimer);
-#endif
-
 #ifdef CONFIG_COMPAT_32BIT_TIME
-SYS_NI(timer_settime32);
-SYS_NI(timer_gettime32);
 
 SYSCALL_DEFINE2(clock_settime32, const clockid_t, which_clock,
 		struct old_timespec32 __user *, tp)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index df697c74d5197a..84e8a0f6e4e0b0 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1252,9 +1252,7 @@ static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = {
 };
 
 #ifdef CONFIG_KEYS
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "kfuncs which will be used in BPF programs");
+__bpf_kfunc_start_defs();
 
 /**
  * bpf_lookup_user_key - lookup a key by its serial
@@ -1404,7 +1402,7 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
 }
 #endif /* CONFIG_SYSTEM_DATA_VERIFICATION */
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(key_sig_kfunc_set)
 BTF_ID_FLAGS(func, bpf_lookup_user_key, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE)
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index 6fd7d4ecbbc67b..fa03094e9e6981 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -48,7 +48,7 @@ static void rethook_free_rcu(struct rcu_head *head)
  */
 void rethook_stop(struct rethook *rh)
 {
-	WRITE_ONCE(rh->handler, NULL);
+	rcu_assign_pointer(rh->handler, NULL);
 }
 
 /**
@@ -63,7 +63,7 @@ void rethook_stop(struct rethook *rh)
  */
 void rethook_free(struct rethook *rh)
 {
-	WRITE_ONCE(rh->handler, NULL);
+	rethook_stop(rh);
 
 	call_rcu(&rh->rcu, rethook_free_rcu);
 }
@@ -82,6 +82,12 @@ static int rethook_fini_pool(struct objpool_head *head, void *context)
 	return 0;
 }
 
+static inline rethook_handler_t rethook_get_handler(struct rethook *rh)
+{
+	return (rethook_handler_t)rcu_dereference_check(rh->handler,
+							rcu_read_lock_any_held());
+}
+
 /**
  * rethook_alloc() - Allocate struct rethook.
  * @data: a data to pass the @handler when hooking the return.
@@ -107,7 +113,7 @@ struct rethook *rethook_alloc(void *data, rethook_handler_t handler,
 		return ERR_PTR(-ENOMEM);
 
 	rh->data = data;
-	rh->handler = handler;
+	rcu_assign_pointer(rh->handler, handler);
 
 	/* initialize the objpool for rethook nodes */
 	if (objpool_init(&rh->pool, num, size, GFP_KERNEL, rh,
@@ -135,9 +141,10 @@ static void free_rethook_node_rcu(struct rcu_head *head)
  */
 void rethook_recycle(struct rethook_node *node)
 {
-	lockdep_assert_preemption_disabled();
+	rethook_handler_t handler;
 
-	if (likely(READ_ONCE(node->rethook->handler)))
+	handler = rethook_get_handler(node->rethook);
+	if (likely(handler))
 		objpool_push(node, &node->rethook->pool);
 	else
 		call_rcu(&node->rcu, free_rethook_node_rcu);
@@ -153,9 +160,7 @@ NOKPROBE_SYMBOL(rethook_recycle);
  */
 struct rethook_node *rethook_try_get(struct rethook *rh)
 {
-	rethook_handler_t handler = READ_ONCE(rh->handler);
-
-	lockdep_assert_preemption_disabled();
+	rethook_handler_t handler = rethook_get_handler(rh);
 
 	/* Check whether @rh is going to be freed. */
 	if (unlikely(!handler))
@@ -300,7 +305,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs,
 		rhn = container_of(first, struct rethook_node, llist);
 		if (WARN_ON_ONCE(rhn->frame != frame))
 			break;
-		handler = READ_ONCE(rhn->rethook->handler);
+		handler = rethook_get_handler(rhn->rethook);
 		if (handler)
 			handler(rhn, rhn->rethook->data,
 				correct_ret_addr, regs);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 43cc47d7faafc7..83eab547f1d1f2 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -644,8 +644,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
 
 	*cnt = rb_time_cnt(top);
 
-	/* If top and bottom counts don't match, this interrupted a write */
-	if (*cnt != rb_time_cnt(bottom))
+	/* If top, msb or bottom counts don't match, this interrupted a write */
+	if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom))
 		return false;
 
 	/* The shift to msb will lose its cnt bits */
@@ -700,44 +700,6 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
 	return local_try_cmpxchg(l, &expect, set);
 }
 
-static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
-{
-	unsigned long cnt, top, bottom, msb;
-	unsigned long cnt2, top2, bottom2, msb2;
-	u64 val;
-
-	/* The cmpxchg always fails if it interrupted an update */
-	 if (!__rb_time_read(t, &val, &cnt2))
-		 return false;
-
-	 if (val != expect)
-		 return false;
-
-	 cnt = local_read(&t->cnt);
-	 if ((cnt & 3) != cnt2)
-		 return false;
-
-	 cnt2 = cnt + 1;
-
-	 rb_time_split(val, &top, &bottom, &msb);
-	 top = rb_time_val_cnt(top, cnt);
-	 bottom = rb_time_val_cnt(bottom, cnt);
-
-	 rb_time_split(set, &top2, &bottom2, &msb2);
-	 top2 = rb_time_val_cnt(top2, cnt2);
-	 bottom2 = rb_time_val_cnt(bottom2, cnt2);
-
-	if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2))
-		return false;
-	if (!rb_time_read_cmpxchg(&t->msb, msb, msb2))
-		return false;
-	if (!rb_time_read_cmpxchg(&t->top, top, top2))
-		return false;
-	if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2))
-		return false;
-	return true;
-}
-
 #else /* 64 bits */
 
 /* local64_t always succeeds */
@@ -751,11 +713,6 @@ static void rb_time_set(rb_time_t *t, u64 val)
 {
 	local64_set(&t->time, val);
 }
-
-static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
-{
-	return local64_try_cmpxchg(&t->time, &expect, set);
-}
 #endif
 
 /*
@@ -1787,6 +1744,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 		free_buffer_page(bpage);
 	}
 
+	free_page((unsigned long)cpu_buffer->free_page);
+
 	kfree(cpu_buffer);
 }
 
@@ -2407,7 +2366,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter)
 	 */
 	barrier();
 
-	if ((iter->head + length) > commit || length > BUF_MAX_DATA_SIZE)
+	if ((iter->head + length) > commit || length > BUF_PAGE_SIZE)
 		/* Writer corrupted the read? */
 		goto reset;
 
@@ -2981,25 +2940,6 @@ static unsigned rb_calculate_event_length(unsigned length)
 	return length;
 }
 
-static u64 rb_time_delta(struct ring_buffer_event *event)
-{
-	switch (event->type_len) {
-	case RINGBUF_TYPE_PADDING:
-		return 0;
-
-	case RINGBUF_TYPE_TIME_EXTEND:
-		return rb_event_time_stamp(event);
-
-	case RINGBUF_TYPE_TIME_STAMP:
-		return 0;
-
-	case RINGBUF_TYPE_DATA:
-		return event->time_delta;
-	default:
-		return 0;
-	}
-}
-
 static inline bool
 rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 		  struct ring_buffer_event *event)
@@ -3007,8 +2947,6 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	unsigned long new_index, old_index;
 	struct buffer_page *bpage;
 	unsigned long addr;
-	u64 write_stamp;
-	u64 delta;
 
 	new_index = rb_event_index(event);
 	old_index = new_index + rb_event_ts_length(event);
@@ -3017,41 +2955,34 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 
 	bpage = READ_ONCE(cpu_buffer->tail_page);
 
-	delta = rb_time_delta(event);
-
-	if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp))
-		return false;
-
-	/* Make sure the write stamp is read before testing the location */
-	barrier();
-
+	/*
+	 * Make sure the tail_page is still the same and
+	 * the next write location is the end of this event
+	 */
 	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
 		unsigned long write_mask =
 			local_read(&bpage->write) & ~RB_WRITE_MASK;
 		unsigned long event_length = rb_event_length(event);
 
-		/* Something came in, can't discard */
-		if (!rb_time_cmpxchg(&cpu_buffer->write_stamp,
-				       write_stamp, write_stamp - delta))
-			return false;
-
 		/*
-		 * It's possible that the event time delta is zero
-		 * (has the same time stamp as the previous event)
-		 * in which case write_stamp and before_stamp could
-		 * be the same. In such a case, force before_stamp
-		 * to be different than write_stamp. It doesn't
-		 * matter what it is, as long as its different.
+		 * For the before_stamp to be different than the write_stamp
+		 * to make sure that the next event adds an absolute
+		 * value and does not rely on the saved write stamp, which
+		 * is now going to be bogus.
+		 *
+		 * By setting the before_stamp to zero, the next event
+		 * is not going to use the write_stamp and will instead
+		 * create an absolute timestamp. This means there's no
+		 * reason to update the wirte_stamp!
 		 */
-		if (!delta)
-			rb_time_set(&cpu_buffer->before_stamp, 0);
+		rb_time_set(&cpu_buffer->before_stamp, 0);
 
 		/*
 		 * If an event were to come in now, it would see that the
 		 * write_stamp and the before_stamp are different, and assume
 		 * that this event just added itself before updating
 		 * the write stamp. The interrupting event will fix the
-		 * write stamp for us, and use the before stamp as its delta.
+		 * write stamp for us, and use an absolute timestamp.
 		 */
 
 		/*
@@ -3488,7 +3419,7 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
 		return;
 
 	/*
-	 * If this interrupted another event, 
+	 * If this interrupted another event,
 	 */
 	if (atomic_inc_return(this_cpu_ptr(&checking)) != 1)
 		goto out;
@@ -3582,7 +3513,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		 * absolute timestamp.
 		 * Don't bother if this is the start of a new page (w == 0).
 		 */
-		if (unlikely(!a_ok || !b_ok || (info->before != info->after && w))) {
+		if (!w) {
+			/* Use the sub-buffer timestamp */
+			info->delta = 0;
+		} else if (unlikely(!a_ok || !b_ok || info->before != info->after)) {
 			info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND;
 			info->length += RB_LEN_TIME_EXTEND;
 		} else {
@@ -3605,26 +3539,19 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 
 	/* See if we shot pass the end of this buffer page */
 	if (unlikely(write > BUF_PAGE_SIZE)) {
-		/* before and after may now different, fix it up*/
-		b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
-		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
-		if (a_ok && b_ok && info->before != info->after)
-			(void)rb_time_cmpxchg(&cpu_buffer->before_stamp,
-					      info->before, info->after);
-		if (a_ok && b_ok)
-			check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
+		check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
 		return rb_move_tail(cpu_buffer, tail, info);
 	}
 
 	if (likely(tail == w)) {
-		u64 save_before;
-		bool s_ok;
-
 		/* Nothing interrupted us between A and C */
  /*D*/		rb_time_set(&cpu_buffer->write_stamp, info->ts);
-		barrier();
- /*E*/		s_ok = rb_time_read(&cpu_buffer->before_stamp, &save_before);
-		RB_WARN_ON(cpu_buffer, !s_ok);
+		/*
+		 * If something came in between C and D, the write stamp
+		 * may now not be in sync. But that's fine as the before_stamp
+		 * will be different and then next event will just be forced
+		 * to use an absolute timestamp.
+		 */
 		if (likely(!(info->add_timestamp &
 			     (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE))))
 			/* This did not interrupt any time update */
@@ -3632,41 +3559,40 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		else
 			/* Just use full timestamp for interrupting event */
 			info->delta = info->ts;
-		barrier();
 		check_buffer(cpu_buffer, info, tail);
-		if (unlikely(info->ts != save_before)) {
-			/* SLOW PATH - Interrupted between C and E */
-
-			a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
-			RB_WARN_ON(cpu_buffer, !a_ok);
-
-			/* Write stamp must only go forward */
-			if (save_before > info->after) {
-				/*
-				 * We do not care about the result, only that
-				 * it gets updated atomically.
-				 */
-				(void)rb_time_cmpxchg(&cpu_buffer->write_stamp,
-						      info->after, save_before);
-			}
-		}
 	} else {
 		u64 ts;
 		/* SLOW PATH - Interrupted between A and C */
-		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
-		/* Was interrupted before here, write_stamp must be valid */
+
+		/* Save the old before_stamp */
+		a_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
 		RB_WARN_ON(cpu_buffer, !a_ok);
+
+		/*
+		 * Read a new timestamp and update the before_stamp to make
+		 * the next event after this one force using an absolute
+		 * timestamp. This is in case an interrupt were to come in
+		 * between E and F.
+		 */
 		ts = rb_time_stamp(cpu_buffer->buffer);
+		rb_time_set(&cpu_buffer->before_stamp, ts);
+
 		barrier();
- /*E*/		if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
-		    info->after < ts &&
-		    rb_time_cmpxchg(&cpu_buffer->write_stamp,
-				    info->after, ts)) {
-			/* Nothing came after this event between C and E */
+ /*E*/		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+		/* Was interrupted before here, write_stamp must be valid */
+		RB_WARN_ON(cpu_buffer, !a_ok);
+		barrier();
+ /*F*/		if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
+		    info->after == info->before && info->after < ts) {
+			/*
+			 * Nothing came after this event between C and F, it is
+			 * safe to use info->after for the delta as it
+			 * matched info->before and is still valid.
+			 */
 			info->delta = ts - info->after;
 		} else {
 			/*
-			 * Interrupted between C and E:
+			 * Interrupted between C and F:
 			 * Lost the previous events time stamp. Just set the
 			 * delta to zero, and this will be the same time as
 			 * the event this event interrupted. And the events that
@@ -3717,6 +3643,12 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	int nr_loops = 0;
 	int add_ts_default;
 
+	/* ring buffer does cmpxchg, make sure it is safe in NMI context */
+	if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) &&
+	    (unlikely(in_nmi()))) {
+		return NULL;
+	}
+
 	rb_start_commit(cpu_buffer);
 	/* The commit page can not change after this */
 
@@ -3740,6 +3672,8 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) {
 		add_ts_default = RB_ADD_STAMP_ABSOLUTE;
 		info.length += RB_LEN_TIME_EXTEND;
+		if (info.length > BUF_MAX_DATA_SIZE)
+			goto out_fail;
 	} else {
 		add_ts_default = RB_ADD_STAMP_NONE;
 	}
@@ -5121,7 +5055,8 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags)
 	if (!iter)
 		return NULL;
 
-	iter->event = kmalloc(BUF_MAX_DATA_SIZE, flags);
+	/* Holds the entire event: data and meta data */
+	iter->event = kmalloc(BUF_PAGE_SIZE, flags);
 	if (!iter->event) {
 		kfree(iter);
 		return NULL;
diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c
index 8dfe85499d4a2b..354c2117be43f7 100644
--- a/kernel/trace/synth_event_gen_test.c
+++ b/kernel/trace/synth_event_gen_test.c
@@ -477,6 +477,17 @@ static int __init synth_event_gen_test_init(void)
 
 	ret = test_trace_synth_event();
 	WARN_ON(ret);
+
+	/* Disable when done */
+	trace_array_set_clr_event(gen_synth_test->tr,
+				  "synthetic",
+				  "gen_synth_test", false);
+	trace_array_set_clr_event(empty_synth_test->tr,
+				  "synthetic",
+				  "empty_synth_test", false);
+	trace_array_set_clr_event(create_synth_test->tr,
+				  "synthetic",
+				  "create_synth_test", false);
  out:
 	return ret;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9aebf904ff9738..199df497db07eb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2360,13 +2360,7 @@ int is_tracing_stopped(void)
 	return global_trace.stop_count;
 }
 
-/**
- * tracing_start - quick start of the tracer
- *
- * If tracing is enabled but was stopped by tracing_stop,
- * this will start the tracer back up.
- */
-void tracing_start(void)
+static void tracing_start_tr(struct trace_array *tr)
 {
 	struct trace_buffer *buffer;
 	unsigned long flags;
@@ -2374,119 +2368,83 @@ void tracing_start(void)
 	if (tracing_disabled)
 		return;
 
-	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
-	if (--global_trace.stop_count) {
-		if (global_trace.stop_count < 0) {
+	raw_spin_lock_irqsave(&tr->start_lock, flags);
+	if (--tr->stop_count) {
+		if (WARN_ON_ONCE(tr->stop_count < 0)) {
 			/* Someone screwed up their debugging */
-			WARN_ON_ONCE(1);
-			global_trace.stop_count = 0;
+			tr->stop_count = 0;
 		}
 		goto out;
 	}
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&global_trace.max_lock);
+	arch_spin_lock(&tr->max_lock);
 
-	buffer = global_trace.array_buffer.buffer;
+	buffer = tr->array_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_enable(buffer);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	buffer = global_trace.max_buffer.buffer;
+	buffer = tr->max_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_enable(buffer);
 #endif
 
-	arch_spin_unlock(&global_trace.max_lock);
-
- out:
-	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
-}
-
-static void tracing_start_tr(struct trace_array *tr)
-{
-	struct trace_buffer *buffer;
-	unsigned long flags;
-
-	if (tracing_disabled)
-		return;
-
-	/* If global, we need to also start the max tracer */
-	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
-		return tracing_start();
-
-	raw_spin_lock_irqsave(&tr->start_lock, flags);
-
-	if (--tr->stop_count) {
-		if (tr->stop_count < 0) {
-			/* Someone screwed up their debugging */
-			WARN_ON_ONCE(1);
-			tr->stop_count = 0;
-		}
-		goto out;
-	}
-
-	buffer = tr->array_buffer.buffer;
-	if (buffer)
-		ring_buffer_record_enable(buffer);
+	arch_spin_unlock(&tr->max_lock);
 
  out:
 	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
 }
 
 /**
- * tracing_stop - quick stop of the tracer
+ * tracing_start - quick start of the tracer
  *
- * Light weight way to stop tracing. Use in conjunction with
- * tracing_start.
+ * If tracing is enabled but was stopped by tracing_stop,
+ * this will start the tracer back up.
  */
-void tracing_stop(void)
+void tracing_start(void)
+
+{
+	return tracing_start_tr(&global_trace);
+}
+
+static void tracing_stop_tr(struct trace_array *tr)
 {
 	struct trace_buffer *buffer;
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
-	if (global_trace.stop_count++)
+	raw_spin_lock_irqsave(&tr->start_lock, flags);
+	if (tr->stop_count++)
 		goto out;
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&global_trace.max_lock);
+	arch_spin_lock(&tr->max_lock);
 
-	buffer = global_trace.array_buffer.buffer;
+	buffer = tr->array_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_disable(buffer);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	buffer = global_trace.max_buffer.buffer;
+	buffer = tr->max_buffer.buffer;
 	if (buffer)
 		ring_buffer_record_disable(buffer);
 #endif
 
-	arch_spin_unlock(&global_trace.max_lock);
+	arch_spin_unlock(&tr->max_lock);
 
  out:
-	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
+	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
 }
 
-static void tracing_stop_tr(struct trace_array *tr)
+/**
+ * tracing_stop - quick stop of the tracer
+ *
+ * Light weight way to stop tracing. Use in conjunction with
+ * tracing_start.
+ */
+void tracing_stop(void)
 {
-	struct trace_buffer *buffer;
-	unsigned long flags;
-
-	/* If global, we need to also stop the max tracer */
-	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
-		return tracing_stop();
-
-	raw_spin_lock_irqsave(&tr->start_lock, flags);
-	if (tr->stop_count++)
-		goto out;
-
-	buffer = tr->array_buffer.buffer;
-	if (buffer)
-		ring_buffer_record_disable(buffer);
-
- out:
-	raw_spin_unlock_irqrestore(&tr->start_lock, flags);
+	return tracing_stop_tr(&global_trace);
 }
 
 static int trace_save_cmdline(struct task_struct *tsk)
@@ -2770,8 +2728,11 @@ void trace_buffered_event_enable(void)
 	for_each_tracing_cpu(cpu) {
 		page = alloc_pages_node(cpu_to_node(cpu),
 					GFP_KERNEL | __GFP_NORETRY, 0);
-		if (!page)
-			goto failed;
+		/* This is just an optimization and can handle failures */
+		if (!page) {
+			pr_err("Failed to allocate event buffer\n");
+			break;
+		}
 
 		event = page_address(page);
 		memset(event, 0, sizeof(*event));
@@ -2785,10 +2746,6 @@ void trace_buffered_event_enable(void)
 			WARN_ON_ONCE(1);
 		preempt_enable();
 	}
-
-	return;
- failed:
-	trace_buffered_event_disable();
 }
 
 static void enable_trace_buffered_event(void *data)
@@ -2823,11 +2780,9 @@ void trace_buffered_event_disable(void)
 	if (--trace_buffered_event_ref)
 		return;
 
-	preempt_disable();
 	/* For each CPU, set the buffer as used. */
-	smp_call_function_many(tracing_buffer_mask,
-			       disable_trace_buffered_event, NULL, 1);
-	preempt_enable();
+	on_each_cpu_mask(tracing_buffer_mask, disable_trace_buffered_event,
+			 NULL, true);
 
 	/* Wait for all current users to finish */
 	synchronize_rcu();
@@ -2836,17 +2791,19 @@ void trace_buffered_event_disable(void)
 		free_page((unsigned long)per_cpu(trace_buffered_event, cpu));
 		per_cpu(trace_buffered_event, cpu) = NULL;
 	}
+
 	/*
-	 * Make sure trace_buffered_event is NULL before clearing
-	 * trace_buffered_event_cnt.
+	 * Wait for all CPUs that potentially started checking if they can use
+	 * their event buffer only after the previous synchronize_rcu() call and
+	 * they still read a valid pointer from trace_buffered_event. It must be
+	 * ensured they don't see cleared trace_buffered_event_cnt else they
+	 * could wrongly decide to use the pointed-to buffer which is now freed.
 	 */
-	smp_wmb();
+	synchronize_rcu();
 
-	preempt_disable();
-	/* Do the work on each cpu */
-	smp_call_function_many(tracing_buffer_mask,
-			       enable_trace_buffered_event, NULL, 1);
-	preempt_enable();
+	/* For each CPU, relinquish the buffer */
+	on_each_cpu_mask(tracing_buffer_mask, enable_trace_buffered_event, NULL,
+			 true);
 }
 
 static struct trace_buffer *temp_buffer;
@@ -4765,7 +4722,11 @@ static int s_show(struct seq_file *m, void *v)
 		iter->leftover = ret;
 
 	} else {
-		print_trace_line(iter);
+		ret = print_trace_line(iter);
+		if (ret == TRACE_TYPE_PARTIAL_LINE) {
+			iter->seq.full = 0;
+			trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n");
+		}
 		ret = trace_print_seq(m, &iter->seq);
 		/*
 		 * If we overflow the seq_file buffer, then it will
@@ -5007,6 +4968,12 @@ int tracing_release_file_tr(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+int tracing_single_release_file_tr(struct inode *inode, struct file *filp)
+{
+	tracing_release_file_tr(inode, filp);
+	return single_release(inode, filp);
+}
+
 static int tracing_mark_open(struct inode *inode, struct file *filp)
 {
 	stream_open(inode, filp);
@@ -6387,13 +6354,15 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
 	if (!tr->array_buffer.buffer)
 		return 0;
 
+	/* Do not allow tracing while resizing ring buffer */
+	tracing_stop_tr(tr);
+
 	ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu);
 	if (ret < 0)
-		return ret;
+		goto out_start;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) ||
-	    !tr->current_trace->use_max_tr)
+	if (!tr->allocated_snapshot)
 		goto out;
 
 	ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu);
@@ -6418,7 +6387,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
 			WARN_ON(1);
 			tracing_disabled = 1;
 		}
-		return ret;
+		goto out_start;
 	}
 
 	update_buffer_entries(&tr->max_buffer, cpu);
@@ -6427,7 +6396,8 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr,
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
 	update_buffer_entries(&tr->array_buffer, cpu);
-
+ out_start:
+	tracing_start_tr(tr);
 	return ret;
 }
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index b7f4ea25a19431..0489e72c8169c1 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -617,6 +617,7 @@ int tracing_open_generic(struct inode *inode, struct file *filp);
 int tracing_open_generic_tr(struct inode *inode, struct file *filp);
 int tracing_open_file_tr(struct inode *inode, struct file *filp);
 int tracing_release_file_tr(struct inode *inode, struct file *filp);
+int tracing_single_release_file_tr(struct inode *inode, struct file *filp);
 bool tracing_is_disabled(void);
 bool tracer_tracing_is_on(struct trace_array *tr);
 void tracer_tracing_on(struct trace_array *tr);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 1abc07fba1b91d..5ecf3c8bde205f 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5623,10 +5623,12 @@ static int event_hist_open(struct inode *inode, struct file *file)
 {
 	int ret;
 
-	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	ret = tracing_open_file_tr(inode, file);
 	if (ret)
 		return ret;
 
+	/* Clear private_data to avoid warning in single_open() */
+	file->private_data = NULL;
 	return single_open(file, hist_show, file);
 }
 
@@ -5634,7 +5636,7 @@ const struct file_operations event_hist_fops = {
 	.open = event_hist_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = single_release,
+	.release = tracing_single_release_file_tr,
 };
 
 #ifdef CONFIG_HIST_TRIGGERS_DEBUG
@@ -5900,10 +5902,12 @@ static int event_hist_debug_open(struct inode *inode, struct file *file)
 {
 	int ret;
 
-	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	ret = tracing_open_file_tr(inode, file);
 	if (ret)
 		return ret;
 
+	/* Clear private_data to avoid warning in single_open() */
+	file->private_data = NULL;
 	return single_open(file, hist_debug_show, file);
 }
 
@@ -5911,7 +5915,7 @@ const struct file_operations event_hist_debug_fops = {
 	.open = event_hist_debug_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = single_release,
+	.release = tracing_single_release_file_tr,
 };
 #endif
 
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 846e02c0fb59a2..e7af286af4f1ad 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1137,7 +1137,7 @@ EXPORT_SYMBOL_GPL(synth_event_add_fields);
  * @cmd: A pointer to the dynevent_cmd struct representing the new event
  * @name: The name of the synthetic event
  * @mod: The module creating the event, NULL if not created from a module
- * @args: Variable number of arg (pairs), one pair for each field
+ * @...: Variable number of arg (pairs), one pair for each field
  *
  * NOTE: Users normally won't want to call this function directly, but
  * rather use the synth_event_gen_cmd_start() wrapper, which
@@ -1695,7 +1695,7 @@ __synth_event_trace_end(struct synth_event_trace_state *trace_state)
  * synth_event_trace - Trace a synthetic event
  * @file: The trace_event_file representing the synthetic event
  * @n_vals: The number of values in vals
- * @args: Variable number of args containing the event values
+ * @...: Variable number of args containing the event values
  *
  * Trace a synthetic event using the values passed in the variable
  * argument list.
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 8bfe23af9c739a..7d2ddbcfa377cf 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -927,11 +927,12 @@ static int parse_symbol_and_return(int argc, const char *argv[],
 	for (i = 2; i < argc; i++) {
 		tmp = strstr(argv[i], "$retval");
 		if (tmp && !isalnum(tmp[7]) && tmp[7] != '_') {
+			if (is_tracepoint) {
+				trace_probe_log_set_index(i);
+				trace_probe_log_err(tmp - argv[i], RETVAL_ON_PROBE);
+				return -EINVAL;
+			}
 			*is_return = true;
-			/*
-			 * NOTE: Don't check is_tracepoint here, because it will
-			 * be checked when the argument is parsed.
-			 */
 			break;
 		}
 	}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index a3442db356709c..52f8b537dd0a08 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1020,9 +1020,9 @@ EXPORT_SYMBOL_GPL(kprobe_event_cmd_init);
 /**
  * __kprobe_event_gen_cmd_start - Generate a kprobe event command from arg list
  * @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @kretprobe: Is this a return probe?
  * @name: The name of the kprobe event
  * @loc: The location of the kprobe event
- * @kretprobe: Is this a return probe?
  * @...: Variable number of arg (pairs), one pair for each field
  *
  * NOTE: Users normally won't want to call this function directly, but
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index d8b302d0108302..3e7fa44dc2b248 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1587,11 +1587,12 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter,
 {
 	struct print_entry *field;
 	struct trace_seq *s = &iter->seq;
+	int max = iter->ent_size - offsetof(struct print_entry, buf);
 
 	trace_assign_type(field, iter->ent);
 
 	seq_print_ip_sym(s, field->ip, flags);
-	trace_seq_printf(s, ": %s", field->buf);
+	trace_seq_printf(s, ": %.*s", max, field->buf);
 
 	return trace_handle_return(s);
 }
@@ -1600,10 +1601,11 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags,
 					 struct trace_event *event)
 {
 	struct print_entry *field;
+	int max = iter->ent_size - offsetof(struct print_entry, buf);
 
 	trace_assign_type(field, iter->ent);
 
-	trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf);
+	trace_seq_printf(&iter->seq, "# %lx %.*s", field->ip, max, field->buf);
 
 	return trace_handle_return(&iter->seq);
 }
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index cc7d53d9dc0191..4405f81248fbc7 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1739,21 +1739,6 @@ config DEBUG_MAPLE_TREE
 
 endmenu
 
-config DEBUG_CREDENTIALS
-	bool "Debug credential management"
-	depends on DEBUG_KERNEL
-	help
-	  Enable this to turn on some debug checking for credential
-	  management.  The additional code keeps track of the number of
-	  pointers from task_structs to any given cred struct, and checks to
-	  see that this number never exceeds the usage count of the cred
-	  struct.
-
-	  Furthermore, if SELinux is enabled, this also checks that the
-	  security pointer in the cred struct is never seen to be invalid.
-
-	  If unsure, say N.
-
 source "kernel/rcu/Kconfig.debug"
 
 config DEBUG_WQ_FORCE_RR_CPU
diff --git a/lib/closure.c b/lib/closure.c
index f86c9eeafb35ad..c16540552d61bc 100644
--- a/lib/closure.c
+++ b/lib/closure.c
@@ -36,7 +36,7 @@ static inline void closure_put_after_sub(struct closure *cl, int flags)
 			closure_debug_destroy(cl);
 
 			if (destructor)
-				destructor(cl);
+				destructor(&cl->work);
 
 			if (parent)
 				closure_put(parent);
@@ -108,8 +108,9 @@ struct closure_syncer {
 	int			done;
 };
 
-static void closure_sync_fn(struct closure *cl)
+static CLOSURE_CALLBACK(closure_sync_fn)
 {
+	struct closure *cl = container_of(ws, struct closure, work);
 	struct closure_syncer *s = cl->s;
 	struct task_struct *p;
 
diff --git a/lib/errname.c b/lib/errname.c
index dd1b998552cd94..4f9112b38f3ad6 100644
--- a/lib/errname.c
+++ b/lib/errname.c
@@ -111,9 +111,6 @@ static const char *names_0[] = {
 	E(ENOSPC),
 	E(ENOSR),
 	E(ENOSTR),
-#ifdef ENOSYM
-	E(ENOSYM),
-#endif
 	E(ENOSYS),
 	E(ENOTBLK),
 	E(ENOTCONN),
@@ -144,9 +141,6 @@ static const char *names_0[] = {
 #endif
 	E(EREMOTE),
 	E(EREMOTEIO),
-#ifdef EREMOTERELEASE
-	E(EREMOTERELEASE),
-#endif
 	E(ERESTART),
 	E(ERFKILL),
 	E(EROFS),
diff --git a/lib/fw_table.c b/lib/fw_table.c
index b51f30a28e47b9..294df54e33b6fe 100644
--- a/lib/fw_table.c
+++ b/lib/fw_table.c
@@ -7,7 +7,7 @@
  *  Copyright (C) 2023 Intel Corp.
  */
 #include <linux/errno.h>
-#include <linux/fw_table.h>
+#include <linux/acpi.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
diff --git a/lib/group_cpus.c b/lib/group_cpus.c
index aa3f6815bb1240..ee272c4cefcc13 100644
--- a/lib/group_cpus.c
+++ b/lib/group_cpus.c
@@ -366,13 +366,25 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 	if (!masks)
 		goto fail_node_to_cpumask;
 
-	/* Stabilize the cpumasks */
-	cpus_read_lock();
 	build_node_to_cpumask(node_to_cpumask);
 
+	/*
+	 * Make a local cache of 'cpu_present_mask', so the two stages
+	 * spread can observe consistent 'cpu_present_mask' without holding
+	 * cpu hotplug lock, then we can reduce deadlock risk with cpu
+	 * hotplug code.
+	 *
+	 * Here CPU hotplug may happen when reading `cpu_present_mask`, and
+	 * we can live with the case because it only affects that hotplug
+	 * CPU is handled in the 1st or 2nd stage, and either way is correct
+	 * from API user viewpoint since 2-stage spread is sort of
+	 * optimization.
+	 */
+	cpumask_copy(npresmsk, data_race(cpu_present_mask));
+
 	/* grouping present CPUs first */
 	ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask,
-				  cpu_present_mask, nmsk, masks);
+				  npresmsk, nmsk, masks);
 	if (ret < 0)
 		goto fail_build_affinity;
 	nr_present = ret;
@@ -387,15 +399,13 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 		curgrp = 0;
 	else
 		curgrp = nr_present;
-	cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask);
+	cpumask_andnot(npresmsk, cpu_possible_mask, npresmsk);
 	ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask,
 				  npresmsk, nmsk, masks);
 	if (ret >= 0)
 		nr_others = ret;
 
  fail_build_affinity:
-	cpus_read_unlock();
-
 	if (ret >= 0)
 		WARN_ON(nr_present + nr_others < numgrps);
 
diff --git a/lib/idr.c b/lib/idr.c
index 13f2758c237735..da36054c3ca020 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -508,7 +508,7 @@ void ida_free(struct ida *ida, unsigned int id)
 			goto delete;
 		xas_store(&xas, xa_mk_value(v));
 	} else {
-		if (!test_bit(bit, bitmap->bitmap))
+		if (!bitmap || !test_bit(bit, bitmap->bitmap))
 			goto err;
 		__clear_bit(bit, bitmap->bitmap);
 		xas_set_mark(&xas, XA_FREE_MARK);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index de7d11cf4c6356..8ff6824a100539 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -409,7 +409,7 @@ size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t byte
 		void *kaddr = kmap_local_page(page);
 		size_t n = min(bytes, (size_t)PAGE_SIZE - offset);
 
-		n = iterate_and_advance(i, bytes, kaddr,
+		n = iterate_and_advance(i, n, kaddr + offset,
 					copy_to_user_iter_nofault,
 					memcpy_to_iter);
 		kunmap_local(kaddr);
diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c
index 99d2a3a528e1ed..de2113a58fa034 100644
--- a/lib/kunit/kunit-test.c
+++ b/lib/kunit/kunit-test.c
@@ -562,7 +562,7 @@ static void kunit_log_test(struct kunit *test)
 	KUNIT_EXPECT_TRUE(test, test->log->append_newlines);
 
 	full_log = string_stream_get_string(test->log);
-	kunit_add_action(test, (kunit_action_t *)kfree, full_log);
+	kunit_add_action(test, kfree_wrapper, full_log);
 	KUNIT_EXPECT_NOT_ERR_OR_NULL(test,
 				     strstr(full_log, "put this in log."));
 	KUNIT_EXPECT_NOT_ERR_OR_NULL(test,
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index f2eb71f1a66c1d..7aceb07a1af9f6 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -338,6 +338,36 @@ void kunit_init_test(struct kunit *test, const char *name, struct string_stream
 }
 EXPORT_SYMBOL_GPL(kunit_init_test);
 
+/* Only warn when a test takes more than twice the threshold */
+#define KUNIT_SPEED_WARNING_MULTIPLIER	2
+
+/* Slow tests are defined as taking more than 1s */
+#define KUNIT_SPEED_SLOW_THRESHOLD_S	1
+
+#define KUNIT_SPEED_SLOW_WARNING_THRESHOLD_S	\
+	(KUNIT_SPEED_WARNING_MULTIPLIER * KUNIT_SPEED_SLOW_THRESHOLD_S)
+
+#define s_to_timespec64(s) ns_to_timespec64((s) * NSEC_PER_SEC)
+
+static void kunit_run_case_check_speed(struct kunit *test,
+				       struct kunit_case *test_case,
+				       struct timespec64 duration)
+{
+	struct timespec64 slow_thr =
+		s_to_timespec64(KUNIT_SPEED_SLOW_WARNING_THRESHOLD_S);
+	enum kunit_speed speed = test_case->attr.speed;
+
+	if (timespec64_compare(&duration, &slow_thr) < 0)
+		return;
+
+	if (speed == KUNIT_SPEED_VERY_SLOW || speed == KUNIT_SPEED_SLOW)
+		return;
+
+	kunit_warn(test,
+		   "Test should be marked slow (runtime: %lld.%09lds)",
+		   duration.tv_sec, duration.tv_nsec);
+}
+
 /*
  * Initializes and runs test case. Does not clean up or do post validations.
  */
@@ -345,6 +375,8 @@ static void kunit_run_case_internal(struct kunit *test,
 				    struct kunit_suite *suite,
 				    struct kunit_case *test_case)
 {
+	struct timespec64 start, end;
+
 	if (suite->init) {
 		int ret;
 
@@ -356,7 +388,13 @@ static void kunit_run_case_internal(struct kunit *test,
 		}
 	}
 
+	ktime_get_ts64(&start);
+
 	test_case->run_case(test);
+
+	ktime_get_ts64(&end);
+
+	kunit_run_case_check_speed(test, test_case, timespec64_sub(end, start));
 }
 
 static void kunit_case_internal_cleanup(struct kunit *test)
@@ -670,6 +708,8 @@ int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_
 		return 0;
 	}
 
+	kunit_suite_counter = 1;
+
 	static_branch_inc(&kunit_running);
 
 	for (i = 0; i < num_suites; i++) {
@@ -696,8 +736,6 @@ void __kunit_test_suites_exit(struct kunit_suite **suites, int num_suites)
 
 	for (i = 0; i < num_suites; i++)
 		kunit_exit_suite(suites[i]);
-
-	kunit_suite_counter = 1;
 }
 EXPORT_SYMBOL_GPL(__kunit_test_suites_exit);
 
diff --git a/lib/objpool.c b/lib/objpool.c
index ce0087f64400c2..cfdc0242088497 100644
--- a/lib/objpool.c
+++ b/lib/objpool.c
@@ -201,6 +201,23 @@ static inline void *objpool_try_get_slot(struct objpool_head *pool, int cpu)
 	while (head != READ_ONCE(slot->last)) {
 		void *obj;
 
+		/*
+		 * data visibility of 'last' and 'head' could be out of
+		 * order since memory updating of 'last' and 'head' are
+		 * performed in push() and pop() independently
+		 *
+		 * before any retrieving attempts, pop() must guarantee
+		 * 'last' is behind 'head', that is to say, there must
+		 * be available objects in slot, which could be ensured
+		 * by condition 'last != head && last - head <= nr_objs'
+		 * that is equivalent to 'last - head - 1 < nr_objs' as
+		 * 'last' and 'head' are both unsigned int32
+		 */
+		if (READ_ONCE(slot->last) - head - 1 >= pool->nr_objs) {
+			head = READ_ONCE(slot->head);
+			continue;
+		}
+
 		/* obj must be retrieved before moving forward head */
 		obj = READ_ONCE(slot->entries[head & slot->mask]);
 
diff --git a/lib/test_ida.c b/lib/test_ida.c
index b0688062596150..55105baa19da9a 100644
--- a/lib/test_ida.c
+++ b/lib/test_ida.c
@@ -150,6 +150,45 @@ static void ida_check_conv(struct ida *ida)
 	IDA_BUG_ON(ida, !ida_is_empty(ida));
 }
 
+/*
+ * Check various situations where we attempt to free an ID we don't own.
+ */
+static void ida_check_bad_free(struct ida *ida)
+{
+	unsigned long i;
+
+	printk("vvv Ignore \"not allocated\" warnings\n");
+	/* IDA is empty; all of these will fail */
+	ida_free(ida, 0);
+	for (i = 0; i < 31; i++)
+		ida_free(ida, 1 << i);
+
+	/* IDA contains a single value entry */
+	IDA_BUG_ON(ida, ida_alloc_min(ida, 3, GFP_KERNEL) != 3);
+	ida_free(ida, 0);
+	for (i = 0; i < 31; i++)
+		ida_free(ida, 1 << i);
+
+	/* IDA contains a single bitmap */
+	IDA_BUG_ON(ida, ida_alloc_min(ida, 1023, GFP_KERNEL) != 1023);
+	ida_free(ida, 0);
+	for (i = 0; i < 31; i++)
+		ida_free(ida, 1 << i);
+
+	/* IDA contains a tree */
+	IDA_BUG_ON(ida, ida_alloc_min(ida, (1 << 20) - 1, GFP_KERNEL) != (1 << 20) - 1);
+	ida_free(ida, 0);
+	for (i = 0; i < 31; i++)
+		ida_free(ida, 1 << i);
+	printk("^^^ \"not allocated\" warnings over\n");
+
+	ida_free(ida, 3);
+	ida_free(ida, 1023);
+	ida_free(ida, (1 << 20) - 1);
+
+	IDA_BUG_ON(ida, !ida_is_empty(ida));
+}
+
 static DEFINE_IDA(ida);
 
 static int ida_checks(void)
@@ -162,6 +201,7 @@ static int ida_checks(void)
 	ida_check_leaf(&ida, 1024 * 64);
 	ida_check_max(&ida);
 	ida_check_conv(&ida);
+	ida_check_bad_free(&ida);
 
 	printk("IDA: %u of %u tests passed\n", tests_passed, tests_run);
 	return (tests_run != tests_passed) ? 0 : -EINVAL;
diff --git a/lib/test_objpool.c b/lib/test_objpool.c
index a9407840213851..bfdb815998328d 100644
--- a/lib/test_objpool.c
+++ b/lib/test_objpool.c
@@ -311,7 +311,7 @@ static void ot_fini_sync(struct ot_context *sop)
 	ot_kfree(sop->test, sop, sizeof(*sop));
 }
 
-struct {
+static struct {
 	struct ot_context * (*init)(struct ot_test *oc);
 	void (*fini)(struct ot_context *sop);
 } g_ot_sync_ops[] = {
@@ -475,7 +475,7 @@ static struct ot_context *ot_init_async_m0(struct ot_test *test)
 	return sop;
 }
 
-struct {
+static struct {
 	struct ot_context * (*init)(struct ot_test *oc);
 	void (*fini)(struct ot_context *sop);
 } g_ot_async_ops[] = {
@@ -632,7 +632,7 @@ static int ot_start_async(struct ot_test *test)
 #define NODE_COMPACT sizeof(struct ot_node)
 #define NODE_VMALLOC (512)
 
-struct ot_test g_testcases[] = {
+static struct ot_test g_testcases[] = {
 
 	/* sync & normal */
 	{0, 0, NODE_COMPACT, 1000, 0,  1,  0,  0, "sync: percpu objpool"},
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 3e3733a7084fb7..552738f14275a7 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -2111,15 +2111,20 @@ char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf,
 
 	/* Loop starting from the root node to the current node. */
 	for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) {
-		struct fwnode_handle *__fwnode =
-			fwnode_get_nth_parent(fwnode, depth);
+		/*
+		 * Only get a reference for other nodes (i.e. parent nodes).
+		 * fwnode refcount may be 0 here.
+		 */
+		struct fwnode_handle *__fwnode = depth ?
+			fwnode_get_nth_parent(fwnode, depth) : fwnode;
 
 		buf = string(buf, end, fwnode_get_name_prefix(__fwnode),
 			     default_str_spec);
 		buf = string(buf, end, fwnode_get_name(__fwnode),
 			     default_str_spec);
 
-		fwnode_handle_put(__fwnode);
+		if (depth)
+			fwnode_handle_put(__fwnode);
 	}
 
 	return buf;
diff --git a/lib/zstd/common/fse_decompress.c b/lib/zstd/common/fse_decompress.c
index a0d06095be83de..8dcb8ca39767c8 100644
--- a/lib/zstd/common/fse_decompress.c
+++ b/lib/zstd/common/fse_decompress.c
@@ -312,7 +312,7 @@ size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size
 
 typedef struct {
     short ncount[FSE_MAX_SYMBOL_VALUE + 1];
-    FSE_DTable dtable[1]; /* Dynamically sized */
+    FSE_DTable dtable[]; /* Dynamically sized */
 } FSE_DecompressWksp;
 
 
diff --git a/mm/Kconfig b/mm/Kconfig
index 89971a894b6058..57cd378c73d67f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1201,13 +1201,6 @@ config ANON_VMA_NAME
 	  area from being merged with adjacent virtual memory areas due to the
 	  difference in their name.
 
-config USERFAULTFD
-	bool "Enable userfaultfd() system call"
-	depends on MMU
-	help
-	  Enable the userfaultfd() system call that allows to intercept and
-	  handle page faults in userland.
-
 config HAVE_ARCH_USERFAULTFD_WP
 	bool
 	help
@@ -1218,6 +1211,14 @@ config HAVE_ARCH_USERFAULTFD_MINOR
 	help
 	  Arch has userfaultfd minor fault support
 
+menuconfig USERFAULTFD
+	bool "Enable userfaultfd() system call"
+	depends on MMU
+	help
+	  Enable the userfaultfd() system call that allows to intercept and
+	  handle page faults in userland.
+
+if USERFAULTFD
 config PTE_MARKER_UFFD_WP
 	bool "Userfaultfd write protection support for shmem/hugetlbfs"
 	default y
@@ -1227,6 +1228,7 @@ config PTE_MARKER_UFFD_WP
 	  Allows to create marker PTEs for userfaultfd write protection
 	  purposes.  It is required to enable userfaultfd write protection on
 	  file-backed memory types like shmem and hugetlbfs.
+endif # USERFAULTFD
 
 # multi-gen LRU {
 config LRU_GEN
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 630077d95dc607..3a05e71509b9db 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -445,6 +445,8 @@ struct damon_ctx *damon_new_ctx(void)
 	if (!ctx)
 		return NULL;
 
+	init_completion(&ctx->kdamond_started);
+
 	ctx->attrs.sample_interval = 5 * 1000;
 	ctx->attrs.aggr_interval = 100 * 1000;
 	ctx->attrs.ops_update_interval = 60 * 1000 * 1000;
@@ -668,11 +670,14 @@ static int __damon_start(struct damon_ctx *ctx)
 	mutex_lock(&ctx->kdamond_lock);
 	if (!ctx->kdamond) {
 		err = 0;
+		reinit_completion(&ctx->kdamond_started);
 		ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d",
 				nr_running_ctxs);
 		if (IS_ERR(ctx->kdamond)) {
 			err = PTR_ERR(ctx->kdamond);
 			ctx->kdamond = NULL;
+		} else {
+			wait_for_completion(&ctx->kdamond_started);
 		}
 	}
 	mutex_unlock(&ctx->kdamond_lock);
@@ -924,7 +929,7 @@ static bool __damos_filter_out(struct damon_ctx *ctx, struct damon_target *t,
 		matched = true;
 		break;
 	default:
-		break;
+		return false;
 	}
 
 	return matched == filter->matching;
@@ -1225,6 +1230,7 @@ static void damon_split_region_at(struct damon_target *t,
 	new->age = r->age;
 	new->last_nr_accesses = r->last_nr_accesses;
 	new->nr_accesses_bp = r->nr_accesses_bp;
+	new->nr_accesses = r->nr_accesses;
 
 	damon_insert_region(new, r, damon_next_region(r), t);
 }
@@ -1432,6 +1438,7 @@ static int kdamond_fn(void *data)
 
 	pr_debug("kdamond (%d) starts\n", current->pid);
 
+	complete(&ctx->kdamond_started);
 	kdamond_init_intervals_sis(ctx);
 
 	if (ctx->ops.init)
diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index 45bd0fd4a8b161..fe0fe2562000b3 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -139,6 +139,13 @@ static const struct kobj_type damon_sysfs_scheme_region_ktype = {
  * damon_sysfs_before_damos_apply() understands the situation by showing the
  * 'finished' status and do nothing.
  *
+ * If DAMOS is not applied to any region due to any reasons including the
+ * access pattern, the watermarks, the quotas, and the filters,
+ * ->before_damos_apply() will not be called back.  Until the situation is
+ * changed, the update will not be finished.  To avoid this,
+ * damon_sysfs_after_sampling() set the status as 'finished' if more than two
+ * apply intervals of the scheme is passed while the state is 'idle'.
+ *
  *  Finally, the tried regions request handling finisher function
  *  (damon_sysfs_schemes_update_regions_stop()) unregisters the callbacks.
  */
@@ -154,6 +161,7 @@ struct damon_sysfs_scheme_regions {
 	int nr_regions;
 	unsigned long total_bytes;
 	enum damos_sysfs_regions_upd_status upd_status;
+	unsigned long upd_timeout_jiffies;
 };
 
 static struct damon_sysfs_scheme_regions *
@@ -162,6 +170,9 @@ damon_sysfs_scheme_regions_alloc(void)
 	struct damon_sysfs_scheme_regions *regions = kmalloc(sizeof(*regions),
 			GFP_KERNEL);
 
+	if (!regions)
+		return NULL;
+
 	regions->kobj = (struct kobject){};
 	INIT_LIST_HEAD(&regions->regions_list);
 	regions->nr_regions = 0;
@@ -1823,6 +1834,8 @@ static int damon_sysfs_before_damos_apply(struct damon_ctx *ctx,
 		return 0;
 
 	region = damon_sysfs_scheme_region_alloc(r);
+	if (!region)
+		return 0;
 	list_add_tail(&region->list, &sysfs_regions->regions_list);
 	sysfs_regions->nr_regions++;
 	if (kobject_init_and_add(&region->kobj,
@@ -1849,7 +1862,9 @@ static int damon_sysfs_after_sampling(struct damon_ctx *ctx)
 	for (i = 0; i < sysfs_schemes->nr; i++) {
 		sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions;
 		if (sysfs_regions->upd_status ==
-				DAMOS_TRIED_REGIONS_UPD_STARTED)
+				DAMOS_TRIED_REGIONS_UPD_STARTED ||
+				time_after(jiffies,
+					sysfs_regions->upd_timeout_jiffies))
 			sysfs_regions->upd_status =
 				DAMOS_TRIED_REGIONS_UPD_FINISHED;
 	}
@@ -1880,14 +1895,41 @@ int damon_sysfs_schemes_clear_regions(
 	return 0;
 }
 
+static struct damos *damos_sysfs_nth_scheme(int n, struct damon_ctx *ctx)
+{
+	struct damos *scheme;
+	int i = 0;
+
+	damon_for_each_scheme(scheme, ctx) {
+		if (i == n)
+			return scheme;
+		i++;
+	}
+	return NULL;
+}
+
 static void damos_tried_regions_init_upd_status(
-		struct damon_sysfs_schemes *sysfs_schemes)
+		struct damon_sysfs_schemes *sysfs_schemes,
+		struct damon_ctx *ctx)
 {
 	int i;
+	struct damos *scheme;
+	struct damon_sysfs_scheme_regions *sysfs_regions;
 
-	for (i = 0; i < sysfs_schemes->nr; i++)
-		sysfs_schemes->schemes_arr[i]->tried_regions->upd_status =
-			DAMOS_TRIED_REGIONS_UPD_IDLE;
+	for (i = 0; i < sysfs_schemes->nr; i++) {
+		sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions;
+		scheme = damos_sysfs_nth_scheme(i, ctx);
+		if (!scheme) {
+			sysfs_regions->upd_status =
+				DAMOS_TRIED_REGIONS_UPD_FINISHED;
+			continue;
+		}
+		sysfs_regions->upd_status = DAMOS_TRIED_REGIONS_UPD_IDLE;
+		sysfs_regions->upd_timeout_jiffies = jiffies +
+			2 * usecs_to_jiffies(scheme->apply_interval_us ?
+					scheme->apply_interval_us :
+					ctx->attrs.sample_interval);
+	}
 }
 
 /* Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock */
@@ -1897,7 +1939,7 @@ int damon_sysfs_schemes_update_regions_start(
 {
 	damon_sysfs_schemes_clear_regions(sysfs_schemes, ctx);
 	damon_sysfs_schemes_for_damos_callback = sysfs_schemes;
-	damos_tried_regions_init_upd_status(sysfs_schemes);
+	damos_tried_regions_init_upd_status(sysfs_schemes, ctx);
 	damos_regions_upd_total_bytes_only = total_bytes_only;
 	ctx->callback.before_damos_apply = damon_sysfs_before_damos_apply;
 	ctx->callback.after_sampling = damon_sysfs_after_sampling;
diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index e27846708b5a24..7472404456aa81 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1172,7 +1172,7 @@ static int damon_sysfs_update_target(struct damon_target *target,
 		struct damon_ctx *ctx,
 		struct damon_sysfs_target *sys_target)
 {
-	int err;
+	int err = 0;
 
 	if (damon_target_has_pid(ctx)) {
 		err = damon_sysfs_update_target_pid(target, sys_target->pid);
@@ -1203,8 +1203,10 @@ static int damon_sysfs_set_targets(struct damon_ctx *ctx,
 
 	damon_for_each_target_safe(t, next, ctx) {
 		if (i < sysfs_targets->nr) {
-			damon_sysfs_update_target(t, ctx,
+			err = damon_sysfs_update_target(t, ctx,
 					sysfs_targets->targets_arr[i]);
+			if (err)
+				return err;
 		} else {
 			if (damon_target_has_pid(ctx))
 				put_pid(t->pid);
diff --git a/mm/filemap.c b/mm/filemap.c
index 9710f43a89acd3..f1c8c278310fd5 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3371,7 +3371,7 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio,
 		}
 	}
 
-	if (pmd_none(*vmf->pmd))
+	if (pmd_none(*vmf->pmd) && vmf->prealloc_pte)
 		pmd_install(mm, vmf->pmd, &vmf->prealloc_pte);
 
 	return false;
@@ -3443,7 +3443,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
 		 * handled in the specific fault path, and it'll prohibit the
 		 * fault-around logic.
 		 */
-		if (!pte_none(vmf->pte[count]))
+		if (!pte_none(ptep_get(&vmf->pte[count])))
 			goto skip;
 
 		count++;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f31f02472396e7..4f542444a91f2a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2769,13 +2769,15 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			int nr = folio_nr_pages(folio);
 
 			xas_split(&xas, folio, folio_order(folio));
-			if (folio_test_swapbacked(folio)) {
-				__lruvec_stat_mod_folio(folio, NR_SHMEM_THPS,
-							-nr);
-			} else {
-				__lruvec_stat_mod_folio(folio, NR_FILE_THPS,
-							-nr);
-				filemap_nr_thps_dec(mapping);
+			if (folio_test_pmd_mappable(folio)) {
+				if (folio_test_swapbacked(folio)) {
+					__lruvec_stat_mod_folio(folio,
+							NR_SHMEM_THPS, -nr);
+				} else {
+					__lruvec_stat_mod_folio(folio,
+							NR_FILE_THPS, -nr);
+					filemap_nr_thps_dec(mapping);
+				}
 			}
 		}
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1169ef2f2176fa..6feb3e0630d186 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1182,6 +1182,13 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
 	return (get_vma_private_data(vma) & flag) != 0;
 }
 
+bool __vma_private_lock(struct vm_area_struct *vma)
+{
+	return !(vma->vm_flags & VM_MAYSHARE) &&
+		get_vma_private_data(vma) & ~HPAGE_RESV_MASK &&
+		is_vma_resv_set(vma, HPAGE_RESV_OWNER);
+}
+
 void hugetlb_dup_vma_private(struct vm_area_struct *vma)
 {
 	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 1eacca03bedd20..5501363d6b3125 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -642,32 +642,16 @@ static struct kmemleak_object *__alloc_object(gfp_t gfp)
 	if (!object) {
 		pr_warn("Cannot allocate a kmemleak_object structure\n");
 		kmemleak_disable();
+		return NULL;
 	}
 
-	return object;
-}
-
-static int __link_object(struct kmemleak_object *object, unsigned long ptr,
-			 size_t size, int min_count, bool is_phys)
-{
-
-	struct kmemleak_object *parent;
-	struct rb_node **link, *rb_parent;
-	unsigned long untagged_ptr;
-	unsigned long untagged_objp;
-
 	INIT_LIST_HEAD(&object->object_list);
 	INIT_LIST_HEAD(&object->gray_list);
 	INIT_HLIST_HEAD(&object->area_list);
 	raw_spin_lock_init(&object->lock);
 	atomic_set(&object->use_count, 1);
-	object->flags = OBJECT_ALLOCATED | (is_phys ? OBJECT_PHYS : 0);
-	object->pointer = ptr;
-	object->size = kfence_ksize((void *)ptr) ?: size;
 	object->excess_ref = 0;
-	object->min_count = min_count;
 	object->count = 0;			/* white color initially */
-	object->jiffies = jiffies;
 	object->checksum = 0;
 	object->del_state = 0;
 
@@ -692,6 +676,24 @@ static int __link_object(struct kmemleak_object *object, unsigned long ptr,
 	/* kernel backtrace */
 	object->trace_handle = set_track_prepare();
 
+	return object;
+}
+
+static int __link_object(struct kmemleak_object *object, unsigned long ptr,
+			 size_t size, int min_count, bool is_phys)
+{
+
+	struct kmemleak_object *parent;
+	struct rb_node **link, *rb_parent;
+	unsigned long untagged_ptr;
+	unsigned long untagged_objp;
+
+	object->flags = OBJECT_ALLOCATED | (is_phys ? OBJECT_PHYS : 0);
+	object->pointer = ptr;
+	object->size = kfence_ksize((void *)ptr) ?: size;
+	object->min_count = min_count;
+	object->jiffies = jiffies;
+
 	untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr);
 	/*
 	 * Only update min_addr and max_addr with object
@@ -1150,6 +1152,7 @@ EXPORT_SYMBOL_GPL(kmemleak_free_percpu);
 void __ref kmemleak_update_trace(const void *ptr)
 {
 	struct kmemleak_object *object;
+	depot_stack_handle_t trace_handle;
 	unsigned long flags;
 
 	pr_debug("%s(0x%px)\n", __func__, ptr);
@@ -1166,8 +1169,9 @@ void __ref kmemleak_update_trace(const void *ptr)
 		return;
 	}
 
+	trace_handle = set_track_prepare();
 	raw_spin_lock_irqsave(&object->lock, flags);
-	object->trace_handle = set_track_prepare();
+	object->trace_handle = trace_handle;
 	raw_spin_unlock_irqrestore(&object->lock, flags);
 
 	put_object(object);
diff --git a/mm/ksm.c b/mm/ksm.c
index 7efcc68ccc6eae..6a831009b4cbf9 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -468,7 +468,7 @@ static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long nex
 			page = pfn_swap_entry_to_page(entry);
 	}
 	/* return 1 if the page is an normal ksm page or KSM-placed zero page */
-	ret = (page && PageKsm(page)) || is_ksm_zero_pte(*pte);
+	ret = (page && PageKsm(page)) || is_ksm_zero_pte(ptent);
 	pte_unmap_unlock(pte, ptl);
 	return ret;
 }
diff --git a/mm/madvise.c b/mm/madvise.c
index cf4d694280e98a..6214a1ab5654f4 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -335,6 +335,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 	struct folio *folio = NULL;
 	LIST_HEAD(folio_list);
 	bool pageout_anon_only_filter;
+	unsigned int batch_count = 0;
 
 	if (fatal_signal_pending(current))
 		return -EINTR;
@@ -416,6 +417,7 @@ huge_unlock:
 regular_folio:
 #endif
 	tlb_change_page_size(tlb, PAGE_SIZE);
+restart:
 	start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (!start_pte)
 		return 0;
@@ -424,6 +426,15 @@ regular_folio:
 	for (; addr < end; pte++, addr += PAGE_SIZE) {
 		ptent = ptep_get(pte);
 
+		if (++batch_count == SWAP_CLUSTER_MAX) {
+			batch_count = 0;
+			if (need_resched()) {
+				pte_unmap_unlock(start_pte, ptl);
+				cond_resched();
+				goto restart;
+			}
+		}
+
 		if (pte_none(ptent))
 			continue;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 774bd6e21e2788..b226090fd9061c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2936,7 +2936,8 @@ void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg)
  * Moreover, it should not come from DMA buffer and is not readily
  * reclaimable. So those GFP bits should be masked off.
  */
-#define OBJCGS_CLEAR_MASK	(__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT)
+#define OBJCGS_CLEAR_MASK	(__GFP_DMA | __GFP_RECLAIMABLE | \
+				 __GFP_ACCOUNT | __GFP_NOFAIL)
 
 /*
  * mod_objcg_mlstate() may be called with irq enabled, so
@@ -3165,6 +3166,7 @@ __always_inline struct obj_cgroup *current_obj_cgroup(void)
 	return NULL;
 
 from_memcg:
+	objcg = NULL;
 	for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
 		/*
 		 * Memcg pointer is protected by scope (see set_active_memcg())
@@ -3175,7 +3177,6 @@ from_memcg:
 		objcg = rcu_dereference_check(memcg->objcg, 1);
 		if (likely(objcg))
 			break;
-		objcg = NULL;
 	}
 
 	return objcg;
diff --git a/mm/memory.c b/mm/memory.c
index 1f18ed4a54971d..5c757fba8858a5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1517,6 +1517,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				continue;
 		} else {
 			/* We should have covered all the swap entry types */
+			pr_alert("unrecognized swap entry 0x%lx\n", entry.val);
 			WARN_ON_ONCE(1);
 		}
 		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ab41a511e20a8e..7a5fc89a865289 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1129,6 +1129,9 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages)
 	kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages));
 }
 
+/*
+ * Must be called with mem_hotplug_lock in write mode.
+ */
 int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 		       struct zone *zone, struct memory_group *group)
 {
@@ -1149,7 +1152,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 			 !IS_ALIGNED(pfn + nr_pages, PAGES_PER_SECTION)))
 		return -EINVAL;
 
-	mem_hotplug_begin();
 
 	/* associate pfn range with the zone */
 	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE);
@@ -1208,7 +1210,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 	writeback_set_ratelimit();
 
 	memory_notify(MEM_ONLINE, &arg);
-	mem_hotplug_done();
 	return 0;
 
 failed_addition:
@@ -1217,7 +1218,6 @@ failed_addition:
 		 (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1);
 	memory_notify(MEM_CANCEL_ONLINE, &arg);
 	remove_pfn_range_from_zone(zone, pfn, nr_pages);
-	mem_hotplug_done();
 	return ret;
 }
 
@@ -1458,7 +1458,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 	/* create memory block devices after memory was added */
 	ret = create_memory_block_devices(start, size, params.altmap, group);
 	if (ret) {
-		arch_remove_memory(start, size, NULL);
+		arch_remove_memory(start, size, params.altmap);
 		goto error_free;
 	}
 
@@ -1863,6 +1863,9 @@ static int count_system_ram_pages_cb(unsigned long start_pfn,
 	return 0;
 }
 
+/*
+ * Must be called with mem_hotplug_lock in write mode.
+ */
 int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 			struct zone *zone, struct memory_group *group)
 {
@@ -1885,8 +1888,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 			 !IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION)))
 		return -EINVAL;
 
-	mem_hotplug_begin();
-
 	/*
 	 * Don't allow to offline memory blocks that contain holes.
 	 * Consequently, memory blocks with holes can never get onlined
@@ -2031,7 +2032,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 
 	memory_notify(MEM_OFFLINE, &arg);
 	remove_pfn_range_from_zone(zone, start_pfn, nr_pages);
-	mem_hotplug_done();
 	return 0;
 
 failed_removal_isolated:
@@ -2046,7 +2046,6 @@ failed_removal:
 		 (unsigned long long) start_pfn << PAGE_SHIFT,
 		 ((unsigned long long) end_pfn << PAGE_SHIFT) - 1,
 		 reason);
-	mem_hotplug_done();
 	return ret;
 }
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 46f2f5d3d183b5..ee2fd6a6af4072 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -3107,7 +3107,7 @@ EXPORT_SYMBOL_GPL(folio_wait_writeback_killable);
  */
 void folio_wait_stable(struct folio *folio)
 {
-	if (folio_inode(folio)->i_sb->s_iflags & SB_I_STABLE_WRITES)
+	if (mapping_stable_writes(folio_mapping(folio)))
 		folio_wait_writeback(folio);
 }
 EXPORT_SYMBOL_GPL(folio_wait_stable);
diff --git a/mm/shmem.c b/mm/shmem.c
index 91e2620148b2f6..0d1ce70bce3802 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1080,7 +1080,24 @@ whole_folios:
 				}
 				VM_BUG_ON_FOLIO(folio_test_writeback(folio),
 						folio);
-				truncate_inode_folio(mapping, folio);
+
+				if (!folio_test_large(folio)) {
+					truncate_inode_folio(mapping, folio);
+				} else if (truncate_inode_partial_folio(folio, lstart, lend)) {
+					/*
+					 * If we split a page, reset the loop so
+					 * that we pick up the new sub pages.
+					 * Otherwise the THP was entirely
+					 * dropped or the target range was
+					 * zeroed, so just continue the loop as
+					 * is.
+					 */
+					if (!folio_test_large(folio)) {
+						folio_unlock(folio);
+						index = start;
+						break;
+					}
+				}
 			}
 			folio_unlock(folio);
 		}
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 96d9eae5c7cc8e..0b6ca553bebec5 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -312,7 +312,7 @@ static int mfill_atomic_pte_poison(pmd_t *dst_pmd,
 
 	ret = -EEXIST;
 	/* Refuse to overwrite any PTE, even a PTE marker (e.g. UFFD WP). */
-	if (!pte_none(*dst_pte))
+	if (!pte_none(ptep_get(dst_pte)))
 		goto out_unlock;
 
 	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
diff --git a/mm/util.c b/mm/util.c
index aa01f6ea5a75b7..744b4d7e3fae2d 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -414,6 +414,15 @@ static int mmap_is_legacy(struct rlimit *rlim_stack)
 
 static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
 {
+#ifdef CONFIG_STACK_GROWSUP
+	/*
+	 * For an upwards growing stack the calculation is much simpler.
+	 * Memory for the maximum stack size is reserved at the top of the
+	 * task. mmap_base starts directly below the stack and grows
+	 * downwards.
+	 */
+	return PAGE_ALIGN_DOWN(mmap_upper_limit(rlim_stack) - rnd);
+#else
 	unsigned long gap = rlim_stack->rlim_cur;
 	unsigned long pad = stack_guard_gap;
 
@@ -431,6 +440,7 @@ static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
 		gap = MAX_GAP;
 
 	return PAGE_ALIGN(STACK_TOP - gap - rnd);
+#endif
 }
 
 void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 506f8220c5fe53..9dd8977de5a223 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4089,6 +4089,9 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
 	else
 		VM_WARN_ON_ONCE(true);
 
+	WRITE_ONCE(lruvec->lrugen.seg, seg);
+	WRITE_ONCE(lruvec->lrugen.gen, new);
+
 	hlist_nulls_del_rcu(&lruvec->lrugen.list);
 
 	if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD)
@@ -4099,9 +4102,6 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
 	pgdat->memcg_lru.nr_memcgs[old]--;
 	pgdat->memcg_lru.nr_memcgs[new]++;
 
-	lruvec->lrugen.gen = new;
-	WRITE_ONCE(lruvec->lrugen.seg, seg);
-
 	if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq))
 		WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1);
 
@@ -4124,11 +4124,11 @@ void lru_gen_online_memcg(struct mem_cgroup *memcg)
 
 		gen = get_memcg_gen(pgdat->memcg_lru.seq);
 
+		lruvec->lrugen.gen = gen;
+
 		hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]);
 		pgdat->memcg_lru.nr_memcgs[gen]++;
 
-		lruvec->lrugen.gen = gen;
-
 		spin_unlock_irq(&pgdat->memcg_lru.lock);
 	}
 }
@@ -4232,7 +4232,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	}
 
 	/* protected */
-	if (tier > tier_idx) {
+	if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) {
 		int hist = lru_hist_from_seq(lrugen->min_seq[type]);
 
 		gen = folio_inc_gen(lruvec, folio, false);
@@ -4598,7 +4598,12 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
 	}
 
 	/* try to scrape all its memory if this memcg was deleted */
-	*nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total;
+	if (!mem_cgroup_online(memcg)) {
+		*nr_to_scan = total;
+		return false;
+	}
+
+	*nr_to_scan = total >> sc->priority;
 
 	/*
 	 * The aging tries to be lazy to reduce the overhead, while the eviction
@@ -4635,7 +4640,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool
 	DEFINE_MAX_SEQ(lruvec);
 
 	if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg))
-		return 0;
+		return -1;
 
 	if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan))
 		return nr_to_scan;
@@ -4648,20 +4653,41 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool
 	return try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false) ? -1 : 0;
 }
 
-static unsigned long get_nr_to_reclaim(struct scan_control *sc)
+static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
 {
+	int i;
+	enum zone_watermarks mark;
+
 	/* don't abort memcg reclaim to ensure fairness */
 	if (!root_reclaim(sc))
-		return -1;
+		return false;
+
+	if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order)))
+		return true;
+
+	/* check the order to exclude compaction-induced reclaim */
+	if (!current_is_kswapd() || sc->order)
+		return false;
+
+	mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ?
+	       WMARK_PROMO : WMARK_HIGH;
+
+	for (i = 0; i <= sc->reclaim_idx; i++) {
+		struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i;
+		unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH;
+
+		if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0))
+			return false;
+	}
 
-	return max(sc->nr_to_reclaim, compact_gap(sc->order));
+	/* kswapd should abort if all eligible zones are safe */
+	return true;
 }
 
 static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 {
 	long nr_to_scan;
 	unsigned long scanned = 0;
-	unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
 	int swappiness = get_swappiness(lruvec, sc);
 
 	/* clean file folios are more likely to exist */
@@ -4683,13 +4709,13 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 		if (scanned >= nr_to_scan)
 			break;
 
-		if (sc->nr_reclaimed >= nr_to_reclaim)
+		if (should_abort_scan(lruvec, sc))
 			break;
 
 		cond_resched();
 	}
 
-	/* whether try_to_inc_max_seq() was successful */
+	/* whether this lruvec should be rotated */
 	return nr_to_scan < 0;
 }
 
@@ -4698,14 +4724,9 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 	bool success;
 	unsigned long scanned = sc->nr_scanned;
 	unsigned long reclaimed = sc->nr_reclaimed;
-	int seg = lru_gen_memcg_seg(lruvec);
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
-	/* see the comment on MEMCG_NR_GENS */
-	if (!lruvec_is_sizable(lruvec, sc))
-		return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
-
 	mem_cgroup_calculate_protection(NULL, memcg);
 
 	if (mem_cgroup_below_min(NULL, memcg))
@@ -4713,7 +4734,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 
 	if (mem_cgroup_below_low(NULL, memcg)) {
 		/* see the comment on MEMCG_NR_GENS */
-		if (seg != MEMCG_LRU_TAIL)
+		if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL)
 			return MEMCG_LRU_TAIL;
 
 		memcg_memory_event(memcg, MEMCG_LOW);
@@ -4729,7 +4750,15 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 
 	flush_reclaim_state(sc);
 
-	return success ? MEMCG_LRU_YOUNG : 0;
+	if (success && mem_cgroup_online(memcg))
+		return MEMCG_LRU_YOUNG;
+
+	if (!success && lruvec_is_sizable(lruvec, sc))
+		return 0;
+
+	/* one retry if offlined or too small */
+	return lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL ?
+	       MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
 }
 
 #ifdef CONFIG_MEMCG
@@ -4743,14 +4772,13 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
 	struct lruvec *lruvec;
 	struct lru_gen_folio *lrugen;
 	struct mem_cgroup *memcg;
-	const struct hlist_nulls_node *pos;
-	unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
+	struct hlist_nulls_node *pos;
 
+	gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
 	bin = first_bin = get_random_u32_below(MEMCG_NR_BINS);
 restart:
 	op = 0;
 	memcg = NULL;
-	gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
 
 	rcu_read_lock();
 
@@ -4761,6 +4789,10 @@ restart:
 		}
 
 		mem_cgroup_put(memcg);
+		memcg = NULL;
+
+		if (gen != READ_ONCE(lrugen->gen))
+			continue;
 
 		lruvec = container_of(lrugen, struct lruvec, lrugen);
 		memcg = lruvec_memcg(lruvec);
@@ -4777,7 +4809,7 @@ restart:
 
 		rcu_read_lock();
 
-		if (sc->nr_reclaimed >= nr_to_reclaim)
+		if (should_abort_scan(lruvec, sc))
 			break;
 	}
 
@@ -4788,7 +4820,7 @@ restart:
 
 	mem_cgroup_put(memcg);
 
-	if (sc->nr_reclaimed >= nr_to_reclaim)
+	if (!is_a_nulls(pos))
 		return;
 
 	/* restart if raced with lru_gen_rotate_memcg() */
@@ -4845,16 +4877,14 @@ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control
 	if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH)
 		return;
 	/*
-	 * Determine the initial priority based on ((total / MEMCG_NR_GENS) >>
-	 * priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the
-	 * estimated reclaimed_to_scanned_ratio = inactive / total.
+	 * Determine the initial priority based on
+	 * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim,
+	 * where reclaimed_to_scanned_ratio = inactive / total.
 	 */
 	reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE);
 	if (get_swappiness(lruvec, sc))
 		reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON);
 
-	reclaimable /= MEMCG_NR_GENS;
-
 	/* round down reclaimable and round up sc->nr_to_reclaim */
 	priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1);
 
diff --git a/mm/workingset.c b/mm/workingset.c
index b192e44a0e7ccc..33baad203277d1 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -313,10 +313,10 @@ static void lru_gen_refault(struct folio *folio, void *shadow)
 	 * 1. For pages accessed through page tables, hotter pages pushed out
 	 *    hot pages which refaulted immediately.
 	 * 2. For pages accessed multiple times through file descriptors,
-	 *    numbers of accesses might have been out of the range.
+	 *    they would have been protected by sort_folio().
 	 */
-	if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) {
-		folio_set_workingset(folio);
+	if (lru_gen_in_fault() || refs >= BIT(LRU_REFS_WIDTH) - 1) {
+		set_mask_bits(&folio->flags, 0, LRU_REFS_MASK | BIT(PG_workingset));
 		mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
 	}
 unlock:
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 0beb44f2fe1f0d..f001582345052f 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -407,6 +407,8 @@ int vlan_vids_add_by_dev(struct net_device *dev,
 		return 0;
 
 	list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+		if (!vlan_hw_filter_capable(by_dev, vid_info->proto))
+			continue;
 		err = vlan_vid_add(dev, vid_info->proto, vid_info->vid);
 		if (err)
 			goto unwind;
@@ -417,6 +419,8 @@ unwind:
 	list_for_each_entry_continue_reverse(vid_info,
 					     &vlan_info->vid_list,
 					     list) {
+		if (!vlan_hw_filter_capable(by_dev, vid_info->proto))
+			continue;
 		vlan_vid_del(dev, vid_info->proto, vid_info->vid);
 	}
 
@@ -436,8 +440,11 @@ void vlan_vids_del_by_dev(struct net_device *dev,
 	if (!vlan_info)
 		return;
 
-	list_for_each_entry(vid_info, &vlan_info->vid_list, list)
+	list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+		if (!vlan_hw_filter_capable(by_dev, vid_info->proto))
+			continue;
 		vlan_vid_del(dev, vid_info->proto, vid_info->vid);
+	}
 }
 EXPORT_SYMBOL(vlan_vids_del_by_dev);
 
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 4e3a2a1ffcb3fa..0e6603b1ec906a 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -394,6 +394,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
 				uint16_t *nwname = va_arg(ap, uint16_t *);
 				char ***wnames = va_arg(ap, char ***);
 
+				*wnames = NULL;
+
 				errcode = p9pdu_readf(pdu, proto_version,
 								"w", nwname);
 				if (!errcode) {
@@ -403,6 +405,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
 							  GFP_NOFS);
 					if (!*wnames)
 						errcode = -ENOMEM;
+					else
+						(*wnames)[0] = NULL;
 				}
 
 				if (!errcode) {
@@ -414,8 +418,10 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
 								proto_version,
 								"s",
 								&(*wnames)[i]);
-						if (errcode)
+						if (errcode) {
+							(*wnames)[i] = NULL;
 							break;
+						}
 					}
 				}
 
@@ -423,11 +429,14 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
 					if (*wnames) {
 						int i;
 
-						for (i = 0; i < *nwname; i++)
+						for (i = 0; i < *nwname; i++) {
+							if (!(*wnames)[i])
+								break;
 							kfree((*wnames)[i]);
+						}
+						kfree(*wnames);
+						*wnames = NULL;
 					}
-					kfree(*wnames);
-					*wnames = NULL;
 				}
 			}
 			break;
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 9ba04a69ec2ae7..a852ec093fa8b9 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1775,15 +1775,14 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		break;
 	}
 	case TIOCINQ: {
-		/*
-		 * These two are safe on a single CPU system as only
-		 * user tasks fiddle here
-		 */
-		struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+		struct sk_buff *skb;
 		long amount = 0;
 
+		spin_lock_irq(&sk->sk_receive_queue.lock);
+		skb = skb_peek(&sk->sk_receive_queue);
 		if (skb)
 			amount = skb->len - sizeof(struct ddpehdr);
+		spin_unlock_irq(&sk->sk_receive_queue.lock);
 		rc = put_user(amount, (int __user *)argp);
 		break;
 	}
diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c
index 838ebf0cabbfb7..f81f8d56f5c0c5 100644
--- a/net/atm/ioctl.c
+++ b/net/atm/ioctl.c
@@ -73,14 +73,17 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd,
 	case SIOCINQ:
 	{
 		struct sk_buff *skb;
+		int amount;
 
 		if (sock->state != SS_CONNECTED) {
 			error = -EINVAL;
 			goto done;
 		}
+		spin_lock_irq(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
-		error = put_user(skb ? skb->len : 0,
-				 (int __user *)argp) ? -EFAULT : 0;
+		amount = skb ? skb->len : 0;
+		spin_unlock_irq(&sk->sk_receive_queue.lock);
+		error = put_user(amount, (int __user *)argp) ? -EFAULT : 0;
 		goto done;
 	}
 	case ATM_SETSC:
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 336a7616545468..b93464ac3517f4 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -309,11 +309,14 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	if (flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
+	lock_sock(sk);
+
 	skb = skb_recv_datagram(sk, flags, &err);
 	if (!skb) {
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
-			return 0;
+			err = 0;
 
+		release_sock(sk);
 		return err;
 	}
 
@@ -343,6 +346,8 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	skb_free_datagram(sk, skb);
 
+	release_sock(sk);
+
 	if (flags & MSG_TRUNC)
 		copied = skblen;
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 0849e0dafa951c..ebf17b51072fc1 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -516,6 +516,9 @@ static u8 hci_cc_read_class_of_dev(struct hci_dev *hdev, void *data,
 {
 	struct hci_rp_read_class_of_dev *rp = data;
 
+	if (WARN_ON(!hdev))
+		return HCI_ERROR_UNSPECIFIED;
+
 	bt_dev_dbg(hdev, "status 0x%2.2x", rp->status);
 
 	if (rp->status)
@@ -747,9 +750,23 @@ static u8 hci_cc_read_enc_key_size(struct hci_dev *hdev, void *data,
 	} else {
 		conn->enc_key_size = rp->key_size;
 		status = 0;
+
+		if (conn->enc_key_size < hdev->min_enc_key_size) {
+			/* As slave role, the conn->state has been set to
+			 * BT_CONNECTED and l2cap conn req might not be received
+			 * yet, at this moment the l2cap layer almost does
+			 * nothing with the non-zero status.
+			 * So we also clear encrypt related bits, and then the
+			 * handler of l2cap conn req will get the right secure
+			 * state at a later time.
+			 */
+			status = HCI_ERROR_AUTH_FAILURE;
+			clear_bit(HCI_CONN_ENCRYPT, &conn->flags);
+			clear_bit(HCI_CONN_AES_CCM, &conn->flags);
+		}
 	}
 
-	hci_encrypt_cfm(conn, 0);
+	hci_encrypt_cfm(conn, status);
 
 done:
 	hci_dev_unlock(hdev);
@@ -820,8 +837,6 @@ static u8 hci_cc_write_auth_payload_timeout(struct hci_dev *hdev, void *data,
 	if (!rp->status)
 		conn->auth_payload_timeout = get_unaligned_le16(sent + 2);
 
-	hci_encrypt_cfm(conn, 0);
-
 unlock:
 	hci_dev_unlock(hdev);
 
@@ -2304,7 +2319,8 @@ static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status)
 		return;
 	}
 
-	set_bit(HCI_INQUIRY, &hdev->flags);
+	if (hci_sent_cmd_data(hdev, HCI_OP_INQUIRY))
+		set_bit(HCI_INQUIRY, &hdev->flags);
 }
 
 static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status)
@@ -3683,12 +3699,8 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data,
 		cp.handle = cpu_to_le16(conn->handle);
 		cp.timeout = cpu_to_le16(hdev->auth_payload_timeout);
 		if (hci_send_cmd(conn->hdev, HCI_OP_WRITE_AUTH_PAYLOAD_TO,
-				 sizeof(cp), &cp)) {
+				 sizeof(cp), &cp))
 			bt_dev_err(hdev, "write auth payload timeout failed");
-			goto notify;
-		}
-
-		goto unlock;
 	}
 
 notify:
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 17ca13e8c044cb..baeebee41cd9e8 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -6492,6 +6492,14 @@ drop:
 	kfree_skb(skb);
 }
 
+static inline void l2cap_sig_send_rej(struct l2cap_conn *conn, u16 ident)
+{
+	struct l2cap_cmd_rej_unk rej;
+
+	rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD);
+	l2cap_send_cmd(conn, ident, L2CAP_COMMAND_REJ, sizeof(rej), &rej);
+}
+
 static inline void l2cap_sig_channel(struct l2cap_conn *conn,
 				     struct sk_buff *skb)
 {
@@ -6517,23 +6525,24 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn,
 
 		if (len > skb->len || !cmd->ident) {
 			BT_DBG("corrupted command");
+			l2cap_sig_send_rej(conn, cmd->ident);
 			break;
 		}
 
 		err = l2cap_bredr_sig_cmd(conn, cmd, len, skb->data);
 		if (err) {
-			struct l2cap_cmd_rej_unk rej;
-
 			BT_ERR("Wrong link type (%d)", err);
-
-			rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD);
-			l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ,
-				       sizeof(rej), &rej);
+			l2cap_sig_send_rej(conn, cmd->ident);
 		}
 
 		skb_pull(skb, len);
 	}
 
+	if (skb->len > 0) {
+		BT_DBG("corrupted command");
+		l2cap_sig_send_rej(conn, 0);
+	}
+
 drop:
 	kfree_skb(skb);
 }
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index ba2e00646e8e82..9dd815b6603feb 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2897,7 +2897,8 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 	for (i = 0; i < key_count; i++) {
 		struct mgmt_link_key_info *key = &cp->keys[i];
 
-		if (key->addr.type != BDADDR_BREDR || key->type > 0x08)
+		/* Considering SMP over BREDR/LE, there is no need to check addr_type */
+		if (key->type > 0x08)
 			return mgmt_cmd_status(sk, hdev->id,
 					       MGMT_OP_LOAD_LINK_KEYS,
 					       MGMT_STATUS_INVALID_PARAMS);
@@ -7130,6 +7131,7 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
 
 	for (i = 0; i < irk_count; i++) {
 		struct mgmt_irk_info *irk = &cp->irks[i];
+		u8 addr_type = le_addr_type(irk->addr.type);
 
 		if (hci_is_blocked_key(hdev,
 				       HCI_BLOCKED_KEY_TYPE_IRK,
@@ -7139,8 +7141,12 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
 			continue;
 		}
 
+		/* When using SMP over BR/EDR, the addr type should be set to BREDR */
+		if (irk->addr.type == BDADDR_BREDR)
+			addr_type = BDADDR_BREDR;
+
 		hci_add_irk(hdev, &irk->addr.bdaddr,
-			    le_addr_type(irk->addr.type), irk->val,
+			    addr_type, irk->val,
 			    BDADDR_ANY);
 	}
 
@@ -7221,6 +7227,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 	for (i = 0; i < key_count; i++) {
 		struct mgmt_ltk_info *key = &cp->keys[i];
 		u8 type, authenticated;
+		u8 addr_type = le_addr_type(key->addr.type);
 
 		if (hci_is_blocked_key(hdev,
 				       HCI_BLOCKED_KEY_TYPE_LTK,
@@ -7255,8 +7262,12 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 			continue;
 		}
 
+		/* When using SMP over BR/EDR, the addr type should be set to BREDR */
+		if (key->addr.type == BDADDR_BREDR)
+			addr_type = BDADDR_BREDR;
+
 		hci_add_ltk(hdev, &key->addr.bdaddr,
-			    le_addr_type(key->addr.type), type, authenticated,
+			    addr_type, type, authenticated,
 			    key->val, key->enc_size, key->ediv, key->rand);
 	}
 
@@ -9523,7 +9534,7 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 
 	ev.store_hint = persistent;
 	bacpy(&ev.key.addr.bdaddr, &key->bdaddr);
-	ev.key.addr.type = BDADDR_BREDR;
+	ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type);
 	ev.key.type = key->type;
 	memcpy(ev.key.val, key->val, HCI_LINK_KEY_SIZE);
 	ev.key.pin_len = key->pin_len;
@@ -9574,7 +9585,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent)
 		ev.store_hint = persistent;
 
 	bacpy(&ev.key.addr.bdaddr, &key->bdaddr);
-	ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type);
+	ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type);
 	ev.key.type = mgmt_ltk_type(key);
 	ev.key.enc_size = key->enc_size;
 	ev.key.ediv = key->ediv;
@@ -9603,7 +9614,7 @@ void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent)
 
 	bacpy(&ev.rpa, &irk->rpa);
 	bacpy(&ev.irk.addr.bdaddr, &irk->bdaddr);
-	ev.irk.addr.type = link_to_bdaddr(LE_LINK, irk->addr_type);
+	ev.irk.addr.type = link_to_bdaddr(irk->link_type, irk->addr_type);
 	memcpy(ev.irk.val, irk->val, sizeof(irk->val));
 
 	mgmt_event(MGMT_EV_NEW_IRK, hdev, &ev, sizeof(ev), NULL);
@@ -9632,7 +9643,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk,
 		ev.store_hint = persistent;
 
 	bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr);
-	ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type);
+	ev.key.addr.type = link_to_bdaddr(csrk->link_type, csrk->bdaddr_type);
 	ev.key.type = csrk->type;
 	memcpy(ev.key.val, csrk->val, sizeof(csrk->val));
 
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 5f2f97de295eb6..1e7ea3a4b7ef32 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -1059,6 +1059,7 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 	}
 
 	if (smp->remote_irk) {
+		smp->remote_irk->link_type = hcon->type;
 		mgmt_new_irk(hdev, smp->remote_irk, persistent);
 
 		/* Now that user space can be considered to know the
@@ -1078,24 +1079,28 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 	}
 
 	if (smp->csrk) {
+		smp->csrk->link_type = hcon->type;
 		smp->csrk->bdaddr_type = hcon->dst_type;
 		bacpy(&smp->csrk->bdaddr, &hcon->dst);
 		mgmt_new_csrk(hdev, smp->csrk, persistent);
 	}
 
 	if (smp->responder_csrk) {
+		smp->responder_csrk->link_type = hcon->type;
 		smp->responder_csrk->bdaddr_type = hcon->dst_type;
 		bacpy(&smp->responder_csrk->bdaddr, &hcon->dst);
 		mgmt_new_csrk(hdev, smp->responder_csrk, persistent);
 	}
 
 	if (smp->ltk) {
+		smp->ltk->link_type = hcon->type;
 		smp->ltk->bdaddr_type = hcon->dst_type;
 		bacpy(&smp->ltk->bdaddr, &hcon->dst);
 		mgmt_new_ltk(hdev, smp->ltk, persistent);
 	}
 
 	if (smp->responder_ltk) {
+		smp->responder_ltk->link_type = hcon->type;
 		smp->responder_ltk->bdaddr_type = hcon->dst_type;
 		bacpy(&smp->responder_ltk->bdaddr, &hcon->dst);
 		mgmt_new_ltk(hdev, smp->responder_ltk, persistent);
@@ -1115,6 +1120,8 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 		key = hci_add_link_key(hdev, smp->conn->hcon, &hcon->dst,
 				       smp->link_key, type, 0, &persistent);
 		if (key) {
+			key->link_type = hcon->type;
+			key->bdaddr_type = hcon->dst_type;
 			mgmt_new_link_key(hdev, key, persistent);
 
 			/* Don't keep debug keys around if the relevant
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 0841f8d824198d..c9fdcc5cdce10d 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -503,9 +503,8 @@ out:
  * architecture dependent calling conventions. 7+ can be supported in the
  * future.
  */
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
+
 __bpf_kfunc int bpf_fentry_test1(int a)
 {
 	return a + 1;
@@ -605,7 +604,7 @@ __bpf_kfunc void bpf_kfunc_call_memb_release(struct prog_test_member *p)
 {
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(bpf_test_modify_return_ids)
 BTF_ID_FLAGS(func, bpf_modify_return_test)
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index 8f19253024b0aa..74136021955257 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -135,3 +135,4 @@ static void __exit ebtable_broute_fini(void)
 module_init(ebtable_broute_init);
 module_exit(ebtable_broute_fini);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Force packets to be routed instead of bridged");
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index 278f324e67524a..dacd81b12e6264 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -116,3 +116,4 @@ static void __exit ebtable_filter_fini(void)
 module_init(ebtable_filter_init);
 module_exit(ebtable_filter_fini);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ebtables legacy filter table");
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index 9066f7f376d57e..0f2a8c6118d42e 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -116,3 +116,4 @@ static void __exit ebtable_nat_fini(void)
 module_init(ebtable_nat_init);
 module_exit(ebtable_nat_fini);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ebtables legacy stateless nat table");
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index aa23479b20b2ae..99d82676f780ac 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -2595,3 +2595,4 @@ EXPORT_SYMBOL(ebt_do_table);
 module_init(ebtables_init);
 module_exit(ebtables_fini);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ebtables legacy core");
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index 71056ee847736b..abb090f94ed260 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -37,7 +37,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
 	ktime_t tstamp = skb->tstamp;
 	struct ip_frag_state state;
 	struct iphdr *iph;
-	int err;
+	int err = 0;
 
 	/* for offloaded checksums cleanup checksum before fragmentation */
 	if (skb->ip_summed == CHECKSUM_PARTIAL &&
@@ -416,3 +416,4 @@ module_exit(nf_conntrack_l3proto_bridge_fini);
 
 MODULE_ALIAS("nf_conntrack-" __stringify(AF_BRIDGE));
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Bridge IPv4 and IPv6 connection tracking");
diff --git a/net/core/dev.c b/net/core/dev.c
index 0d548431f3fadf..ad20bebe153fc7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1119,7 +1119,9 @@ static int __dev_alloc_name(struct net *net, const char *name, char *res)
 	if (i == max_netdevices)
 		return -ENFILE;
 
-	snprintf(res, IFNAMSIZ, name, i);
+	/* 'res' and 'name' could overlap, use 'buf' as an intermediate buffer */
+	strscpy(buf, name, IFNAMSIZ);
+	snprintf(res, IFNAMSIZ, buf, i);
 	return i;
 }
 
@@ -3470,6 +3472,9 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
 	if (gso_segs > READ_ONCE(dev->gso_max_segs))
 		return features & ~NETIF_F_GSO_MASK;
 
+	if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size)))
+		return features & ~NETIF_F_GSO_MASK;
+
 	if (!skb_shinfo(skb)->gso_type) {
 		skb_warn_bad_offload(skb);
 		return features & ~NETIF_F_GSO_MASK;
@@ -10049,6 +10054,54 @@ void netif_tx_stop_all_queues(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_tx_stop_all_queues);
 
+static int netdev_do_alloc_pcpu_stats(struct net_device *dev)
+{
+	void __percpu *v;
+
+	/* Drivers implementing ndo_get_peer_dev must support tstat
+	 * accounting, so that skb_do_redirect() can bump the dev's
+	 * RX stats upon network namespace switch.
+	 */
+	if (dev->netdev_ops->ndo_get_peer_dev &&
+	    dev->pcpu_stat_type != NETDEV_PCPU_STAT_TSTATS)
+		return -EOPNOTSUPP;
+
+	switch (dev->pcpu_stat_type) {
+	case NETDEV_PCPU_STAT_NONE:
+		return 0;
+	case NETDEV_PCPU_STAT_LSTATS:
+		v = dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
+		break;
+	case NETDEV_PCPU_STAT_TSTATS:
+		v = dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+		break;
+	case NETDEV_PCPU_STAT_DSTATS:
+		v = dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return v ? 0 : -ENOMEM;
+}
+
+static void netdev_do_free_pcpu_stats(struct net_device *dev)
+{
+	switch (dev->pcpu_stat_type) {
+	case NETDEV_PCPU_STAT_NONE:
+		return;
+	case NETDEV_PCPU_STAT_LSTATS:
+		free_percpu(dev->lstats);
+		break;
+	case NETDEV_PCPU_STAT_TSTATS:
+		free_percpu(dev->tstats);
+		break;
+	case NETDEV_PCPU_STAT_DSTATS:
+		free_percpu(dev->dstats);
+		break;
+	}
+}
+
 /**
  * register_netdevice() - register a network device
  * @dev: device to register
@@ -10109,9 +10162,13 @@ int register_netdevice(struct net_device *dev)
 		goto err_uninit;
 	}
 
+	ret = netdev_do_alloc_pcpu_stats(dev);
+	if (ret)
+		goto err_uninit;
+
 	ret = dev_index_reserve(net, dev->ifindex);
 	if (ret < 0)
-		goto err_uninit;
+		goto err_free_pcpu;
 	dev->ifindex = ret;
 
 	/* Transfer changeable features to wanted_features and enable
@@ -10217,6 +10274,8 @@ err_uninit_notify:
 	call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev);
 err_ifindex_release:
 	dev_index_release(net, dev->ifindex);
+err_free_pcpu:
+	netdev_do_free_pcpu_stats(dev);
 err_uninit:
 	if (dev->netdev_ops->ndo_uninit)
 		dev->netdev_ops->ndo_uninit(dev);
@@ -10469,6 +10528,7 @@ void netdev_run_todo(void)
 		WARN_ON(rcu_access_pointer(dev->ip_ptr));
 		WARN_ON(rcu_access_pointer(dev->ip6_ptr));
 
+		netdev_do_free_pcpu_stats(dev);
 		if (dev->priv_destructor)
 			dev->priv_destructor(dev);
 		if (dev->needs_free_netdev)
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index aff31cd944c29d..b240d9aae4a643 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -183,7 +183,7 @@ out:
 }
 
 static const struct genl_multicast_group dropmon_mcgrps[] = {
-	{ .name = "events", },
+	{ .name = "events", .cap_sys_admin = 1 },
 };
 
 static void send_dm_alert(struct work_struct *work)
@@ -1619,11 +1619,13 @@ static const struct genl_small_ops dropmon_ops[] = {
 		.cmd = NET_DM_CMD_START,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = net_dm_cmd_trace,
+		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NET_DM_CMD_STOP,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = net_dm_cmd_trace,
+		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NET_DM_CMD_CONFIG_GET,
diff --git a/net/core/filter.c b/net/core/filter.c
index 21d75108c2e94b..1737884be52f85 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -81,6 +81,7 @@
 #include <net/xdp.h>
 #include <net/mptcp.h>
 #include <net/netfilter/nf_conntrack_bpf.h>
+#include <net/netkit.h>
 #include <linux/un.h>
 
 #include "dev.h"
@@ -2468,6 +2469,16 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = {
 DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
 EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
 
+static struct net_device *skb_get_peer_dev(struct net_device *dev)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (likely(ops->ndo_get_peer_dev))
+		return INDIRECT_CALL_1(ops->ndo_get_peer_dev,
+				       netkit_peer_dev, dev);
+	return NULL;
+}
+
 int skb_do_redirect(struct sk_buff *skb)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
@@ -2481,17 +2492,15 @@ int skb_do_redirect(struct sk_buff *skb)
 	if (unlikely(!dev))
 		goto out_drop;
 	if (flags & BPF_F_PEER) {
-		const struct net_device_ops *ops = dev->netdev_ops;
-
-		if (unlikely(!ops->ndo_get_peer_dev ||
-			     !skb_at_tc_ingress(skb)))
+		if (unlikely(!skb_at_tc_ingress(skb)))
 			goto out_drop;
-		dev = ops->ndo_get_peer_dev(dev);
+		dev = skb_get_peer_dev(dev);
 		if (unlikely(!dev ||
 			     !(dev->flags & IFF_UP) ||
 			     net_eq(net, dev_net(dev))))
 			goto out_drop;
 		skb->dev = dev;
+		dev_sw_netstats_rx_add(dev, skb->len);
 		return -EAGAIN;
 	}
 	return flags & BPF_F_NEIGH ?
@@ -2593,6 +2602,22 @@ BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg *, msg, u32, bytes)
 	return 0;
 }
 
+static void sk_msg_reset_curr(struct sk_msg *msg)
+{
+	u32 i = msg->sg.start;
+	u32 len = 0;
+
+	do {
+		len += sk_msg_elem(msg, i)->length;
+		sk_msg_iter_var_next(i);
+		if (len >= msg->sg.size)
+			break;
+	} while (i != msg->sg.end);
+
+	msg->sg.curr = i;
+	msg->sg.copybreak = 0;
+}
+
 static const struct bpf_func_proto bpf_msg_cork_bytes_proto = {
 	.func           = bpf_msg_cork_bytes,
 	.gpl_only       = false,
@@ -2712,6 +2737,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
 		      msg->sg.end - shift + NR_MSG_FRAG_IDS :
 		      msg->sg.end - shift;
 out:
+	sk_msg_reset_curr(msg);
 	msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset;
 	msg->data_end = msg->data + bytes;
 	return 0;
@@ -2848,6 +2874,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
 		msg->sg.data[new] = rsge;
 	}
 
+	sk_msg_reset_curr(msg);
 	sk_msg_compute_data_pointers(msg);
 	return 0;
 }
@@ -3016,6 +3043,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
 
 	sk_mem_uncharge(msg->sk, len - pop);
 	msg->sg.size -= (len - pop);
+	sk_msg_reset_curr(msg);
 	sk_msg_compute_data_pointers(msg);
 	return 0;
 }
@@ -11767,9 +11795,7 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id)
 	return func;
 }
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 __bpf_kfunc int bpf_dynptr_from_skb(struct sk_buff *skb, u64 flags,
 				    struct bpf_dynptr_kern *ptr__uninit)
 {
@@ -11816,7 +11842,7 @@ __bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern,
 
 	return 0;
 }
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
 			       struct bpf_dynptr_kern *ptr__uninit)
@@ -11879,10 +11905,7 @@ static int __init bpf_kfunc_init(void)
 }
 late_initcall(bpf_kfunc_init);
 
-/* Disables missing prototype warnings */
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 /* bpf_sock_destroy: Destroy the given socket with ECONNABORTED error code.
  *
@@ -11916,7 +11939,7 @@ __bpf_kfunc int bpf_sock_destroy(struct sock_common *sock)
 	return sk->sk_prot->diag_destroy(sk, ECONNABORTED);
 }
 
-__diag_pop()
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(bpf_sk_iter_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_sock_destroy, KF_TRUSTED_ARGS)
diff --git a/net/core/gso_test.c b/net/core/gso_test.c
index ceb684be4cbf86..4c2e77bd12f4b1 100644
--- a/net/core/gso_test.c
+++ b/net/core/gso_test.c
@@ -180,18 +180,17 @@ static void gso_test_func(struct kunit *test)
 	}
 
 	if (tcase->frag_skbs) {
-		unsigned int total_size = 0, total_true_size = 0, alloc_size = 0;
+		unsigned int total_size = 0, total_true_size = 0;
 		struct sk_buff *frag_skb, *prev = NULL;
 
-		page = alloc_page(GFP_KERNEL);
-		KUNIT_ASSERT_NOT_NULL(test, page);
-		page_ref_add(page, tcase->nr_frag_skbs - 1);
-
 		for (i = 0; i < tcase->nr_frag_skbs; i++) {
 			unsigned int frag_size;
 
+			page = alloc_page(GFP_KERNEL);
+			KUNIT_ASSERT_NOT_NULL(test, page);
+
 			frag_size = tcase->frag_skbs[i];
-			frag_skb = build_skb(page_address(page) + alloc_size,
+			frag_skb = build_skb(page_address(page),
 					     frag_size + shinfo_size);
 			KUNIT_ASSERT_NOT_NULL(test, frag_skb);
 			__skb_put(frag_skb, frag_size);
@@ -204,11 +203,8 @@ static void gso_test_func(struct kunit *test)
 
 			total_size += frag_size;
 			total_true_size += frag_skb->truesize;
-			alloc_size += frag_size + shinfo_size;
 		}
 
-		KUNIT_ASSERT_LE(test, alloc_size, PAGE_SIZE);
-
 		skb->len += total_size;
 		skb->data_len += total_size;
 		skb->truesize += total_true_size;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index df81c1f0a57047..552719c3bbc3d7 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -253,9 +253,11 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 {
 	int max_clean = atomic_read(&tbl->gc_entries) -
 			READ_ONCE(tbl->gc_thresh2);
+	u64 tmax = ktime_get_ns() + NSEC_PER_MSEC;
 	unsigned long tref = jiffies - 5 * HZ;
 	struct neighbour *n, *tmp;
 	int shrunk = 0;
+	int loop = 0;
 
 	NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs);
 
@@ -278,11 +280,16 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 				shrunk++;
 			if (shrunk >= max_clean)
 				break;
+			if (++loop == 16) {
+				if (ktime_get_ns() > tmax)
+					goto unlock;
+				loop = 0;
+			}
 		}
 	}
 
 	WRITE_ONCE(tbl->last_flush, jiffies);
-
+unlock:
 	write_unlock_bh(&tbl->lock);
 
 	return shrunk;
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 5e409b98aba0f0..dec5443372360b 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -217,8 +217,12 @@ static int page_pool_init(struct page_pool *pool,
 		return -ENOMEM;
 #endif
 
-	if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0)
+	if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) {
+#ifdef CONFIG_PAGE_POOL_STATS
+		free_percpu(pool->recycle_stats);
+#endif
 		return -ENOMEM;
+	}
 
 	atomic_set(&pool->pages_state_release_cnt, 0);
 
diff --git a/net/core/scm.c b/net/core/scm.c
index 880027ecf51650..7dc47c17d8638a 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -26,6 +26,7 @@
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
 #include <linux/errqueue.h>
+#include <linux/io_uring.h>
 
 #include <linux/uaccess.h>
 
@@ -103,6 +104,11 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
 
 		if (fd < 0 || !(file = fget_raw(fd)))
 			return -EBADF;
+		/* don't allow io_uring files */
+		if (io_uring_get_socket(file)) {
+			fput(file);
+			return -EINVAL;
+		}
 		*fpp++ = file;
 		fpl->count++;
 	}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b157efea5dea88..94cc40a6f79756 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4522,8 +4522,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 		/* GSO partial only requires that we trim off any excess that
 		 * doesn't fit into an MSS sized block, so take care of that
 		 * now.
+		 * Cap len to not accidentally hit GSO_BY_FRAGS.
 		 */
-		partial_segs = len / mss;
+		partial_segs = min(len, GSO_BY_FRAGS - 1) / mss;
 		if (partial_segs > 1)
 			mss *= partial_segs;
 		else
@@ -4824,7 +4825,9 @@ static __always_inline unsigned int skb_ext_total_length(void)
 static void skb_extensions_init(void)
 {
 	BUILD_BUG_ON(SKB_EXT_NUM >= 8);
+#if !IS_ENABLED(CONFIG_KCOV_INSTRUMENT_ALL)
 	BUILD_BUG_ON(skb_ext_total_length() > 255);
+#endif
 
 	skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache",
 					     SKB_EXT_ALIGN_VALUE * skb_ext_total_length(),
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 6c31eefbd77786..93ecfceac1bc49 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -826,6 +826,8 @@ static void sk_psock_destroy(struct work_struct *work)
 
 	if (psock->sk_redir)
 		sock_put(psock->sk_redir);
+	if (psock->sk_pair)
+		sock_put(psock->sk_pair);
 	sock_put(psock->sk);
 	kfree(psock);
 }
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 4292c2ed182866..27d733c0f65e16 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -536,6 +536,8 @@ static bool sock_map_sk_state_allowed(const struct sock *sk)
 {
 	if (sk_is_tcp(sk))
 		return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN);
+	if (sk_is_stream_unix(sk))
+		return (1 << sk->sk_state) & TCPF_ESTABLISHED;
 	return true;
 }
 
diff --git a/net/core/stream.c b/net/core/stream.c
index 96fbcb9bbb30a5..b16dfa568a2d5b 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -79,7 +79,7 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
 		remove_wait_queue(sk_sleep(sk), &wait);
 		sk->sk_write_pending--;
 	} while (!done);
-	return 0;
+	return done < 0 ? done : 0;
 }
 EXPORT_SYMBOL(sk_stream_wait_connect);
 
diff --git a/net/core/xdp.c b/net/core/xdp.c
index df4789ab512d72..b6f1d6dab3f2e3 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -696,9 +696,7 @@ struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf)
 	return nxdpf;
 }
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
 
 /**
  * bpf_xdp_metadata_rx_timestamp - Read XDP frame RX timestamp.
@@ -738,7 +736,7 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return -EOPNOTSUPP;
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(xdp_metadata_kfunc_ids)
 #define XDP_METADATA_KFUNC(_, __, name, ___) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS)
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 1b8cbfda6e5dbd..44b033fe1ef685 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -629,9 +629,6 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (dccp_parse_options(sk, dreq, skb))
 		goto drop_and_free;
 
-	if (security_inet_conn_request(sk, skb, req))
-		goto drop_and_free;
-
 	ireq = inet_rsk(req);
 	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
 	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
@@ -639,6 +636,9 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	ireq->ireq_family = AF_INET;
 	ireq->ir_iif = READ_ONCE(sk->sk_bound_dev_if);
 
+	if (security_inet_conn_request(sk, skb, req))
+		goto drop_and_free;
+
 	/*
 	 * Step 3: Process LISTEN state
 	 *
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 8d344b219f84ae..4550b680665a57 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -360,15 +360,15 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (dccp_parse_options(sk, dreq, skb))
 		goto drop_and_free;
 
-	if (security_inet_conn_request(sk, skb, req))
-		goto drop_and_free;
-
 	ireq = inet_rsk(req);
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
 	ireq->ireq_family = AF_INET6;
 	ireq->ir_mark = inet_request_mark(sk, skb);
 
+	if (security_inet_conn_request(sk, skb, req))
+		goto drop_and_free;
+
 	if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) ||
 	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
 	    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c
index 9cbae016924989..788dfdc498a955 100644
--- a/net/devlink/netlink_gen.c
+++ b/net/devlink/netlink_gen.c
@@ -15,7 +15,7 @@ const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_
 	[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY, },
 	[DEVLINK_PORT_FN_ATTR_STATE] = NLA_POLICY_MAX(NLA_U8, 1),
 	[DEVLINK_PORT_FN_ATTR_OPSTATE] = NLA_POLICY_MAX(NLA_U8, 1),
-	[DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(3),
+	[DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(15),
 };
 
 const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1] = {
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index 01e54b46ae0b97..2a6d363763a2bc 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -91,6 +91,7 @@ const struct cred *dns_resolver_cache;
 static int
 dns_resolver_preparse(struct key_preparsed_payload *prep)
 {
+	const struct dns_server_list_v1_header *v1;
 	const struct dns_payload_header *bin;
 	struct user_key_payload *upayload;
 	unsigned long derrno;
@@ -122,6 +123,13 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
 			return -EINVAL;
 		}
 
+		v1 = (const struct dns_server_list_v1_header *)bin;
+		if ((v1->status != DNS_LOOKUP_GOOD &&
+		     v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) {
+			if (prep->expiry == TIME64_MAX)
+				prep->expiry = ktime_get_real_seconds() + 1;
+		}
+
 		result_len = datalen;
 		goto store_result;
 	}
@@ -314,7 +322,7 @@ static long dns_resolver_read(const struct key *key,
 
 struct key_type key_type_dns_resolver = {
 	.name		= "dns_resolver",
-	.flags		= KEY_TYPE_NET_DOMAIN,
+	.flags		= KEY_TYPE_NET_DOMAIN | KEY_TYPE_INSTANT_REAP,
 	.preparse	= dns_resolver_preparse,
 	.free_preparse	= dns_resolver_free_preparse,
 	.instantiate	= generic_key_instantiate,
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 3bbd5afb7b31cf..fe3553f60bf39e 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -505,6 +505,7 @@ static int ethnl_default_dumpit(struct sk_buff *skb,
 				ret = skb->len;
 			break;
 		}
+		ret = 0;
 	}
 	rtnl_unlock();
 
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index b71dab630a8732..80cdc6f6b34c97 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -342,9 +342,7 @@ struct sk_buff *prp_create_tagged_frame(struct hsr_frame_info *frame,
 	skb = skb_copy_expand(frame->skb_std, 0,
 			      skb_tailroom(frame->skb_std) + HSR_HLEN,
 			      GFP_ATOMIC);
-	prp_fill_rct(skb, frame, port);
-
-	return skb;
+	return prp_fill_rct(skb, frame, port);
 }
 
 static void hsr_deliver_master(struct sk_buff *skb, struct net_device *dev,
diff --git a/net/ife/ife.c b/net/ife/ife.c
index 13bbf8cb6a3961..be05b690b9ef29 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -82,6 +82,7 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen)
 	if (unlikely(!pskb_may_pull(skb, total_pull)))
 		return NULL;
 
+	ifehdr = (struct ifeheadr *)(skb->data + skb->dev->hard_header_len);
 	skb_set_mac_header(skb, total_pull);
 	__skb_pull(skb, total_pull);
 	*metalen = ifehdrln - IFE_METAHDRLEN;
diff --git a/net/ipv4/fou_bpf.c b/net/ipv4/fou_bpf.c
index 3760a14b6b576b..4da03bf45c9b75 100644
--- a/net/ipv4/fou_bpf.c
+++ b/net/ipv4/fou_bpf.c
@@ -22,9 +22,7 @@ enum bpf_fou_encap_type {
 	FOU_BPF_ENCAP_GUE,
 };
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in BTF");
+__bpf_kfunc_start_defs();
 
 /* bpf_skb_set_fou_encap - Set FOU encap parameters
  *
@@ -100,7 +98,7 @@ __bpf_kfunc int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx,
 	return 0;
 }
 
-__diag_pop()
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(fou_kfunc_set)
 BTF_ID_FLAGS(func, bpf_skb_set_fou_encap)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 76c3ea75b8ddc0..efeeca2b13285a 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -216,8 +216,10 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
 	int tv = get_random_u32_below(max_delay);
 
 	im->tm_running = 1;
-	if (!mod_timer(&im->timer, jiffies+tv+2))
-		refcount_inc(&im->refcnt);
+	if (refcount_inc_not_zero(&im->refcnt)) {
+		if (mod_timer(&im->timer, jiffies + tv + 2))
+			ip_ma_put(im);
+	}
 }
 
 static void igmp_gq_start_timer(struct in_device *in_dev)
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index f01aee832aab2f..7d0e7aaa71e0a1 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -1481,5 +1481,6 @@ static void __exit inet_diag_exit(void)
 module_init(inet_diag_init);
 module_exit(inet_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("INET/INET6: socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2 /* AF_INET */);
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10 /* AF_INET6 */);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 598c1b114d2c22..a532f749e47781 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -751,12 +751,12 @@ int __inet_hash(struct sock *sk, struct sock *osk)
 		if (err)
 			goto unlock;
 	}
+	sock_set_flag(sk, SOCK_RCU_FREE);
 	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
 		sk->sk_family == AF_INET6)
 		__sk_nulls_add_node_tail_rcu(sk, &ilb2->nulls_head);
 	else
 		__sk_nulls_add_node_rcu(sk, &ilb2->nulls_head);
-	sock_set_flag(sk, SOCK_RCU_FREE);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
 unlock:
 	spin_unlock(&ilb2->lock);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 22a26d1d29a09d..5169c3c72cffe4 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -635,15 +635,18 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 	}
 
 	if (dev->header_ops) {
+		int pull_len = tunnel->hlen + sizeof(struct iphdr);
+
 		if (skb_cow_head(skb, 0))
 			goto free_skb;
 
 		tnl_params = (const struct iphdr *)skb->data;
 
-		/* Pull skb since ip_tunnel_xmit() needs skb->data pointing
-		 * to gre header.
-		 */
-		skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
+		if (!pskb_network_may_pull(skb, pull_len))
+			goto free_skb;
+
+		/* ip_tunnel_xmit() needs skb->data pointing to gre header. */
+		skb_pull(skb, pull_len);
 		skb_reset_mac_header(skb);
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL &&
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index 56f6ecc43451ec..4d42d0756fd70c 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -170,3 +170,4 @@ module_init(iptable_nat_init);
 module_exit(iptable_nat_exit);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("iptables legacy nat table");
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index ca5e5b21587cda..0e7f53964d0af6 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -108,3 +108,4 @@ static void __exit iptable_raw_fini(void)
 module_init(iptable_raw_init);
 module_exit(iptable_raw_fini);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("iptables legacy raw table");
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 265b39bc435b4c..482e733c337582 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -186,3 +186,4 @@ module_init(nf_defrag_init);
 module_exit(nf_defrag_fini);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv4 defragmentation support");
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index f33aeab9424f75..f01b038fc1cda0 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -336,3 +336,4 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook)
 EXPORT_SYMBOL_GPL(nf_send_unreach);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv4 packet rejection core");
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
index 63a40e4b678f59..fe2140c8375c8e 100644
--- a/net/ipv4/raw_diag.c
+++ b/net/ipv4/raw_diag.c
@@ -257,5 +257,6 @@ static void __exit raw_diag_exit(void)
 module_init(raw_diag_init);
 module_exit(raw_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RAW socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-255 /* AF_INET - IPPROTO_RAW */);
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10-255 /* AF_INET6 - IPPROTO_RAW */);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 3290a4442b4ac7..16615d107cf06f 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -780,7 +780,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 			goto reject_redirect;
 	}
 
-	n = __ipv4_neigh_lookup(rt->dst.dev, new_gw);
+	n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw);
 	if (!n)
 		n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev);
 	if (!IS_ERR(n)) {
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 98b25e5d147bac..d37282c06e3da0 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -306,7 +306,7 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 	treq->af_specific = af_ops;
 
 	treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
-	treq->req_usec_ts = -1;
+	treq->req_usec_ts = false;
 
 #if IS_ENABLED(CONFIG_MPTCP)
 	treq->is_mptcp = sk_is_mptcp(sk);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 53bcc17c91e4c4..ff6838ca2e5806 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3368,9 +3368,25 @@ int tcp_set_window_clamp(struct sock *sk, int val)
 			return -EINVAL;
 		tp->window_clamp = 0;
 	} else {
-		tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
-			SOCK_MIN_RCVBUF / 2 : val;
-		tp->rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp);
+		u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp;
+		u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
+						SOCK_MIN_RCVBUF / 2 : val;
+
+		if (new_window_clamp == old_window_clamp)
+			return 0;
+
+		tp->window_clamp = new_window_clamp;
+		if (new_window_clamp < old_window_clamp) {
+			/* need to apply the reserved mem provisioning only
+			 * when shrinking the window clamp
+			 */
+			__tcp_adjust_rcv_ssthresh(sk, tp->window_clamp);
+
+		} else {
+			new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp);
+			tp->rcv_ssthresh = max(new_rcv_ssthresh,
+					       tp->rcv_ssthresh);
+		}
 	}
 	return 0;
 }
@@ -3594,6 +3610,10 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case TCP_AO_REPAIR:
+		if (!tcp_can_repair_sock(sk)) {
+			err = -EPERM;
+			break;
+		}
 		err = tcp_ao_set_repair(sk, optval, optlen);
 		break;
 #ifdef CONFIG_TCP_AO
@@ -4293,6 +4313,8 @@ zerocopy_rcv_out:
 	}
 #endif
 	case TCP_AO_REPAIR:
+		if (!tcp_can_repair_sock(sk))
+			return -EPERM;
 		return tcp_ao_get_repair(sk, optval, optlen);
 	case TCP_AO_GET_KEYS:
 	case TCP_AO_INFO: {
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index ef5472ed615887..f8308d3f565e9d 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -851,7 +851,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
 	const struct tcp_ao_hdr *aoh;
 	struct tcp_ao_key *key;
 
-	treq->maclen = 0;
+	treq->used_tcp_ao = false;
 
 	if (tcp_parse_auth_options(th, NULL, &aoh) || !aoh)
 		return;
@@ -863,7 +863,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
 
 	treq->ao_rcv_next = aoh->keyid;
 	treq->ao_keyid = aoh->rnext_keyid;
-	treq->maclen = tcp_ao_maclen(key);
+	treq->used_tcp_ao = true;
 }
 
 static enum skb_drop_reason
@@ -1100,7 +1100,7 @@ void tcp_ao_connect_init(struct sock *sk)
 			ao_info->current_key = key;
 		if (!ao_info->rnext_key)
 			ao_info->rnext_key = key;
-		tp->tcp_header_len += tcp_ao_len(key);
+		tp->tcp_header_len += tcp_ao_len_aligned(key);
 
 		ao_info->lisn = htonl(tp->write_seq);
 		ao_info->snd_sne = 0;
@@ -1315,7 +1315,8 @@ static int tcp_ao_parse_crypto(struct tcp_ao_add *cmd, struct tcp_ao_key *key)
 	key->maclen = cmd->maclen ?: 12; /* 12 is the default in RFC5925 */
 
 	/* Check: maclen + tcp-ao header <= (MAX_TCP_OPTION_SPACE - mss
-	 *					- tstamp - wscale - sackperm),
+	 *					- tstamp (including sackperm)
+	 *					- wscale),
 	 * see tcp_syn_options(), tcp_synack_options(), commit 33ad798c924b.
 	 *
 	 * In order to allow D-SACK with TCP-AO, the header size should be:
@@ -1342,10 +1343,10 @@ static int tcp_ao_parse_crypto(struct tcp_ao_add *cmd, struct tcp_ao_key *key)
 	 * large to leave sufficient option space.
 	 */
 	syn_tcp_option_space = MAX_TCP_OPTION_SPACE;
+	syn_tcp_option_space -= TCPOLEN_MSS_ALIGNED;
 	syn_tcp_option_space -= TCPOLEN_TSTAMP_ALIGNED;
 	syn_tcp_option_space -= TCPOLEN_WSCALE_ALIGNED;
-	syn_tcp_option_space -= TCPOLEN_SACKPERM_ALIGNED;
-	if (tcp_ao_len(key) > syn_tcp_option_space) {
+	if (tcp_ao_len_aligned(key) > syn_tcp_option_space) {
 		err = -EMSGSIZE;
 		goto err_kfree;
 	}
@@ -1607,6 +1608,15 @@ static int tcp_ao_add_cmd(struct sock *sk, unsigned short int family,
 		if (!dev || !l3index)
 			return -EINVAL;
 
+		if (!bound_dev_if || bound_dev_if != cmd.ifindex) {
+			/* tcp_ao_established_key() doesn't expect having
+			 * non peer-matching key on an established TCP-AO
+			 * connection.
+			 */
+			if (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)))
+				return -EINVAL;
+		}
+
 		/* It's still possible to bind after adding keys or even
 		 * re-bind to a different dev (with CAP_NET_RAW).
 		 * So, no reason to return error here, rather try to be
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 01b50fa7918988..4cbe4b44425a6a 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -247,4 +247,5 @@ static void __exit tcp_diag_exit(void)
 module_init(tcp_diag_init);
 module_exit(tcp_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("TCP socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-6 /* AF_INET - IPPROTO_TCP */);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 50aaa1527150bd..701cb87043f280 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3871,8 +3871,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	 * then we can probably ignore it.
 	 */
 	if (before(ack, prior_snd_una)) {
+		u32 max_window;
+
+		/* do not accept ACK for bytes we never sent. */
+		max_window = min_t(u64, tp->max_window, tp->bytes_acked);
 		/* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */
-		if (before(ack, prior_snd_una - tp->max_window)) {
+		if (before(ack, prior_snd_una - max_window)) {
 			if (!(flag & FLAG_NO_CHALLENGE_ACK))
 				tcp_send_challenge_ack(sk);
 			return -SKB_DROP_REASON_TCP_TOO_OLD_ACK;
@@ -4364,6 +4368,23 @@ EXPORT_SYMBOL(tcp_do_parse_auth_options);
  * up to bandwidth of 18Gigabit/sec. 8) ]
  */
 
+/* Estimates max number of increments of remote peer TSval in
+ * a replay window (based on our current RTO estimation).
+ */
+static u32 tcp_tsval_replay(const struct sock *sk)
+{
+	/* If we use usec TS resolution,
+	 * then expect the remote peer to use the same resolution.
+	 */
+	if (tcp_sk(sk)->tcp_usec_ts)
+		return inet_csk(sk)->icsk_rto * (USEC_PER_SEC / HZ);
+
+	/* RFC 7323 recommends a TSval clock between 1ms and 1sec.
+	 * We know that some OS (including old linux) can use 1200 Hz.
+	 */
+	return inet_csk(sk)->icsk_rto * 1200 / HZ;
+}
+
 static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -4371,7 +4392,7 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
 	u32 seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
 
-	return (/* 1. Pure ACK with correct sequence number. */
+	return	/* 1. Pure ACK with correct sequence number. */
 		(th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) &&
 
 		/* 2. ... and duplicate ACK. */
@@ -4381,7 +4402,8 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
 		!tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) &&
 
 		/* 4. ... and sits in replay window. */
-		(s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ);
+		(s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <=
+		tcp_tsval_replay(sk);
 }
 
 static inline bool tcp_paws_discard(const struct sock *sk,
@@ -7115,7 +7137,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	req->syncookie = want_cookie;
 	tcp_rsk(req)->af_specific = af_ops;
 	tcp_rsk(req)->ts_off = 0;
-	tcp_rsk(req)->req_usec_ts = -1;
+	tcp_rsk(req)->req_usec_ts = false;
 #if IS_ENABLED(CONFIG_MPTCP)
 	tcp_rsk(req)->is_mptcp = 0;
 #endif
@@ -7143,9 +7165,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if (!dst)
 		goto drop_and_free;
 
-	if (tmp_opt.tstamp_ok)
+	if (tmp_opt.tstamp_ok) {
+		tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst);
 		tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb);
-
+	}
 	if (!want_cookie && !isn) {
 		int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog);
 
@@ -7181,11 +7204,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh))
 		goto drop_and_release; /* Invalid TCP options */
 	if (aoh) {
-		tcp_rsk(req)->maclen = aoh->length - sizeof(struct tcp_ao_hdr);
+		tcp_rsk(req)->used_tcp_ao = true;
 		tcp_rsk(req)->ao_rcv_next = aoh->keyid;
 		tcp_rsk(req)->ao_keyid = aoh->rnext_keyid;
+
 	} else {
-		tcp_rsk(req)->maclen = 0;
+		tcp_rsk(req)->used_tcp_ao = false;
 	}
 #endif
 	tcp_rsk(req)->snt_isn = isn;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5f693bbd578d22..0c50c5a32b84a3 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -690,7 +690,7 @@ static bool tcp_v4_ao_sign_reset(const struct sock *sk, struct sk_buff *skb,
 
 	reply_options[0] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key) << 16) |
 				 (aoh->rnext_keyid << 8) | keyid);
-	arg->iov[0].iov_len += round_up(tcp_ao_len(key), 4);
+	arg->iov[0].iov_len += tcp_ao_len_aligned(key);
 	reply->doff = arg->iov[0].iov_len / 4;
 
 	if (tcp_ao_hash_hdr(AF_INET, (char *)&reply_options[1],
@@ -978,7 +978,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
 					  (tcp_ao_len(key->ao_key) << 16) |
 					  (key->ao_key->sndid << 8) |
 					  key->rcv_next);
-		arg.iov[0].iov_len += round_up(tcp_ao_len(key->ao_key), 4);
+		arg.iov[0].iov_len += tcp_ao_len_aligned(key->ao_key);
 		rep.th.doff = arg.iov[0].iov_len / 4;
 
 		tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset],
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index a9807eeb311ca6..9e85f2a0bddd49 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -615,7 +615,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	ao_key = treq->af_specific->ao_lookup(sk, req,
 				tcp_rsk(req)->ao_keyid, -1);
 	if (ao_key)
-		newtp->tcp_header_len += tcp_ao_len(ao_key);
+		newtp->tcp_header_len += tcp_ao_len_aligned(ao_key);
  #endif
 	if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
 		newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f558c054cf6e75..e3167ad965676f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -601,6 +601,44 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
 }
 #endif
 
+static __be32 *process_tcp_ao_options(struct tcp_sock *tp,
+				      const struct tcp_request_sock *tcprsk,
+				      struct tcp_out_options *opts,
+				      struct tcp_key *key, __be32 *ptr)
+{
+#ifdef CONFIG_TCP_AO
+	u8 maclen = tcp_ao_maclen(key->ao_key);
+
+	if (tcprsk) {
+		u8 aolen = maclen + sizeof(struct tcp_ao_hdr);
+
+		*ptr++ = htonl((TCPOPT_AO << 24) | (aolen << 16) |
+			       (tcprsk->ao_keyid << 8) |
+			       (tcprsk->ao_rcv_next));
+	} else {
+		struct tcp_ao_key *rnext_key;
+		struct tcp_ao_info *ao_info;
+
+		ao_info = rcu_dereference_check(tp->ao_info,
+			lockdep_sock_is_held(&tp->inet_conn.icsk_inet.sk));
+		rnext_key = READ_ONCE(ao_info->rnext_key);
+		if (WARN_ON_ONCE(!rnext_key))
+			return ptr;
+		*ptr++ = htonl((TCPOPT_AO << 24) |
+			       (tcp_ao_len(key->ao_key) << 16) |
+			       (key->ao_key->sndid << 8) |
+			       (rnext_key->rcvid));
+	}
+	opts->hash_location = (__u8 *)ptr;
+	ptr += maclen / sizeof(*ptr);
+	if (unlikely(maclen % sizeof(*ptr))) {
+		memset(ptr, TCPOPT_NOP, sizeof(*ptr));
+		ptr++;
+	}
+#endif
+	return ptr;
+}
+
 /* Write previously computed TCP options to the packet.
  *
  * Beware: Something in the Internet is very sensitive to the ordering of
@@ -629,37 +667,7 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
 		opts->hash_location = (__u8 *)ptr;
 		ptr += 4;
 	} else if (tcp_key_is_ao(key)) {
-#ifdef CONFIG_TCP_AO
-		u8 maclen = tcp_ao_maclen(key->ao_key);
-
-		if (tcprsk) {
-			u8 aolen = maclen + sizeof(struct tcp_ao_hdr);
-
-			*ptr++ = htonl((TCPOPT_AO << 24) | (aolen << 16) |
-				       (tcprsk->ao_keyid << 8) |
-				       (tcprsk->ao_rcv_next));
-		} else {
-			struct tcp_ao_key *rnext_key;
-			struct tcp_ao_info *ao_info;
-
-			ao_info = rcu_dereference_check(tp->ao_info,
-				lockdep_sock_is_held(&tp->inet_conn.icsk_inet.sk));
-			rnext_key = READ_ONCE(ao_info->rnext_key);
-			if (WARN_ON_ONCE(!rnext_key))
-				goto out_ao;
-			*ptr++ = htonl((TCPOPT_AO << 24) |
-				       (tcp_ao_len(key->ao_key) << 16) |
-				       (key->ao_key->sndid << 8) |
-				       (rnext_key->rcvid));
-		}
-		opts->hash_location = (__u8 *)ptr;
-		ptr += maclen / sizeof(*ptr);
-		if (unlikely(maclen % sizeof(*ptr))) {
-			memset(ptr, TCPOPT_NOP, sizeof(*ptr));
-			ptr++;
-		}
-out_ao:
-#endif
+		ptr = process_tcp_ao_options(tp, tcprsk, opts, key, ptr);
 	}
 	if (unlikely(opts->mss)) {
 		*ptr++ = htonl((TCPOPT_MSS << 24) |
@@ -817,7 +825,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 		timestamps = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps);
 		if (tcp_key_is_ao(key)) {
 			opts->options |= OPTION_AO;
-			remaining -= tcp_ao_len(key->ao_key);
+			remaining -= tcp_ao_len_aligned(key->ao_key);
 		}
 	}
 
@@ -907,7 +915,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 			ireq->tstamp_ok &= !ireq->sack_ok;
 	} else if (tcp_key_is_ao(key)) {
 		opts->options |= OPTION_AO;
-		remaining -= tcp_ao_len(key->ao_key);
+		remaining -= tcp_ao_len_aligned(key->ao_key);
 		ireq->tstamp_ok &= !ireq->sack_ok;
 	}
 
@@ -974,7 +982,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 		size += TCPOLEN_MD5SIG_ALIGNED;
 	} else if (tcp_key_is_ao(key)) {
 		opts->options |= OPTION_AO;
-		size += tcp_ao_len(key->ao_key);
+		size += tcp_ao_len_aligned(key->ao_key);
 	}
 
 	if (likely(tp->rx_opt.tstamp_ok)) {
@@ -3285,7 +3293,13 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 	if (skb_still_in_host_queue(sk, skb))
 		return -EBUSY;
 
+start:
 	if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
+		if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;
+			TCP_SKB_CB(skb)->seq++;
+			goto start;
+		}
 		if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
 			WARN_ON_ONCE(1);
 			return -EINVAL;
@@ -3693,8 +3707,6 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
 
 	memset(&opts, 0, sizeof(opts));
-	if (tcp_rsk(req)->req_usec_ts < 0)
-		tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst);
 	now = tcp_clock_ns();
 #ifdef CONFIG_SYN_COOKIES
 	if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok))
@@ -3714,7 +3726,6 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	if (tcp_rsk_used_ao(req)) {
 #ifdef CONFIG_TCP_AO
 		struct tcp_ao_key *ao_key = NULL;
-		u8 maclen = tcp_rsk(req)->maclen;
 		u8 keyid = tcp_rsk(req)->ao_keyid;
 
 		ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req),
@@ -3724,13 +3735,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 		 * for another peer-matching key, but the peer has requested
 		 * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here.
 		 */
-		if (unlikely(!ao_key || tcp_ao_maclen(ao_key) != maclen)) {
-			u8 key_maclen = ao_key ? tcp_ao_maclen(ao_key) : 0;
-
+		if (unlikely(!ao_key)) {
 			rcu_read_unlock();
 			kfree_skb(skb);
-			net_warn_ratelimited("TCP-AO: the keyid %u with maclen %u|%u from SYN packet is not present - not sending SYNACK\n",
-					     keyid, maclen, key_maclen);
+			net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n",
+					     keyid);
 			return NULL;
 		}
 		key.ao_key = ao_key;
diff --git a/net/ipv4/tcp_sigpool.c b/net/ipv4/tcp_sigpool.c
index 65a8eaae2fec6c..55b310a722c7d5 100644
--- a/net/ipv4/tcp_sigpool.c
+++ b/net/ipv4/tcp_sigpool.c
@@ -231,7 +231,7 @@ static void cpool_schedule_cleanup(struct kref *kref)
  */
 void tcp_sigpool_release(unsigned int id)
 {
-	if (WARN_ON_ONCE(id > cpool_populated || !cpool[id].alg))
+	if (WARN_ON_ONCE(id >= cpool_populated || !cpool[id].alg))
 		return;
 
 	/* slow-path */
@@ -245,7 +245,7 @@ EXPORT_SYMBOL_GPL(tcp_sigpool_release);
  */
 void tcp_sigpool_get(unsigned int id)
 {
-	if (WARN_ON_ONCE(id > cpool_populated || !cpool[id].alg))
+	if (WARN_ON_ONCE(id >= cpool_populated || !cpool[id].alg))
 		return;
 	kref_get(&cpool[id].kref);
 }
@@ -256,7 +256,7 @@ int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c) __cond_acquires(RC
 	struct crypto_ahash *hash;
 
 	rcu_read_lock_bh();
-	if (WARN_ON_ONCE(id > cpool_populated || !cpool[id].alg)) {
+	if (WARN_ON_ONCE(id >= cpool_populated || !cpool[id].alg)) {
 		rcu_read_unlock_bh();
 		return -EINVAL;
 	}
@@ -301,7 +301,7 @@ EXPORT_SYMBOL_GPL(tcp_sigpool_end);
  */
 size_t tcp_sigpool_algo(unsigned int id, char *buf, size_t buf_len)
 {
-	if (WARN_ON_ONCE(id > cpool_populated || !cpool[id].alg))
+	if (WARN_ON_ONCE(id >= cpool_populated || !cpool[id].alg))
 		return -EINVAL;
 
 	return strscpy(buf, cpool[id].alg, buf_len);
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index de3f2d31f510a9..dc41a22ee80e82 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -296,5 +296,6 @@ static void __exit udp_diag_exit(void)
 module_init(udp_diag_init);
 module_exit(udp_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("UDP socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-17 /* AF_INET - IPPROTO_UDP */);
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-136 /* AF_INET - IPPROTO_UDPLITE */);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3aaea56b516601..2692a7b24c4097 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -6149,11 +6149,7 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev,
 	pmsg->prefix_len = pinfo->prefix_len;
 	pmsg->prefix_type = pinfo->type;
 	pmsg->prefix_pad3 = 0;
-	pmsg->prefix_flags = 0;
-	if (pinfo->onlink)
-		pmsg->prefix_flags |= IF_PREFIX_ONLINK;
-	if (pinfo->autoconf)
-		pmsg->prefix_flags |= IF_PREFIX_AUTOCONF;
+	pmsg->prefix_flags = pinfo->flags;
 
 	if (nla_put(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix))
 		goto nla_put_failure;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 28b01a068412ab..4fc2cae0d116c5 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -160,8 +160,6 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh)
 	INIT_LIST_HEAD(&f6i->fib6_siblings);
 	refcount_set(&f6i->fib6_ref, 1);
 
-	INIT_HLIST_NODE(&f6i->gc_link);
-
 	return f6i;
 }
 
@@ -248,7 +246,6 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
 				   net->ipv6.fib6_null_entry);
 		table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 		inet_peer_base_init(&table->tb6_peers);
-		INIT_HLIST_HEAD(&table->tb6_gc_hlist);
 	}
 
 	return table;
@@ -1060,8 +1057,6 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 				    lockdep_is_held(&table->tb6_lock));
 		}
 	}
-
-	fib6_clean_expires_locked(rt);
 }
 
 /*
@@ -1123,10 +1118,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 				if (!(iter->fib6_flags & RTF_EXPIRES))
 					return -EEXIST;
 				if (!(rt->fib6_flags & RTF_EXPIRES))
-					fib6_clean_expires_locked(iter);
+					fib6_clean_expires(iter);
 				else
-					fib6_set_expires_locked(iter,
-								rt->expires);
+					fib6_set_expires(iter, rt->expires);
 
 				if (rt->fib6_pmtu)
 					fib6_metric_set(iter, RTAX_MTU,
@@ -1485,10 +1479,6 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
 		if (rt->nh)
 			list_add(&rt->nh_list, &rt->nh->f6i_list);
 		__fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net));
-
-		if (fib6_has_expires(rt))
-			hlist_add_head(&rt->gc_link, &table->tb6_gc_hlist);
-
 		fib6_start_gc(info->nl_net, rt);
 	}
 
@@ -1511,13 +1501,9 @@ out:
 			if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) {
 				pn_leaf = fib6_find_prefix(info->nl_net, table,
 							   pn);
-#if RT6_DEBUG >= 2
-				if (!pn_leaf) {
-					WARN_ON(!pn_leaf);
+				if (!pn_leaf)
 					pn_leaf =
 					    info->nl_net->ipv6.fib6_null_entry;
-				}
-#endif
 				fib6_info_hold(pn_leaf);
 				rcu_assign_pointer(pn->leaf, pn_leaf);
 			}
@@ -2295,8 +2281,9 @@ static void fib6_flush_trees(struct net *net)
  *	Garbage collection
  */
 
-static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
+static int fib6_age(struct fib6_info *rt, void *arg)
 {
+	struct fib6_gc_args *gc_args = arg;
 	unsigned long now = jiffies;
 
 	/*
@@ -2304,7 +2291,7 @@ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
 	 *	Routes are expired even if they are in use.
 	 */
 
-	if (fib6_has_expires(rt) && rt->expires) {
+	if (rt->fib6_flags & RTF_EXPIRES && rt->expires) {
 		if (time_after(now, rt->expires)) {
 			RT6_TRACE("expiring %p\n", rt);
 			return -1;
@@ -2321,40 +2308,6 @@ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
 	return 0;
 }
 
-static void fib6_gc_table(struct net *net,
-			  struct fib6_table *tb6,
-			  struct fib6_gc_args *gc_args)
-{
-	struct fib6_info *rt;
-	struct hlist_node *n;
-	struct nl_info info = {
-		.nl_net = net,
-		.skip_notify = false,
-	};
-
-	hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link)
-		if (fib6_age(rt, gc_args) == -1)
-			fib6_del(rt, &info);
-}
-
-static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args)
-{
-	struct fib6_table *table;
-	struct hlist_head *head;
-	unsigned int h;
-
-	rcu_read_lock();
-	for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
-		head = &net->ipv6.fib_table_hash[h];
-		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
-			spin_lock_bh(&table->tb6_lock);
-			fib6_gc_table(net, table, gc_args);
-			spin_unlock_bh(&table->tb6_lock);
-		}
-	}
-	rcu_read_unlock();
-}
-
 void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 {
 	struct fib6_gc_args gc_args;
@@ -2370,7 +2323,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 			  net->ipv6.sysctl.ip6_rt_gc_interval;
 	gc_args.more = 0;
 
-	fib6_gc_all(net, &gc_args);
+	fib6_clean_all(net, fib6_age, &gc_args);
 	now = jiffies;
 	net->ipv6.ip6_rt_last_gc = now;
 
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index bf3cb3a13600cd..52cf104e347881 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -170,3 +170,4 @@ module_init(ip6table_nat_init);
 module_exit(ip6table_nat_exit);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Ip6tables legacy nat table");
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index 08861d5d1f4db3..fc9f6754028f2c 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -106,3 +106,4 @@ static void __exit ip6table_raw_fini(void)
 module_init(ip6table_raw_init);
 module_exit(ip6table_raw_fini);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Ip6tables legacy raw table");
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index d59b296b4f5190..be7817fbc024d0 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -182,3 +182,4 @@ module_init(nf_defrag_init);
 module_exit(nf_defrag_fini);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv6 defragmentation support");
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 58ccdb08c0fd18..d45bc54b7ea55d 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -413,3 +413,4 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in,
 EXPORT_SYMBOL_GPL(nf_send_unreach6);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv6 packet rejection core");
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index b132feae3393f3..ea1dec8448fce8 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3763,10 +3763,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		rt->dst_nocount = true;
 
 	if (cfg->fc_flags & RTF_EXPIRES)
-		fib6_set_expires_locked(rt, jiffies +
-					clock_t_to_jiffies(cfg->fc_expires));
+		fib6_set_expires(rt, jiffies +
+				clock_t_to_jiffies(cfg->fc_expires));
 	else
-		fib6_clean_expires_locked(rt);
+		fib6_clean_expires(rt);
 
 	if (cfg->fc_protocol == RTPROT_UNSPEC)
 		cfg->fc_protocol = RTPROT_BOOT;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 500f6ed3b8cf93..12eedc6ca2ccae 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -181,14 +181,15 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	treq = tcp_rsk(req);
 	treq->tfo_listener = false;
 
-	if (security_inet_conn_request(sk, skb, req))
-		goto out_free;
-
 	req->mss = mss;
 	ireq->ir_rmt_port = th->source;
 	ireq->ir_num = ntohs(th->dest);
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
+
+	if (security_inet_conn_request(sk, skb, req))
+		goto out_free;
+
 	if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) ||
 	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
 	    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 937a02c2e53453..8c6623496dd7e9 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -881,7 +881,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	if (tcp_key_is_md5(key))
 		tot_len += TCPOLEN_MD5SIG_ALIGNED;
 	if (tcp_key_is_ao(key))
-		tot_len += tcp_ao_len(key->ao_key);
+		tot_len += tcp_ao_len_aligned(key->ao_key);
 
 #ifdef CONFIG_MPTCP
 	if (rst && !tcp_key_is_md5(key)) {
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index dd1d8ffd5f5941..65d1f6755f98f0 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1946,4 +1946,5 @@ module_init(kcm_init);
 module_exit(kcm_exit);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("KCM (Kernel Connection Multiplexor) sockets");
 MODULE_ALIAS_NETPROTO(PF_KCM);
diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c
index 7cac441862e216..51bccfb00a9cd9 100644
--- a/net/llc/llc_input.c
+++ b/net/llc/llc_input.c
@@ -127,8 +127,14 @@ static inline int llc_fixup_skb(struct sk_buff *skb)
 	skb->transport_header += llc_len;
 	skb_pull(skb, llc_len);
 	if (skb->protocol == htons(ETH_P_802_2)) {
-		__be16 pdulen = eth_hdr(skb)->h_proto;
-		s32 data_size = ntohs(pdulen) - llc_len;
+		__be16 pdulen;
+		s32 data_size;
+
+		if (skb->mac_len < ETH_HLEN)
+			return 0;
+
+		pdulen = eth_hdr(skb)->h_proto;
+		data_size = ntohs(pdulen) - llc_len;
 
 		if (data_size < 0 ||
 		    !pskb_may_pull(skb, data_size))
diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c
index 79d1cef8f15a92..06fb8e6944b06a 100644
--- a/net/llc/llc_s_ac.c
+++ b/net/llc/llc_s_ac.c
@@ -153,6 +153,9 @@ int llc_sap_action_send_test_r(struct llc_sap *sap, struct sk_buff *skb)
 	int rc = 1;
 	u32 data_size;
 
+	if (skb->mac_len < ETH_HLEN)
+		return 1;
+
 	llc_pdu_decode_sa(skb, mac_da);
 	llc_pdu_decode_da(skb, mac_sa);
 	llc_pdu_decode_ssap(skb, &dsap);
diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c
index 05c6ae0920534b..f5065429251095 100644
--- a/net/llc/llc_station.c
+++ b/net/llc/llc_station.c
@@ -76,6 +76,9 @@ static int llc_station_ac_send_test_r(struct sk_buff *skb)
 	u32 data_size;
 	struct sk_buff *nskb;
 
+	if (skb->mac_len < ETH_HLEN)
+		goto out;
+
 	/* The test request command is type U (llc_len = 3) */
 	data_size = ntohs(eth_hdr(skb)->h_proto) - 3;
 	nskb = llc_alloc_frame(NULL, skb->dev, LLC_PDU_TYPE_U, data_size);
diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index 037ab74f5ade5b..cb0291decf2e56 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -88,7 +88,7 @@ config MAC80211_LEDS
 
 config MAC80211_DEBUGFS
 	bool "Export mac80211 internals in DebugFS"
-	depends on MAC80211 && DEBUG_FS
+	depends on MAC80211 && CFG80211_DEBUGFS
 	help
 	  Select this to see extensive information about
 	  the internal state of mac80211 in debugfs.
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 606b1b2e41235e..eb1d3ef843538c 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1788,10 +1788,10 @@ static int sta_link_apply_parameters(struct ieee80211_local *local,
 					  lockdep_is_held(&local->hw.wiphy->mtx));
 
 	/*
-	 * If there are no changes, then accept a link that doesn't exist,
+	 * If there are no changes, then accept a link that exist,
 	 * unless it's a new link.
 	 */
-	if (params->link_id < 0 && !new_link &&
+	if (params->link_id >= 0 && !new_link &&
 	    !params->link_mac && !params->txpwr_set &&
 	    !params->supported_rates_len &&
 	    !params->ht_capa && !params->vht_capa &&
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index ec91e131b29e5a..80aeb25f1b68d1 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -22,88 +22,148 @@
 #include "debugfs_netdev.h"
 #include "driver-ops.h"
 
+struct ieee80211_if_read_sdata_data {
+	ssize_t (*format)(const struct ieee80211_sub_if_data *, char *, int);
+	struct ieee80211_sub_if_data *sdata;
+};
+
+static ssize_t ieee80211_if_read_sdata_handler(struct wiphy *wiphy,
+					       struct file *file,
+					       char *buf,
+					       size_t bufsize,
+					       void *data)
+{
+	struct ieee80211_if_read_sdata_data *d = data;
+
+	return d->format(d->sdata, buf, bufsize);
+}
+
 static ssize_t ieee80211_if_read_sdata(
-	struct ieee80211_sub_if_data *sdata,
+	struct file *file,
 	char __user *userbuf,
 	size_t count, loff_t *ppos,
 	ssize_t (*format)(const struct ieee80211_sub_if_data *sdata, char *, int))
 {
+	struct ieee80211_sub_if_data *sdata = file->private_data;
+	struct ieee80211_if_read_sdata_data data = {
+		.format = format,
+		.sdata = sdata,
+	};
 	char buf[200];
-	ssize_t ret = -EINVAL;
 
-	wiphy_lock(sdata->local->hw.wiphy);
-	ret = (*format)(sdata, buf, sizeof(buf));
-	wiphy_unlock(sdata->local->hw.wiphy);
+	return wiphy_locked_debugfs_read(sdata->local->hw.wiphy,
+					 file, buf, sizeof(buf),
+					 userbuf, count, ppos,
+					 ieee80211_if_read_sdata_handler,
+					 &data);
+}
 
-	if (ret >= 0)
-		ret = simple_read_from_buffer(userbuf, count, ppos, buf, ret);
+struct ieee80211_if_write_sdata_data {
+	ssize_t (*write)(struct ieee80211_sub_if_data *, const char *, int);
+	struct ieee80211_sub_if_data *sdata;
+};
+
+static ssize_t ieee80211_if_write_sdata_handler(struct wiphy *wiphy,
+						struct file *file,
+						char *buf,
+						size_t count,
+						void *data)
+{
+	struct ieee80211_if_write_sdata_data *d = data;
 
-	return ret;
+	return d->write(d->sdata, buf, count);
 }
 
 static ssize_t ieee80211_if_write_sdata(
-	struct ieee80211_sub_if_data *sdata,
+	struct file *file,
 	const char __user *userbuf,
 	size_t count, loff_t *ppos,
 	ssize_t (*write)(struct ieee80211_sub_if_data *sdata, const char *, int))
 {
+	struct ieee80211_sub_if_data *sdata = file->private_data;
+	struct ieee80211_if_write_sdata_data data = {
+		.write = write,
+		.sdata = sdata,
+	};
 	char buf[64];
-	ssize_t ret;
 
-	if (count >= sizeof(buf))
-		return -E2BIG;
+	return wiphy_locked_debugfs_write(sdata->local->hw.wiphy,
+					  file, buf, sizeof(buf),
+					  userbuf, count,
+					  ieee80211_if_write_sdata_handler,
+					  &data);
+}
 
-	if (copy_from_user(buf, userbuf, count))
-		return -EFAULT;
-	buf[count] = '\0';
+struct ieee80211_if_read_link_data {
+	ssize_t (*format)(const struct ieee80211_link_data *, char *, int);
+	struct ieee80211_link_data *link;
+};
 
-	wiphy_lock(sdata->local->hw.wiphy);
-	ret = (*write)(sdata, buf, count);
-	wiphy_unlock(sdata->local->hw.wiphy);
+static ssize_t ieee80211_if_read_link_handler(struct wiphy *wiphy,
+					      struct file *file,
+					      char *buf,
+					      size_t bufsize,
+					      void *data)
+{
+	struct ieee80211_if_read_link_data *d = data;
 
-	return ret;
+	return d->format(d->link, buf, bufsize);
 }
 
 static ssize_t ieee80211_if_read_link(
-	struct ieee80211_link_data *link,
+	struct file *file,
 	char __user *userbuf,
 	size_t count, loff_t *ppos,
 	ssize_t (*format)(const struct ieee80211_link_data *link, char *, int))
 {
+	struct ieee80211_link_data *link = file->private_data;
+	struct ieee80211_if_read_link_data data = {
+		.format = format,
+		.link = link,
+	};
 	char buf[200];
-	ssize_t ret = -EINVAL;
 
-	wiphy_lock(link->sdata->local->hw.wiphy);
-	ret = (*format)(link, buf, sizeof(buf));
-	wiphy_unlock(link->sdata->local->hw.wiphy);
+	return wiphy_locked_debugfs_read(link->sdata->local->hw.wiphy,
+					 file, buf, sizeof(buf),
+					 userbuf, count, ppos,
+					 ieee80211_if_read_link_handler,
+					 &data);
+}
+
+struct ieee80211_if_write_link_data {
+	ssize_t (*write)(struct ieee80211_link_data *, const char *, int);
+	struct ieee80211_link_data *link;
+};
 
-	if (ret >= 0)
-		ret = simple_read_from_buffer(userbuf, count, ppos, buf, ret);
+static ssize_t ieee80211_if_write_link_handler(struct wiphy *wiphy,
+					       struct file *file,
+					       char *buf,
+					       size_t count,
+					       void *data)
+{
+	struct ieee80211_if_write_sdata_data *d = data;
 
-	return ret;
+	return d->write(d->sdata, buf, count);
 }
 
 static ssize_t ieee80211_if_write_link(
-	struct ieee80211_link_data *link,
+	struct file *file,
 	const char __user *userbuf,
 	size_t count, loff_t *ppos,
 	ssize_t (*write)(struct ieee80211_link_data *link, const char *, int))
 {
+	struct ieee80211_link_data *link = file->private_data;
+	struct ieee80211_if_write_link_data data = {
+		.write = write,
+		.link = link,
+	};
 	char buf[64];
-	ssize_t ret;
-
-	if (count >= sizeof(buf))
-		return -E2BIG;
-
-	if (copy_from_user(buf, userbuf, count))
-		return -EFAULT;
-	buf[count] = '\0';
-
-	wiphy_lock(link->sdata->local->hw.wiphy);
-	ret = (*write)(link, buf, count);
-	wiphy_unlock(link->sdata->local->hw.wiphy);
 
-	return ret;
+	return wiphy_locked_debugfs_write(link->sdata->local->hw.wiphy,
+					  file, buf, sizeof(buf),
+					  userbuf, count,
+					  ieee80211_if_write_link_handler,
+					  &data);
 }
 
 #define IEEE80211_IF_FMT(name, type, field, format_string)		\
@@ -173,7 +233,7 @@ static ssize_t ieee80211_if_read_##name(struct file *file,		\
 					char __user *userbuf,		\
 					size_t count, loff_t *ppos)	\
 {									\
-	return ieee80211_if_read_sdata(file->private_data,		\
+	return ieee80211_if_read_sdata(file,				\
 				       userbuf, count, ppos,		\
 				       ieee80211_if_fmt_##name);	\
 }
@@ -183,7 +243,7 @@ static ssize_t ieee80211_if_write_##name(struct file *file,		\
 					 const char __user *userbuf,	\
 					 size_t count, loff_t *ppos)	\
 {									\
-	return ieee80211_if_write_sdata(file->private_data, userbuf,	\
+	return ieee80211_if_write_sdata(file, userbuf,			\
 					count, ppos,			\
 					ieee80211_if_parse_##name);	\
 }
@@ -211,7 +271,7 @@ static ssize_t ieee80211_if_read_##name(struct file *file,		\
 					char __user *userbuf,		\
 					size_t count, loff_t *ppos)	\
 {									\
-	return ieee80211_if_read_link(file->private_data,		\
+	return ieee80211_if_read_link(file,				\
 				      userbuf, count, ppos,		\
 				      ieee80211_if_fmt_##name);	\
 }
@@ -221,7 +281,7 @@ static ssize_t ieee80211_if_write_##name(struct file *file,		\
 					 const char __user *userbuf,	\
 					 size_t count, loff_t *ppos)	\
 {									\
-	return ieee80211_if_write_link(file->private_data, userbuf,	\
+	return ieee80211_if_write_link(file, userbuf,			\
 				       count, ppos,			\
 				       ieee80211_if_parse_##name);	\
 }
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 06e3613bf46bd9..5bf507ebb096be 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -312,23 +312,14 @@ static ssize_t sta_aql_write(struct file *file, const char __user *userbuf,
 STA_OPS_RW(aql);
 
 
-static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
-					size_t count, loff_t *ppos)
+static ssize_t sta_agg_status_do_read(struct wiphy *wiphy, struct file *file,
+				      char *buf, size_t bufsz, void *data)
 {
-	char *buf, *p;
-	ssize_t bufsz = 71 + IEEE80211_NUM_TIDS * 40;
+	struct sta_info *sta = data;
+	char *p = buf;
 	int i;
-	struct sta_info *sta = file->private_data;
 	struct tid_ampdu_rx *tid_rx;
 	struct tid_ampdu_tx *tid_tx;
-	ssize_t ret;
-
-	buf = kzalloc(bufsz, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-	p = buf;
-
-	rcu_read_lock();
 
 	p += scnprintf(p, bufsz + buf - p, "next dialog_token: %#02x\n",
 			sta->ampdu_mlme.dialog_token_allocator + 1);
@@ -338,8 +329,8 @@ static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
 	for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
 		bool tid_rx_valid;
 
-		tid_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[i]);
-		tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[i]);
+		tid_rx = wiphy_dereference(wiphy, sta->ampdu_mlme.tid_rx[i]);
+		tid_tx = wiphy_dereference(wiphy, sta->ampdu_mlme.tid_tx[i]);
 		tid_rx_valid = test_bit(i, sta->ampdu_mlme.agg_session_valid);
 
 		p += scnprintf(p, bufsz + buf - p, "%02d", i);
@@ -358,31 +349,39 @@ static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
 				tid_tx ? skb_queue_len(&tid_tx->pending) : 0);
 		p += scnprintf(p, bufsz + buf - p, "\n");
 	}
-	rcu_read_unlock();
 
-	ret = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf);
+	return p - buf;
+}
+
+static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
+				   size_t count, loff_t *ppos)
+{
+	struct sta_info *sta = file->private_data;
+	struct wiphy *wiphy = sta->local->hw.wiphy;
+	size_t bufsz = 71 + IEEE80211_NUM_TIDS * 40;
+	char *buf = kmalloc(bufsz, GFP_KERNEL);
+	ssize_t ret;
+
+	if (!buf)
+		return -ENOMEM;
+
+	ret = wiphy_locked_debugfs_read(wiphy, file, buf, bufsz,
+					userbuf, count, ppos,
+					sta_agg_status_do_read, sta);
 	kfree(buf);
+
 	return ret;
 }
 
-static ssize_t sta_agg_status_write(struct file *file, const char __user *userbuf,
-				    size_t count, loff_t *ppos)
+static ssize_t sta_agg_status_do_write(struct wiphy *wiphy, struct file *file,
+				       char *buf, size_t count, void *data)
 {
-	char _buf[25] = {}, *buf = _buf;
-	struct sta_info *sta = file->private_data;
+	struct sta_info *sta = data;
 	bool start, tx;
 	unsigned long tid;
-	char *pos;
+	char *pos = buf;
 	int ret, timeout = 5000;
 
-	if (count > sizeof(_buf))
-		return -EINVAL;
-
-	if (copy_from_user(buf, userbuf, count))
-		return -EFAULT;
-
-	buf[sizeof(_buf) - 1] = '\0';
-	pos = buf;
 	buf = strsep(&pos, " ");
 	if (!buf)
 		return -EINVAL;
@@ -420,7 +419,6 @@ static ssize_t sta_agg_status_write(struct file *file, const char __user *userbu
 	if (ret || tid >= IEEE80211_NUM_TIDS)
 		return -EINVAL;
 
-	wiphy_lock(sta->local->hw.wiphy);
 	if (tx) {
 		if (start)
 			ret = ieee80211_start_tx_ba_session(&sta->sta, tid,
@@ -432,10 +430,22 @@ static ssize_t sta_agg_status_write(struct file *file, const char __user *userbu
 					       3, true);
 		ret = 0;
 	}
-	wiphy_unlock(sta->local->hw.wiphy);
 
 	return ret ?: count;
 }
+
+static ssize_t sta_agg_status_write(struct file *file,
+				    const char __user *userbuf,
+				    size_t count, loff_t *ppos)
+{
+	struct sta_info *sta = file->private_data;
+	struct wiphy *wiphy = sta->local->hw.wiphy;
+	char _buf[26];
+
+	return wiphy_locked_debugfs_write(wiphy, file, _buf, sizeof(_buf),
+					  userbuf, count,
+					  sta_agg_status_do_write, sta);
+}
 STA_OPS_RW(agg_status);
 
 /* link sta attributes */
diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index 7938ec87ef25be..d3820333cd59c8 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2015 Intel Deutschland GmbH
- * Copyright (C) 2022 Intel Corporation
+ * Copyright (C) 2022-2023 Intel Corporation
  */
 #include <net/mac80211.h>
 #include "ieee80211_i.h"
@@ -589,6 +589,10 @@ int drv_change_sta_links(struct ieee80211_local *local,
 	if (ret)
 		return ret;
 
+	/* during reconfig don't add it to debugfs again */
+	if (local->in_reconfig)
+		return 0;
+
 	for_each_set_bit(link_id, &links_to_add, IEEE80211_MLD_MAX_NUM_LINKS) {
 		link_sta = rcu_dereference_protected(info->link[link_id],
 						     lockdep_is_held(&local->hw.wiphy->mtx));
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 568633b38c4736..f690c385a345a6 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -23,7 +23,7 @@
 static inline struct ieee80211_sub_if_data *
 get_bss_sdata(struct ieee80211_sub_if_data *sdata)
 {
-	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+	if (sdata && sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
 		sdata = container_of(sdata->bss, struct ieee80211_sub_if_data,
 				     u.ap);
 
@@ -695,11 +695,14 @@ static inline void drv_flush(struct ieee80211_local *local,
 			     struct ieee80211_sub_if_data *sdata,
 			     u32 queues, bool drop)
 {
-	struct ieee80211_vif *vif = sdata ? &sdata->vif : NULL;
+	struct ieee80211_vif *vif;
 
 	might_sleep();
 	lockdep_assert_wiphy(local->hw.wiphy);
 
+	sdata = get_bss_sdata(sdata);
+	vif = sdata ? &sdata->vif : NULL;
+
 	if (sdata && !check_sdata_in_driver(sdata))
 		return;
 
@@ -716,6 +719,8 @@ static inline void drv_flush_sta(struct ieee80211_local *local,
 	might_sleep();
 	lockdep_assert_wiphy(local->hw.wiphy);
 
+	sdata = get_bss_sdata(sdata);
+
 	if (sdata && !check_sdata_in_driver(sdata))
 		return;
 
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index 68cea2685224b9..749f4ecab99030 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -271,6 +271,7 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata,
 	case NL80211_CHAN_WIDTH_80:
 	case NL80211_CHAN_WIDTH_80P80:
 	case NL80211_CHAN_WIDTH_160:
+	case NL80211_CHAN_WIDTH_320:
 		bw = ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ?
 				IEEE80211_STA_RX_BW_40 : IEEE80211_STA_RX_BW_20;
 		break;
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index dbabeefe451513..28bf794f67f8c4 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -1068,8 +1068,8 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata,
 	case WLAN_SP_MESH_PEERING_OPEN:
 		if (!matches_local)
 			event = OPN_RJCT;
-		if (!mesh_plink_free_count(sdata) ||
-		    (sta->mesh->plid && sta->mesh->plid != plid))
+		else if (!mesh_plink_free_count(sdata) ||
+			 (sta->mesh->plid && sta->mesh->plid != plid))
 			event = OPN_IGNR;
 		else
 			event = OPN_ACPT;
@@ -1077,9 +1077,9 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata,
 	case WLAN_SP_MESH_PEERING_CONFIRM:
 		if (!matches_local)
 			event = CNF_RJCT;
-		if (!mesh_plink_free_count(sdata) ||
-		    sta->mesh->llid != llid ||
-		    (sta->mesh->plid && sta->mesh->plid != plid))
+		else if (!mesh_plink_free_count(sdata) ||
+			 sta->mesh->llid != llid ||
+			 (sta->mesh->plid && sta->mesh->plid != plid))
 			event = CNF_IGNR;
 		else
 			event = CNF_ACPT;
@@ -1247,6 +1247,8 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata,
 			return;
 	}
 	elems = ieee802_11_parse_elems(baseaddr, len - baselen, true, NULL);
-	mesh_process_plink_frame(sdata, mgmt, elems, rx_status);
-	kfree(elems);
+	if (elems) {
+		mesh_process_plink_frame(sdata, mgmt, elems, rx_status);
+		kfree(elems);
+	}
 }
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 887b496f2b81ed..c8998cf01b7a54 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -5782,7 +5782,7 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata,
 {
 	const struct ieee80211_multi_link_elem *ml;
 	const struct element *sub;
-	size_t ml_len;
+	ssize_t ml_len;
 	unsigned long removed_links = 0;
 	u16 link_removal_timeout[IEEE80211_MLD_MAX_NUM_LINKS] = {};
 	u8 link_id;
@@ -5798,6 +5798,8 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata,
 					     elems->scratch + elems->scratch_len -
 					     elems->scratch_pos,
 					     WLAN_EID_FRAGMENT);
+	if (ml_len < 0)
+		return;
 
 	elems->ml_reconf = (const void *)elems->scratch_pos;
 	elems->ml_reconf_len = ml_len;
diff --git a/net/mptcp/crypto_test.c b/net/mptcp/crypto_test.c
index 017248dea038c1..220414e5c850f4 100644
--- a/net/mptcp/crypto_test.c
+++ b/net/mptcp/crypto_test.c
@@ -70,3 +70,4 @@ static struct kunit_suite mptcp_crypto_suite = {
 kunit_test_suite(mptcp_crypto_suite);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("KUnit tests for MPTCP Crypto");
diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c
index 8df1bdb647e299..5409c2ea3f5728 100644
--- a/net/mptcp/mptcp_diag.c
+++ b/net/mptcp/mptcp_diag.c
@@ -245,4 +245,5 @@ static void __exit mptcp_diag_exit(void)
 module_init(mptcp_diag_init);
 module_exit(mptcp_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MPTCP socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-262 /* AF_INET - IPPROTO_MPTCP */);
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index cd15ec73073e05..c53914012d01d3 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -108,6 +108,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			mp_opt->suboptions |= OPTION_MPTCP_DSS;
 			mp_opt->use_map = 1;
 			mp_opt->mpc_map = 1;
+			mp_opt->use_ack = 0;
 			mp_opt->data_len = get_unaligned_be16(ptr);
 			ptr += 2;
 		}
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 1529ec35881552..bf4d96f6f99a6e 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1515,8 +1515,9 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
 	struct mptcp_pm_addr_entry *entry;
 
 	list_for_each_entry(entry, rm_list, list) {
-		remove_anno_list_by_saddr(msk, &entry->addr);
-		if (alist.nr < MPTCP_RM_IDS_MAX)
+		if ((remove_anno_list_by_saddr(msk, &entry->addr) ||
+		     lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) &&
+		    alist.nr < MPTCP_RM_IDS_MAX)
 			alist.ids[alist.nr++] = entry->addr.id;
 	}
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a0b8356cd8c58f..5cd5c3f535a821 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1230,6 +1230,8 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk,
 	mptcp_do_fallback(ssk);
 }
 
+#define MPTCP_MAX_GSO_SIZE (GSO_LEGACY_MAX_SIZE - (MAX_TCP_HEADER + 1))
+
 static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 			      struct mptcp_data_frag *dfrag,
 			      struct mptcp_sendmsg_info *info)
@@ -1256,6 +1258,8 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 		return -EAGAIN;
 
 	/* compute send limit */
+	if (unlikely(ssk->sk_gso_max_size > MPTCP_MAX_GSO_SIZE))
+		ssk->sk_gso_max_size = MPTCP_MAX_GSO_SIZE;
 	info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
 	copy = info->size_goal;
 
@@ -3398,11 +3402,12 @@ static void mptcp_release_cb(struct sock *sk)
 	if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags))
 		__mptcp_clean_una_wakeup(sk);
 	if (unlikely(msk->cb_flags)) {
-		/* be sure to set the current sk state before tacking actions
-		 * depending on sk_state, that is processing MPTCP_ERROR_REPORT
+		/* be sure to sync the msk state before taking actions
+		 * depending on sk_state (MPTCP_ERROR_REPORT)
+		 * On sk release avoid actions depending on the first subflow
 		 */
-		if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags))
-			__mptcp_set_connected(sk);
+		if (__test_and_clear_bit(MPTCP_SYNC_STATE, &msk->cb_flags) && msk->first)
+			__mptcp_sync_state(sk, msk->pending_state);
 		if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags))
 			__mptcp_error_report(sk);
 		if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags))
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index fe6f2d399ee898..aa1a93fe40ffaf 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -124,7 +124,7 @@
 #define MPTCP_ERROR_REPORT	3
 #define MPTCP_RETRANSMIT	4
 #define MPTCP_FLUSH_JOIN_LIST	5
-#define MPTCP_CONNECTED		6
+#define MPTCP_SYNC_STATE	6
 #define MPTCP_SYNC_SNDBUF	7
 
 struct mptcp_skb_cb {
@@ -296,6 +296,9 @@ struct mptcp_sock {
 	bool		use_64bit_ack; /* Set when we received a 64-bit DSN */
 	bool		csum_enabled;
 	bool		allow_infinite_fallback;
+	u8		pending_state; /* A subflow asked to set this sk_state,
+					* protected by the msk data lock
+					*/
 	u8		mpc_endpoint_id;
 	u8		recvmsg_inq:1,
 			cork:1,
@@ -728,7 +731,7 @@ void mptcp_get_options(const struct sk_buff *skb,
 		       struct mptcp_options_received *mp_opt);
 
 void mptcp_finish_connect(struct sock *sk);
-void __mptcp_set_connected(struct sock *sk);
+void __mptcp_sync_state(struct sock *sk, int state);
 void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout);
 
 static inline void mptcp_stop_tout_timer(struct sock *sk)
@@ -1115,7 +1118,7 @@ static inline bool subflow_simultaneous_connect(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 
-	return sk->sk_state == TCP_ESTABLISHED &&
+	return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1) &&
 	       is_active_ssk(subflow) &&
 	       !subflow->conn_finished;
 }
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 77f5e8932abf64..35368073370048 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -738,8 +738,11 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname,
 	val = READ_ONCE(inet_sk(sk)->tos);
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		bool slow;
 
+		slow = lock_sock_fast(ssk);
 		__ip_sock_set_tos(ssk, val);
+		unlock_sock_fast(ssk, slow);
 	}
 	release_sock(sk);
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index a4f3c27f0309f9..6d7684c35e9331 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -419,22 +419,28 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc
 	return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport;
 }
 
-void __mptcp_set_connected(struct sock *sk)
+void __mptcp_sync_state(struct sock *sk, int state)
 {
-	__mptcp_propagate_sndbuf(sk, mptcp_sk(sk)->first);
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	__mptcp_propagate_sndbuf(sk, msk->first);
 	if (sk->sk_state == TCP_SYN_SENT) {
-		inet_sk_state_store(sk, TCP_ESTABLISHED);
+		inet_sk_state_store(sk, state);
 		sk->sk_state_change(sk);
 	}
 }
 
-static void mptcp_set_connected(struct sock *sk)
+static void mptcp_propagate_state(struct sock *sk, struct sock *ssk)
 {
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
 	mptcp_data_lock(sk);
-	if (!sock_owned_by_user(sk))
-		__mptcp_set_connected(sk);
-	else
-		__set_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->cb_flags);
+	if (!sock_owned_by_user(sk)) {
+		__mptcp_sync_state(sk, ssk->sk_state);
+	} else {
+		msk->pending_state = ssk->sk_state;
+		__set_bit(MPTCP_SYNC_STATE, &msk->cb_flags);
+	}
 	mptcp_data_unlock(sk);
 }
 
@@ -496,7 +502,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		subflow_set_remote_key(msk, subflow, &mp_opt);
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
 		mptcp_finish_connect(sk);
-		mptcp_set_connected(parent);
+		mptcp_propagate_state(parent, sk);
 	} else if (subflow->request_join) {
 		u8 hmac[SHA256_DIGEST_SIZE];
 
@@ -540,7 +546,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	} else if (mptcp_check_fallback(sk)) {
 fallback:
 		mptcp_rcv_space_init(msk, sk);
-		mptcp_set_connected(parent);
+		mptcp_propagate_state(parent, sk);
 	}
 	return;
 
@@ -1740,7 +1746,7 @@ static void subflow_state_change(struct sock *sk)
 		mptcp_rcv_space_init(msk, sk);
 		pr_fallback(msk);
 		subflow->conn_finished = 1;
-		mptcp_set_connected(parent);
+		mptcp_propagate_state(parent, sk);
 	}
 
 	/* as recvmsg() does not acquire the subflow socket for ssk selection
diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c
index 0758865ab658ea..bfff53e668da68 100644
--- a/net/mptcp/token_test.c
+++ b/net/mptcp/token_test.c
@@ -143,3 +143,4 @@ static struct kunit_suite mptcp_token_suite = {
 kunit_test_suite(mptcp_token_suite);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("KUnit tests for MPTCP Token");
diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c
index f8854bff286cbd..62fb1031763d14 100644
--- a/net/ncsi/ncsi-aen.c
+++ b/net/ncsi/ncsi-aen.c
@@ -89,11 +89,6 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp,
 	if ((had_link == has_link) || chained)
 		return 0;
 
-	if (had_link)
-		netif_carrier_off(ndp->ndev.dev);
-	else
-		netif_carrier_on(ndp->ndev.dev);
-
 	if (!ndp->multi_package && !nc->package->multi_channel) {
 		if (had_link) {
 			ndp->flags |= NCSI_DEV_RESHUFFLE;
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 35d2f9c9ada025..4c133e06be1de2 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -61,6 +61,8 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
 	ip_set_dereference((inst)->ip_set_list)[id]
 #define ip_set_ref_netlink(inst,id)	\
 	rcu_dereference_raw((inst)->ip_set_list)[id]
+#define ip_set_dereference_nfnl(p)	\
+	rcu_dereference_check(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
 
 /* The set types are implemented in modules and registered set types
  * can be found in ip_set_type_list. Adding/deleting types is
@@ -708,15 +710,10 @@ __ip_set_put_netlink(struct ip_set *set)
 static struct ip_set *
 ip_set_rcu_get(struct net *net, ip_set_id_t index)
 {
-	struct ip_set *set;
 	struct ip_set_net *inst = ip_set_pernet(net);
 
-	rcu_read_lock();
-	/* ip_set_list itself needs to be protected */
-	set = rcu_dereference(inst->ip_set_list)[index];
-	rcu_read_unlock();
-
-	return set;
+	/* ip_set_list and the set pointer need to be protected */
+	return ip_set_dereference_nfnl(inst->ip_set_list)[index];
 }
 
 static inline void
@@ -1397,6 +1394,9 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info,
 	ip_set(inst, to_id) = from;
 	write_unlock_bh(&ip_set_ref_lock);
 
+	/* Make sure all readers of the old set pointers are completed. */
+	synchronize_rcu();
+
 	return 0;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 3230506ae3ffd8..a2c16b5010877c 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -2450,3 +2450,4 @@ static void __exit ip_vs_cleanup(void)
 module_init(ip_vs_init);
 module_exit(ip_vs_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IP Virtual Server");
diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c
index 5e6ec32aff2b14..75f4c231f4a027 100644
--- a/net/netfilter/ipvs/ip_vs_dh.c
+++ b/net/netfilter/ipvs/ip_vs_dh.c
@@ -270,3 +270,4 @@ static void __exit ip_vs_dh_cleanup(void)
 module_init(ip_vs_dh_init);
 module_exit(ip_vs_dh_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs destination hashing scheduler");
diff --git a/net/netfilter/ipvs/ip_vs_fo.c b/net/netfilter/ipvs/ip_vs_fo.c
index b846cc385279e1..ab117e5bc34ead 100644
--- a/net/netfilter/ipvs/ip_vs_fo.c
+++ b/net/netfilter/ipvs/ip_vs_fo.c
@@ -72,3 +72,4 @@ static void __exit ip_vs_fo_cleanup(void)
 module_init(ip_vs_fo_init);
 module_exit(ip_vs_fo_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs weighted failover scheduler");
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index ef1f45e43b6308..f53899d1241622 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -635,3 +635,4 @@ static void __exit ip_vs_ftp_exit(void)
 module_init(ip_vs_ftp_init);
 module_exit(ip_vs_ftp_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs ftp helper");
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index cf78ba4ce5ffd2..8ceec7a2fa8f30 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -632,3 +632,4 @@ static void __exit ip_vs_lblc_cleanup(void)
 module_init(ip_vs_lblc_init);
 module_exit(ip_vs_lblc_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs locality-based least-connection scheduler");
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 9eddf118b40ec0..0fb64707213f83 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -817,3 +817,4 @@ static void __exit ip_vs_lblcr_cleanup(void)
 module_init(ip_vs_lblcr_init);
 module_exit(ip_vs_lblcr_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs locality-based least-connection with replication scheduler");
diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c
index 9d34d81fc6f1c0..c2764505e380f5 100644
--- a/net/netfilter/ipvs/ip_vs_lc.c
+++ b/net/netfilter/ipvs/ip_vs_lc.c
@@ -86,3 +86,4 @@ static void __exit ip_vs_lc_cleanup(void)
 module_init(ip_vs_lc_init);
 module_exit(ip_vs_lc_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs least connection scheduler");
diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c
index f56862a8751888..ed7f5c889b417b 100644
--- a/net/netfilter/ipvs/ip_vs_nq.c
+++ b/net/netfilter/ipvs/ip_vs_nq.c
@@ -136,3 +136,4 @@ static void __exit ip_vs_nq_cleanup(void)
 module_init(ip_vs_nq_init);
 module_exit(ip_vs_nq_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs never queue scheduler");
diff --git a/net/netfilter/ipvs/ip_vs_ovf.c b/net/netfilter/ipvs/ip_vs_ovf.c
index c03066fdd5ca69..c7708b809700de 100644
--- a/net/netfilter/ipvs/ip_vs_ovf.c
+++ b/net/netfilter/ipvs/ip_vs_ovf.c
@@ -79,3 +79,4 @@ static void __exit ip_vs_ovf_cleanup(void)
 module_init(ip_vs_ovf_init);
 module_exit(ip_vs_ovf_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs overflow connection scheduler");
diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index 0ac6705a61d3b0..e4ce1d9a63f913 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -185,3 +185,4 @@ static void __exit ip_vs_sip_cleanup(void)
 module_init(ip_vs_sip_init);
 module_exit(ip_vs_sip_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs sip helper");
diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c
index 38495c6f6c7cc8..6baa34dff9f045 100644
--- a/net/netfilter/ipvs/ip_vs_rr.c
+++ b/net/netfilter/ipvs/ip_vs_rr.c
@@ -122,4 +122,5 @@ static void __exit ip_vs_rr_cleanup(void)
 
 module_init(ip_vs_rr_init);
 module_exit(ip_vs_rr_cleanup);
+MODULE_DESCRIPTION("ipvs round-robin scheduler");
 MODULE_LICENSE("GPL");
diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c
index 7663288e535873..a46f99a5661848 100644
--- a/net/netfilter/ipvs/ip_vs_sed.c
+++ b/net/netfilter/ipvs/ip_vs_sed.c
@@ -137,3 +137,4 @@ static void __exit ip_vs_sed_cleanup(void)
 module_init(ip_vs_sed_init);
 module_exit(ip_vs_sed_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs shortest expected delay scheduler");
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index c2028e41209298..92e77d7a6b50ef 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -376,3 +376,4 @@ static void __exit ip_vs_sh_cleanup(void)
 module_init(ip_vs_sh_init);
 module_exit(ip_vs_sh_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs source hashing scheduler");
diff --git a/net/netfilter/ipvs/ip_vs_twos.c b/net/netfilter/ipvs/ip_vs_twos.c
index 3308e4cc740aea..8d5419edde5072 100644
--- a/net/netfilter/ipvs/ip_vs_twos.c
+++ b/net/netfilter/ipvs/ip_vs_twos.c
@@ -137,3 +137,4 @@ static void __exit ip_vs_twos_cleanup(void)
 module_init(ip_vs_twos_init);
 module_exit(ip_vs_twos_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs power of twos choice scheduler");
diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c
index 09f584b564a0e1..9fa500927c0a07 100644
--- a/net/netfilter/ipvs/ip_vs_wlc.c
+++ b/net/netfilter/ipvs/ip_vs_wlc.c
@@ -109,3 +109,4 @@ static void __exit ip_vs_wlc_cleanup(void)
 module_init(ip_vs_wlc_init);
 module_exit(ip_vs_wlc_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs weighted least connection scheduler");
diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c
index 1bc7a0789d85ad..85ce0d04afac41 100644
--- a/net/netfilter/ipvs/ip_vs_wrr.c
+++ b/net/netfilter/ipvs/ip_vs_wrr.c
@@ -263,3 +263,4 @@ static void __exit ip_vs_wrr_cleanup(void)
 module_init(ip_vs_wrr_init);
 module_exit(ip_vs_wrr_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs weighted round-robin scheduler");
diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
index e502ec00b2fe1e..0e4beae421f830 100644
--- a/net/netfilter/nf_bpf_link.c
+++ b/net/netfilter/nf_bpf_link.c
@@ -31,7 +31,7 @@ struct bpf_nf_link {
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 static const struct nf_defrag_hook *
 get_proto_defrag_hook(struct bpf_nf_link *link,
-		      const struct nf_defrag_hook __rcu *global_hook,
+		      const struct nf_defrag_hook __rcu **ptr_global_hook,
 		      const char *mod)
 {
 	const struct nf_defrag_hook *hook;
@@ -39,7 +39,7 @@ get_proto_defrag_hook(struct bpf_nf_link *link,
 
 	/* RCU protects us from races against module unloading */
 	rcu_read_lock();
-	hook = rcu_dereference(global_hook);
+	hook = rcu_dereference(*ptr_global_hook);
 	if (!hook) {
 		rcu_read_unlock();
 		err = request_module(mod);
@@ -47,7 +47,7 @@ get_proto_defrag_hook(struct bpf_nf_link *link,
 			return ERR_PTR(err < 0 ? err : -EINVAL);
 
 		rcu_read_lock();
-		hook = rcu_dereference(global_hook);
+		hook = rcu_dereference(*ptr_global_hook);
 	}
 
 	if (hook && try_module_get(hook->owner)) {
@@ -78,7 +78,7 @@ static int bpf_nf_enable_defrag(struct bpf_nf_link *link)
 	switch (link->hook_ops.pf) {
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
 	case NFPROTO_IPV4:
-		hook = get_proto_defrag_hook(link, nf_defrag_v4_hook, "nf_defrag_ipv4");
+		hook = get_proto_defrag_hook(link, &nf_defrag_v4_hook, "nf_defrag_ipv4");
 		if (IS_ERR(hook))
 			return PTR_ERR(hook);
 
@@ -87,7 +87,7 @@ static int bpf_nf_enable_defrag(struct bpf_nf_link *link)
 #endif
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 	case NFPROTO_IPV6:
-		hook = get_proto_defrag_hook(link, nf_defrag_v6_hook, "nf_defrag_ipv6");
+		hook = get_proto_defrag_hook(link, &nf_defrag_v6_hook, "nf_defrag_ipv6");
 		if (IS_ERR(hook))
 			return PTR_ERR(hook);
 
diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c
index b21799d468d281..475358ec821296 100644
--- a/net/netfilter/nf_conntrack_bpf.c
+++ b/net/netfilter/nf_conntrack_bpf.c
@@ -230,9 +230,7 @@ static int _nf_conntrack_btf_struct_access(struct bpf_verifier_log *log,
 	return 0;
 }
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in nf_conntrack BTF");
+__bpf_kfunc_start_defs();
 
 /* bpf_xdp_ct_alloc - Allocate a new CT entry
  *
@@ -467,7 +465,7 @@ __bpf_kfunc int bpf_ct_change_status(struct nf_conn *nfct, u32 status)
 	return nf_ct_change_status_common(nfct, status);
 }
 
-__diag_pop()
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(nf_ct_kfunc_set)
 BTF_ID_FLAGS(func, bpf_xdp_ct_alloc, KF_ACQUIRE | KF_RET_NULL)
diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c
index 9fb9b80312989b..cfa0fe0356de67 100644
--- a/net/netfilter/nf_conntrack_broadcast.c
+++ b/net/netfilter/nf_conntrack_broadcast.c
@@ -82,3 +82,4 @@ out:
 EXPORT_SYMBOL_GPL(nf_conntrack_broadcast_help);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Broadcast connection tracking helper");
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 334db22199c1d6..fb0ae15e96dfe4 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -57,6 +57,7 @@
 #include "nf_internals.h"
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("List and change connection tracking table");
 
 struct ctnetlink_list_dump_ctx {
 	struct nf_conn *last;
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index c928ff63b10e47..f36727ed91e1a4 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -699,3 +699,4 @@ MODULE_ALIAS("ip_conntrack");
 MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET));
 MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6));
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv4 and IPv6 connection tracking");
diff --git a/net/netfilter/nf_nat_bpf.c b/net/netfilter/nf_nat_bpf.c
index 141ee7783223da..6e3b2f58855fc0 100644
--- a/net/netfilter/nf_nat_bpf.c
+++ b/net/netfilter/nf_nat_bpf.c
@@ -12,9 +12,7 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_nat.h>
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in nf_nat BTF");
+__bpf_kfunc_start_defs();
 
 /* bpf_ct_set_nat_info - Set source or destination nat address
  *
@@ -54,7 +52,7 @@ __bpf_kfunc int bpf_ct_set_nat_info(struct nf_conn___init *nfct,
 	return nf_nat_setup_info(ct, &range, manip) == NF_DROP ? -ENOMEM : 0;
 }
 
-__diag_pop()
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(nf_nat_kfunc_set)
 BTF_ID_FLAGS(func, bpf_ct_set_nat_info, KF_TRUSTED_ARGS)
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index c4e0516a8dfab4..c3d7ecbc777ce0 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -1263,6 +1263,7 @@ static void __exit nf_nat_cleanup(void)
 }
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Network address translation core");
 
 module_init(nf_nat_init);
 module_exit(nf_nat_cleanup);
diff --git a/net/netfilter/nf_nat_redirect.c b/net/netfilter/nf_nat_redirect.c
index 6616ba5d0b0490..5b37487d9d11fa 100644
--- a/net/netfilter/nf_nat_redirect.c
+++ b/net/netfilter/nf_nat_redirect.c
@@ -80,6 +80,26 @@ EXPORT_SYMBOL_GPL(nf_nat_redirect_ipv4);
 
 static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT;
 
+static bool nf_nat_redirect_ipv6_usable(const struct inet6_ifaddr *ifa, unsigned int scope)
+{
+	unsigned int ifa_addr_type = ipv6_addr_type(&ifa->addr);
+
+	if (ifa_addr_type & IPV6_ADDR_MAPPED)
+		return false;
+
+	if ((ifa->flags & IFA_F_TENTATIVE) && (!(ifa->flags & IFA_F_OPTIMISTIC)))
+		return false;
+
+	if (scope) {
+		unsigned int ifa_scope = ifa_addr_type & IPV6_ADDR_SCOPE_MASK;
+
+		if (!(scope & ifa_scope))
+			return false;
+	}
+
+	return true;
+}
+
 unsigned int
 nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
 		     unsigned int hooknum)
@@ -89,14 +109,19 @@ nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
 	if (hooknum == NF_INET_LOCAL_OUT) {
 		newdst.in6 = loopback_addr;
 	} else {
+		unsigned int scope = ipv6_addr_scope(&ipv6_hdr(skb)->daddr);
 		struct inet6_dev *idev;
-		struct inet6_ifaddr *ifa;
 		bool addr = false;
 
 		idev = __in6_dev_get(skb->dev);
 		if (idev != NULL) {
+			const struct inet6_ifaddr *ifa;
+
 			read_lock_bh(&idev->lock);
 			list_for_each_entry(ifa, &idev->addr_list, if_list) {
+				if (!nf_nat_redirect_ipv6_usable(ifa, scope))
+					continue;
+
 				newdst.in6 = ifa->addr;
 				addr = true;
 				break;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 3c1fd8283bf405..c5c17c6e80eda1 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -803,7 +803,7 @@ static struct nft_table *nft_table_lookup(const struct net *net,
 
 static struct nft_table *nft_table_lookup_byhandle(const struct net *net,
 						   const struct nlattr *nla,
-						   u8 genmask, u32 nlpid)
+						   int family, u8 genmask, u32 nlpid)
 {
 	struct nftables_pernet *nft_net;
 	struct nft_table *table;
@@ -811,6 +811,7 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net,
 	nft_net = nft_pernet(net);
 	list_for_each_entry(table, &nft_net->tables, list) {
 		if (be64_to_cpu(nla_get_be64(nla)) == table->handle &&
+		    table->family == family &&
 		    nft_active_genmask(table, genmask)) {
 			if (nft_table_has_owner(table) &&
 			    nlpid && table->nlpid != nlpid)
@@ -1544,7 +1545,7 @@ static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info,
 
 	if (nla[NFTA_TABLE_HANDLE]) {
 		attr = nla[NFTA_TABLE_HANDLE];
-		table = nft_table_lookup_byhandle(net, attr, genmask,
+		table = nft_table_lookup_byhandle(net, attr, family, genmask,
 						  NETLINK_CB(skb).portid);
 	} else {
 		attr = nla[NFTA_TABLE_NAME];
@@ -6520,6 +6521,12 @@ static int nft_setelem_deactivate(const struct net *net,
 	return ret;
 }
 
+static void nft_setelem_catchall_destroy(struct nft_set_elem_catchall *catchall)
+{
+	list_del_rcu(&catchall->list);
+	kfree_rcu(catchall, rcu);
+}
+
 static void nft_setelem_catchall_remove(const struct net *net,
 					const struct nft_set *set,
 					struct nft_elem_priv *elem_priv)
@@ -6528,8 +6535,7 @@ static void nft_setelem_catchall_remove(const struct net *net,
 
 	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
 		if (catchall->elem == elem_priv) {
-			list_del_rcu(&catchall->list);
-			kfree_rcu(catchall, rcu);
+			nft_setelem_catchall_destroy(catchall);
 			break;
 		}
 	}
@@ -7258,10 +7264,11 @@ static int nf_tables_delsetelem(struct sk_buff *skb,
 
 		if (err < 0) {
 			NL_SET_BAD_ATTR(extack, attr);
-			break;
+			return err;
 		}
 	}
-	return err;
+
+	return 0;
 }
 
 /*
@@ -9674,9 +9681,8 @@ void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans)
 	call_rcu(&trans->rcu, nft_trans_gc_trans_free);
 }
 
-static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc,
-						  unsigned int gc_seq,
-						  bool sync)
+struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc,
+						 unsigned int gc_seq)
 {
 	struct nft_set_elem_catchall *catchall;
 	const struct nft_set *set = gc->set;
@@ -9692,11 +9698,7 @@ static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc,
 
 		nft_set_elem_dead(ext);
 dead_elem:
-		if (sync)
-			gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
-		else
-			gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
-
+		gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC);
 		if (!gc)
 			return NULL;
 
@@ -9706,15 +9708,32 @@ dead_elem:
 	return gc;
 }
 
-struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc,
-						 unsigned int gc_seq)
-{
-	return nft_trans_gc_catchall(gc, gc_seq, false);
-}
-
 struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
 {
-	return nft_trans_gc_catchall(gc, 0, true);
+	struct nft_set_elem_catchall *catchall, *next;
+	const struct nft_set *set = gc->set;
+	struct nft_elem_priv *elem_priv;
+	struct nft_set_ext *ext;
+
+	WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net));
+
+	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
+		ext = nft_set_elem_ext(set, catchall->elem);
+
+		if (!nft_set_elem_expired(ext))
+			continue;
+
+		gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
+		if (!gc)
+			return NULL;
+
+		elem_priv = catchall->elem;
+		nft_setelem_data_deactivate(gc->net, gc->set, elem_priv);
+		nft_setelem_catchall_destroy(catchall);
+		nft_trans_gc_elem_add(gc, elem_priv);
+	}
+
+	return gc;
 }
 
 static void nf_tables_module_autoload_cleanup(struct net *net)
@@ -11386,4 +11405,5 @@ module_exit(nf_tables_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_DESCRIPTION("Framework for packet filtering and classification");
 MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFTABLES);
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index 50723ba0828905..c0fc431991e88d 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -447,4 +447,5 @@ module_init(nfnl_osf_init);
 module_exit(nfnl_osf_fini);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Passive OS fingerprint matching");
 MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF);
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index e596d1a842f702..f6e791a6810151 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -38,13 +38,14 @@ void nft_byteorder_eval(const struct nft_expr *expr,
 
 	switch (priv->size) {
 	case 8: {
+		u64 *dst64 = (void *)dst;
 		u64 src64;
 
 		switch (priv->op) {
 		case NFT_BYTEORDER_NTOH:
 			for (i = 0; i < priv->len / 8; i++) {
 				src64 = nft_reg_load64(&src[i]);
-				nft_reg_store64(&dst[i],
+				nft_reg_store64(&dst64[i],
 						be64_to_cpu((__force __be64)src64));
 			}
 			break;
@@ -52,7 +53,7 @@ void nft_byteorder_eval(const struct nft_expr *expr,
 			for (i = 0; i < priv->len / 8; i++) {
 				src64 = (__force __u64)
 					cpu_to_be64(nft_reg_load64(&src[i]));
-				nft_reg_store64(&dst[i], src64);
+				nft_reg_store64(&dst64[i], src64);
 			}
 			break;
 		}
diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c
index 98e4946100c548..40e230d8b712e6 100644
--- a/net/netfilter/nft_chain_nat.c
+++ b/net/netfilter/nft_chain_nat.c
@@ -137,6 +137,7 @@ module_init(nft_chain_nat_init);
 module_exit(nft_chain_nat_exit);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("nftables network address translation support");
 #ifdef CONFIG_NF_TABLES_IPV4
 MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat");
 #endif
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index b18a7903912597..c09dba57354c17 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -280,10 +280,15 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 			priv->expr_array[i] = dynset_expr;
 			priv->num_exprs++;
 
-			if (set->num_exprs &&
-			    dynset_expr->ops != set->exprs[i]->ops) {
-				err = -EOPNOTSUPP;
-				goto err_expr_free;
+			if (set->num_exprs) {
+				if (i >= set->num_exprs) {
+					err = -EINVAL;
+					goto err_expr_free;
+				}
+				if (dynset_expr->ops != set->exprs[i]->ops) {
+					err = -EOPNOTSUPP;
+					goto err_expr_free;
+				}
 			}
 			i++;
 		}
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index 3fbaa7bf41f9c7..6eb571d0c3fdfc 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -214,7 +214,7 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr,
 
 		offset = i + priv->offset;
 		if (priv->flags & NFT_EXTHDR_F_PRESENT) {
-			*dest = 1;
+			nft_reg_store8(dest, 1);
 		} else {
 			if (priv->len % NFT_REG32_SIZE)
 				dest[priv->len / NFT_REG32_SIZE] = 0;
@@ -461,7 +461,7 @@ static void nft_exthdr_dccp_eval(const struct nft_expr *expr,
 		type = bufp[0];
 
 		if (type == priv->type) {
-			*dest = 1;
+			nft_reg_store8(dest, 1);
 			return;
 		}
 
diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c
index 04b51f28533217..37cfe6dd712d8b 100644
--- a/net/netfilter/nft_fib.c
+++ b/net/netfilter/nft_fib.c
@@ -145,11 +145,15 @@ void nft_fib_store_result(void *reg, const struct nft_fib *priv,
 	switch (priv->result) {
 	case NFT_FIB_RESULT_OIF:
 		index = dev ? dev->ifindex : 0;
-		*dreg = (priv->flags & NFTA_FIB_F_PRESENT) ? !!index : index;
+		if (priv->flags & NFTA_FIB_F_PRESENT)
+			nft_reg_store8(dreg, !!index);
+		else
+			*dreg = index;
+
 		break;
 	case NFT_FIB_RESULT_OIFNAME:
 		if (priv->flags & NFTA_FIB_F_PRESENT)
-			*dreg = !!dev;
+			nft_reg_store8(dreg, !!dev);
 		else
 			strscpy_pad(reg, dev ? dev->name : "", IFNAMSIZ);
 		break;
@@ -204,4 +208,5 @@ bool nft_fib_reduce(struct nft_regs_track *track,
 EXPORT_SYMBOL_GPL(nft_fib_reduce);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Query routing table from nftables");
 MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c
index a5268e6dd32f1b..358e742afad703 100644
--- a/net/netfilter/nft_fwd_netdev.c
+++ b/net/netfilter/nft_fwd_netdev.c
@@ -270,4 +270,5 @@ module_exit(nft_fwd_netdev_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_DESCRIPTION("nftables netdev packet forwarding support");
 MODULE_ALIAS_NFT_AF_EXPR(5, "fwd");
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index f7da7c43333b5a..ba0d3683a45d32 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -63,7 +63,7 @@ nft_meta_get_eval_time(enum nft_meta_keys key,
 {
 	switch (key) {
 	case NFT_META_TIME_NS:
-		nft_reg_store64(dest, ktime_get_real_ns());
+		nft_reg_store64((u64 *)dest, ktime_get_real_ns());
 		break;
 	case NFT_META_TIME_DAY:
 		nft_reg_store8(dest, nft_meta_weekday());
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 701977af3ee851..7252fcdae34993 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -2043,6 +2043,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set,
 
 		e = f->mt[r].e;
 
+		if (!nft_set_elem_active(&e->ext, iter->genmask))
+			goto cont;
+
 		iter->err = iter->fn(ctx, set, iter, &e->priv);
 		if (iter->err < 0)
 			goto out;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 6f1186abd47b43..baa3fea4fe65c8 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -624,14 +624,12 @@ static void nft_rbtree_gc(struct nft_set *set)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe, *rbe_end = NULL;
-	struct nftables_pernet *nft_net;
 	struct rb_node *node, *next;
 	struct nft_trans_gc *gc;
 	struct net *net;
 
 	set  = nft_set_container_of(priv);
 	net  = read_pnet(&set->net);
-	nft_net = nft_pernet(net);
 
 	gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL);
 	if (!gc)
diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c
index e85ce69924aee9..50332888c8d233 100644
--- a/net/netfilter/xt_owner.c
+++ b/net/netfilter/xt_owner.c
@@ -76,18 +76,23 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par)
 		 */
 		return false;
 
-	filp = sk->sk_socket->file;
-	if (filp == NULL)
+	read_lock_bh(&sk->sk_callback_lock);
+	filp = sk->sk_socket ? sk->sk_socket->file : NULL;
+	if (filp == NULL) {
+		read_unlock_bh(&sk->sk_callback_lock);
 		return ((info->match ^ info->invert) &
 		       (XT_OWNER_UID | XT_OWNER_GID)) == 0;
+	}
 
 	if (info->match & XT_OWNER_UID) {
 		kuid_t uid_min = make_kuid(net->user_ns, info->uid_min);
 		kuid_t uid_max = make_kuid(net->user_ns, info->uid_max);
 		if ((uid_gte(filp->f_cred->fsuid, uid_min) &&
 		     uid_lte(filp->f_cred->fsuid, uid_max)) ^
-		    !(info->invert & XT_OWNER_UID))
+		    !(info->invert & XT_OWNER_UID)) {
+			read_unlock_bh(&sk->sk_callback_lock);
 			return false;
+		}
 	}
 
 	if (info->match & XT_OWNER_GID) {
@@ -112,10 +117,13 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par)
 			}
 		}
 
-		if (match ^ !(info->invert & XT_OWNER_GID))
+		if (match ^ !(info->invert & XT_OWNER_GID)) {
+			read_unlock_bh(&sk->sk_callback_lock);
 			return false;
+		}
 	}
 
+	read_unlock_bh(&sk->sk_callback_lock);
 	return true;
 }
 
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 7ddb9a78e3fc88..ef93e0d3bee04c 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -561,7 +561,7 @@ recent_mt_proc_write(struct file *file, const char __user *input,
 {
 	struct recent_table *t = pde_data(file_inode(file));
 	struct recent_entry *e;
-	char buf[sizeof("+b335:1d35:1e55:dead:c0de:1715:5afe:c0de")];
+	char buf[sizeof("+b335:1d35:1e55:dead:c0de:1715:255.255.255.255")];
 	const char *c = buf;
 	union nf_inet_addr addr = {};
 	u_int16_t family;
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index 9c4f231be27572..1eeff9422856eb 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -257,5 +257,6 @@ static void __exit netlink_diag_exit(void)
 
 module_init(netlink_diag_init);
 module_exit(netlink_diag_exit);
+MODULE_DESCRIPTION("Netlink-based socket monitoring/diagnostic interface (sock_diag)");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 16 /* AF_NETLINK */);
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 92ef5ed2e7b042..9c7ffd10df2a72 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1691,6 +1691,9 @@ static int genl_bind(struct net *net, int group)
 		if ((grp->flags & GENL_UNS_ADMIN_PERM) &&
 		    !ns_capable(net->user_ns, CAP_NET_ADMIN))
 			ret = -EPERM;
+		if (grp->cap_sys_admin &&
+		    !ns_capable(net->user_ns, CAP_SYS_ADMIN))
+			ret = -EPERM;
 
 		break;
 	}
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 0b9a785dea4595..3019a4406ca4f7 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -985,7 +985,7 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
 		if (err)
 			return err;
 
-		nf_conn_act_ct_ext_add(ct);
+		nf_conn_act_ct_ext_add(skb, ct, ctinfo);
 	} else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
 		   labels_nonzero(&info->labels.mask)) {
 		err = ovs_ct_set_labels(ct, key, &info->labels.value,
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a84e00b5904be0..7adf48549a3b7d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4300,7 +4300,7 @@ static void packet_mm_open(struct vm_area_struct *vma)
 	struct sock *sk = sock->sk;
 
 	if (sk)
-		atomic_inc(&pkt_sk(sk)->mapped);
+		atomic_long_inc(&pkt_sk(sk)->mapped);
 }
 
 static void packet_mm_close(struct vm_area_struct *vma)
@@ -4310,7 +4310,7 @@ static void packet_mm_close(struct vm_area_struct *vma)
 	struct sock *sk = sock->sk;
 
 	if (sk)
-		atomic_dec(&pkt_sk(sk)->mapped);
+		atomic_long_dec(&pkt_sk(sk)->mapped);
 }
 
 static const struct vm_operations_struct packet_mmap_ops = {
@@ -4405,7 +4405,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 
 	err = -EBUSY;
 	if (!closing) {
-		if (atomic_read(&po->mapped))
+		if (atomic_long_read(&po->mapped))
 			goto out;
 		if (packet_read_pending(rb))
 			goto out;
@@ -4508,7 +4508,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 
 	err = -EBUSY;
 	mutex_lock(&po->pg_vec_lock);
-	if (closing || atomic_read(&po->mapped) == 0) {
+	if (closing || atomic_long_read(&po->mapped) == 0) {
 		err = 0;
 		spin_lock_bh(&rb_queue->lock);
 		swap(rb->pg_vec, pg_vec);
@@ -4526,9 +4526,9 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		po->prot_hook.func = (po->rx_ring.pg_vec) ?
 						tpacket_rcv : packet_rcv;
 		skb_queue_purge(rb_queue);
-		if (atomic_read(&po->mapped))
-			pr_err("packet_mmap: vma is busy: %d\n",
-			       atomic_read(&po->mapped));
+		if (atomic_long_read(&po->mapped))
+			pr_err("packet_mmap: vma is busy: %ld\n",
+			       atomic_long_read(&po->mapped));
 	}
 	mutex_unlock(&po->pg_vec_lock);
 
@@ -4606,7 +4606,7 @@ static int packet_mmap(struct file *file, struct socket *sock,
 		}
 	}
 
-	atomic_inc(&po->mapped);
+	atomic_long_inc(&po->mapped);
 	vma->vm_ops = &packet_mmap_ops;
 	err = 0;
 
diff --git a/net/packet/diag.c b/net/packet/diag.c
index f6b200cb3c0668..9a7980e3309d6a 100644
--- a/net/packet/diag.c
+++ b/net/packet/diag.c
@@ -262,4 +262,5 @@ static void __exit packet_diag_exit(void)
 module_init(packet_diag_init);
 module_exit(packet_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("PACKET socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 17 /* AF_PACKET */);
diff --git a/net/packet/internal.h b/net/packet/internal.h
index d29c94c45159dd..d5d70712007ad3 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -122,7 +122,7 @@ struct packet_sock {
 	__be16			num;
 	struct packet_rollover	*rollover;
 	struct packet_mclist	*mclist;
-	atomic_t		mapped;
+	atomic_long_t		mapped;
 	enum tpacket_versions	tp_version;
 	unsigned int		tp_hdrlen;
 	unsigned int		tp_reserve;
diff --git a/net/psample/psample.c b/net/psample/psample.c
index 81a794e36f5358..c34e902855dbef 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -31,7 +31,8 @@ enum psample_nl_multicast_groups {
 
 static const struct genl_multicast_group psample_nl_mcgrps[] = {
 	[PSAMPLE_NL_MCGRP_CONFIG] = { .name = PSAMPLE_NL_MCGRP_CONFIG_NAME },
-	[PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME },
+	[PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME,
+				      .flags = GENL_UNS_ADMIN_PERM },
 };
 
 static struct genl_family psample_nl_family __ro_after_init;
diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
index 5a81505fba9ac4..4e32d659524e0d 100644
--- a/net/rfkill/rfkill-gpio.c
+++ b/net/rfkill/rfkill-gpio.c
@@ -126,6 +126,14 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	ret = gpiod_direction_output(rfkill->reset_gpio, true);
+	if (ret)
+		return ret;
+
+	ret = gpiod_direction_output(rfkill->shutdown_gpio, true);
+	if (ret)
+		return ret;
+
 	rfkill->rfkill_dev = rfkill_alloc(rfkill->name, &pdev->dev,
 					  rfkill->type, &rfkill_gpio_ops,
 					  rfkill);
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 0cc5a4e19900e1..ef81d019b20f48 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -182,21 +182,47 @@ void rose_kill_by_neigh(struct rose_neigh *neigh)
  */
 static void rose_kill_by_device(struct net_device *dev)
 {
-	struct sock *s;
+	struct sock *sk, *array[16];
+	struct rose_sock *rose;
+	bool rescan;
+	int i, cnt;
 
+start:
+	rescan = false;
+	cnt = 0;
 	spin_lock_bh(&rose_list_lock);
-	sk_for_each(s, &rose_list) {
-		struct rose_sock *rose = rose_sk(s);
+	sk_for_each(sk, &rose_list) {
+		rose = rose_sk(sk);
+		if (rose->device == dev) {
+			if (cnt == ARRAY_SIZE(array)) {
+				rescan = true;
+				break;
+			}
+			sock_hold(sk);
+			array[cnt++] = sk;
+		}
+	}
+	spin_unlock_bh(&rose_list_lock);
 
+	for (i = 0; i < cnt; i++) {
+		sk = array[cnt];
+		rose = rose_sk(sk);
+		lock_sock(sk);
+		spin_lock_bh(&rose_list_lock);
 		if (rose->device == dev) {
-			rose_disconnect(s, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
+			rose_disconnect(sk, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
 			if (rose->neighbour)
 				rose->neighbour->use--;
 			netdev_put(rose->device, &rose->dev_tracker);
 			rose->device = NULL;
 		}
+		spin_unlock_bh(&rose_list_lock);
+		release_sock(sk);
+		sock_put(sk);
+		cond_resched();
 	}
-	spin_unlock_bh(&rose_list_lock);
+	if (rescan)
+		goto start;
 }
 
 /*
@@ -656,7 +682,10 @@ static int rose_release(struct socket *sock)
 		break;
 	}
 
+	spin_lock_bh(&rose_list_lock);
 	netdev_put(rose->device, &rose->dev_tracker);
+	rose->device = NULL;
+	spin_unlock_bh(&rose_list_lock);
 	sock->sk = NULL;
 	release_sock(sk);
 	sock_put(sk);
@@ -1315,9 +1344,11 @@ static int rose_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	case TIOCINQ: {
 		struct sk_buff *skb;
 		long amount = 0L;
-		/* These two are safe on a single CPU system as only user tasks fiddle here */
+
+		spin_lock_irq(&sk->sk_receive_queue.lock);
 		if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL)
 			amount = skb->len;
+		spin_unlock_irq(&sk->sk_receive_queue.lock);
 		return put_user(amount, (unsigned int __user *) argp);
 	}
 
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 981ca5b98bcb90..1d95f8bc769fa2 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -73,6 +73,7 @@ static void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local)
 static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call,
 					       gfp_t gfp)
 {
+	static atomic_t rxrpc_bundle_id;
 	struct rxrpc_bundle *bundle;
 
 	bundle = kzalloc(sizeof(*bundle), gfp);
@@ -85,6 +86,7 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call,
 		bundle->upgrade		= test_bit(RXRPC_CALL_UPGRADE, &call->flags);
 		bundle->service_id	= call->dest_srx.srx_service;
 		bundle->security_level	= call->security_level;
+		bundle->debug_id	= atomic_inc_return(&rxrpc_bundle_id);
 		refcount_set(&bundle->ref, 1);
 		atomic_set(&bundle->active, 1);
 		INIT_LIST_HEAD(&bundle->waiting_calls);
@@ -105,7 +107,8 @@ struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle,
 
 static void rxrpc_free_bundle(struct rxrpc_bundle *bundle)
 {
-	trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_free);
+	trace_rxrpc_bundle(bundle->debug_id, refcount_read(&bundle->ref),
+			   rxrpc_bundle_free);
 	rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle);
 	key_put(bundle->key);
 	kfree(bundle);
@@ -239,7 +242,6 @@ dont_reuse:
  */
 int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp)
 {
-	static atomic_t rxrpc_bundle_id;
 	struct rxrpc_bundle *bundle, *candidate;
 	struct rxrpc_local *local = call->local;
 	struct rb_node *p, **pp, *parent;
@@ -306,7 +308,6 @@ int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp)
 	}
 
 	_debug("new bundle");
-	candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id);
 	rb_link_node(&candidate->local_node, parent, pp);
 	rb_insert_color(&candidate->local_node, &local->client_bundles);
 	call->bundle = rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call);
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index ac85d4644a3c3a..df8a271948a1c1 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -212,7 +212,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
 		conn->idle_timestamp = jiffies;
 		if (atomic_dec_and_test(&conn->active))
 			rxrpc_set_service_reap_timer(conn->rxnet,
-						     jiffies + rxrpc_connection_expiry);
+						     jiffies + rxrpc_connection_expiry * HZ);
 	}
 
 	rxrpc_put_call(call, rxrpc_call_put_io_thread);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 030d64f282f370..92495e73b86991 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -643,12 +643,8 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call,
 			clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail);
 			smp_mb(); /* Read data before setting avail bit */
 			set_bit(i, &call->rtt_avail);
-			if (type != rxrpc_rtt_rx_cancel)
-				rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial,
-						   sent_at, resp_time);
-			else
-				trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_cancel, i,
-						   orig_serial, acked_serial, 0, 0);
+			rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial,
+					   sent_at, resp_time);
 			matched = true;
 		}
 
@@ -801,28 +797,21 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 			   summary.ack_reason, nr_acks);
 	rxrpc_inc_stat(call->rxnet, stat_rx_acks[ack.reason]);
 
-	switch (ack.reason) {
-	case RXRPC_ACK_PING_RESPONSE:
-		rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
-					 rxrpc_rtt_rx_ping_response);
-		break;
-	case RXRPC_ACK_REQUESTED:
-		rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
-					 rxrpc_rtt_rx_requested_ack);
-		break;
-	default:
-		if (acked_serial != 0)
+	if (acked_serial != 0) {
+		switch (ack.reason) {
+		case RXRPC_ACK_PING_RESPONSE:
 			rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
-						 rxrpc_rtt_rx_cancel);
-		break;
-	}
-
-	if (ack.reason == RXRPC_ACK_PING) {
-		rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial,
-			       rxrpc_propose_ack_respond_to_ping);
-	} else if (sp->hdr.flags & RXRPC_REQUEST_ACK) {
-		rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, ack_serial,
-			       rxrpc_propose_ack_respond_to_ack);
+						 rxrpc_rtt_rx_ping_response);
+			break;
+		case RXRPC_ACK_REQUESTED:
+			rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
+						 rxrpc_rtt_rx_requested_ack);
+			break;
+		default:
+			rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
+						 rxrpc_rtt_rx_other_ack);
+			break;
+		}
 	}
 
 	/* If we get an EXCEEDS_WINDOW ACK from the server, it probably
@@ -835,7 +824,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	    rxrpc_is_client_call(call)) {
 		rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
 					  0, -ENETRESET);
-		return;
+		goto send_response;
 	}
 
 	/* If we get an OUT_OF_SEQUENCE ACK from the server, that can also
@@ -849,7 +838,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	    rxrpc_is_client_call(call)) {
 		rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
 					  0, -ENETRESET);
-		return;
+		goto send_response;
 	}
 
 	/* Discard any out-of-order or duplicate ACKs (outside lock). */
@@ -857,7 +846,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 		trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial,
 					   first_soft_ack, call->acks_first_seq,
 					   prev_pkt, call->acks_prev_seq);
-		return;
+		goto send_response;
 	}
 
 	info.rxMTU = 0;
@@ -897,7 +886,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	case RXRPC_CALL_SERVER_AWAIT_ACK:
 		break;
 	default:
-		return;
+		goto send_response;
 	}
 
 	if (before(hard_ack, call->acks_hard_ack) ||
@@ -909,7 +898,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	if (after(hard_ack, call->acks_hard_ack)) {
 		if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) {
 			rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ack);
-			return;
+			goto send_response;
 		}
 	}
 
@@ -927,6 +916,14 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 				   rxrpc_propose_ack_ping_for_lost_reply);
 
 	rxrpc_congestion_management(call, skb, &summary, acked_serial);
+
+send_response:
+	if (ack.reason == RXRPC_ACK_PING)
+		rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial,
+			       rxrpc_propose_ack_respond_to_ping);
+	else if (sp->hdr.flags & RXRPC_REQUEST_ACK)
+		rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, ack_serial,
+			       rxrpc_propose_ack_respond_to_ack);
 }
 
 /*
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 7d910aee4f8cb2..c553a30e9c8386 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -87,7 +87,7 @@ static void rxrpc_client_conn_reap_timeout(struct timer_list *timer)
 	struct rxrpc_local *local =
 		container_of(timer, struct rxrpc_local, client_conn_reap_timer);
 
-	if (local->kill_all_client_conns &&
+	if (!local->kill_all_client_conns &&
 	    test_and_set_bit(RXRPC_CLIENT_CONN_REAP_TIMER, &local->client_conn_flags))
 		rxrpc_wake_up_io_thread(local);
 }
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 9d3f26bf0440d9..c39252d61ebbb7 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1098,7 +1098,7 @@ repeat:
 			}
 		} else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) {
 			if (unlikely(!rcu_access_pointer(a->goto_chain))) {
-				net_warn_ratelimited("can't go to NULL chain!\n");
+				tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
 				return TC_ACT_SHOT;
 			}
 			tcf_action_goto_chain_exec(a, res);
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 9583645e86c280..f69c47945175b6 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -286,9 +286,31 @@ static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow)
 	       !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags);
 }
 
+static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft);
+
+static void tcf_ct_nf_get(struct nf_flowtable *ft)
+{
+	struct tcf_ct_flow_table *ct_ft =
+		container_of(ft, struct tcf_ct_flow_table, nf_ft);
+
+	tcf_ct_flow_table_get_ref(ct_ft);
+}
+
+static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft);
+
+static void tcf_ct_nf_put(struct nf_flowtable *ft)
+{
+	struct tcf_ct_flow_table *ct_ft =
+		container_of(ft, struct tcf_ct_flow_table, nf_ft);
+
+	tcf_ct_flow_table_put(ct_ft);
+}
+
 static struct nf_flowtable_type flowtable_ct = {
 	.gc		= tcf_ct_flow_is_outdated,
 	.action		= tcf_ct_flow_table_fill_actions,
+	.get		= tcf_ct_nf_get,
+	.put		= tcf_ct_nf_put,
 	.owner		= THIS_MODULE,
 };
 
@@ -337,9 +359,13 @@ err_alloc:
 	return err;
 }
 
+static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft)
+{
+	refcount_inc(&ct_ft->ref);
+}
+
 static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
 {
-	struct flow_block_cb *block_cb, *tmp_cb;
 	struct tcf_ct_flow_table *ct_ft;
 	struct flow_block *block;
 
@@ -347,13 +373,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
 			     rwork);
 	nf_flow_table_free(&ct_ft->nf_ft);
 
-	/* Remove any remaining callbacks before cleanup */
 	block = &ct_ft->nf_ft.flow_block;
 	down_write(&ct_ft->nf_ft.flow_block_lock);
-	list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) {
-		list_del(&block_cb->list);
-		flow_block_cb_free(block_cb);
-	}
+	WARN_ON(!list_empty(&block->cb_list));
 	up_write(&ct_ft->nf_ft.flow_block_lock);
 	kfree(ct_ft);
 
@@ -376,6 +398,17 @@ static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry,
 	entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir];
 }
 
+static void tcf_ct_flow_ct_ext_ifidx_update(struct flow_offload *entry)
+{
+	struct nf_conn_act_ct_ext *act_ct_ext;
+
+	act_ct_ext = nf_conn_act_ct_ext_find(entry->ct);
+	if (act_ct_ext) {
+		tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL);
+		tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY);
+	}
+}
+
 static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft,
 				  struct nf_conn *ct,
 				  bool tcp, bool bidirectional)
@@ -671,6 +704,8 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p,
 	else
 		ctinfo = IP_CT_ESTABLISHED_REPLY;
 
+	nf_conn_act_ct_ext_fill(skb, ct, ctinfo);
+	tcf_ct_flow_ct_ext_ifidx_update(flow);
 	flow_offload_refresh(nf_ft, flow, force_refresh);
 	if (!test_bit(IPS_ASSURED_BIT, &ct->status)) {
 		/* Process this flow in SW to allow promoting to ASSURED */
@@ -1034,7 +1069,7 @@ do_nat:
 		tcf_ct_act_set_labels(ct, p->labels, p->labels_mask);
 
 		if (!nf_ct_is_confirmed(ct))
-			nf_conn_act_ct_ext_add(ct);
+			nf_conn_act_ct_ext_add(skb, ct, ctinfo);
 
 		/* This will take care of sending queued events
 		 * even if the connection is already confirmed.
@@ -1536,6 +1571,9 @@ static int tcf_ct_offload_act_setup(struct tc_action *act, void *entry_data,
 	if (bind) {
 		struct flow_action_entry *entry = entry_data;
 
+		if (tcf_ct_helper(act))
+			return -EOPNOTSUPP;
+
 		entry->id = FLOW_ACTION_CT;
 		entry->ct.action = tcf_ct_action(act);
 		entry->ct.zone = tcf_ct_zone(act);
diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c
index c9a811f4c7eeed..393b78729216cc 100644
--- a/net/sched/act_gate.c
+++ b/net/sched/act_gate.c
@@ -677,4 +677,5 @@ static void __exit gate_cleanup_module(void)
 
 module_init(gate_init_module);
 module_exit(gate_cleanup_module);
+MODULE_DESCRIPTION("TC gate action");
 MODULE_LICENSE("GPL v2");
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 1daeb2182b70e2..1976bd1639863f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1658,6 +1658,7 @@ static inline int __tcf_classify(struct sk_buff *skb,
 				 int act_index,
 				 u32 *last_executed_chain)
 {
+	u32 orig_reason = res->drop_reason;
 #ifdef CONFIG_NET_CLS_ACT
 	const int max_reclassify_loop = 16;
 	const struct tcf_proto *first_tp;
@@ -1712,8 +1713,14 @@ reclassify:
 			goto reset;
 		}
 #endif
-		if (err >= 0)
+		if (err >= 0) {
+			/* Policy drop or drop reason is over-written by
+			 * classifiers with a bogus value(0) */
+			if (err == TC_ACT_SHOT &&
+			    res->drop_reason == SKB_NOT_DROPPED_YET)
+				tcf_set_drop_reason(res, orig_reason);
 			return err;
+		}
 	}
 
 	if (unlikely(n)) {
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 1b92c33b5f8193..a1f56931330cab 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -341,4 +341,5 @@ static void __exit exit_basic(void)
 
 module_init(init_basic)
 module_exit(exit_basic)
+MODULE_DESCRIPTION("TC basic classifier");
 MODULE_LICENSE("GPL");
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index bd9322d71910bf..7ee8dbf49ed0d3 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -222,4 +222,5 @@ static void __exit exit_cgroup_cls(void)
 
 module_init(init_cgroup_cls);
 module_exit(exit_cgroup_cls);
+MODULE_DESCRIPTION("TC cgroup classifier");
 MODULE_LICENSE("GPL");
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index c49d6af0e04807..afc534ee0a1867 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -446,4 +446,5 @@ static void __exit exit_fw(void)
 
 module_init(init_fw)
 module_exit(exit_fw)
+MODULE_DESCRIPTION("SKB mark based TC classifier");
 MODULE_LICENSE("GPL");
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 1424bfeaca73ff..12a505db418323 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -684,4 +684,5 @@ static void __exit exit_route4(void)
 
 module_init(init_route4)
 module_exit(exit_route4)
+MODULE_DESCRIPTION("Routing table realm based TC classifier");
 MODULE_LICENSE("GPL");
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 6663e971a13e76..d5bdfd4a765582 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -1489,4 +1489,5 @@ static void __exit exit_u32(void)
 
 module_init(init_u32)
 module_exit(exit_u32)
+MODULE_DESCRIPTION("Universal 32bit based TC Classifier");
 MODULE_LICENSE("GPL");
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index cac870eb789730..9a0b85190a2c65 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -574,3 +574,4 @@ static void __exit cbs_module_exit(void)
 module_init(cbs_module_init)
 module_exit(cbs_module_exit)
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Credit Based shaper");
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 19c851125901f6..ae1da08e268f1a 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -513,3 +513,4 @@ module_init(choke_module_init)
 module_exit(choke_module_exit)
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Choose and keep responsive flows scheduler");
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 19901e77cd3b7f..097740a9afeafc 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -495,3 +495,4 @@ static void __exit drr_exit(void)
 module_init(drr_init);
 module_exit(drr_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Deficit Round Robin scheduler");
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index 61d1f0e32cf356..4808159a546608 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -513,3 +513,4 @@ static void __exit etf_module_exit(void)
 module_init(etf_module_init)
 module_exit(etf_module_exit)
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Earliest TxTime First (ETF) qdisc");
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index b10efeaf0629d2..f7c88495946b0b 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -826,3 +826,4 @@ static void __exit ets_exit(void)
 module_init(ets_init);
 module_exit(ets_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Enhanced Transmission Selection(ETS) scheduler");
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index e1040421b79797..450f5c67ac4956 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -269,3 +269,4 @@ struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops,
 	return q ? : ERR_PTR(err);
 }
 EXPORT_SYMBOL(fifo_create_dflt);
+MODULE_DESCRIPTION("Single queue packet and byte based First In First Out(P/BFIFO) scheduler");
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 0fd18c344ab5ae..3a31c47fea9bd9 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -919,14 +919,8 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = {
 	[TCA_FQ_TIMER_SLACK]		= { .type = NLA_U32 },
 	[TCA_FQ_HORIZON]		= { .type = NLA_U32 },
 	[TCA_FQ_HORIZON_DROP]		= { .type = NLA_U8 },
-	[TCA_FQ_PRIOMAP]		= {
-			.type = NLA_BINARY,
-			.len = sizeof(struct tc_prio_qopt),
-		},
-	[TCA_FQ_WEIGHTS]		= {
-			.type = NLA_BINARY,
-			.len = FQ_BANDS * sizeof(s32),
-		},
+	[TCA_FQ_PRIOMAP]		= NLA_POLICY_EXACT_LEN(sizeof(struct tc_prio_qopt)),
+	[TCA_FQ_WEIGHTS]		= NLA_POLICY_EXACT_LEN(FQ_BANDS * sizeof(s32)),
 };
 
 /* compress a u8 array with all elems <= 3 to an array of 2-bit fields */
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 872d127c9db42a..8c61eb3dc94319 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -945,3 +945,4 @@ module_init(gred_module_init)
 module_exit(gred_module_exit)
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Generic Random Early Detection qdisc");
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 880c5f16b29ccf..16c45da4036a7e 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1693,5 +1693,6 @@ hfsc_cleanup(void)
 }
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Hierarchical Fair Service Curve scheduler");
 module_init(hfsc_init);
 module_exit(hfsc_cleanup);
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 0d947414e61611..7349233eaa9b65 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -2179,3 +2179,4 @@ static void __exit htb_module_exit(void)
 module_init(htb_module_init)
 module_exit(htb_module_exit)
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Hierarchical Token Bucket scheduler");
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index a463a63192c3c7..5fa9eaa79bfc9e 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -370,3 +370,4 @@ module_exit(ingress_module_exit);
 
 MODULE_ALIAS("sch_clsact");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Ingress and clsact based ingress and egress qdiscs");
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 793009f445c03b..43e53ee00a56a7 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -789,3 +789,4 @@ module_init(mqprio_module_init);
 module_exit(mqprio_module_exit);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Classful multiqueue prio qdisc");
diff --git a/net/sched/sch_mqprio_lib.c b/net/sched/sch_mqprio_lib.c
index 83b3793c4012e7..b3a5572c167b71 100644
--- a/net/sched/sch_mqprio_lib.c
+++ b/net/sched/sch_mqprio_lib.c
@@ -129,3 +129,4 @@ void mqprio_fp_to_offload(u32 fp[TC_QOPT_MAX_QUEUE],
 EXPORT_SYMBOL_GPL(mqprio_fp_to_offload);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Shared mqprio qdisc code currently between taprio and mqprio");
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 75c9c860182b40..d66d5f0ec08053 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -410,3 +410,4 @@ module_init(multiq_module_init)
 module_exit(multiq_module_exit)
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Multi queue to hardware queue mapping qdisc");
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 6ba2dc191ed941..fa678eb8852841 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -1307,3 +1307,4 @@ static void __exit netem_module_exit(void)
 module_init(netem_module_init)
 module_exit(netem_module_exit)
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Network characteristics emulator qdisc");
diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c
index 35f49edf63dbf2..992f0c8d79886c 100644
--- a/net/sched/sch_plug.c
+++ b/net/sched/sch_plug.c
@@ -226,3 +226,4 @@ static void __exit plug_module_exit(void)
 module_init(plug_module_init)
 module_exit(plug_module_exit)
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Qdisc to plug and unplug traffic via netlink control");
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index fdc5ef52c3ee92..8ecdd3ef6f8ea0 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -433,3 +433,4 @@ module_init(prio_module_init)
 module_exit(prio_module_exit)
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Simple 3-band priority qdisc");
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 28315166fe8e1f..48a604c320c76d 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -1535,3 +1535,4 @@ static void __exit qfq_exit(void)
 module_init(qfq_init);
 module_exit(qfq_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Quick Fair Queueing Plus qdisc");
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 16277b6a0238da..607b6c8b3a9bf2 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -563,3 +563,4 @@ module_init(red_module_init)
 module_exit(red_module_exit)
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Random Early Detection qdisc");
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 66dcb18638fea4..eb77558fa367eb 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -937,3 +937,4 @@ static void __exit sfq_module_exit(void)
 module_init(sfq_module_init)
 module_exit(sfq_module_exit)
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Stochastic Fairness qdisc");
diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c
index 5df2dacb7b1aba..28beb11762d8a3 100644
--- a/net/sched/sch_skbprio.c
+++ b/net/sched/sch_skbprio.c
@@ -307,3 +307,4 @@ module_init(skbprio_module_init)
 module_exit(skbprio_module_exit)
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SKB priority based scheduling qdisc");
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 2e1949de4171ad..31a8252bd09c91 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -2572,3 +2572,4 @@ static void __exit taprio_module_exit(void)
 module_init(taprio_module_init);
 module_exit(taprio_module_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Time Aware Priority qdisc");
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 17d2d00ddb182d..dd6b1a723bf727 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -621,3 +621,4 @@ static void __exit tbf_module_exit(void)
 module_init(tbf_module_init)
 module_exit(tbf_module_exit)
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Token Bucket Filter qdisc");
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 7721239c185fb0..59304611dc0050 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -523,3 +523,4 @@ module_init(teql_init);
 module_exit(teql_exit);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("True (or trivial) link equalizer qdisc");
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index c3d6b92dd3862f..eb05131ff1dd67 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -527,4 +527,5 @@ static void __exit sctp_diag_exit(void)
 module_init(sctp_diag_init);
 module_exit(sctp_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SCTP socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-132);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index abd2667734d4cb..73eebddbbf41d3 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -275,7 +275,7 @@ static int __smc_release(struct smc_sock *smc)
 
 	if (!smc->use_fallback) {
 		rc = smc_close_active(smc);
-		sock_set_flag(sk, SOCK_DEAD);
+		smc_sock_set_flag(sk, SOCK_DEAD);
 		sk->sk_shutdown |= SHUTDOWN_MASK;
 	} else {
 		if (sk->sk_state != SMC_CLOSED) {
@@ -598,8 +598,12 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc)
 	struct smc_llc_qentry *qentry;
 	int rc;
 
-	/* receive CONFIRM LINK request from server over RoCE fabric */
-	qentry = smc_llc_wait(link->lgr, NULL, SMC_LLC_WAIT_TIME,
+	/* Receive CONFIRM LINK request from server over RoCE fabric.
+	 * Increasing the client's timeout by twice as much as the server's
+	 * timeout by default can temporarily avoid decline messages of
+	 * both sides crossing or colliding
+	 */
+	qentry = smc_llc_wait(link->lgr, NULL, 2 * SMC_LLC_WAIT_TIME,
 			      SMC_LLC_CONFIRM_LINK);
 	if (!qentry) {
 		struct smc_clc_msg_decline dclc;
@@ -719,7 +723,7 @@ static void smcd_conn_save_peer_info(struct smc_sock *smc,
 	int bufsize = smc_uncompress_bufsize(clc->d0.dmbe_size);
 
 	smc->conn.peer_rmbe_idx = clc->d0.dmbe_idx;
-	smc->conn.peer_token = clc->d0.token;
+	smc->conn.peer_token = ntohll(clc->d0.token);
 	/* msg header takes up space in the buffer */
 	smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg);
 	atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size);
@@ -1411,7 +1415,7 @@ static int smc_connect_ism(struct smc_sock *smc,
 		if (rc)
 			return rc;
 	}
-	ini->ism_peer_gid[ini->ism_selected] = aclc->d0.gid;
+	ini->ism_peer_gid[ini->ism_selected] = ntohll(aclc->d0.gid);
 
 	/* there is only one lgr role for SMC-D; use server lock */
 	mutex_lock(&smc_server_lgr_pending);
@@ -1743,7 +1747,7 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc)
 		if (new_clcsock)
 			sock_release(new_clcsock);
 		new_sk->sk_state = SMC_CLOSED;
-		sock_set_flag(new_sk, SOCK_DEAD);
+		smc_sock_set_flag(new_sk, SOCK_DEAD);
 		sock_put(new_sk); /* final */
 		*new_smc = NULL;
 		goto out;
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 24745fde4ac264..e377980b84145d 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -377,4 +377,9 @@ int smc_nl_dump_hs_limitation(struct sk_buff *skb, struct netlink_callback *cb);
 int smc_nl_enable_hs_limitation(struct sk_buff *skb, struct genl_info *info);
 int smc_nl_disable_hs_limitation(struct sk_buff *skb, struct genl_info *info);
 
+static inline void smc_sock_set_flag(struct sock *sk, enum sock_flags flag)
+{
+	set_bit(flag, &sk->sk_flags);
+}
+
 #endif	/* __SMC_H */
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 89105e95b4523f..3c06625ceb200e 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -28,13 +28,15 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 {
 	struct smc_cdc_tx_pend *cdcpend = (struct smc_cdc_tx_pend *)pnd_snd;
 	struct smc_connection *conn = cdcpend->conn;
+	struct smc_buf_desc *sndbuf_desc;
 	struct smc_sock *smc;
 	int diff;
 
+	sndbuf_desc = conn->sndbuf_desc;
 	smc = container_of(conn, struct smc_sock, conn);
 	bh_lock_sock(&smc->sk);
-	if (!wc_status) {
-		diff = smc_curs_diff(cdcpend->conn->sndbuf_desc->len,
+	if (!wc_status && sndbuf_desc) {
+		diff = smc_curs_diff(sndbuf_desc->len,
 				     &cdcpend->conn->tx_curs_fin,
 				     &cdcpend->cursor);
 		/* sndbuf_space is decreased in smc_sendmsg */
@@ -114,9 +116,6 @@ int smc_cdc_msg_send(struct smc_connection *conn,
 	union smc_host_cursor cfed;
 	int rc;
 
-	if (unlikely(!READ_ONCE(conn->sndbuf_desc)))
-		return -ENOBUFS;
-
 	smc_cdc_add_pending_send(conn, pend);
 
 	conn->tx_cdc_seq++;
@@ -385,7 +384,7 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 		smc->sk.sk_shutdown |= RCV_SHUTDOWN;
 		if (smc->clcsock && smc->clcsock->sk)
 			smc->clcsock->sk->sk_shutdown |= RCV_SHUTDOWN;
-		sock_set_flag(&smc->sk, SOCK_DONE);
+		smc_sock_set_flag(&smc->sk, SOCK_DONE);
 		sock_hold(&smc->sk); /* sock_put in close_work */
 		if (!queue_work(smc_close_wq, &conn->close_work))
 			sock_put(&smc->sk);
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 8deb46c28f1d55..72f4d81a3f41f2 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -1004,6 +1004,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 {
 	struct smc_connection *conn = &smc->conn;
 	struct smc_clc_first_contact_ext_v2x fce;
+	struct smcd_dev *smcd = conn->lgr->smcd;
 	struct smc_clc_msg_accept_confirm *clc;
 	struct smc_clc_fce_gid_ext gle;
 	struct smc_clc_msg_trail trl;
@@ -1021,17 +1022,15 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 		memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER,
 		       sizeof(SMCD_EYECATCHER));
 		clc->hdr.typev1 = SMC_TYPE_D;
-		clc->d0.gid =
-			conn->lgr->smcd->ops->get_local_gid(conn->lgr->smcd);
-		clc->d0.token = conn->rmb_desc->token;
+		clc->d0.gid = htonll(smcd->ops->get_local_gid(smcd));
+		clc->d0.token = htonll(conn->rmb_desc->token);
 		clc->d0.dmbe_size = conn->rmbe_size_comp;
 		clc->d0.dmbe_idx = 0;
 		memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
 		if (version == SMC_V1) {
 			clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
 		} else {
-			clc_v2->d1.chid =
-				htons(smc_ism_get_chid(conn->lgr->smcd));
+			clc_v2->d1.chid = htons(smc_ism_get_chid(smcd));
 			if (eid && eid[0])
 				memcpy(clc_v2->d1.eid, eid, SMC_MAX_EID_LEN);
 			len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2;
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index c5c8e7db775a76..08155a96a02a17 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -204,8 +204,8 @@ struct smcr_clc_msg_accept_confirm {	/* SMCR accept/confirm */
 } __packed;
 
 struct smcd_clc_msg_accept_confirm_common {	/* SMCD accept/confirm */
-	u64 gid;		/* Sender GID */
-	u64 token;		/* DMB token */
+	__be64 gid;		/* Sender GID */
+	__be64 token;		/* DMB token */
 	u8 dmbe_idx;		/* DMBE index */
 #if defined(__BIG_ENDIAN_BITFIELD)
 	u8 dmbe_size : 4,	/* buf size (compressed) */
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index dbdf03e8aa5b55..10219f55aad14d 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -116,7 +116,8 @@ static void smc_close_cancel_work(struct smc_sock *smc)
 	struct sock *sk = &smc->sk;
 
 	release_sock(sk);
-	cancel_work_sync(&smc->conn.close_work);
+	if (cancel_work_sync(&smc->conn.close_work))
+		sock_put(sk);
 	cancel_delayed_work_sync(&smc->conn.tx_work);
 	lock_sock(sk);
 }
@@ -173,7 +174,7 @@ void smc_close_active_abort(struct smc_sock *smc)
 		break;
 	}
 
-	sock_set_flag(sk, SOCK_DEAD);
+	smc_sock_set_flag(sk, SOCK_DEAD);
 	sk->sk_state_change(sk);
 
 	if (release_clcsock) {
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index 7ff2152971a5b8..a584613aca1256 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -268,5 +268,6 @@ static void __exit smc_diag_exit(void)
 module_init(smc_diag_init);
 module_exit(smc_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SMC socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 43 /* AF_SMC */);
 MODULE_ALIAS_GENL_FAMILY(SMCR_GENL_FAMILY_NAME);
diff --git a/net/socket.c b/net/socket.c
index 0d1c4e78fc7f8c..3379c64217a4c1 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1685,20 +1685,16 @@ struct file *__sys_socket_file(int family, int type, int protocol)
  *	Therefore, __weak is needed to ensure that the call is still
  *	emitted, by telling the compiler that we don't know what the
  *	function might eventually be.
- *
- *	__diag_* below are needed to dismiss the missing prototype warning.
  */
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "A fmod_ret entry point for BPF programs");
+__bpf_hook_start();
 
 __weak noinline int update_socket_protocol(int family, int type, int protocol)
 {
 	return protocol;
 }
 
-__diag_pop();
+__bpf_hook_end();
 
 int __sys_socket(int family, int type, int protocol)
 {
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 7bfe7d9a32aa60..04534ea537c8fd 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -40,9 +40,6 @@ static unsigned long number_cred_unused;
 
 static struct cred machine_cred = {
 	.usage = ATOMIC_INIT(1),
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	.magic = CRED_MAGIC,
-#endif
 };
 
 /*
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index fee83d1024bc8d..1b71055fc391a6 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -654,9 +654,8 @@ static bool svc_alloc_arg(struct svc_rqst *rqstp)
 	}
 
 	for (filled = 0; filled < pages; filled = ret) {
-		ret = alloc_pages_bulk_array_node(GFP_KERNEL,
-						  rqstp->rq_pool->sp_id,
-						  pages, rqstp->rq_pages);
+		ret = alloc_pages_bulk_array(GFP_KERNEL, pages,
+					     rqstp->rq_pages);
 		if (ret > filled)
 			/* Made progress, don't sleep yet */
 			continue;
diff --git a/net/tipc/diag.c b/net/tipc/diag.c
index 73137f4aeb68f9..18733451c9e0c2 100644
--- a/net/tipc/diag.c
+++ b/net/tipc/diag.c
@@ -113,4 +113,5 @@ module_init(tipc_diag_init);
 module_exit(tipc_diag_exit);
 
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("TIPC socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_TIPC);
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index e8fd257c0e6888..1a9a5bdaccf4fc 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -88,7 +88,7 @@ const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = {
 
 const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
 	[TIPC_NLA_LINK_UNSPEC]		= { .type = NLA_UNSPEC },
-	[TIPC_NLA_LINK_NAME]		= { .type = NLA_STRING,
+	[TIPC_NLA_LINK_NAME]		= { .type = NLA_NUL_STRING,
 					    .len = TIPC_MAX_LINK_NAME },
 	[TIPC_NLA_LINK_MTU]		= { .type = NLA_U32 },
 	[TIPC_NLA_LINK_BROADCAST]	= { .type = NLA_FLAG },
@@ -125,7 +125,7 @@ const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = {
 
 const struct nla_policy tipc_nl_bearer_policy[TIPC_NLA_BEARER_MAX + 1]	= {
 	[TIPC_NLA_BEARER_UNSPEC]	= { .type = NLA_UNSPEC },
-	[TIPC_NLA_BEARER_NAME]		= { .type = NLA_STRING,
+	[TIPC_NLA_BEARER_NAME]		= { .type = NLA_NUL_STRING,
 					    .len = TIPC_MAX_BEARER_NAME },
 	[TIPC_NLA_BEARER_PROP]		= { .type = NLA_NESTED },
 	[TIPC_NLA_BEARER_DOMAIN]	= { .type = NLA_U32 }
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 5bc076f2fa74a2..c763008a8adbaa 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -102,6 +102,7 @@ static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len)
 		return -EMSGSIZE;
 
 	skb_put(skb, TLV_SPACE(len));
+	memset(tlv, 0, TLV_SPACE(len));
 	tlv->tlv_type = htons(type);
 	tlv->tlv_len = htons(TLV_LENGTH(len));
 	if (len && data)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index a78e8e72240913..e37b4d2e2acde2 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -952,6 +952,8 @@ static int tls_sw_sendmsg_splice(struct sock *sk, struct msghdr *msg,
 		}
 
 		sk_msg_page_add(msg_pl, page, part, off);
+		msg_pl->sg.copybreak = 0;
+		msg_pl->sg.curr = msg_pl->sg.end;
 		sk_mem_charge(sk, part);
 		*copied += part;
 		try_to_copy -= part;
@@ -1232,11 +1234,14 @@ void tls_sw_splice_eof(struct socket *sock)
 	lock_sock(sk);
 
 retry:
+	/* same checks as in tls_sw_push_pending_record() */
 	rec = ctx->open_rec;
 	if (!rec)
 		goto unlock;
 
 	msg_pl = &rec->msg_plaintext;
+	if (msg_pl->sg.size == 0)
+		goto unlock;
 
 	/* Check the BPF advisor and perform transmission. */
 	ret = bpf_exec_tx_verdict(msg_pl, sk, false, TLS_RECORD_TYPE_DATA,
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 45506a95b25f8a..ac1f2bc18fc968 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -213,8 +213,6 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb)
 }
 #endif /* CONFIG_SECURITY_NETWORK */
 
-#define unix_peer(sk) (unix_sk(sk)->peer)
-
 static inline int unix_our_peer(struct sock *sk, struct sock *osk)
 {
 	return unix_peer(osk) == sk;
@@ -2581,15 +2579,16 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 
 	if (!(state->flags & MSG_PEEK))
 		WRITE_ONCE(u->oob_skb, NULL);
-
+	else
+		skb_get(oob_skb);
 	unix_state_unlock(sk);
 
 	chunk = state->recv_actor(oob_skb, 0, chunk, state);
 
-	if (!(state->flags & MSG_PEEK)) {
+	if (!(state->flags & MSG_PEEK))
 		UNIXCB(oob_skb).consumed += 1;
-		kfree_skb(oob_skb);
-	}
+
+	consume_skb(oob_skb);
 
 	mutex_unlock(&u->iolock);
 
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 616b55c5b89080..bec09a3a1d44ce 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -339,4 +339,5 @@ static void __exit unix_diag_exit(void)
 module_init(unix_diag_init);
 module_exit(unix_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("UNIX socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 1 /* AF_LOCAL */);
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index 2f9d8271c6ec7d..7ea7c3a0d0d062 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -159,12 +159,17 @@ int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool re
 
 int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 {
+	struct sock *sk_pair;
+
 	if (restore) {
 		sk->sk_write_space = psock->saved_write_space;
 		sock_replace_proto(sk, psock->sk_proto);
 		return 0;
 	}
 
+	sk_pair = unix_peer(sk);
+	sock_hold(sk_pair);
+	psock->sk_pair = sk_pair;
 	unix_stream_bpf_check_needs_rebuild(psock->sk_proto);
 	sock_replace_proto(sk, &unix_stream_bpf_prot);
 	return 0;
diff --git a/net/vmw_vsock/diag.c b/net/vmw_vsock/diag.c
index a2823b1c5e28b1..2e29994f92ffa2 100644
--- a/net/vmw_vsock/diag.c
+++ b/net/vmw_vsock/diag.c
@@ -174,5 +174,6 @@ static void __exit vsock_diag_exit(void)
 module_init(vsock_diag_init);
 module_exit(vsock_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("VMware Virtual Sockets monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG,
 			       40 /* AF_VSOCK */);
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index e22c81435ef7df..6df246b5326063 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -59,8 +59,7 @@ static bool virtio_transport_can_zcopy(const struct virtio_transport *t_ops,
 	t_ops = virtio_transport_get_ops(info->vsk);
 
 	if (t_ops->can_msgzerocopy) {
-		int pages_in_iov = iov_iter_npages(iov_iter, MAX_SKB_FRAGS);
-		int pages_to_send = min(pages_in_iov, MAX_SKB_FRAGS);
+		int pages_to_send = iov_iter_npages(iov_iter, MAX_SKB_FRAGS);
 
 		/* +1 is for packet header. */
 		return t_ops->can_msgzerocopy(pages_to_send + 1);
@@ -130,6 +129,8 @@ static void virtio_transport_init_hdr(struct sk_buff *skb,
 	hdr->dst_port	= cpu_to_le32(dst_port);
 	hdr->flags	= cpu_to_le32(info->flags);
 	hdr->len	= cpu_to_le32(payload_len);
+	hdr->buf_alloc	= cpu_to_le32(0);
+	hdr->fwd_cnt	= cpu_to_le32(0);
 }
 
 static void virtio_transport_copy_nonlinear_skb(const struct sk_buff *skb,
@@ -842,7 +843,7 @@ static s64 virtio_transport_has_space(struct vsock_sock *vsk)
 	struct virtio_vsock_sock *vvs = vsk->trans;
 	s64 bytes;
 
-	bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
+	bytes = (s64)vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
 	if (bytes < 0)
 		bytes = 0;
 
@@ -1369,11 +1370,17 @@ virtio_transport_recv_connected(struct sock *sk,
 			vsk->peer_shutdown |= RCV_SHUTDOWN;
 		if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SHUTDOWN_SEND)
 			vsk->peer_shutdown |= SEND_SHUTDOWN;
-		if (vsk->peer_shutdown == SHUTDOWN_MASK &&
-		    vsock_stream_has_data(vsk) <= 0 &&
-		    !sock_flag(sk, SOCK_DONE)) {
-			(void)virtio_transport_reset(vsk, NULL);
-			virtio_transport_do_close(vsk, true);
+		if (vsk->peer_shutdown == SHUTDOWN_MASK) {
+			if (vsock_stream_has_data(vsk) <= 0 && !sock_flag(sk, SOCK_DONE)) {
+				(void)virtio_transport_reset(vsk, NULL);
+				virtio_transport_do_close(vsk, true);
+			}
+			/* Remove this socket anyway because the remote peer sent
+			 * the shutdown. This way a new connection will succeed
+			 * if the remote peer uses the same source port,
+			 * even if the old socket is still unreleased, but now disconnected.
+			 */
+			vsock_remove_sock(vsk);
 		}
 		if (le32_to_cpu(virtio_vsock_hdr(skb)->flags))
 			sk->sk_state_change(sk);
diff --git a/net/wireless/certs/wens.hex b/net/wireless/certs/wens.hex
new file mode 100644
index 00000000000000..0d50369bede989
--- /dev/null
+++ b/net/wireless/certs/wens.hex
@@ -0,0 +1,87 @@
+/* Chen-Yu Tsai's regdb certificate */
+0x30, 0x82, 0x02, 0xa7, 0x30, 0x82, 0x01, 0x8f,
+0x02, 0x14, 0x61, 0xc0, 0x38, 0x65, 0x1a, 0xab,
+0xdc, 0xf9, 0x4b, 0xd0, 0xac, 0x7f, 0xf0, 0x6c,
+0x72, 0x48, 0xdb, 0x18, 0xc6, 0x00, 0x30, 0x0d,
+0x06, 0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d,
+0x01, 0x01, 0x0b, 0x05, 0x00, 0x30, 0x0f, 0x31,
+0x0d, 0x30, 0x0b, 0x06, 0x03, 0x55, 0x04, 0x03,
+0x0c, 0x04, 0x77, 0x65, 0x6e, 0x73, 0x30, 0x20,
+0x17, 0x0d, 0x32, 0x33, 0x31, 0x32, 0x30, 0x31,
+0x30, 0x37, 0x34, 0x31, 0x31, 0x34, 0x5a, 0x18,
+0x0f, 0x32, 0x31, 0x32, 0x33, 0x31, 0x31, 0x30,
+0x37, 0x30, 0x37, 0x34, 0x31, 0x31, 0x34, 0x5a,
+0x30, 0x0f, 0x31, 0x0d, 0x30, 0x0b, 0x06, 0x03,
+0x55, 0x04, 0x03, 0x0c, 0x04, 0x77, 0x65, 0x6e,
+0x73, 0x30, 0x82, 0x01, 0x22, 0x30, 0x0d, 0x06,
+0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d, 0x01,
+0x01, 0x01, 0x05, 0x00, 0x03, 0x82, 0x01, 0x0f,
+0x00, 0x30, 0x82, 0x01, 0x0a, 0x02, 0x82, 0x01,
+0x01, 0x00, 0xa9, 0x7a, 0x2c, 0x78, 0x4d, 0xa7,
+0x19, 0x2d, 0x32, 0x52, 0xa0, 0x2e, 0x6c, 0xef,
+0x88, 0x7f, 0x15, 0xc5, 0xb6, 0x69, 0x54, 0x16,
+0x43, 0x14, 0x79, 0x53, 0xb7, 0xae, 0x88, 0xfe,
+0xc0, 0xb7, 0x5d, 0x47, 0x8e, 0x1a, 0xe1, 0xef,
+0xb3, 0x90, 0x86, 0xda, 0xd3, 0x64, 0x81, 0x1f,
+0xce, 0x5d, 0x9e, 0x4b, 0x6e, 0x58, 0x02, 0x3e,
+0xb2, 0x6f, 0x5e, 0x42, 0x47, 0x41, 0xf4, 0x2c,
+0xb8, 0xa8, 0xd4, 0xaa, 0xc0, 0x0e, 0xe6, 0x48,
+0xf0, 0xa8, 0xce, 0xcb, 0x08, 0xae, 0x37, 0xaf,
+0xf6, 0x40, 0x39, 0xcb, 0x55, 0x6f, 0x5b, 0x4f,
+0x85, 0x34, 0xe6, 0x69, 0x10, 0x50, 0x72, 0x5e,
+0x4e, 0x9d, 0x4c, 0xba, 0x38, 0x36, 0x0d, 0xce,
+0x73, 0x38, 0xd7, 0x27, 0x02, 0x2a, 0x79, 0x03,
+0xe1, 0xac, 0xcf, 0xb0, 0x27, 0x85, 0x86, 0x93,
+0x17, 0xab, 0xec, 0x42, 0x77, 0x37, 0x65, 0x8a,
+0x44, 0xcb, 0xd6, 0x42, 0x93, 0x92, 0x13, 0xe3,
+0x39, 0x45, 0xc5, 0x6e, 0x00, 0x4a, 0x7f, 0xcb,
+0x42, 0x17, 0x2b, 0x25, 0x8c, 0xb8, 0x17, 0x3b,
+0x15, 0x36, 0x59, 0xde, 0x42, 0xce, 0x21, 0xe6,
+0xb6, 0xc7, 0x6e, 0x5e, 0x26, 0x1f, 0xf7, 0x8a,
+0x57, 0x9e, 0xa5, 0x96, 0x72, 0xb7, 0x02, 0x32,
+0xeb, 0x07, 0x2b, 0x73, 0xe2, 0x4f, 0x66, 0x58,
+0x9a, 0xeb, 0x0f, 0x07, 0xb6, 0xab, 0x50, 0x8b,
+0xc3, 0x8f, 0x17, 0xfa, 0x0a, 0x99, 0xc2, 0x16,
+0x25, 0xbf, 0x2d, 0x6b, 0x1a, 0xaa, 0xe6, 0x3e,
+0x5f, 0xeb, 0x6d, 0x9b, 0x5d, 0x4d, 0x42, 0x83,
+0x2d, 0x39, 0xb8, 0xc9, 0xac, 0xdb, 0x3a, 0x91,
+0x50, 0xdf, 0xbb, 0xb1, 0x76, 0x6d, 0x15, 0x73,
+0xfd, 0xc6, 0xe6, 0x6b, 0x71, 0x9e, 0x67, 0x36,
+0x22, 0x83, 0x79, 0xb1, 0xd6, 0xb8, 0x84, 0x52,
+0xaf, 0x96, 0x5b, 0xc3, 0x63, 0x02, 0x4e, 0x78,
+0x70, 0x57, 0x02, 0x03, 0x01, 0x00, 0x01, 0x30,
+0x0d, 0x06, 0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7,
+0x0d, 0x01, 0x01, 0x0b, 0x05, 0x00, 0x03, 0x82,
+0x01, 0x01, 0x00, 0x24, 0x28, 0xee, 0x22, 0x74,
+0x7f, 0x7c, 0xfa, 0x6c, 0x1f, 0xb3, 0x18, 0xd1,
+0xc2, 0x3d, 0x7d, 0x29, 0x42, 0x88, 0xad, 0x82,
+0xa5, 0xb1, 0x8a, 0x05, 0xd0, 0xec, 0x5c, 0x91,
+0x20, 0xf6, 0x82, 0xfd, 0xd5, 0x67, 0x60, 0x5f,
+0x31, 0xf5, 0xbd, 0x88, 0x91, 0x70, 0xbd, 0xb8,
+0xb9, 0x8c, 0x88, 0xfe, 0x53, 0xc9, 0x54, 0x9b,
+0x43, 0xc4, 0x7a, 0x43, 0x74, 0x6b, 0xdd, 0xb0,
+0xb1, 0x3b, 0x33, 0x45, 0x46, 0x78, 0xa3, 0x1c,
+0xef, 0x54, 0x68, 0xf7, 0x85, 0x9c, 0xe4, 0x51,
+0x6f, 0x06, 0xaf, 0x81, 0xdb, 0x2a, 0x7b, 0x7b,
+0x6f, 0xa8, 0x9c, 0x67, 0xd8, 0xcb, 0xc9, 0x91,
+0x40, 0x00, 0xae, 0xd9, 0xa1, 0x9f, 0xdd, 0xa6,
+0x43, 0x0e, 0x28, 0x7b, 0xaa, 0x1b, 0xe9, 0x84,
+0xdb, 0x76, 0x64, 0x42, 0x70, 0xc9, 0xc0, 0xeb,
+0xae, 0x84, 0x11, 0x16, 0x68, 0x4e, 0x84, 0x9e,
+0x7e, 0x92, 0x36, 0xee, 0x1c, 0x3b, 0x08, 0x63,
+0xeb, 0x79, 0x84, 0x15, 0x08, 0x9d, 0xaf, 0xc8,
+0x9a, 0xc7, 0x34, 0xd3, 0x94, 0x4b, 0xd1, 0x28,
+0x97, 0xbe, 0xd1, 0x45, 0x75, 0xdc, 0x35, 0x62,
+0xac, 0x1d, 0x1f, 0xb7, 0xb7, 0x15, 0x87, 0xc8,
+0x98, 0xc0, 0x24, 0x31, 0x56, 0x8d, 0xed, 0xdb,
+0x06, 0xc6, 0x46, 0xbf, 0x4b, 0x6d, 0xa6, 0xd5,
+0xab, 0xcc, 0x60, 0xfc, 0xe5, 0x37, 0xb6, 0x53,
+0x7d, 0x58, 0x95, 0xa9, 0x56, 0xc7, 0xf7, 0xee,
+0xc3, 0xa0, 0x76, 0xf7, 0x65, 0x4d, 0x53, 0xfa,
+0xff, 0x5f, 0x76, 0x33, 0x5a, 0x08, 0xfa, 0x86,
+0x92, 0x5a, 0x13, 0xfa, 0x1a, 0xfc, 0xf2, 0x1b,
+0x8c, 0x7f, 0x42, 0x6d, 0xb7, 0x7e, 0xb7, 0xb4,
+0xf0, 0xc7, 0x83, 0xbb, 0xa2, 0x81, 0x03, 0x2d,
+0xd4, 0x2a, 0x63, 0x3f, 0xf7, 0x31, 0x2e, 0x40,
+0x33, 0x5c, 0x46, 0xbc, 0x9b, 0xc1, 0x05, 0xa5,
+0x45, 0x4e, 0xc3,
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 758c9a2a12c0d3..409d74c57ca0d8 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -191,13 +191,13 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
 		return err;
 	}
 
+	wiphy_lock(&rdev->wiphy);
 	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
 		if (!wdev->netdev)
 			continue;
 		nl80211_notify_iface(rdev, wdev, NL80211_CMD_DEL_INTERFACE);
 	}
 
-	wiphy_lock(&rdev->wiphy);
 	nl80211_notify_wiphy(rdev, NL80211_CMD_DEL_WIPHY);
 
 	wiphy_net_set(&rdev->wiphy, net);
@@ -206,13 +206,13 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
 	WARN_ON(err);
 
 	nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY);
-	wiphy_unlock(&rdev->wiphy);
 
 	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
 		if (!wdev->netdev)
 			continue;
 		nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE);
 	}
+	wiphy_unlock(&rdev->wiphy);
 
 	return 0;
 }
@@ -221,7 +221,9 @@ static void cfg80211_rfkill_poll(struct rfkill *rfkill, void *data)
 {
 	struct cfg80211_registered_device *rdev = data;
 
+	wiphy_lock(&rdev->wiphy);
 	rdev_rfkill_poll(rdev);
+	wiphy_unlock(&rdev->wiphy);
 }
 
 void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev,
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 4c692c7faf30d4..cb61d33d4f1ebc 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -293,6 +293,7 @@ struct cfg80211_cqm_config {
 	u32 rssi_hyst;
 	s32 last_rssi_event_value;
 	enum nl80211_cqm_rssi_threshold_event last_rssi_event_type;
+	bool use_range_api;
 	int n_rssi_thresholds;
 	s32 rssi_thresholds[] __counted_by(n_rssi_thresholds);
 };
diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c
index 0878b162890af7..40e49074e2eeb9 100644
--- a/net/wireless/debugfs.c
+++ b/net/wireless/debugfs.c
@@ -4,6 +4,7 @@
  *
  * Copyright 2009	Luis R. Rodriguez <lrodriguez@atheros.com>
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright (C) 2023 Intel Corporation
  */
 
 #include <linux/slab.h>
@@ -109,3 +110,162 @@ void cfg80211_debugfs_rdev_add(struct cfg80211_registered_device *rdev)
 	DEBUGFS_ADD(long_retry_limit);
 	DEBUGFS_ADD(ht40allow_map);
 }
+
+struct debugfs_read_work {
+	struct wiphy_work work;
+	ssize_t (*handler)(struct wiphy *wiphy,
+			   struct file *file,
+			   char *buf,
+			   size_t count,
+			   void *data);
+	struct wiphy *wiphy;
+	struct file *file;
+	char *buf;
+	size_t bufsize;
+	void *data;
+	ssize_t ret;
+	struct completion completion;
+};
+
+static void wiphy_locked_debugfs_read_work(struct wiphy *wiphy,
+					   struct wiphy_work *work)
+{
+	struct debugfs_read_work *w = container_of(work, typeof(*w), work);
+
+	w->ret = w->handler(w->wiphy, w->file, w->buf, w->bufsize, w->data);
+	complete(&w->completion);
+}
+
+static void wiphy_locked_debugfs_read_cancel(struct dentry *dentry,
+					     void *data)
+{
+	struct debugfs_read_work *w = data;
+
+	wiphy_work_cancel(w->wiphy, &w->work);
+	complete(&w->completion);
+}
+
+ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file,
+				  char *buf, size_t bufsize,
+				  char __user *userbuf, size_t count,
+				  loff_t *ppos,
+				  ssize_t (*handler)(struct wiphy *wiphy,
+						     struct file *file,
+						     char *buf,
+						     size_t bufsize,
+						     void *data),
+				  void *data)
+{
+	struct debugfs_read_work work = {
+		.handler = handler,
+		.wiphy = wiphy,
+		.file = file,
+		.buf = buf,
+		.bufsize = bufsize,
+		.data = data,
+		.ret = -ENODEV,
+		.completion = COMPLETION_INITIALIZER_ONSTACK(work.completion),
+	};
+	struct debugfs_cancellation cancellation = {
+		.cancel = wiphy_locked_debugfs_read_cancel,
+		.cancel_data = &work,
+	};
+
+	/* don't leak stack data or whatever */
+	memset(buf, 0, bufsize);
+
+	wiphy_work_init(&work.work, wiphy_locked_debugfs_read_work);
+	wiphy_work_queue(wiphy, &work.work);
+
+	debugfs_enter_cancellation(file, &cancellation);
+	wait_for_completion(&work.completion);
+	debugfs_leave_cancellation(file, &cancellation);
+
+	if (work.ret < 0)
+		return work.ret;
+
+	if (WARN_ON(work.ret > bufsize))
+		return -EINVAL;
+
+	return simple_read_from_buffer(userbuf, count, ppos, buf, work.ret);
+}
+EXPORT_SYMBOL_GPL(wiphy_locked_debugfs_read);
+
+struct debugfs_write_work {
+	struct wiphy_work work;
+	ssize_t (*handler)(struct wiphy *wiphy,
+			   struct file *file,
+			   char *buf,
+			   size_t count,
+			   void *data);
+	struct wiphy *wiphy;
+	struct file *file;
+	char *buf;
+	size_t count;
+	void *data;
+	ssize_t ret;
+	struct completion completion;
+};
+
+static void wiphy_locked_debugfs_write_work(struct wiphy *wiphy,
+					    struct wiphy_work *work)
+{
+	struct debugfs_write_work *w = container_of(work, typeof(*w), work);
+
+	w->ret = w->handler(w->wiphy, w->file, w->buf, w->count, w->data);
+	complete(&w->completion);
+}
+
+static void wiphy_locked_debugfs_write_cancel(struct dentry *dentry,
+					      void *data)
+{
+	struct debugfs_write_work *w = data;
+
+	wiphy_work_cancel(w->wiphy, &w->work);
+	complete(&w->completion);
+}
+
+ssize_t wiphy_locked_debugfs_write(struct wiphy *wiphy,
+				   struct file *file, char *buf, size_t bufsize,
+				   const char __user *userbuf, size_t count,
+				   ssize_t (*handler)(struct wiphy *wiphy,
+						      struct file *file,
+						      char *buf,
+						      size_t count,
+						      void *data),
+				   void *data)
+{
+	struct debugfs_write_work work = {
+		.handler = handler,
+		.wiphy = wiphy,
+		.file = file,
+		.buf = buf,
+		.count = count,
+		.data = data,
+		.ret = -ENODEV,
+		.completion = COMPLETION_INITIALIZER_ONSTACK(work.completion),
+	};
+	struct debugfs_cancellation cancellation = {
+		.cancel = wiphy_locked_debugfs_write_cancel,
+		.cancel_data = &work,
+	};
+
+	/* mostly used for strings so enforce NUL-termination for safety */
+	if (count >= bufsize)
+		return -EINVAL;
+
+	memset(buf, 0, bufsize);
+
+	if (copy_from_user(buf, userbuf, count))
+		return -EFAULT;
+
+	wiphy_work_init(&work.work, wiphy_locked_debugfs_write_work);
+	wiphy_work_queue(wiphy, &work.work);
+
+	debugfs_enter_cancellation(file, &cancellation);
+	wait_for_completion(&work.completion);
+	debugfs_leave_cancellation(file, &cancellation);
+
+	return work.ret;
+}
+EXPORT_SYMBOL_GPL(wiphy_locked_debugfs_write);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 569234bc2be6ae..1cbbb11ea5033f 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3822,6 +3822,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag
 	struct net_device *dev = wdev->netdev;
 	void *hdr;
 
+	lockdep_assert_wiphy(&rdev->wiphy);
+
 	WARN_ON(cmd != NL80211_CMD_NEW_INTERFACE &&
 		cmd != NL80211_CMD_DEL_INTERFACE &&
 		cmd != NL80211_CMD_SET_INTERFACE);
@@ -3989,6 +3991,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
 
 		if_idx = 0;
 
+		wiphy_lock(&rdev->wiphy);
 		list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
 			if (if_idx < if_start) {
 				if_idx++;
@@ -3998,10 +4001,12 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
 					       cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					       rdev, wdev,
 					       NL80211_CMD_NEW_INTERFACE) < 0) {
+				wiphy_unlock(&rdev->wiphy);
 				goto out;
 			}
 			if_idx++;
 		}
+		wiphy_unlock(&rdev->wiphy);
 
 		wp_idx++;
 	}
@@ -12787,10 +12792,6 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev,
 	int i, n, low_index;
 	int err;
 
-	/* RSSI reporting disabled? */
-	if (!cqm_config)
-		return rdev_set_cqm_rssi_range_config(rdev, dev, 0, 0);
-
 	/*
 	 * Obtain current RSSI value if possible, if not and no RSSI threshold
 	 * event has been received yet, we should receive an event after a
@@ -12865,23 +12866,25 @@ static int nl80211_set_cqm_rssi(struct genl_info *info,
 	    wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)
 		return -EOPNOTSUPP;
 
-	if (n_thresholds <= 1 && rdev->ops->set_cqm_rssi_config) {
-		if (n_thresholds == 0 || thresholds[0] == 0) /* Disabling */
-			return rdev_set_cqm_rssi_config(rdev, dev, 0, 0);
-
-		return rdev_set_cqm_rssi_config(rdev, dev,
-						thresholds[0], hysteresis);
-	}
-
-	if (!wiphy_ext_feature_isset(&rdev->wiphy,
-				     NL80211_EXT_FEATURE_CQM_RSSI_LIST))
-		return -EOPNOTSUPP;
-
 	if (n_thresholds == 1 && thresholds[0] == 0) /* Disabling */
 		n_thresholds = 0;
 
 	old = wiphy_dereference(wdev->wiphy, wdev->cqm_config);
 
+	/* if already disabled just succeed */
+	if (!n_thresholds && !old)
+		return 0;
+
+	if (n_thresholds > 1) {
+		if (!wiphy_ext_feature_isset(&rdev->wiphy,
+					     NL80211_EXT_FEATURE_CQM_RSSI_LIST) ||
+		    !rdev->ops->set_cqm_rssi_range_config)
+			return -EOPNOTSUPP;
+	} else {
+		if (!rdev->ops->set_cqm_rssi_config)
+			return -EOPNOTSUPP;
+	}
+
 	if (n_thresholds) {
 		cqm_config = kzalloc(struct_size(cqm_config, rssi_thresholds,
 						 n_thresholds),
@@ -12894,13 +12897,26 @@ static int nl80211_set_cqm_rssi(struct genl_info *info,
 		memcpy(cqm_config->rssi_thresholds, thresholds,
 		       flex_array_size(cqm_config, rssi_thresholds,
 				       n_thresholds));
+		cqm_config->use_range_api = n_thresholds > 1 ||
+					    !rdev->ops->set_cqm_rssi_config;
 
 		rcu_assign_pointer(wdev->cqm_config, cqm_config);
+
+		if (cqm_config->use_range_api)
+			err = cfg80211_cqm_rssi_update(rdev, dev, cqm_config);
+		else
+			err = rdev_set_cqm_rssi_config(rdev, dev,
+						       thresholds[0],
+						       hysteresis);
 	} else {
 		RCU_INIT_POINTER(wdev->cqm_config, NULL);
+		/* if enabled as range also disable via range */
+		if (old->use_range_api)
+			err = rdev_set_cqm_rssi_range_config(rdev, dev, 0, 0);
+		else
+			err = rdev_set_cqm_rssi_config(rdev, dev, 0, 0);
 	}
 
-	err = cfg80211_cqm_rssi_update(rdev, dev, cqm_config);
 	if (err) {
 		rcu_assign_pointer(wdev->cqm_config, old);
 		kfree_rcu(cqm_config, rcu_head);
@@ -19009,10 +19025,11 @@ void cfg80211_cqm_rssi_notify_work(struct wiphy *wiphy, struct wiphy_work *work)
 	s32 rssi_level;
 
 	cqm_config = wiphy_dereference(wdev->wiphy, wdev->cqm_config);
-	if (!wdev->cqm_config)
+	if (!cqm_config)
 		return;
 
-	cfg80211_cqm_rssi_update(rdev, wdev->netdev, cqm_config);
+	if (cqm_config->use_range_api)
+		cfg80211_cqm_rssi_update(rdev, wdev->netdev, cqm_config);
 
 	rssi_level = cqm_config->last_rssi_event_value;
 	rssi_event = cqm_config->last_rssi_event_type;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index ae9f8cb611f6ca..3da0b52f308d4a 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -947,7 +947,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 
 	rcu_read_lock();
 	if (xsk_check_common(xs))
-		goto skip_tx;
+		goto out;
 
 	pool = xs->pool;
 
@@ -959,12 +959,11 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 			xsk_generic_xmit(sk);
 	}
 
-skip_tx:
 	if (xs->rx && !xskq_prod_is_empty(xs->rx))
 		mask |= EPOLLIN | EPOLLRDNORM;
 	if (xs->tx && xsk_tx_writeable(xs))
 		mask |= EPOLLOUT | EPOLLWRNORM;
-
+out:
 	rcu_read_unlock();
 	return mask;
 }
diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c
index 22b36c8143cfd5..9f8955367275e2 100644
--- a/net/xdp/xsk_diag.c
+++ b/net/xdp/xsk_diag.c
@@ -211,4 +211,5 @@ static void __exit xsk_diag_exit(void)
 module_init(xsk_diag_init);
 module_exit(xsk_diag_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("XDP socket monitoring via SOCK_DIAG");
 MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_XDP);
diff --git a/net/xfrm/xfrm_interface_bpf.c b/net/xfrm/xfrm_interface_bpf.c
index d74f3fd20f2bf2..7d5e920141e9b7 100644
--- a/net/xfrm/xfrm_interface_bpf.c
+++ b/net/xfrm/xfrm_interface_bpf.c
@@ -27,9 +27,7 @@ struct bpf_xfrm_info {
 	int link;
 };
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in xfrm_interface BTF");
+__bpf_kfunc_start_defs();
 
 /* bpf_skb_get_xfrm_info - Get XFRM metadata
  *
@@ -93,7 +91,7 @@ __bpf_kfunc int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx, const struct bp
 	return 0;
 }
 
-__diag_pop()
+__bpf_kfunc_end_defs();
 
 BTF_SET8_START(xfrm_ifc_kfunc_set)
 BTF_ID_FLAGS(func, bpf_skb_get_xfrm_info)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 68d0134bdbf9d1..1a965fe68e0111 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -487,14 +487,14 @@ UIMAGE_OPTS-y ?=
 UIMAGE_TYPE ?= kernel
 UIMAGE_LOADADDR ?= arch_must_set_this
 UIMAGE_ENTRYADDR ?= $(UIMAGE_LOADADDR)
-UIMAGE_NAME ?= 'Linux-$(KERNELRELEASE)'
+UIMAGE_NAME ?= Linux-$(KERNELRELEASE)
 
 quiet_cmd_uimage = UIMAGE  $@
       cmd_uimage = $(BASH) $(MKIMAGE) -A $(UIMAGE_ARCH) -O linux \
 			-C $(UIMAGE_COMPRESSION) $(UIMAGE_OPTS-y) \
 			-T $(UIMAGE_TYPE) \
 			-a $(UIMAGE_LOADADDR) -e $(UIMAGE_ENTRYADDR) \
-			-n $(UIMAGE_NAME) -d $< $@
+			-n '$(UIMAGE_NAME)' -d $< $@
 
 # XZ
 # ---------------------------------------------------------------------------
diff --git a/scripts/checkstack.pl b/scripts/checkstack.pl
index 84f5fb7f1cecc2..f27d552aec43f2 100755
--- a/scripts/checkstack.pl
+++ b/scripts/checkstack.pl
@@ -97,8 +97,7 @@ my (@stack, $re, $dre, $sub, $x, $xs, $funcre, $min_stack);
 		#   11160:       a7 fb ff 60             aghi   %r15,-160
 		# or
 		#  100092:	 e3 f0 ff c8 ff 71	 lay	 %r15,-56(%r15)
-		$re = qr/.*(?:lay|ag?hi).*\%r15,-(([0-9]{2}|[3-9])[0-9]{2})
-		      (?:\(\%r15\))?$/ox;
+		$re = qr/.*(?:lay|ag?hi).*\%r15,-([0-9]+)(?:\(\%r15\))?$/o;
 	} elsif ($arch eq 'sparc' || $arch eq 'sparc64') {
 		# f0019d10:       9d e3 bf 90     save  %sp, -112, %sp
 		$re = qr/.*save.*%sp, -(([0-9]{2}|[3-9])[0-9]{2}), %sp/o;
@@ -139,15 +138,11 @@ $total_size = 0;
 while (my $line = <STDIN>) {
 	if ($line =~ m/$funcre/) {
 		$func = $1;
-		next if $line !~ m/^($xs*)/;
+		next if $line !~ m/^($x*)/;
 		if ($total_size > $min_stack) {
 			push @stack, "$intro$total_size\n";
 		}
-
-		$addr = $1;
-		$addr =~ s/ /0/g;
-		$addr = "0x$addr";
-
+		$addr = "0x$1";
 		$intro = "$addr $func [$file]:";
 		my $padlen = 56 - length($intro);
 		while ($padlen > 0) {
diff --git a/scripts/dtc/dt-extract-compatibles b/scripts/dtc/dt-extract-compatibles
index bd07477dd1440f..5ffb2364409b17 100755
--- a/scripts/dtc/dt-extract-compatibles
+++ b/scripts/dtc/dt-extract-compatibles
@@ -1,8 +1,8 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0-only
 
+import fnmatch
 import os
-import glob
 import re
 import argparse
 
@@ -81,10 +81,20 @@ def print_compat(filename, compatibles):
 	else:
 		print(*compatibles, sep='\n')
 
+def glob_without_symlinks(root, glob):
+	for path, dirs, files in os.walk(root):
+		# Ignore hidden directories
+		for d in dirs:
+			if fnmatch.fnmatch(d, ".*"):
+				dirs.remove(d)
+		for f in files:
+			if fnmatch.fnmatch(f, glob):
+				yield os.path.join(path, f)
+
 def files_to_parse(path_args):
 	for f in path_args:
 		if os.path.isdir(f):
-			for filename in glob.iglob(f + "/**/*.c", recursive=True):
+			for filename in glob_without_symlinks(f, "*.c"):
 				yield filename
 		else:
 			yield f
diff --git a/scripts/gcc-plugins/latent_entropy_plugin.c b/scripts/gcc-plugins/latent_entropy_plugin.c
index 39e86be60dd2d7..ff0b192be91ff6 100644
--- a/scripts/gcc-plugins/latent_entropy_plugin.c
+++ b/scripts/gcc-plugins/latent_entropy_plugin.c
@@ -17,7 +17,7 @@
  *	if (argc <= 1)
  *		printf("%s: no command arguments :(\n", *argv);
  *	else
- *		printf("%s: %d command arguments!\n", *argv, args - 1);
+ *		printf("%s: %d command arguments!\n", *argv, argc - 1);
  * }
  *
  * after:
@@ -47,7 +47,7 @@
  *		// perturb_local_entropy()
  *	} else {
  *		local_entropy ^= 3896280633962944730;
- *		printf("%s: %d command arguments!\n", *argv, args - 1);
+ *		printf("%s: %d command arguments!\n", *argv, argc - 1);
  *	}
  *
  *	// latent_entropy_execute() 4.
diff --git a/scripts/gcc-plugins/randomize_layout_plugin.c b/scripts/gcc-plugins/randomize_layout_plugin.c
index 366395cab490de..746ff2d272f256 100644
--- a/scripts/gcc-plugins/randomize_layout_plugin.c
+++ b/scripts/gcc-plugins/randomize_layout_plugin.c
@@ -278,8 +278,6 @@ static bool is_flexible_array(const_tree field)
 {
 	const_tree fieldtype;
 	const_tree typesize;
-	const_tree elemtype;
-	const_tree elemsize;
 
 	fieldtype = TREE_TYPE(field);
 	typesize = TYPE_SIZE(fieldtype);
@@ -287,20 +285,12 @@ static bool is_flexible_array(const_tree field)
 	if (TREE_CODE(fieldtype) != ARRAY_TYPE)
 		return false;
 
-	elemtype = TREE_TYPE(fieldtype);
-	elemsize = TYPE_SIZE(elemtype);
-
 	/* size of type is represented in bits */
 
 	if (typesize == NULL_TREE && TYPE_DOMAIN(fieldtype) != NULL_TREE &&
 	    TYPE_MAX_VALUE(TYPE_DOMAIN(fieldtype)) == NULL_TREE)
 		return true;
 
-	if (typesize != NULL_TREE &&
-	    (TREE_CONSTANT(typesize) && (!tree_to_uhwi(typesize) ||
-	     tree_to_uhwi(typesize) == tree_to_uhwi(elemsize))))
-		return true;
-
 	return false;
 }
 
@@ -349,8 +339,7 @@ static int relayout_struct(tree type)
 
 	/*
 	 * enforce that we don't randomize the layout of the last
-	 * element of a struct if it's a 0 or 1-length array
-	 * or a proper flexible array
+	 * element of a struct if it's a proper flexible array
 	 */
 	if (is_flexible_array(newtree[num_fields - 1])) {
 		has_flexarray = true;
diff --git a/scripts/gdb/linux/device.py b/scripts/gdb/linux/device.py
index 16376c5cfec641..0eabc5f4f8ca22 100644
--- a/scripts/gdb/linux/device.py
+++ b/scripts/gdb/linux/device.py
@@ -36,26 +36,26 @@ def for_each_bus():
     for kobj in kset_for_each_object(gdb.parse_and_eval('bus_kset')):
         subsys = container_of(kobj, kset_type.get_type().pointer(), 'kobj')
         subsys_priv = container_of(subsys, subsys_private_type.get_type().pointer(), 'subsys')
-        yield subsys_priv['bus']
+        yield subsys_priv
 
 
 def for_each_class():
     for kobj in kset_for_each_object(gdb.parse_and_eval('class_kset')):
         subsys = container_of(kobj, kset_type.get_type().pointer(), 'kobj')
         subsys_priv = container_of(subsys, subsys_private_type.get_type().pointer(), 'subsys')
-        yield subsys_priv['class']
+        yield subsys_priv
 
 
 def get_bus_by_name(name):
     for item in for_each_bus():
-        if item['name'].string() == name:
+        if item['bus']['name'].string() == name:
             return item
     raise gdb.GdbError("Can't find bus type {!r}".format(name))
 
 
 def get_class_by_name(name):
     for item in for_each_class():
-        if item['name'].string() == name:
+        if item['class']['name'].string() == name:
             return item
     raise gdb.GdbError("Can't find device class {!r}".format(name))
 
@@ -70,13 +70,13 @@ def klist_for_each(klist):
 
 
 def bus_for_each_device(bus):
-    for kn in klist_for_each(bus['p']['klist_devices']):
+    for kn in klist_for_each(bus['klist_devices']):
         dp = container_of(kn, device_private_type.get_type().pointer(), 'knode_bus')
         yield dp['device']
 
 
 def class_for_each_device(cls):
-    for kn in klist_for_each(cls['p']['klist_devices']):
+    for kn in klist_for_each(cls['klist_devices']):
         dp = container_of(kn, device_private_type.get_type().pointer(), 'knode_class')
         yield dp['device']
 
@@ -103,7 +103,7 @@ class LxDeviceListBus(gdb.Command):
     def invoke(self, arg, from_tty):
         if not arg:
             for bus in for_each_bus():
-                gdb.write('bus {}:\t{}\n'.format(bus['name'].string(), bus))
+                gdb.write('bus {}:\t{}\n'.format(bus['bus']['name'].string(), bus))
                 for dev in bus_for_each_device(bus):
                     _show_device(dev, level=1)
         else:
@@ -123,7 +123,7 @@ class LxDeviceListClass(gdb.Command):
     def invoke(self, arg, from_tty):
         if not arg:
             for cls in for_each_class():
-                gdb.write("class {}:\t{}\n".format(cls['name'].string(), cls))
+                gdb.write("class {}:\t{}\n".format(cls['class']['name'].string(), cls))
                 for dev in class_for_each_device(cls):
                     _show_device(dev, level=1)
         else:
diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py
index 17ec19e9b5bf6a..aa5ab6251f763b 100644
--- a/scripts/gdb/linux/tasks.py
+++ b/scripts/gdb/linux/tasks.py
@@ -13,7 +13,7 @@
 
 import gdb
 
-from linux import utils
+from linux import utils, lists
 
 
 task_type = utils.CachedType("struct task_struct")
@@ -22,19 +22,15 @@ task_type = utils.CachedType("struct task_struct")
 def task_lists():
     task_ptr_type = task_type.get_type().pointer()
     init_task = gdb.parse_and_eval("init_task").address
-    t = g = init_task
+    t = init_task
 
     while True:
-        while True:
-            yield t
+        thread_head = t['signal']['thread_head']
+        for thread in lists.list_for_each_entry(thread_head, task_ptr_type, 'thread_node'):
+            yield thread
 
-            t = utils.container_of(t['thread_group']['next'],
-                                   task_ptr_type, "thread_group")
-            if t == g:
-                break
-
-        t = g = utils.container_of(g['tasks']['next'],
-                                   task_ptr_type, "tasks")
+        t = utils.container_of(t['tasks']['next'],
+                               task_ptr_type, "tasks")
         if t == init_task:
             return
 
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index 0572330bf8a78a..a76925b46ce630 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -122,9 +122,9 @@ static long long sym_get_range_val(struct symbol *sym, int base)
 static void sym_validate_range(struct symbol *sym)
 {
 	struct property *prop;
+	struct symbol *range_sym;
 	int base;
 	long long val, val2;
-	char str[64];
 
 	switch (sym->type) {
 	case S_INT:
@@ -140,17 +140,15 @@ static void sym_validate_range(struct symbol *sym)
 	if (!prop)
 		return;
 	val = strtoll(sym->curr.val, NULL, base);
-	val2 = sym_get_range_val(prop->expr->left.sym, base);
+	range_sym = prop->expr->left.sym;
+	val2 = sym_get_range_val(range_sym, base);
 	if (val >= val2) {
-		val2 = sym_get_range_val(prop->expr->right.sym, base);
+		range_sym = prop->expr->right.sym;
+		val2 = sym_get_range_val(range_sym, base);
 		if (val <= val2)
 			return;
 	}
-	if (sym->type == S_INT)
-		sprintf(str, "%lld", val2);
-	else
-		sprintf(str, "0x%llx", val2);
-	sym->curr.val = xstrdup(str);
+	sym->curr.val = range_sym->curr.val;
 }
 
 static void sym_set_changed(struct symbol *sym)
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 973b5e5ae2dddc..cb6406f485a960 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1383,13 +1383,15 @@ static void section_rela(struct module *mod, struct elf_info *elf,
 	const Elf_Rela *rela;
 
 	for (rela = start; rela < stop; rela++) {
+		Elf_Sym *tsym;
 		Elf_Addr taddr, r_offset;
 		unsigned int r_type, r_sym;
 
 		r_offset = TO_NATIVE(rela->r_offset);
 		get_rel_type_and_sym(elf, rela->r_info, &r_type, &r_sym);
 
-		taddr = TO_NATIVE(rela->r_addend);
+		tsym = elf->symtab_start + r_sym;
+		taddr = tsym->st_value + TO_NATIVE(rela->r_addend);
 
 		switch (elf->hdr->e_machine) {
 		case EM_RISCV:
@@ -1404,7 +1406,7 @@ static void section_rela(struct module *mod, struct elf_info *elf,
 			break;
 		}
 
-		check_section_mismatch(mod, elf, elf->symtab_start + r_sym,
+		check_section_mismatch(mod, elf, tsym,
 				       fsecndx, fromsec, r_offset, taddr);
 	}
 }
diff --git a/scripts/sign-file.c b/scripts/sign-file.c
index 598ef5465f8256..3edb156ae52c30 100644
--- a/scripts/sign-file.c
+++ b/scripts/sign-file.c
@@ -322,7 +322,7 @@ int main(int argc, char **argv)
 				     CMS_NOSMIMECAP | use_keyid |
 				     use_signed_attrs),
 		    "CMS_add1_signer");
-		ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) < 0,
+		ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) != 1,
 		    "CMS_final");
 
 #else
@@ -341,10 +341,10 @@ int main(int argc, char **argv)
 			b = BIO_new_file(sig_file_name, "wb");
 			ERR(!b, "%s", sig_file_name);
 #ifndef USE_PKCS7
-			ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) < 0,
+			ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) != 1,
 			    "%s", sig_file_name);
 #else
-			ERR(i2d_PKCS7_bio(b, pkcs7) < 0,
+			ERR(i2d_PKCS7_bio(b, pkcs7) != 1,
 			    "%s", sig_file_name);
 #endif
 			BIO_free(b);
@@ -374,9 +374,9 @@ int main(int argc, char **argv)
 
 	if (!raw_sig) {
 #ifndef USE_PKCS7
-		ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) < 0, "%s", dest_name);
+		ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) != 1, "%s", dest_name);
 #else
-		ERR(i2d_PKCS7_bio(bd, pkcs7) < 0, "%s", dest_name);
+		ERR(i2d_PKCS7_bio(bd, pkcs7) != 1, "%s", dest_name);
 #endif
 	} else {
 		BIO *b;
@@ -396,7 +396,7 @@ int main(int argc, char **argv)
 	ERR(BIO_write(bd, &sig_info, sizeof(sig_info)) < 0, "%s", dest_name);
 	ERR(BIO_write(bd, magic_number, sizeof(magic_number) - 1) < 0, "%s", dest_name);
 
-	ERR(BIO_free(bd) < 0, "%s", dest_name);
+	ERR(BIO_free(bd) != 1, "%s", dest_name);
 
 	/* Finally, if we're signing in place, replace the original. */
 	if (replace_orig)
diff --git a/security/keys/gc.c b/security/keys/gc.c
index 3c90807476eb0e..eaddaceda14eab 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -67,6 +67,19 @@ void key_schedule_gc(time64_t gc_at)
 }
 
 /*
+ * Set the expiration time on a key.
+ */
+void key_set_expiry(struct key *key, time64_t expiry)
+{
+	key->expiry = expiry;
+	if (expiry != TIME64_MAX) {
+		if (!(key->type->flags & KEY_TYPE_INSTANT_REAP))
+			expiry += key_gc_delay;
+		key_schedule_gc(expiry);
+	}
+}
+
+/*
  * Schedule a dead links collection run.
  */
 void key_schedule_gc_links(void)
@@ -176,7 +189,6 @@ static void key_garbage_collector(struct work_struct *work)
 	static u8 gc_state;		/* Internal persistent state */
 #define KEY_GC_REAP_AGAIN	0x01	/* - Need another cycle */
 #define KEY_GC_REAPING_LINKS	0x02	/* - We need to reap links */
-#define KEY_GC_SET_TIMER	0x04	/* - We need to restart the timer */
 #define KEY_GC_REAPING_DEAD_1	0x10	/* - We need to mark dead keys */
 #define KEY_GC_REAPING_DEAD_2	0x20	/* - We need to reap dead key links */
 #define KEY_GC_REAPING_DEAD_3	0x40	/* - We need to reap dead keys */
@@ -184,21 +196,17 @@ static void key_garbage_collector(struct work_struct *work)
 
 	struct rb_node *cursor;
 	struct key *key;
-	time64_t new_timer, limit;
+	time64_t new_timer, limit, expiry;
 
 	kenter("[%lx,%x]", key_gc_flags, gc_state);
 
 	limit = ktime_get_real_seconds();
-	if (limit > key_gc_delay)
-		limit -= key_gc_delay;
-	else
-		limit = key_gc_delay;
 
 	/* Work out what we're going to be doing in this pass */
 	gc_state &= KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2;
 	gc_state <<= 1;
 	if (test_and_clear_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags))
-		gc_state |= KEY_GC_REAPING_LINKS | KEY_GC_SET_TIMER;
+		gc_state |= KEY_GC_REAPING_LINKS;
 
 	if (test_and_clear_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags))
 		gc_state |= KEY_GC_REAPING_DEAD_1;
@@ -233,8 +241,11 @@ continue_scanning:
 			}
 		}
 
-		if (gc_state & KEY_GC_SET_TIMER) {
-			if (key->expiry > limit && key->expiry < new_timer) {
+		expiry = key->expiry;
+		if (expiry != TIME64_MAX) {
+			if (!(key->type->flags & KEY_TYPE_INSTANT_REAP))
+				expiry += key_gc_delay;
+			if (expiry > limit && expiry < new_timer) {
 				kdebug("will expire %x in %lld",
 				       key_serial(key), key->expiry - limit);
 				new_timer = key->expiry;
@@ -276,7 +287,7 @@ maybe_resched:
 	 */
 	kdebug("pass complete");
 
-	if (gc_state & KEY_GC_SET_TIMER && new_timer != (time64_t)TIME64_MAX) {
+	if (new_timer != TIME64_MAX) {
 		new_timer += key_gc_delay;
 		key_schedule_gc(new_timer);
 	}
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 471cf36dedc026..2cffa6dc82557b 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -167,6 +167,7 @@ extern unsigned key_gc_delay;
 extern void keyring_gc(struct key *keyring, time64_t limit);
 extern void keyring_restriction_gc(struct key *keyring,
 				   struct key_type *dead_type);
+void key_set_expiry(struct key *key, time64_t expiry);
 extern void key_schedule_gc(time64_t gc_at);
 extern void key_schedule_gc_links(void);
 extern void key_gc_keytype(struct key_type *ktype);
@@ -215,10 +216,18 @@ extern struct key *key_get_instantiation_authkey(key_serial_t target_id);
  */
 static inline bool key_is_dead(const struct key *key, time64_t limit)
 {
+	time64_t expiry = key->expiry;
+
+	if (expiry != TIME64_MAX) {
+		if (!(key->type->flags & KEY_TYPE_INSTANT_REAP))
+			expiry += key_gc_delay;
+		if (expiry <= limit)
+			return true;
+	}
+
 	return
 		key->flags & ((1 << KEY_FLAG_DEAD) |
 			      (1 << KEY_FLAG_INVALIDATED)) ||
-		(key->expiry > 0 && key->expiry <= limit) ||
 		key->domain_tag->removed;
 }
 
diff --git a/security/keys/key.c b/security/keys/key.c
index 0260a1902922eb..5b10641debd549 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -294,6 +294,7 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 	key->uid = uid;
 	key->gid = gid;
 	key->perm = perm;
+	key->expiry = TIME64_MAX;
 	key->restrict_link = restrict_link;
 	key->last_used_at = ktime_get_real_seconds();
 
@@ -463,10 +464,7 @@ static int __key_instantiate_and_link(struct key *key,
 			if (authkey)
 				key_invalidate(authkey);
 
-			if (prep->expiry != TIME64_MAX) {
-				key->expiry = prep->expiry;
-				key_schedule_gc(prep->expiry + key_gc_delay);
-			}
+			key_set_expiry(key, prep->expiry);
 		}
 	}
 
@@ -606,8 +604,7 @@ int key_reject_and_link(struct key *key,
 		atomic_inc(&key->user->nikeys);
 		mark_key_instantiated(key, -error);
 		notify_key(key, NOTIFY_KEY_INSTANTIATED, -error);
-		key->expiry = ktime_get_real_seconds() + timeout;
-		key_schedule_gc(key->expiry + key_gc_delay);
+		key_set_expiry(key, ktime_get_real_seconds() + timeout);
 
 		if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags))
 			awaken = 1;
@@ -723,16 +720,14 @@ found_kernel_type:
 
 void key_set_timeout(struct key *key, unsigned timeout)
 {
-	time64_t expiry = 0;
+	time64_t expiry = TIME64_MAX;
 
 	/* make the changes with the locks held to prevent races */
 	down_write(&key->sem);
 
 	if (timeout > 0)
 		expiry = ktime_get_real_seconds() + timeout;
-
-	key->expiry = expiry;
-	key_schedule_gc(key->expiry + key_gc_delay);
+	key_set_expiry(key, expiry);
 
 	up_write(&key->sem);
 }
diff --git a/security/keys/proc.c b/security/keys/proc.c
index d0cde6685627f2..4f4e2c1824f18b 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -198,7 +198,7 @@ static int proc_keys_show(struct seq_file *m, void *v)
 
 	/* come up with a suitable timeout value */
 	expiry = READ_ONCE(key->expiry);
-	if (expiry == 0) {
+	if (expiry == TIME64_MAX) {
 		memcpy(xbuf, "perm", 5);
 	} else if (now >= expiry) {
 		memcpy(xbuf, "expd", 5);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index feda711c6b7b84..340b2bbbb2dd35 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -1660,8 +1660,6 @@ static int inode_has_perm(const struct cred *cred,
 	struct inode_security_struct *isec;
 	u32 sid;
 
-	validate_creds(cred);
-
 	if (unlikely(IS_PRIVATE(inode)))
 		return 0;
 
@@ -3056,8 +3054,6 @@ static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode,
 	struct inode_security_struct *isec;
 	u32 sid;
 
-	validate_creds(cred);
-
 	ad.type = LSM_AUDIT_DATA_DENTRY;
 	ad.u.dentry = dentry;
 	sid = cred_sid(cred);
@@ -3101,8 +3097,6 @@ static int selinux_inode_permission(struct inode *inode, int mask)
 	if (!mask)
 		return 0;
 
-	validate_creds(cred);
-
 	if (unlikely(IS_PRIVATE(inode)))
 		return 0;
 
diff --git a/sound/core/info.c b/sound/core/info.c
index 0b2f04dcb58979..e2f302e55bbb20 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -56,7 +56,7 @@ struct snd_info_private_data {
 };
 
 static int snd_info_version_init(void);
-static void snd_info_disconnect(struct snd_info_entry *entry);
+static void snd_info_clear_entries(struct snd_info_entry *entry);
 
 /*
 
@@ -569,11 +569,16 @@ void snd_info_card_disconnect(struct snd_card *card)
 {
 	if (!card)
 		return;
-	mutex_lock(&info_mutex);
+
 	proc_remove(card->proc_root_link);
-	card->proc_root_link = NULL;
 	if (card->proc_root)
-		snd_info_disconnect(card->proc_root);
+		proc_remove(card->proc_root->p);
+
+	mutex_lock(&info_mutex);
+	if (card->proc_root)
+		snd_info_clear_entries(card->proc_root);
+	card->proc_root_link = NULL;
+	card->proc_root = NULL;
 	mutex_unlock(&info_mutex);
 }
 
@@ -745,15 +750,14 @@ struct snd_info_entry *snd_info_create_card_entry(struct snd_card *card,
 }
 EXPORT_SYMBOL(snd_info_create_card_entry);
 
-static void snd_info_disconnect(struct snd_info_entry *entry)
+static void snd_info_clear_entries(struct snd_info_entry *entry)
 {
 	struct snd_info_entry *p;
 
 	if (!entry->p)
 		return;
 	list_for_each_entry(p, &entry->children, list)
-		snd_info_disconnect(p);
-	proc_remove(entry->p);
+		snd_info_clear_entries(p);
 	entry->p = NULL;
 }
 
@@ -770,8 +774,9 @@ void snd_info_free_entry(struct snd_info_entry * entry)
 	if (!entry)
 		return;
 	if (entry->p) {
+		proc_remove(entry->p);
 		mutex_lock(&info_mutex);
-		snd_info_disconnect(entry);
+		snd_info_clear_entries(entry);
 		mutex_unlock(&info_mutex);
 	}
 
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 20bb2d7c8d4bf6..6d0c9c37796c22 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -253,6 +253,7 @@ static const char * const snd_pcm_state_names[] = {
 	STATE(DRAINING),
 	STATE(PAUSED),
 	STATE(SUSPENDED),
+	STATE(DISCONNECTED),
 };
 
 static const char * const snd_pcm_access_names[] = {
diff --git a/sound/drivers/pcmtest.c b/sound/drivers/pcmtest.c
index b59b78a0922409..b8bff5522bce20 100644
--- a/sound/drivers/pcmtest.c
+++ b/sound/drivers/pcmtest.c
@@ -397,7 +397,6 @@ static int snd_pcmtst_pcm_close(struct snd_pcm_substream *substream)
 	struct pcmtst_buf_iter *v_iter = substream->runtime->private_data;
 
 	timer_shutdown_sync(&v_iter->timer_instance);
-	v_iter->substream = NULL;
 	playback_capture_test = !v_iter->is_buf_corrupted;
 	kfree(v_iter);
 	return 0;
@@ -435,6 +434,7 @@ static int snd_pcmtst_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		// We can't call timer_shutdown_sync here, as it is forbidden to sleep here
 		v_iter->suspend = true;
+		timer_delete(&v_iter->timer_instance);
 		break;
 	}
 
@@ -512,12 +512,22 @@ static int snd_pcmtst_ioctl(struct snd_pcm_substream *substream, unsigned int cm
 	return snd_pcm_lib_ioctl(substream, cmd, arg);
 }
 
+static int snd_pcmtst_sync_stop(struct snd_pcm_substream *substream)
+{
+	struct pcmtst_buf_iter *v_iter = substream->runtime->private_data;
+
+	timer_delete_sync(&v_iter->timer_instance);
+
+	return 0;
+}
+
 static const struct snd_pcm_ops snd_pcmtst_playback_ops = {
 	.open =		snd_pcmtst_pcm_open,
 	.close =	snd_pcmtst_pcm_close,
 	.trigger =	snd_pcmtst_pcm_trigger,
 	.hw_params =	snd_pcmtst_pcm_hw_params,
 	.ioctl =	snd_pcmtst_ioctl,
+	.sync_stop =	snd_pcmtst_sync_stop,
 	.hw_free =	snd_pcmtst_pcm_hw_free,
 	.prepare =	snd_pcmtst_pcm_prepare,
 	.pointer =	snd_pcmtst_pcm_pointer,
@@ -530,6 +540,7 @@ static const struct snd_pcm_ops snd_pcmtst_capture_ops = {
 	.hw_params =	snd_pcmtst_pcm_hw_params,
 	.hw_free =	snd_pcmtst_pcm_hw_free,
 	.ioctl =	snd_pcmtst_ioctl,
+	.sync_stop =	snd_pcmtst_sync_stop,
 	.prepare =	snd_pcmtst_pcm_prepare,
 	.pointer =	snd_pcmtst_pcm_pointer,
 };
diff --git a/sound/hda/intel-nhlt.c b/sound/hda/intel-nhlt.c
index 2c4dfc0b7e342c..696a958d93e9c3 100644
--- a/sound/hda/intel-nhlt.c
+++ b/sound/hda/intel-nhlt.c
@@ -238,7 +238,7 @@ EXPORT_SYMBOL(intel_nhlt_ssp_mclk_mask);
 
 static struct nhlt_specific_cfg *
 nhlt_get_specific_cfg(struct device *dev, struct nhlt_fmt *fmt, u8 num_ch,
-		      u32 rate, u8 vbps, u8 bps)
+		      u32 rate, u8 vbps, u8 bps, bool ignore_vbps)
 {
 	struct nhlt_fmt_cfg *cfg = fmt->fmt_config;
 	struct wav_fmt *wfmt;
@@ -255,8 +255,12 @@ nhlt_get_specific_cfg(struct device *dev, struct nhlt_fmt *fmt, u8 num_ch,
 		dev_dbg(dev, "Endpoint format: ch=%d fmt=%d/%d rate=%d\n",
 			wfmt->channels, _vbps, _bps, wfmt->samples_per_sec);
 
+		/*
+		 * When looking for exact match of configuration ignore the vbps
+		 * from NHLT table when ignore_vbps is true
+		 */
 		if (wfmt->channels == num_ch && wfmt->samples_per_sec == rate &&
-		    vbps == _vbps && bps == _bps)
+		    (ignore_vbps || vbps == _vbps) && bps == _bps)
 			return &cfg->config;
 
 		cfg = (struct nhlt_fmt_cfg *)(cfg->config.caps + cfg->config.size);
@@ -289,6 +293,7 @@ intel_nhlt_get_endpoint_blob(struct device *dev, struct nhlt_acpi_table *nhlt,
 {
 	struct nhlt_specific_cfg *cfg;
 	struct nhlt_endpoint *epnt;
+	bool ignore_vbps = false;
 	struct nhlt_fmt *fmt;
 	int i;
 
@@ -298,7 +303,26 @@ intel_nhlt_get_endpoint_blob(struct device *dev, struct nhlt_acpi_table *nhlt,
 	dev_dbg(dev, "Looking for configuration:\n");
 	dev_dbg(dev, "  vbus_id=%d link_type=%d dir=%d, dev_type=%d\n",
 		bus_id, link_type, dir, dev_type);
-	dev_dbg(dev, "  ch=%d fmt=%d/%d rate=%d\n", num_ch, vbps, bps, rate);
+	if (link_type == NHLT_LINK_DMIC && bps == 32 && (vbps == 24 || vbps == 32)) {
+		/*
+		 * The DMIC hardware supports only one type of 32 bits sample
+		 * size, which is 24 bit sampling on the MSB side and bits[1:0]
+		 * are used for indicating the channel number.
+		 * It has been observed that some NHLT tables have the vbps
+		 * specified as 32 while some uses 24.
+		 * The format these variations describe are identical, the
+		 * hardware is configured and behaves the same way.
+		 * Note: when the samples assumed to be vbps=32 then the 'noise'
+		 * introduced by the lower two bits (channel number) have no
+		 * real life implication on audio quality.
+		 */
+		dev_dbg(dev,
+			"  ch=%d fmt=%d rate=%d (vbps is ignored for DMIC 32bit format)\n",
+			num_ch, bps, rate);
+		ignore_vbps = true;
+	} else {
+		dev_dbg(dev, "  ch=%d fmt=%d/%d rate=%d\n", num_ch, vbps, bps, rate);
+	}
 	dev_dbg(dev, "Endpoint count=%d\n", nhlt->endpoint_count);
 
 	epnt = (struct nhlt_endpoint *)nhlt->desc;
@@ -307,7 +331,8 @@ intel_nhlt_get_endpoint_blob(struct device *dev, struct nhlt_acpi_table *nhlt,
 		if (nhlt_check_ep_match(dev, epnt, bus_id, link_type, dir, dev_type)) {
 			fmt = (struct nhlt_fmt *)(epnt->config.caps + epnt->config.size);
 
-			cfg = nhlt_get_specific_cfg(dev, fmt, num_ch, rate, vbps, bps);
+			cfg = nhlt_get_specific_cfg(dev, fmt, num_ch, rate,
+						    vbps, bps, ignore_vbps);
 			if (cfg)
 				return cfg;
 		}
diff --git a/sound/oss/dmasound/dmasound_paula.c b/sound/oss/dmasound/dmasound_paula.c
index 23cf8284ce369e..0ba8f0c4cd99a2 100644
--- a/sound/oss/dmasound/dmasound_paula.c
+++ b/sound/oss/dmasound/dmasound_paula.c
@@ -720,15 +720,14 @@ static int __init amiga_audio_probe(struct platform_device *pdev)
 	return dmasound_init();
 }
 
-static int __exit amiga_audio_remove(struct platform_device *pdev)
+static void __exit amiga_audio_remove(struct platform_device *pdev)
 {
 	dmasound_deinit();
-	return 0;
 }
 
 static struct platform_driver amiga_audio_driver = {
-	.remove = __exit_p(amiga_audio_remove),
-	.driver   = {
+	.remove_new = __exit_p(amiga_audio_remove),
+	.driver = {
 		.name	= "amiga-audio",
 	},
 };
diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c
index b2db8091f0ed65..92ca2b3b6c9240 100644
--- a/sound/pci/hda/cs35l41_hda.c
+++ b/sound/pci/hda/cs35l41_hda.c
@@ -504,7 +504,6 @@ static void cs35l41_shutdown_dsp(struct cs35l41_hda *cs35l41)
 
 	cs_dsp_stop(dsp);
 	cs_dsp_power_down(dsp);
-	cs35l41->firmware_running = false;
 	dev_dbg(cs35l41->dev, "Unloaded Firmware\n");
 }
 
@@ -550,7 +549,7 @@ static void cs35l41_hda_play_start(struct device *dev)
 
 	cs35l41->playback_started = true;
 
-	if (cs35l41->firmware_running) {
+	if (cs35l41->cs_dsp.running) {
 		regmap_multi_reg_write(reg, cs35l41_hda_config_dsp,
 				       ARRAY_SIZE(cs35l41_hda_config_dsp));
 		regmap_update_bits(reg, CS35L41_PWR_CTRL2,
@@ -580,7 +579,7 @@ static void cs35l41_mute(struct device *dev, bool mute)
 			regmap_multi_reg_write(reg, cs35l41_hda_mute, ARRAY_SIZE(cs35l41_hda_mute));
 		} else {
 			dev_dbg(dev, "Unmuting\n");
-			if (cs35l41->firmware_running) {
+			if (cs35l41->cs_dsp.running) {
 				regmap_multi_reg_write(reg, cs35l41_hda_unmute_dsp,
 						ARRAY_SIZE(cs35l41_hda_unmute_dsp));
 			} else {
@@ -599,7 +598,7 @@ static void cs35l41_hda_play_done(struct device *dev)
 	dev_dbg(dev, "Play (Complete)\n");
 
 	cs35l41_global_enable(dev, reg, cs35l41->hw_cfg.bst_type, 1,
-			      cs35l41->firmware_running);
+			      &cs35l41->cs_dsp);
 	cs35l41_mute(dev, false);
 }
 
@@ -612,7 +611,7 @@ static void cs35l41_hda_pause_start(struct device *dev)
 
 	cs35l41_mute(dev, true);
 	cs35l41_global_enable(dev, reg, cs35l41->hw_cfg.bst_type, 0,
-			      cs35l41->firmware_running);
+			      &cs35l41->cs_dsp);
 }
 
 static void cs35l41_hda_pause_done(struct device *dev)
@@ -625,7 +624,7 @@ static void cs35l41_hda_pause_done(struct device *dev)
 	regmap_update_bits(reg, CS35L41_PWR_CTRL2, CS35L41_AMP_EN_MASK, 0 << CS35L41_AMP_EN_SHIFT);
 	if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST)
 		regmap_write(reg, CS35L41_GPIO1_CTRL1, 0x00000001);
-	if (cs35l41->firmware_running) {
+	if (cs35l41->cs_dsp.running) {
 		cs35l41_set_cspl_mbox_cmd(dev, reg, CSPL_MBOX_CMD_PAUSE);
 		regmap_update_bits(reg, CS35L41_PWR_CTRL2,
 				   CS35L41_VMON_EN_MASK | CS35L41_IMON_EN_MASK,
@@ -675,7 +674,7 @@ static void cs35l41_hda_playback_hook(struct device *dev, int action)
 		break;
 	case HDA_GEN_PCM_ACT_CLOSE:
 		mutex_lock(&cs35l41->fw_mutex);
-		if (!cs35l41->firmware_running && cs35l41->request_fw_load &&
+		if (!cs35l41->cs_dsp.running && cs35l41->request_fw_load &&
 		    !cs35l41->fw_request_ongoing) {
 			dev_info(dev, "Requesting Firmware Load after HDA_GEN_PCM_ACT_CLOSE\n");
 			cs35l41->fw_request_ongoing = true;
@@ -761,10 +760,9 @@ static int cs35l41_verify_id(struct cs35l41_hda *cs35l41, unsigned int *regid, u
 static int cs35l41_ready_for_reset(struct cs35l41_hda *cs35l41)
 {
 	mutex_lock(&cs35l41->fw_mutex);
-	if (cs35l41->firmware_running) {
+	if (cs35l41->cs_dsp.running) {
 		cs35l41->cs_dsp.running = false;
 		cs35l41->cs_dsp.booted = false;
-		cs35l41->firmware_running = false;
 	}
 	regcache_mark_dirty(cs35l41->regmap);
 	mutex_unlock(&cs35l41->fw_mutex);
@@ -925,7 +923,7 @@ static int cs35l41_runtime_suspend(struct device *dev)
 
 	mutex_lock(&cs35l41->fw_mutex);
 
-	if (cs35l41->firmware_running) {
+	if (cs35l41->cs_dsp.running) {
 		ret = cs35l41_enter_hibernate(cs35l41->dev, cs35l41->regmap,
 					      cs35l41->hw_cfg.bst_type);
 		if (ret)
@@ -960,7 +958,7 @@ static int cs35l41_runtime_resume(struct device *dev)
 
 	regcache_cache_only(cs35l41->regmap, false);
 
-	if (cs35l41->firmware_running)	{
+	if (cs35l41->cs_dsp.running)	{
 		ret = cs35l41_exit_hibernate(cs35l41->dev, cs35l41->regmap);
 		if (ret) {
 			dev_warn(cs35l41->dev, "Unable to exit Hibernate.");
@@ -1052,8 +1050,6 @@ static int cs35l41_smart_amp(struct cs35l41_hda *cs35l41)
 		goto clean_dsp;
 	}
 
-	cs35l41->firmware_running = true;
-
 	return 0;
 
 clean_dsp:
@@ -1063,10 +1059,10 @@ clean_dsp:
 
 static void cs35l41_load_firmware(struct cs35l41_hda *cs35l41, bool load)
 {
-	if (cs35l41->firmware_running && !load) {
+	if (cs35l41->cs_dsp.running && !load) {
 		dev_dbg(cs35l41->dev, "Unloading Firmware\n");
 		cs35l41_shutdown_dsp(cs35l41);
-	} else if (!cs35l41->firmware_running && load) {
+	} else if (!cs35l41->cs_dsp.running && load) {
 		dev_dbg(cs35l41->dev, "Loading Firmware\n");
 		cs35l41_smart_amp(cs35l41);
 	} else {
@@ -1346,7 +1342,7 @@ static int cs35l41_hda_bind(struct device *dev, struct device *master, void *mas
 		 cs35l41->acpi_subsystem_id, cs35l41->hw_cfg.bst_type,
 		 cs35l41->hw_cfg.gpio1.func == CS35l41_VSPK_SWITCH,
 		 cs35l41->hw_cfg.spk_pos ? 'R' : 'L',
-		 cs35l41->firmware_running, cs35l41->speaker_id);
+		 cs35l41->cs_dsp.running, cs35l41->speaker_id);
 
 	return ret;
 }
@@ -1830,6 +1826,7 @@ err:
 	if (cs35l41_safe_reset(cs35l41->regmap, cs35l41->hw_cfg.bst_type))
 		gpiod_set_value_cansleep(cs35l41->reset_gpio, 0);
 	gpiod_put(cs35l41->reset_gpio);
+	gpiod_put(cs35l41->cs_gpio);
 	acpi_dev_put(cs35l41->dacpi);
 	kfree(cs35l41->acpi_subsystem_id);
 
@@ -1857,6 +1854,7 @@ void cs35l41_hda_remove(struct device *dev)
 	if (cs35l41_safe_reset(cs35l41->regmap, cs35l41->hw_cfg.bst_type))
 		gpiod_set_value_cansleep(cs35l41->reset_gpio, 0);
 	gpiod_put(cs35l41->reset_gpio);
+	gpiod_put(cs35l41->cs_gpio);
 	kfree(cs35l41->acpi_subsystem_id);
 }
 EXPORT_SYMBOL_NS_GPL(cs35l41_hda_remove, SND_HDA_SCODEC_CS35L41);
diff --git a/sound/pci/hda/cs35l41_hda.h b/sound/pci/hda/cs35l41_hda.h
index ce3f2bb6ffd08a..3d925d677213d4 100644
--- a/sound/pci/hda/cs35l41_hda.h
+++ b/sound/pci/hda/cs35l41_hda.h
@@ -35,8 +35,8 @@ struct cs35l41_amp_efi_data {
 } __packed;
 
 enum cs35l41_hda_spk_pos {
-	CS35l41_LEFT,
-	CS35l41_RIGHT,
+	CS35L41_LEFT,
+	CS35L41_RIGHT,
 };
 
 enum cs35l41_hda_gpio_function {
@@ -50,6 +50,7 @@ struct cs35l41_hda {
 	struct device *dev;
 	struct regmap *regmap;
 	struct gpio_desc *reset_gpio;
+	struct gpio_desc *cs_gpio;
 	struct cs35l41_hw_cfg hw_cfg;
 	struct hda_codec *codec;
 
diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c
index c83328971728f4..194e1179a253e2 100644
--- a/sound/pci/hda/cs35l41_hda_property.c
+++ b/sound/pci/hda/cs35l41_hda_property.c
@@ -6,9 +6,303 @@
 //
 // Author: Stefan Binding <sbinding@opensource.cirrus.com>
 
+#include <linux/acpi.h>
 #include <linux/gpio/consumer.h>
 #include <linux/string.h>
 #include "cs35l41_hda_property.h"
+#include <linux/spi/spi.h>
+
+#define MAX_AMPS 4
+
+struct cs35l41_config {
+	const char *ssid;
+	enum {
+		SPI,
+		I2C
+	} bus;
+	int num_amps;
+	enum {
+		INTERNAL,
+		EXTERNAL
+	} boost_type;
+	u8 channel[MAX_AMPS];
+	int reset_gpio_index; /* -1 if no reset gpio */
+	int spkid_gpio_index; /* -1 if no spkid gpio */
+	int cs_gpio_index; /* -1 if no cs gpio, or cs-gpios already exists, max num amps == 2 */
+	int boost_ind_nanohenry; /* Required if boost_type == Internal */
+	int boost_peak_milliamp; /* Required if boost_type == Internal */
+	int boost_cap_microfarad; /* Required if boost_type == Internal */
+};
+
+static const struct cs35l41_config cs35l41_config_table[] = {
+/*
+ * Device 103C89C6 does have _DSD, however it is setup to use the wrong boost type.
+ * We can override the _DSD to correct the boost type here.
+ * Since this laptop has valid ACPI, we do not need to handle cs-gpios, since that already exists
+ * in the ACPI. The Reset GPIO is also valid, so we can use the Reset defined in _DSD.
+ */
+	{ "103C89C6", SPI, 2, INTERNAL, { CS35L41_RIGHT, CS35L41_LEFT, 0, 0 }, -1, -1, -1, 1000, 4500, 24 },
+	{ "104312AF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431433", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431463", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431473", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 1000, 4500, 24 },
+	{ "10431483", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 1000, 4500, 24 },
+	{ "10431493", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "104314D3", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "104314E3", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431503", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431533", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431573", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431663", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 1000, 4500, 24 },
+	{ "104316D3", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{ "104316F3", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{ "104317F3", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431863", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "104318D3", I2C, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
+	{ "10431C9F", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431CAF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431CCF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431CDF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431CEF", SPI, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
+	{ "10431D1F", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431DA2", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{ "10431E02", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{ "10431EE2", I2C, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 },
+	{ "10431F12", I2C, 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
+	{ "10431F1F", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 0, 0, 0 },
+	{ "10431F62", SPI, 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{}
+};
+
+static int cs35l41_add_gpios(struct cs35l41_hda *cs35l41, struct device *physdev, int reset_gpio,
+			     int spkid_gpio, int cs_gpio_index, int num_amps)
+{
+	struct acpi_gpio_mapping *gpio_mapping = NULL;
+	struct acpi_gpio_params *reset_gpio_params = NULL;
+	struct acpi_gpio_params *spkid_gpio_params = NULL;
+	struct acpi_gpio_params *cs_gpio_params = NULL;
+	unsigned int num_entries = 0;
+	unsigned int reset_index, spkid_index, csgpio_index;
+	int i;
+
+	/*
+	 * GPIO Mapping only needs to be done once, since it would be available for subsequent amps
+	 */
+	if (cs35l41->dacpi->driver_gpios)
+		return 0;
+
+	if (reset_gpio >= 0) {
+		reset_index = num_entries;
+		num_entries++;
+	}
+
+	if (spkid_gpio >= 0) {
+		spkid_index = num_entries;
+		num_entries++;
+	}
+
+	if ((cs_gpio_index >= 0)  && (num_amps == 2)) {
+		csgpio_index = num_entries;
+		num_entries++;
+	}
+
+	if (!num_entries)
+		return 0;
+
+	/* must include termination entry */
+	num_entries++;
+
+	gpio_mapping = devm_kcalloc(physdev, num_entries, sizeof(struct acpi_gpio_mapping),
+				    GFP_KERNEL);
+
+	if (!gpio_mapping)
+		goto err;
+
+	if (reset_gpio >= 0) {
+		gpio_mapping[reset_index].name = "reset-gpios";
+		reset_gpio_params = devm_kcalloc(physdev, num_amps, sizeof(struct acpi_gpio_params),
+						 GFP_KERNEL);
+		if (!reset_gpio_params)
+			goto err;
+
+		for (i = 0; i < num_amps; i++)
+			reset_gpio_params[i].crs_entry_index = reset_gpio;
+
+		gpio_mapping[reset_index].data = reset_gpio_params;
+		gpio_mapping[reset_index].size = num_amps;
+	}
+
+	if (spkid_gpio >= 0) {
+		gpio_mapping[spkid_index].name = "spk-id-gpios";
+		spkid_gpio_params = devm_kcalloc(physdev, num_amps, sizeof(struct acpi_gpio_params),
+						 GFP_KERNEL);
+		if (!spkid_gpio_params)
+			goto err;
+
+		for (i = 0; i < num_amps; i++)
+			spkid_gpio_params[i].crs_entry_index = spkid_gpio;
+
+		gpio_mapping[spkid_index].data = spkid_gpio_params;
+		gpio_mapping[spkid_index].size = num_amps;
+	}
+
+	if ((cs_gpio_index >= 0) && (num_amps == 2)) {
+		gpio_mapping[csgpio_index].name = "cs-gpios";
+		/* only one GPIO CS is supported without using _DSD, obtained using index 0 */
+		cs_gpio_params = devm_kzalloc(physdev, sizeof(struct acpi_gpio_params), GFP_KERNEL);
+		if (!cs_gpio_params)
+			goto err;
+
+		cs_gpio_params->crs_entry_index = cs_gpio_index;
+
+		gpio_mapping[csgpio_index].data = cs_gpio_params;
+		gpio_mapping[csgpio_index].size = 1;
+	}
+
+	return devm_acpi_dev_add_driver_gpios(physdev, gpio_mapping);
+err:
+	devm_kfree(physdev, gpio_mapping);
+	devm_kfree(physdev, reset_gpio_params);
+	devm_kfree(physdev, spkid_gpio_params);
+	devm_kfree(physdev, cs_gpio_params);
+	return -ENOMEM;
+}
+
+static int generic_dsd_config(struct cs35l41_hda *cs35l41, struct device *physdev, int id,
+			      const char *hid)
+{
+	struct cs35l41_hw_cfg *hw_cfg = &cs35l41->hw_cfg;
+	const struct cs35l41_config *cfg;
+	struct gpio_desc *cs_gpiod;
+	struct spi_device *spi;
+	bool dsd_found;
+	int ret;
+
+	for (cfg = cs35l41_config_table; cfg->ssid; cfg++) {
+		if (!strcasecmp(cfg->ssid, cs35l41->acpi_subsystem_id))
+			break;
+	}
+
+	if (!cfg->ssid)
+		return -ENOENT;
+
+	if (!cs35l41->dacpi || cs35l41->dacpi != ACPI_COMPANION(physdev)) {
+		dev_err(cs35l41->dev, "ACPI Device does not match, cannot override _DSD.\n");
+		return -ENODEV;
+	}
+
+	dev_info(cs35l41->dev, "Adding DSD properties for %s\n", cs35l41->acpi_subsystem_id);
+
+	dsd_found = acpi_dev_has_props(cs35l41->dacpi);
+
+	if (!dsd_found) {
+		ret = cs35l41_add_gpios(cs35l41, physdev, cfg->reset_gpio_index,
+						 cfg->spkid_gpio_index, cfg->cs_gpio_index,
+						 cfg->num_amps);
+		if (ret) {
+			dev_err(cs35l41->dev, "Error adding GPIO mapping: %d\n", ret);
+			return ret;
+		}
+	} else if (cfg->reset_gpio_index >= 0 || cfg->spkid_gpio_index >= 0) {
+		dev_warn(cs35l41->dev, "Cannot add Reset/Speaker ID/SPI CS GPIO Mapping, "
+			 "_DSD already exists.\n");
+	}
+
+	if (cfg->bus == SPI) {
+		cs35l41->index = id;
+
+#if IS_ENABLED(CONFIG_SPI)
+		/*
+		 * Manually set the Chip Select for the second amp <cs_gpio_index> in the node.
+		 * This is only supported for systems with 2 amps, since we cannot expand the
+		 * default number of chip selects without using cs-gpios
+		 * The CS GPIO must be set high prior to communicating with the first amp (which
+		 * uses a native chip select), to ensure the second amp does not clash with the
+		 * first.
+		 */
+		if (cfg->cs_gpio_index >= 0) {
+			spi = to_spi_device(cs35l41->dev);
+
+			if (cfg->num_amps != 2) {
+				dev_warn(cs35l41->dev,
+					 "Cannot update SPI CS, Number of Amps (%d) != 2\n",
+					 cfg->num_amps);
+			} else if (dsd_found) {
+				dev_warn(cs35l41->dev,
+					"Cannot update SPI CS, _DSD already exists.\n");
+			} else {
+				/*
+				 * This is obtained using driver_gpios, since only one GPIO for CS
+				 * exists, this can be obtained using index 0.
+				 */
+				cs_gpiod = gpiod_get_index(physdev, "cs", 0, GPIOD_OUT_LOW);
+				if (IS_ERR(cs_gpiod)) {
+					dev_err(cs35l41->dev,
+						"Unable to get Chip Select GPIO descriptor\n");
+					return PTR_ERR(cs_gpiod);
+				}
+				if (id == 1) {
+					spi_set_csgpiod(spi, 0, cs_gpiod);
+					cs35l41->cs_gpio = cs_gpiod;
+				} else {
+					gpiod_set_value_cansleep(cs_gpiod, true);
+					gpiod_put(cs_gpiod);
+				}
+				spi_setup(spi);
+			}
+		}
+#endif
+	} else {
+		if (cfg->num_amps > 2)
+			/*
+			 * i2c addresses for 3/4 amps are used in order: 0x40, 0x41, 0x42, 0x43,
+			 * subtracting 0x40 would give zero-based index
+			 */
+			cs35l41->index = id - 0x40;
+		else
+			/* i2c addr 0x40 for first amp (always), 0x41/0x42 for 2nd amp */
+			cs35l41->index = id == 0x40 ? 0 : 1;
+	}
+
+	if (cfg->num_amps == 3)
+		/* 3 amps means a center channel, so no duplicate channels */
+		cs35l41->channel_index = 0;
+	else
+		/*
+		 * if 4 amps, there are duplicate channels, so they need different indexes
+		 * if 2 amps, no duplicate channels, channel_index would be 0
+		 */
+		cs35l41->channel_index = cs35l41->index / 2;
+
+	cs35l41->reset_gpio = fwnode_gpiod_get_index(acpi_fwnode_handle(cs35l41->dacpi), "reset",
+						     cs35l41->index, GPIOD_OUT_LOW,
+						     "cs35l41-reset");
+	cs35l41->speaker_id = cs35l41_get_speaker_id(physdev, cs35l41->index, cfg->num_amps, -1);
+
+	hw_cfg->spk_pos = cfg->channel[cs35l41->index];
+
+	if (cfg->boost_type == INTERNAL) {
+		hw_cfg->bst_type = CS35L41_INT_BOOST;
+		hw_cfg->bst_ind = cfg->boost_ind_nanohenry;
+		hw_cfg->bst_ipk = cfg->boost_peak_milliamp;
+		hw_cfg->bst_cap = cfg->boost_cap_microfarad;
+		hw_cfg->gpio1.func = CS35L41_NOT_USED;
+		hw_cfg->gpio1.valid = true;
+	} else {
+		hw_cfg->bst_type = CS35L41_EXT_BOOST;
+		hw_cfg->bst_ind = -1;
+		hw_cfg->bst_ipk = -1;
+		hw_cfg->bst_cap = -1;
+		hw_cfg->gpio1.func = CS35l41_VSPK_SWITCH;
+		hw_cfg->gpio1.valid = true;
+	}
+
+	hw_cfg->gpio2.func = CS35L41_INTERRUPT;
+	hw_cfg->gpio2.valid = true;
+	hw_cfg->valid = true;
+
+	return 0;
+}
 
 /*
  * Device CLSA010(0/1) doesn't have _DSD so a gpiod_get by the label reset won't work.
@@ -43,44 +337,6 @@ static int lenovo_legion_no_acpi(struct cs35l41_hda *cs35l41, struct device *phy
 	return 0;
 }
 
-/*
- * Device 103C89C6 does have _DSD, however it is setup to use the wrong boost type.
- * We can override the _DSD to correct the boost type here.
- * Since this laptop has valid ACPI, we do not need to handle cs-gpios, since that already exists
- * in the ACPI.
- */
-static int hp_vision_acpi_fix(struct cs35l41_hda *cs35l41, struct device *physdev, int id,
-			      const char *hid)
-{
-	struct cs35l41_hw_cfg *hw_cfg = &cs35l41->hw_cfg;
-
-	dev_info(cs35l41->dev, "Adding DSD properties for %s\n", cs35l41->acpi_subsystem_id);
-
-	cs35l41->index = id;
-	cs35l41->channel_index = 0;
-
-	/*
-	 * This system has _DSD, it just contains an error, so we can still get the reset using
-	 * the "reset" label.
-	 */
-	cs35l41->reset_gpio = fwnode_gpiod_get_index(acpi_fwnode_handle(cs35l41->dacpi), "reset",
-						     cs35l41->index, GPIOD_OUT_LOW,
-						     "cs35l41-reset");
-	cs35l41->speaker_id = -ENOENT;
-	hw_cfg->spk_pos = cs35l41->index ? 0 : 1; // right:left
-	hw_cfg->gpio1.func = CS35L41_NOT_USED;
-	hw_cfg->gpio1.valid = true;
-	hw_cfg->gpio2.func = CS35L41_INTERRUPT;
-	hw_cfg->gpio2.valid = true;
-	hw_cfg->bst_type = CS35L41_INT_BOOST;
-	hw_cfg->bst_ind = 1000;
-	hw_cfg->bst_ipk = 4500;
-	hw_cfg->bst_cap = 24;
-	hw_cfg->valid = true;
-
-	return 0;
-}
-
 struct cs35l41_prop_model {
 	const char *hid;
 	const char *ssid;
@@ -91,7 +347,36 @@ struct cs35l41_prop_model {
 static const struct cs35l41_prop_model cs35l41_prop_model_table[] = {
 	{ "CLSA0100", NULL, lenovo_legion_no_acpi },
 	{ "CLSA0101", NULL, lenovo_legion_no_acpi },
-	{ "CSC3551", "103C89C6", hp_vision_acpi_fix },
+	{ "CSC3551", "103C89C6", generic_dsd_config },
+	{ "CSC3551", "104312AF", generic_dsd_config },
+	{ "CSC3551", "10431433", generic_dsd_config },
+	{ "CSC3551", "10431463", generic_dsd_config },
+	{ "CSC3551", "10431473", generic_dsd_config },
+	{ "CSC3551", "10431483", generic_dsd_config },
+	{ "CSC3551", "10431493", generic_dsd_config },
+	{ "CSC3551", "104314D3", generic_dsd_config },
+	{ "CSC3551", "104314E3", generic_dsd_config },
+	{ "CSC3551", "10431503", generic_dsd_config },
+	{ "CSC3551", "10431533", generic_dsd_config },
+	{ "CSC3551", "10431573", generic_dsd_config },
+	{ "CSC3551", "10431663", generic_dsd_config },
+	{ "CSC3551", "104316D3", generic_dsd_config },
+	{ "CSC3551", "104316F3", generic_dsd_config },
+	{ "CSC3551", "104317F3", generic_dsd_config },
+	{ "CSC3551", "10431863", generic_dsd_config },
+	{ "CSC3551", "104318D3", generic_dsd_config },
+	{ "CSC3551", "10431C9F", generic_dsd_config },
+	{ "CSC3551", "10431CAF", generic_dsd_config },
+	{ "CSC3551", "10431CCF", generic_dsd_config },
+	{ "CSC3551", "10431CDF", generic_dsd_config },
+	{ "CSC3551", "10431CEF", generic_dsd_config },
+	{ "CSC3551", "10431D1F", generic_dsd_config },
+	{ "CSC3551", "10431DA2", generic_dsd_config },
+	{ "CSC3551", "10431E02", generic_dsd_config },
+	{ "CSC3551", "10431EE2", generic_dsd_config },
+	{ "CSC3551", "10431F12", generic_dsd_config },
+	{ "CSC3551", "10431F1F", generic_dsd_config },
+	{ "CSC3551", "10431F62", generic_dsd_config },
 	{}
 };
 
@@ -104,7 +389,7 @@ int cs35l41_add_dsd_properties(struct cs35l41_hda *cs35l41, struct device *physd
 		if (!strcmp(model->hid, hid) &&
 		    (!model->ssid ||
 		     (cs35l41->acpi_subsystem_id &&
-		      !strcmp(model->ssid, cs35l41->acpi_subsystem_id))))
+		      !strcasecmp(model->ssid, cs35l41->acpi_subsystem_id))))
 			return model->add_prop(cs35l41, physdev, id, hid);
 	}
 
diff --git a/sound/pci/hda/cs35l56_hda_i2c.c b/sound/pci/hda/cs35l56_hda_i2c.c
index 757a4d193e0fb5..a9ef6d86de8397 100644
--- a/sound/pci/hda/cs35l56_hda_i2c.c
+++ b/sound/pci/hda/cs35l56_hda_i2c.c
@@ -21,6 +21,10 @@ static int cs35l56_hda_i2c_probe(struct i2c_client *clt)
 		return -ENOMEM;
 
 	cs35l56->base.dev = &clt->dev;
+
+#ifdef CS35L56_WAKE_HOLD_TIME_US
+	cs35l56->base.can_hibernate = true;
+#endif
 	cs35l56->base.regmap = devm_regmap_init_i2c(clt, &cs35l56_regmap_i2c);
 	if (IS_ERR(cs35l56->base.regmap)) {
 		ret = PTR_ERR(cs35l56->base.regmap);
diff --git a/sound/pci/hda/cs35l56_hda_spi.c b/sound/pci/hda/cs35l56_hda_spi.c
index 756aec342eab7f..27d7fbc56b4c2a 100644
--- a/sound/pci/hda/cs35l56_hda_spi.c
+++ b/sound/pci/hda/cs35l56_hda_spi.c
@@ -21,6 +21,10 @@ static int cs35l56_hda_spi_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	cs35l56->base.dev = &spi->dev;
+
+#ifdef CS35L56_WAKE_HOLD_TIME_US
+	cs35l56->base.can_hibernate = true;
+#endif
 	cs35l56->base.regmap = devm_regmap_init_spi(spi, &cs35l56_regmap_spi);
 	if (IS_ERR(cs35l56->base.regmap)) {
 		ret = PTR_ERR(cs35l56->base.regmap);
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 3c9e6e97ad0f73..2d1df3654424cc 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2068,6 +2068,7 @@ static const struct pci_device_id driver_denylist[] = {
 	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1043, 0x874f) }, /* ASUS ROG Zenith II / Strix */
 	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb59) }, /* MSI TRX40 Creator */
 	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb60) }, /* MSI TRX40 */
+	{ PCI_DEVICE_SUB(0x1022, 0x15e3, 0x1022, 0xd601) }, /* ASRock X670E Taichi */
 	{}
 };
 
@@ -2134,6 +2135,9 @@ static int azx_probe(struct pci_dev *pci,
 	if (chip->driver_caps & AZX_DCAPS_I915_COMPONENT) {
 		err = snd_hdac_i915_init(azx_bus(chip));
 		if (err < 0) {
+			if (err == -EPROBE_DEFER)
+				goto out_free;
+
 			/* if the controller is bound only with HDMI/DP
 			 * (for HSW and BDW), we need to abort the probe;
 			 * for other chips, still continue probing as other
@@ -2238,6 +2242,8 @@ static const struct snd_pci_quirk power_save_denylist[] = {
 	SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0),
 	/* https://bugs.launchpad.net/bugs/1821663 */
 	SND_PCI_QUIRK(0x1631, 0xe017, "Packard Bell NEC IMEDIA 5204", 0),
+	/* KONTRON SinglePC may cause a stall at runtime resume */
+	SND_PCI_QUIRK(0x1734, 0x1232, "KONTRON SinglePC", 0),
 	{}
 };
 #endif /* CONFIG_PM */
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 1cde2a69bdb4ba..78cee53fee02aa 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1993,7 +1993,10 @@ static const struct snd_pci_quirk force_connect_list[] = {
 	SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1),
 	SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1),
 	SND_PCI_QUIRK(0x103c, 0x8715, "HP", 1),
+	SND_PCI_QUIRK(0x1043, 0x86ae, "ASUS", 1),  /* Z170 PRO */
+	SND_PCI_QUIRK(0x1043, 0x86c7, "ASUS", 1),  /* Z170M PLUS */
 	SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1),
+	SND_PCI_QUIRK(0x8086, 0x2060, "Intel NUC5CPYB", 1),
 	SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", 1),
 	{}
 };
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 58006c8bcfb917..c3a75652888677 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -1987,6 +1987,7 @@ enum {
 	ALC887_FIXUP_ASUS_AUDIO,
 	ALC887_FIXUP_ASUS_HMIC,
 	ALCS1200A_FIXUP_MIC_VREF,
+	ALC888VD_FIXUP_MIC_100VREF,
 };
 
 static void alc889_fixup_coef(struct hda_codec *codec,
@@ -2540,6 +2541,13 @@ static const struct hda_fixup alc882_fixups[] = {
 			{}
 		}
 	},
+	[ALC888VD_FIXUP_MIC_100VREF] = {
+		.type = HDA_FIXUP_PINCTLS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x18, PIN_VREF100 }, /* headset mic */
+			{}
+		}
+	},
 };
 
 static const struct snd_pci_quirk alc882_fixup_tbl[] = {
@@ -2609,6 +2617,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x106b, 0x4a00, "Macbook 5,2", ALC889_FIXUP_MBA11_VREF),
 
 	SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD),
+	SND_PCI_QUIRK(0x10ec, 0x12d8, "iBase Elo Touch", ALC888VD_FIXUP_MIC_100VREF),
 	SND_PCI_QUIRK(0x13fe, 0x1009, "Advantech MIT-W101", ALC886_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
@@ -3256,6 +3265,7 @@ static void alc_disable_headset_jack_key(struct hda_codec *codec)
 	case 0x10ec0230:
 	case 0x10ec0236:
 	case 0x10ec0256:
+	case 0x10ec0257:
 	case 0x19e58326:
 		alc_write_coef_idx(codec, 0x48, 0x0);
 		alc_update_coef_idx(codec, 0x49, 0x0045, 0x0);
@@ -3285,6 +3295,7 @@ static void alc_enable_headset_jack_key(struct hda_codec *codec)
 	case 0x10ec0230:
 	case 0x10ec0236:
 	case 0x10ec0256:
+	case 0x10ec0257:
 	case 0x19e58326:
 		alc_write_coef_idx(codec, 0x48, 0xd011);
 		alc_update_coef_idx(codec, 0x49, 0x007f, 0x0045);
@@ -6496,6 +6507,7 @@ static void alc_combo_jack_hp_jd_restart(struct hda_codec *codec)
 	case 0x10ec0236:
 	case 0x10ec0255:
 	case 0x10ec0256:
+	case 0x10ec0257:
 	case 0x19e58326:
 		alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */
 		alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15);
@@ -7249,6 +7261,7 @@ enum {
 	ALC290_FIXUP_SUBWOOFER_HSJACK,
 	ALC269_FIXUP_THINKPAD_ACPI,
 	ALC269_FIXUP_DMIC_THINKPAD_ACPI,
+	ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO,
 	ALC255_FIXUP_ACER_MIC_NO_PRESENCE,
 	ALC255_FIXUP_ASUS_MIC_NO_PRESENCE,
 	ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -7343,8 +7356,10 @@ enum {
 	ALC256_FIXUP_ASUS_MIC_NO_PRESENCE,
 	ALC299_FIXUP_PREDATOR_SPK,
 	ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE,
+	ALC289_FIXUP_DELL_SPK1,
 	ALC289_FIXUP_DELL_SPK2,
 	ALC289_FIXUP_DUAL_SPK,
+	ALC289_FIXUP_RTK_AMP_DUAL_SPK,
 	ALC294_FIXUP_SPK2_TO_DAC1,
 	ALC294_FIXUP_ASUS_DUAL_SPK,
 	ALC285_FIXUP_THINKPAD_X1_GEN7,
@@ -7444,6 +7459,8 @@ enum {
 	ALC287_FIXUP_THINKPAD_I2S_SPK,
 	ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD,
 	ALC2XX_FIXUP_HEADSET_MIC,
+	ALC289_FIXUP_DELL_CS35L41_SPI_2,
+	ALC294_FIXUP_CS35L41_I2C_2,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -7597,6 +7614,14 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc269_fixup_pincfg_U7x7_headset_mic,
 	},
+	[ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x18, 0x03a19020 }, /* headset mic */
+			{ 0x1b, 0x90170150 }, /* speaker */
+			{ }
+		},
+	},
 	[ALC269_FIXUP_AMIC] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -8670,6 +8695,15 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE
 	},
+	[ALC289_FIXUP_DELL_SPK1] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x14, 0x90170140 },
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE
+	},
 	[ALC289_FIXUP_DELL_SPK2] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -8685,6 +8719,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC289_FIXUP_DELL_SPK2
 	},
+	[ALC289_FIXUP_RTK_AMP_DUAL_SPK] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_speaker2_to_dac1,
+		.chained = true,
+		.chain_id = ALC289_FIXUP_DELL_SPK1
+	},
 	[ALC294_FIXUP_SPK2_TO_DAC1] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc285_fixup_speaker2_to_dac1,
@@ -9552,6 +9592,16 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_headset_mic,
 	},
+	[ALC289_FIXUP_DELL_CS35L41_SPI_2] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = cs35l41_fixup_spi_two,
+		.chained = true,
+		.chain_id = ALC289_FIXUP_DUAL_SPK
+	},
+	[ALC294_FIXUP_CS35L41_I2C_2] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = cs35l41_fixup_i2c_two,
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -9655,6 +9705,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK),
 	SND_PCI_QUIRK(0x1028, 0x0b37, "Dell Inspiron 16 Plus 7620 2-in-1", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
 	SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
+	SND_PCI_QUIRK(0x1028, 0x0beb, "Dell XPS 15 9530 (2023)", ALC289_FIXUP_DELL_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1028, 0x0c03, "Dell Precision 5340", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
@@ -9662,13 +9713,15 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0c1c, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1d, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1e, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS),
-	SND_PCI_QUIRK(0x1028, 0x0cbd, "Dell Oasis 13 CS MTL-U", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1028, 0x0cbe, "Dell Oasis 13 2-IN-1 MTL-U", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1028, 0x0cbf, "Dell Oasis 13 Low Weight MTU-L", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1028, 0x0cc1, "Dell Oasis 14 MTL-H/U", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1028, 0x0cc2, "Dell Oasis 14 2-in-1 MTL-H/U", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1028, 0x0cc3, "Dell Oasis 14 Low Weight MTL-U", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1028, 0x0cc4, "Dell Oasis 16 MTL-H/U", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1028, 0x0cbd, "Dell Oasis 13 CS MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1028, 0x0cbe, "Dell Oasis 13 2-IN-1 MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1028, 0x0cbf, "Dell Oasis 13 Low Weight MTU-L", ALC289_FIXUP_DELL_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1028, 0x0cc0, "Dell Oasis 13", ALC289_FIXUP_RTK_AMP_DUAL_SPK),
+	SND_PCI_QUIRK(0x1028, 0x0cc1, "Dell Oasis 14 MTL-H/U", ALC289_FIXUP_DELL_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1028, 0x0cc2, "Dell Oasis 14 2-in-1 MTL-H/U", ALC289_FIXUP_DELL_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1028, 0x0cc3, "Dell Oasis 14 Low Weight MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1028, 0x0cc4, "Dell Oasis 16 MTL-H/U", ALC289_FIXUP_DELL_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1028, 0x0cc5, "Dell Oasis 14", ALC289_FIXUP_RTK_AMP_DUAL_SPK),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
@@ -9742,6 +9795,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x841c, "HP Pavilion 15-CK0xx", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
+	SND_PCI_QUIRK(0x103c, 0x84ae, "HP 15-db0403ng", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x84da, "HP OMEN dc0019-ur", ALC295_FIXUP_HP_OMEN),
 	SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360),
@@ -9801,6 +9855,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED),
+	SND_PCI_QUIRK(0x103c, 0x890e, "HP 255 G8 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8919, "HP Pavilion Aero Laptop 13-be0xxx", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x896d, "HP ZBook Firefly 16 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x896e, "HP EliteBook x360 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
@@ -9836,6 +9891,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b44, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
@@ -9869,12 +9925,16 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x10a1, "ASUS UX391UA", ALC294_FIXUP_ASUS_SPK),
 	SND_PCI_QUIRK(0x1043, 0x10c0, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x10d0, "ASUS X540LA/X540LJ", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1043, 0x10d3, "ASUS K6500ZC", ALC294_FIXUP_ASUS_SPK),
 	SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x11c0, "ASUS X556UR", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x125e, "ASUS Q524UQK", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
@@ -9888,23 +9948,31 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
-	SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650P", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
-	SND_PCI_QUIRK(0x1043, 0x1463, "Asus GA402X", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
-	SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC),
-	SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC),
-	SND_PCI_QUIRK(0x1043, 0x1493, "ASUS GV601V", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650PY/PZ/PV/PU/PYV/PZV/PIV/PVV", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1463, "Asus GA402X/GA402N", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604VI/VC/VE/VG/VJ/VQ/VU/VV/VY/VZ", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603VQ/VU/VV/VJ/VI", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1493, "ASUS GV601VV/VU/VJ/VQ/VI", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x14d3, "ASUS G614JY/JZ/JG", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x14e3, "ASUS G513PI/PU/PV", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1503, "ASUS G733PY/PZ/PZV/PYV", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
-	SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301V", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA/XJ/XQ/XU/XV/XI", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301VV/VQ/VU/VJ/VA/VC/VE/VVC/VQC/VUC/VJC/VEC/VCC", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK),
-	SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZV", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZI/ZJ/ZQ/ZU/ZV", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
+	SND_PCI_QUIRK(0x1043, 0x16d3, "ASUS UX5304VA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
+	SND_PCI_QUIRK(0x1043, 0x16f3, "ASUS UX7602VI/BZ", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1740, "ASUS UX430UA", ALC295_FIXUP_ASUS_DACS),
 	SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK),
-	SND_PCI_QUIRK(0x1043, 0x17f3, "ROG Ally RC71L_RC71L", ALC294_FIXUP_ASUS_ALLY),
+	SND_PCI_QUIRK(0x1043, 0x17f3, "ROG Ally NR2301L/X", ALC294_FIXUP_ASUS_ALLY),
+	SND_PCI_QUIRK(0x1043, 0x1863, "ASUS UX6404VI/VV", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS),
 	SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x18d3, "ASUS UM3504DA", ALC294_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x194e, "ASUS UX563FD", ALC294_FIXUP_ASUS_HPE),
 	SND_PCI_QUIRK(0x1043, 0x1970, "ASUS UX550VE", ALC289_FIXUP_ASUS_GA401),
@@ -9913,30 +9981,43 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
 	SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1a63, "ASUS UX3405MA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B),
 	SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x1b93, "ASUS G614JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1043, 0x1c03, "ASUS UM3406HA", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x1043, 0x1c33, "ASUS UX5304MA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS),
-	SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JI", ALC285_FIXUP_ASUS_HEADSET_MIC),
-	SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
+	SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JU/JV/JI", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JY/JZ/JI/JG", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
-	SND_PCI_QUIRK(0x1043, 0x1d1f, "ASUS ROG Strix G17 2023 (G713PV)", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1ccf, "ASUS G814JU/JV/JI", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x1cdf, "ASUS G814JY/JZ/JG", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x1cef, "ASUS G834JY/JZ/JI/JG", ALC285_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1d1f, "ASUS G713PI/PU/PV/PVN", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE),
+	SND_PCI_QUIRK(0x1043, 0x1da2, "ASUS UP6502ZA/ZD", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
-	SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401),
+	SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1f12, "ASUS UM5302", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1f1f, "ASUS H7604JI/JV/J3D", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC245_FIXUP_CS35L41_SPI_2),
@@ -10140,6 +10221,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x387d, "Yoga S780-16 pro Quad AAC", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x387e, "Yoga S780-16 pro Quad YC", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x3881, "YB9 dual power mode2 YC", ALC287_FIXUP_TAS2781_I2C),
+	SND_PCI_QUIRK(0x17aa, 0x3882, "Lenovo Yoga Pro 7 14APH8", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3884, "Y780 YG DUAL", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x3886, "Y780 VECO DUAL", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x38a7, "Y780P AMD YG dual", ALC287_FIXUP_TAS2781_I2C),
@@ -10201,11 +10283,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
+	SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO),
 	SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC),
 	SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED),
 	SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10),
 	SND_PCI_QUIRK(0x8086, 0x3038, "Intel NUC 13", ALC295_FIXUP_CHROME_BOOK),
 	SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0xf111, 0x0005, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
 
 #if 0
 	/* Below is a quirk table taken from the old code.
@@ -10788,22 +10873,6 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x12, 0x90a60130},
 		{0x17, 0x90170110},
 		{0x21, 0x03211020}),
-	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
-		{0x14, 0x90170110},
-		{0x21, 0x04211020}),
-	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
-		{0x14, 0x90170110},
-		{0x21, 0x04211030}),
-	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
-		ALC295_STANDARD_PINS,
-		{0x17, 0x21014020},
-		{0x18, 0x21a19030}),
-	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
-		ALC295_STANDARD_PINS,
-		{0x17, 0x21014040},
-		{0x18, 0x21a19050}),
-	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
-		ALC295_STANDARD_PINS),
 	SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC298_STANDARD_PINS,
 		{0x17, 0x90170110}),
@@ -10847,6 +10916,9 @@ static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = {
 	SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
 		{0x19, 0x40000000},
 		{0x1b, 0x40000000}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
+		{0x19, 0x40000000},
+		{0x1b, 0x40000000}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x19, 0x40000000},
 		{0x1a, 0x40000000}),
@@ -12144,6 +12216,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x32f7, "Lenovo ThinkCentre M90", ALC897_FIXUP_HEADSET_MIC_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3321, "Lenovo ThinkCentre M70 Gen4", ALC897_FIXUP_HEADSET_MIC_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x331b, "Lenovo ThinkCentre M90 Gen4", ALC897_FIXUP_HEADSET_MIC_PIN),
+	SND_PCI_QUIRK(0x17aa, 0x3364, "Lenovo ThinkCentre M90 Gen5", ALC897_FIXUP_HEADSET_MIC_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3742, "Lenovo TianYi510Pro-14IOB", ALC897_FIXUP_HEADSET_MIC_PIN2),
 	SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD),
 	SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Ideapad Y550", ALC662_FIXUP_IDEAPAD),
diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c
index fb802802939e17..2fb1a7037c82cf 100644
--- a/sound/pci/hda/tas2781_hda_i2c.c
+++ b/sound/pci/hda/tas2781_hda_i2c.c
@@ -455,9 +455,9 @@ static int tas2781_save_calibration(struct tasdevice_priv *tas_priv)
 		status = efi.get_variable(efi_name, &efi_guid, &attr,
 			&tas_priv->cali_data.total_sz,
 			tas_priv->cali_data.data);
-		if (status != EFI_SUCCESS)
-			return -EINVAL;
 	}
+	if (status != EFI_SUCCESS)
+		return -EINVAL;
 
 	tmp_val = (unsigned int *)tas_priv->cali_data.data;
 
@@ -543,6 +543,10 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context)
 
 	tas_priv->fw_state = TASDEVICE_DSP_FW_ALL_OK;
 	tasdevice_prmg_load(tas_priv, 0);
+	if (tas_priv->fmw->nr_programs > 0)
+		tas_priv->cur_prog = 0;
+	if (tas_priv->fmw->nr_configurations > 0)
+		tas_priv->cur_conf = 0;
 
 	/* If calibrated data occurs error, dsp will still works with default
 	 * calibrated data inside algo.
@@ -550,11 +554,6 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context)
 	tas2781_save_calibration(tas_priv);
 
 out:
-	if (tas_priv->fw_state == TASDEVICE_DSP_FW_FAIL) {
-		/*If DSP FW fail, kcontrol won't be created */
-		tasdevice_config_info_remove(tas_priv);
-		tasdevice_dsp_remove(tas_priv);
-	}
 	mutex_unlock(&tas_priv->codec_lock);
 	if (fmw)
 		release_firmware(fmw);
@@ -612,9 +611,13 @@ static void tas2781_hda_unbind(struct device *dev,
 {
 	struct tasdevice_priv *tas_priv = dev_get_drvdata(dev);
 	struct hda_component *comps = master_data;
+	comps = &comps[tas_priv->index];
 
-	if (comps[tas_priv->index].dev == dev)
-		memset(&comps[tas_priv->index], 0, sizeof(*comps));
+	if (comps->dev == dev) {
+		comps->dev = NULL;
+		memset(comps->name, 0, sizeof(comps->name));
+		comps->playback_hook = NULL;
+	}
 
 	tasdevice_config_info_remove(tas_priv);
 	tasdevice_dsp_remove(tas_priv);
@@ -675,14 +678,14 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt)
 
 	pm_runtime_put_autosuspend(tas_priv->dev);
 
+	tas2781_reset(tas_priv);
+
 	ret = component_add(tas_priv->dev, &tas2781_hda_comp_ops);
 	if (ret) {
 		dev_err(tas_priv->dev, "Register component failed: %d\n", ret);
 		pm_runtime_disable(tas_priv->dev);
-		goto err;
 	}
 
-	tas2781_reset(tas_priv);
 err:
 	if (ret)
 		tas2781_hda_remove(&clt->dev);
diff --git a/sound/soc/amd/acp-config.c b/sound/soc/amd/acp-config.c
index 20cee7104c2b30..3bc4b2e41650e6 100644
--- a/sound/soc/amd/acp-config.c
+++ b/sound/soc/amd/acp-config.c
@@ -111,6 +111,20 @@ static const struct config_entry config_table[] = {
 				.matches = {
 					DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "HUAWEI"),
 					DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HVY-WXX9"),
+					DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "M1010"),
+				},
+			},
+			{}
+		},
+	},
+	{
+		.flags = FLAG_AMD_LEGACY,
+		.device = ACP_PCI_DEV_ID,
+		.dmi_table = (const struct dmi_system_id []) {
+			{
+				.matches = {
+					DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "HUAWEI"),
+					DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HVY-WXX9"),
 					DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "M1020"),
 				},
 			},
diff --git a/sound/soc/amd/acp/acp-i2s.c b/sound/soc/amd/acp/acp-i2s.c
index 1185e5aac5233f..60cbc881be6e10 100644
--- a/sound/soc/amd/acp/acp-i2s.c
+++ b/sound/soc/amd/acp/acp-i2s.c
@@ -26,7 +26,6 @@
 
 #define DRV_NAME "acp_i2s_playcap"
 #define	I2S_MASTER_MODE_ENABLE		1
-#define	I2S_MODE_ENABLE			0
 #define	LRCLK_DIV_FIELD			GENMASK(10, 2)
 #define	BCLK_DIV_FIELD			GENMASK(23, 11)
 #define	ACP63_LRCLK_DIV_FIELD		GENMASK(12, 2)
@@ -56,7 +55,8 @@ static inline void acp_set_i2s_clk(struct acp_dev_data *adata, int dai_id)
 	}
 
 	val  = I2S_MASTER_MODE_ENABLE;
-	val |= I2S_MODE_ENABLE & BIT(1);
+	if (adata->tdm_mode)
+		val |= BIT(1);
 
 	switch (chip->acp_rev) {
 	case ACP63_DEV:
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 15a864dcd7bd3a..d83cb6e4c62aec 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -286,6 +286,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "E1504FA"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 B7ED"),
 		}
@@ -370,6 +377,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
+			DMI_MATCH(DMI_BOARD_NAME, "8B2F"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "MECHREVO"),
 			DMI_MATCH(DMI_BOARD_NAME, "MRID6"),
 		}
@@ -381,6 +395,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_VERSION, "pang12"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "System76"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "pang13"),
+		}
+	},
 	{}
 };
 
diff --git a/sound/soc/codecs/aw88395/aw88395.c b/sound/soc/codecs/aw88395/aw88395.c
index 77227c8f01f60d..3c459a67ad0c98 100644
--- a/sound/soc/codecs/aw88395/aw88395.c
+++ b/sound/soc/codecs/aw88395/aw88395.c
@@ -356,7 +356,7 @@ static const struct snd_kcontrol_new aw88395_controls[] = {
 		aw88395_get_fade_in_time, aw88395_set_fade_in_time),
 	SOC_SINGLE_EXT("Volume Ramp Down Step", 0, 0, FADE_TIME_MAX, FADE_TIME_MIN,
 		aw88395_get_fade_out_time, aw88395_set_fade_out_time),
-	SOC_SINGLE_EXT("Calib", 0, 0, 100, 0,
+	SOC_SINGLE_EXT("Calib", 0, 0, AW88395_CALI_RE_MAX, 0,
 		aw88395_re_get, aw88395_re_set),
 	AW88395_PROFILE_EXT("Profile Set", aw88395_profile_info,
 		aw88395_profile_get, aw88395_profile_set),
diff --git a/sound/soc/codecs/aw88399.c b/sound/soc/codecs/aw88399.c
index ce30bc7cdea9f3..54f8457e849704 100644
--- a/sound/soc/codecs/aw88399.c
+++ b/sound/soc/codecs/aw88399.c
@@ -438,7 +438,7 @@ static int aw_dev_set_vcalb(struct aw88399 *aw88399)
 	if (ret)
 		return ret;
 
-	vsense_select = vsense_select & (~AW88399_VDSEL_MASK);
+	vsense_select = vsense_value & (~AW88399_VDSEL_MASK);
 
 	ret = aw88399_dev_get_icalk(aw88399, &icalk);
 	if (ret) {
@@ -486,8 +486,8 @@ static int aw_dev_update_cali_re(struct aw_cali_desc *cali_desc)
 	u32 cali_re;
 	int ret;
 
-	if ((aw_dev->cali_desc.cali_re <= AW88399_CALI_RE_MAX) ||
-			(aw_dev->cali_desc.cali_re >= AW88399_CALI_RE_MIN))
+	if ((aw_dev->cali_desc.cali_re >= AW88399_CALI_RE_MAX) ||
+			(aw_dev->cali_desc.cali_re <= AW88399_CALI_RE_MIN))
 		return -EINVAL;
 
 	cali_re = AW88399_SHOW_RE_TO_DSP_RE((aw_dev->cali_desc.cali_re +
@@ -1710,7 +1710,7 @@ static const struct snd_kcontrol_new aw88399_controls[] = {
 		aw88399_get_fade_in_time, aw88399_set_fade_in_time),
 	SOC_SINGLE_EXT("Volume Ramp Down Step", 0, 0, FADE_TIME_MAX, FADE_TIME_MIN,
 		aw88399_get_fade_out_time, aw88399_set_fade_out_time),
-	SOC_SINGLE_EXT("Calib", 0, 0, 100, 0,
+	SOC_SINGLE_EXT("Calib", 0, 0, AW88399_CALI_RE_MAX, 0,
 		aw88399_re_get, aw88399_re_set),
 	AW88399_PROFILE_EXT("AW88399 Profile Set", aw88399_profile_info,
 		aw88399_profile_get, aw88399_profile_set),
diff --git a/sound/soc/codecs/aw88399.h b/sound/soc/codecs/aw88399.h
index 8b3f1e10198542..4f391099d0f2cc 100644
--- a/sound/soc/codecs/aw88399.h
+++ b/sound/soc/codecs/aw88399.h
@@ -522,7 +522,7 @@ enum {
 
 enum {
 	AW88399_DEV_VDSEL_DAC = 0,
-	AW88399_DEV_VDSEL_VSENSE = 1,
+	AW88399_DEV_VDSEL_VSENSE = 32,
 };
 
 enum {
diff --git a/sound/soc/codecs/cs35l41-lib.c b/sound/soc/codecs/cs35l41-lib.c
index 4569e4f7cf7e90..e9993a39f7d0a3 100644
--- a/sound/soc/codecs/cs35l41-lib.c
+++ b/sound/soc/codecs/cs35l41-lib.c
@@ -16,6 +16,8 @@
 
 #include <sound/cs35l41.h>
 
+#define CS35L41_FIRMWARE_OLD_VERSION 0x001C00 /* v0.28.0 */
+
 static const struct reg_default cs35l41_reg[] = {
 	{ CS35L41_PWR_CTRL1,			0x00000000 },
 	{ CS35L41_PWR_CTRL2,			0x00000000 },
@@ -1214,7 +1216,7 @@ EXPORT_SYMBOL_GPL(cs35l41_safe_reset);
  * the PLL Lock interrupt, in the IRQ handler.
  */
 int cs35l41_global_enable(struct device *dev, struct regmap *regmap, enum cs35l41_boost_type b_type,
-			  int enable, bool firmware_running)
+			  int enable, struct cs_dsp *dsp)
 {
 	int ret;
 	unsigned int gpio1_func, pad_control, pwr_ctrl1, pwr_ctrl3, int_status, pup_pdn_mask;
@@ -1309,7 +1311,7 @@ int cs35l41_global_enable(struct device *dev, struct regmap *regmap, enum cs35l4
 			}
 			regmap_write(regmap, CS35L41_IRQ1_STATUS1, CS35L41_PUP_DONE_MASK);
 
-			if (firmware_running)
+			if (dsp->running && dsp->fw_id_version > CS35L41_FIRMWARE_OLD_VERSION)
 				ret = cs35l41_set_cspl_mbox_cmd(dev, regmap,
 								CSPL_MBOX_CMD_SPK_OUT_ENABLE);
 			else
diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c
index d0e9128ac6d0ca..dfb4ce53491bba 100644
--- a/sound/soc/codecs/cs35l41.c
+++ b/sound/soc/codecs/cs35l41.c
@@ -519,11 +519,11 @@ static int cs35l41_main_amp_event(struct snd_soc_dapm_widget *w,
 						ARRAY_SIZE(cs35l41_pup_patch));
 
 		ret = cs35l41_global_enable(cs35l41->dev, cs35l41->regmap, cs35l41->hw_cfg.bst_type,
-					    1, cs35l41->dsp.cs_dsp.running);
+					    1, &cs35l41->dsp.cs_dsp);
 		break;
 	case SND_SOC_DAPM_POST_PMD:
 		ret = cs35l41_global_enable(cs35l41->dev, cs35l41->regmap, cs35l41->hw_cfg.bst_type,
-					    0, cs35l41->dsp.cs_dsp.running);
+					    0, &cs35l41->dsp.cs_dsp);
 
 		regmap_multi_reg_write_bypassed(cs35l41->regmap,
 						cs35l41_pdn_patch,
diff --git a/sound/soc/codecs/cs35l45-i2c.c b/sound/soc/codecs/cs35l45-i2c.c
index 77e0f8750f3757..bc2af1ed0fe9bb 100644
--- a/sound/soc/codecs/cs35l45-i2c.c
+++ b/sound/soc/codecs/cs35l45-i2c.c
@@ -62,7 +62,7 @@ static struct i2c_driver cs35l45_i2c_driver = {
 	.driver = {
 		.name		= "cs35l45",
 		.of_match_table = cs35l45_of_match,
-		.pm		= &cs35l45_pm_ops,
+		.pm		= pm_ptr(&cs35l45_pm_ops),
 	},
 	.id_table	= cs35l45_id_i2c,
 	.probe		= cs35l45_i2c_probe,
diff --git a/sound/soc/codecs/cs35l45-spi.c b/sound/soc/codecs/cs35l45-spi.c
index 5efb77530cc33e..39e203a5f060c6 100644
--- a/sound/soc/codecs/cs35l45-spi.c
+++ b/sound/soc/codecs/cs35l45-spi.c
@@ -64,7 +64,7 @@ static struct spi_driver cs35l45_spi_driver = {
 	.driver = {
 		.name		= "cs35l45",
 		.of_match_table = cs35l45_of_match,
-		.pm		= &cs35l45_pm_ops,
+		.pm		= pm_ptr(&cs35l45_pm_ops),
 	},
 	.id_table	= cs35l45_id_spi,
 	.probe		= cs35l45_spi_probe,
diff --git a/sound/soc/codecs/cs35l45.c b/sound/soc/codecs/cs35l45.c
index b68853e42fd1e3..44c221745c3b25 100644
--- a/sound/soc/codecs/cs35l45.c
+++ b/sound/soc/codecs/cs35l45.c
@@ -947,6 +947,8 @@ static int cs35l45_enter_hibernate(struct cs35l45_private *cs35l45)
 
 	cs35l45_setup_hibernate(cs35l45);
 
+	regmap_set_bits(cs35l45->regmap, CS35L45_IRQ1_MASK_2, CS35L45_DSP_VIRT2_MBOX_MASK);
+
 	// Don't wait for ACK since bus activity would wake the device
 	regmap_write(cs35l45->regmap, CS35L45_DSP_VIRT1_MBOX_1, CSPL_MBOX_CMD_HIBERNATE);
 
@@ -967,6 +969,8 @@ static int cs35l45_exit_hibernate(struct cs35l45_private *cs35l45)
 					  CSPL_MBOX_CMD_OUT_OF_HIBERNATE);
 			if (!ret) {
 				dev_dbg(cs35l45->dev, "Wake success at cycle: %d\n", j);
+				regmap_clear_bits(cs35l45->regmap, CS35L45_IRQ1_MASK_2,
+						 CS35L45_DSP_VIRT2_MBOX_MASK);
 				return 0;
 			}
 			usleep_range(100, 200);
@@ -982,7 +986,7 @@ static int cs35l45_exit_hibernate(struct cs35l45_private *cs35l45)
 	return -ETIMEDOUT;
 }
 
-static int __maybe_unused cs35l45_runtime_suspend(struct device *dev)
+static int cs35l45_runtime_suspend(struct device *dev)
 {
 	struct cs35l45_private *cs35l45 = dev_get_drvdata(dev);
 
@@ -999,7 +1003,7 @@ static int __maybe_unused cs35l45_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static int __maybe_unused cs35l45_runtime_resume(struct device *dev)
+static int cs35l45_runtime_resume(struct device *dev)
 {
 	struct cs35l45_private *cs35l45 = dev_get_drvdata(dev);
 	int ret;
@@ -1026,6 +1030,46 @@ static int __maybe_unused cs35l45_runtime_resume(struct device *dev)
 	return ret;
 }
 
+static int cs35l45_sys_suspend(struct device *dev)
+{
+	struct cs35l45_private *cs35l45 = dev_get_drvdata(dev);
+
+	dev_dbg(cs35l45->dev, "System suspend, disabling IRQ\n");
+	disable_irq(cs35l45->irq);
+
+	return 0;
+}
+
+static int cs35l45_sys_suspend_noirq(struct device *dev)
+{
+	struct cs35l45_private *cs35l45 = dev_get_drvdata(dev);
+
+	dev_dbg(cs35l45->dev, "Late system suspend, reenabling IRQ\n");
+	enable_irq(cs35l45->irq);
+
+	return 0;
+}
+
+static int cs35l45_sys_resume_noirq(struct device *dev)
+{
+	struct cs35l45_private *cs35l45 = dev_get_drvdata(dev);
+
+	dev_dbg(cs35l45->dev, "Early system resume, disabling IRQ\n");
+	disable_irq(cs35l45->irq);
+
+	return 0;
+}
+
+static int cs35l45_sys_resume(struct device *dev)
+{
+	struct cs35l45_private *cs35l45 = dev_get_drvdata(dev);
+
+	dev_dbg(cs35l45->dev, "System resume, reenabling IRQ\n");
+	enable_irq(cs35l45->irq);
+
+	return 0;
+}
+
 static int cs35l45_apply_property_config(struct cs35l45_private *cs35l45)
 {
 	struct device_node *node = cs35l45->dev->of_node;
@@ -1466,10 +1510,12 @@ void cs35l45_remove(struct cs35l45_private *cs35l45)
 }
 EXPORT_SYMBOL_NS_GPL(cs35l45_remove, SND_SOC_CS35L45);
 
-const struct dev_pm_ops cs35l45_pm_ops = {
-	SET_RUNTIME_PM_OPS(cs35l45_runtime_suspend, cs35l45_runtime_resume, NULL)
+EXPORT_GPL_DEV_PM_OPS(cs35l45_pm_ops) = {
+	RUNTIME_PM_OPS(cs35l45_runtime_suspend, cs35l45_runtime_resume, NULL)
+
+	SYSTEM_SLEEP_PM_OPS(cs35l45_sys_suspend, cs35l45_sys_resume)
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(cs35l45_sys_suspend_noirq, cs35l45_sys_resume_noirq)
 };
-EXPORT_SYMBOL_NS_GPL(cs35l45_pm_ops, SND_SOC_CS35L45);
 
 MODULE_DESCRIPTION("ASoC CS35L45 driver");
 MODULE_AUTHOR("James Schulman, Cirrus Logic Inc, <james.schulman@cirrus.com>");
diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c
index 73454de068cf8c..54a3ea60644384 100644
--- a/sound/soc/codecs/cs42l43-jack.c
+++ b/sound/soc/codecs/cs42l43-jack.c
@@ -237,7 +237,7 @@ error:
 	return ret;
 }
 
-static void cs42l43_start_hs_bias(struct cs42l43_codec *priv, bool force_high)
+static void cs42l43_start_hs_bias(struct cs42l43_codec *priv, bool type_detect)
 {
 	struct cs42l43 *cs42l43 = priv->core;
 	unsigned int val = 0x3 << CS42L43_HSBIAS_MODE_SHIFT;
@@ -247,16 +247,17 @@ static void cs42l43_start_hs_bias(struct cs42l43_codec *priv, bool force_high)
 	regmap_update_bits(cs42l43->regmap, CS42L43_HS2,
 			   CS42L43_HS_CLAMP_DISABLE_MASK, CS42L43_HS_CLAMP_DISABLE_MASK);
 
-	if (!force_high && priv->bias_low)
-		val = 0x2 << CS42L43_HSBIAS_MODE_SHIFT;
-
-	if (priv->bias_sense_ua) {
-		regmap_update_bits(cs42l43->regmap,
-				   CS42L43_HS_BIAS_SENSE_AND_CLAMP_AUTOCONTROL,
-				   CS42L43_HSBIAS_SENSE_EN_MASK |
-				   CS42L43_AUTO_HSBIAS_CLAMP_EN_MASK,
-				   CS42L43_HSBIAS_SENSE_EN_MASK |
-				   CS42L43_AUTO_HSBIAS_CLAMP_EN_MASK);
+	if (!type_detect) {
+		if (priv->bias_low)
+			val = 0x2 << CS42L43_HSBIAS_MODE_SHIFT;
+
+		if (priv->bias_sense_ua)
+			regmap_update_bits(cs42l43->regmap,
+					   CS42L43_HS_BIAS_SENSE_AND_CLAMP_AUTOCONTROL,
+					   CS42L43_HSBIAS_SENSE_EN_MASK |
+					   CS42L43_AUTO_HSBIAS_CLAMP_EN_MASK,
+					   CS42L43_HSBIAS_SENSE_EN_MASK |
+					   CS42L43_AUTO_HSBIAS_CLAMP_EN_MASK);
 	}
 
 	regmap_update_bits(cs42l43->regmap, CS42L43_MIC_DETECT_CONTROL_1,
diff --git a/sound/soc/codecs/cs43130.c b/sound/soc/codecs/cs43130.c
index 0b40fdfb1825bf..d8ec325b9cc906 100644
--- a/sound/soc/codecs/cs43130.c
+++ b/sound/soc/codecs/cs43130.c
@@ -578,7 +578,7 @@ static int cs43130_set_sp_fmt(int dai_id, unsigned int bitwidth_sclk,
 		break;
 	case SND_SOC_DAIFMT_LEFT_J:
 		hi_size = bitwidth_sclk;
-		frm_delay = 2;
+		frm_delay = 0;
 		frm_phase = 1;
 		break;
 	case SND_SOC_DAIFMT_DSP_A:
@@ -1682,7 +1682,7 @@ static ssize_t hpload_dc_r_show(struct device *dev,
 	return cs43130_show_dc(dev, buf, HP_RIGHT);
 }
 
-static u16 const cs43130_ac_freq[CS43130_AC_FREQ] = {
+static const u16 cs43130_ac_freq[CS43130_AC_FREQ] = {
 	24,
 	43,
 	93,
@@ -2362,7 +2362,7 @@ static const struct regmap_config cs43130_regmap = {
 	.use_single_write	= true,
 };
 
-static u16 const cs43130_dc_threshold[CS43130_DC_THRESHOLD] = {
+static const u16 cs43130_dc_threshold[CS43130_DC_THRESHOLD] = {
 	50,
 	120,
 };
diff --git a/sound/soc/codecs/da7219-aad.c b/sound/soc/codecs/da7219-aad.c
index 3bbe8509164932..6bc068cdcbe2a8 100644
--- a/sound/soc/codecs/da7219-aad.c
+++ b/sound/soc/codecs/da7219-aad.c
@@ -696,7 +696,7 @@ static struct da7219_aad_pdata *da7219_aad_fw_to_pdata(struct device *dev)
 		aad_pdata->mic_det_thr =
 			da7219_aad_fw_mic_det_thr(dev, fw_val32);
 	else
-		aad_pdata->mic_det_thr = DA7219_AAD_MIC_DET_THR_500_OHMS;
+		aad_pdata->mic_det_thr = DA7219_AAD_MIC_DET_THR_200_OHMS;
 
 	if (fwnode_property_read_u32(aad_np, "dlg,jack-ins-deb", &fw_val32) >= 0)
 		aad_pdata->jack_ins_deb =
@@ -927,10 +927,15 @@ void da7219_aad_suspend(struct snd_soc_component *component)
 	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
 	u8 micbias_ctrl;
 
+	disable_irq(da7219_aad->irq);
+
 	if (da7219_aad->jack) {
 		/* Disable jack detection during suspend */
 		snd_soc_component_update_bits(component, DA7219_ACCDET_CONFIG_1,
 				    DA7219_ACCDET_EN_MASK, 0);
+		cancel_delayed_work_sync(&da7219_aad->jack_det_work);
+		/* Disable ground switch */
+		snd_soc_component_update_bits(component, 0xFB, 0x01, 0x00);
 
 		/*
 		 * If we have a 4-pole jack inserted, then micbias will be
@@ -947,8 +952,6 @@ void da7219_aad_suspend(struct snd_soc_component *component)
 			}
 		}
 	}
-
-	synchronize_irq(da7219_aad->irq);
 }
 
 void da7219_aad_resume(struct snd_soc_component *component)
@@ -971,6 +974,8 @@ void da7219_aad_resume(struct snd_soc_component *component)
 				    DA7219_ACCDET_EN_MASK,
 				    DA7219_ACCDET_EN_MASK);
 	}
+
+	enable_irq(da7219_aad->irq);
 }
 
 
diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c
index 355f30779a3487..b075689db2dcaa 100644
--- a/sound/soc/codecs/hdac_hda.c
+++ b/sound/soc/codecs/hdac_hda.c
@@ -132,6 +132,9 @@ static struct snd_soc_dai_driver hdac_hda_dais[] = {
 		.sig_bits = 24,
 	},
 },
+};
+
+static struct snd_soc_dai_driver hdac_hda_hdmi_dais[] = {
 {
 	.id = HDAC_HDMI_0_DAI_ID,
 	.name = "intel-hdmi-hifi1",
@@ -607,8 +610,16 @@ static const struct snd_soc_component_driver hdac_hda_codec = {
 	.endianness		= 1,
 };
 
+static const struct snd_soc_component_driver hdac_hda_hdmi_codec = {
+	.probe			= hdac_hda_codec_probe,
+	.remove			= hdac_hda_codec_remove,
+	.idle_bias_on		= false,
+	.endianness		= 1,
+};
+
 static int hdac_hda_dev_probe(struct hdac_device *hdev)
 {
+	struct hdac_hda_priv *hda_pvt = dev_get_drvdata(&hdev->dev);
 	struct hdac_ext_link *hlink;
 	int ret;
 
@@ -621,9 +632,15 @@ static int hdac_hda_dev_probe(struct hdac_device *hdev)
 	snd_hdac_ext_bus_link_get(hdev->bus, hlink);
 
 	/* ASoC specific initialization */
-	ret = devm_snd_soc_register_component(&hdev->dev,
-					 &hdac_hda_codec, hdac_hda_dais,
-					 ARRAY_SIZE(hdac_hda_dais));
+	if (hda_pvt->need_display_power)
+		ret = devm_snd_soc_register_component(&hdev->dev,
+						&hdac_hda_hdmi_codec, hdac_hda_hdmi_dais,
+						ARRAY_SIZE(hdac_hda_hdmi_dais));
+	else
+		ret = devm_snd_soc_register_component(&hdev->dev,
+						&hdac_hda_codec, hdac_hda_dais,
+						ARRAY_SIZE(hdac_hda_dais));
+
 	if (ret < 0) {
 		dev_err(&hdev->dev, "failed to register HDA codec %d\n", ret);
 		return ret;
diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c
index 09eef6042aad6d..0938671700c621 100644
--- a/sound/soc/codecs/hdmi-codec.c
+++ b/sound/soc/codecs/hdmi-codec.c
@@ -850,8 +850,9 @@ static int hdmi_dai_probe(struct snd_soc_dai *dai)
 static void hdmi_codec_jack_report(struct hdmi_codec_priv *hcp,
 				   unsigned int jack_status)
 {
-	if (hcp->jack && jack_status != hcp->jack_status) {
-		snd_soc_jack_report(hcp->jack, jack_status, SND_JACK_LINEOUT);
+	if (jack_status != hcp->jack_status) {
+		if (hcp->jack)
+			snd_soc_jack_report(hcp->jack, jack_status, SND_JACK_LINEOUT);
 		hcp->jack_status = jack_status;
 	}
 }
@@ -877,18 +878,20 @@ static int hdmi_codec_set_jack(struct snd_soc_component *component,
 			       void *data)
 {
 	struct hdmi_codec_priv *hcp = snd_soc_component_get_drvdata(component);
-	int ret = -ENOTSUPP;
 
 	if (hcp->hcd.ops->hook_plugged_cb) {
 		hcp->jack = jack;
-		ret = hcp->hcd.ops->hook_plugged_cb(component->dev->parent,
-						    hcp->hcd.data,
-						    plugged_cb,
-						    component->dev);
-		if (ret)
-			hcp->jack = NULL;
+
+		/*
+		 * Report the initial jack status which may have been provided
+		 * by the parent hdmi driver while the hpd hook was registered.
+		 */
+		snd_soc_jack_report(jack, hcp->jack_status, SND_JACK_LINEOUT);
+
+		return 0;
 	}
-	return ret;
+
+	return -ENOTSUPP;
 }
 
 static int hdmi_dai_spdif_probe(struct snd_soc_dai *dai)
@@ -982,6 +985,21 @@ static int hdmi_of_xlate_dai_id(struct snd_soc_component *component,
 	return ret;
 }
 
+static int hdmi_probe(struct snd_soc_component *component)
+{
+	struct hdmi_codec_priv *hcp = snd_soc_component_get_drvdata(component);
+	int ret = 0;
+
+	if (hcp->hcd.ops->hook_plugged_cb) {
+		ret = hcp->hcd.ops->hook_plugged_cb(component->dev->parent,
+						    hcp->hcd.data,
+						    plugged_cb,
+						    component->dev);
+	}
+
+	return ret;
+}
+
 static void hdmi_remove(struct snd_soc_component *component)
 {
 	struct hdmi_codec_priv *hcp = snd_soc_component_get_drvdata(component);
@@ -992,6 +1010,7 @@ static void hdmi_remove(struct snd_soc_component *component)
 }
 
 static const struct snd_soc_component_driver hdmi_driver = {
+	.probe			= hdmi_probe,
 	.remove			= hdmi_remove,
 	.dapm_widgets		= hdmi_widgets,
 	.num_dapm_widgets	= ARRAY_SIZE(hdmi_widgets),
diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c
index 82f9873ffada0a..124c2e144f3373 100644
--- a/sound/soc/codecs/lpass-tx-macro.c
+++ b/sound/soc/codecs/lpass-tx-macro.c
@@ -2021,6 +2021,11 @@ static int tx_macro_probe(struct platform_device *pdev)
 
 	tx->dev = dev;
 
+	/* Set active_decimator default value */
+	tx->active_decimator[TX_MACRO_AIF1_CAP] = -1;
+	tx->active_decimator[TX_MACRO_AIF2_CAP] = -1;
+	tx->active_decimator[TX_MACRO_AIF3_CAP] = -1;
+
 	/* set MCLK and NPL rates */
 	clk_set_rate(tx->mclk, MCLK_FREQ);
 	clk_set_rate(tx->npl, MCLK_FREQ);
diff --git a/sound/soc/codecs/nau8540.c b/sound/soc/codecs/nau8540.c
index 5cf28d034f094c..f66417a0f29f63 100644
--- a/sound/soc/codecs/nau8540.c
+++ b/sound/soc/codecs/nau8540.c
@@ -530,12 +530,61 @@ static int nau8540_set_tdm_slot(struct snd_soc_dai *dai,
 	return 0;
 }
 
+static int nau8540_dai_trigger(struct snd_pcm_substream *substream,
+			       int cmd, struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct nau8540 *nau8540 = snd_soc_component_get_drvdata(component);
+	struct regmap *regmap = nau8540->regmap;
+	unsigned int val;
+	int ret = 0;
+
+	/* Reading the peak data to detect abnormal data in the ADC channel.
+	 * If abnormal data happens, the driver takes recovery actions to
+	 * refresh the ADC channel.
+	 */
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+		regmap_update_bits(regmap, NAU8540_REG_CLOCK_CTRL,
+				   NAU8540_CLK_AGC_EN, NAU8540_CLK_AGC_EN);
+		regmap_update_bits(regmap, NAU8540_REG_ALC_CONTROL_3,
+				   NAU8540_ALC_CH_ALL_EN, NAU8540_ALC_CH_ALL_EN);
+
+		regmap_read(regmap, NAU8540_REG_PEAK_CH1, &val);
+		dev_dbg(nau8540->dev, "1.ADC CH1 peak data %x", val);
+		if (!val) {
+			regmap_update_bits(regmap, NAU8540_REG_MUTE,
+					   NAU8540_PGA_CH_ALL_MUTE, NAU8540_PGA_CH_ALL_MUTE);
+			regmap_update_bits(regmap, NAU8540_REG_MUTE,
+					   NAU8540_PGA_CH_ALL_MUTE, 0);
+			regmap_write(regmap, NAU8540_REG_RST, 0x1);
+			regmap_write(regmap, NAU8540_REG_RST, 0);
+			regmap_read(regmap, NAU8540_REG_PEAK_CH1, &val);
+			dev_dbg(nau8540->dev, "2.ADC CH1 peak data %x", val);
+			if (!val) {
+				dev_err(nau8540->dev, "Channel recovery failed!!");
+				ret = -EIO;
+			}
+		}
+		regmap_update_bits(regmap, NAU8540_REG_CLOCK_CTRL,
+				   NAU8540_CLK_AGC_EN, 0);
+		regmap_update_bits(regmap, NAU8540_REG_ALC_CONTROL_3,
+				   NAU8540_ALC_CH_ALL_EN, 0);
+		break;
+
+	default:
+		break;
+	}
+
+	return ret;
+}
 
 static const struct snd_soc_dai_ops nau8540_dai_ops = {
 	.startup = nau8540_dai_startup,
 	.hw_params = nau8540_hw_params,
 	.set_fmt = nau8540_set_fmt,
 	.set_tdm_slot = nau8540_set_tdm_slot,
+	.trigger = nau8540_dai_trigger,
 };
 
 #define NAU8540_RATES SNDRV_PCM_RATE_8000_48000
diff --git a/sound/soc/codecs/nau8540.h b/sound/soc/codecs/nau8540.h
index 305ea9207cf0b4..2ce6063d462b91 100644
--- a/sound/soc/codecs/nau8540.h
+++ b/sound/soc/codecs/nau8540.h
@@ -85,6 +85,7 @@
 
 /* CLOCK_CTRL (0x02) */
 #define NAU8540_CLK_ADC_EN		(0x1 << 15)
+#define NAU8540_CLK_AGC_EN		(0x1 << 3)
 #define NAU8540_CLK_I2S_EN		(0x1 << 1)
 
 /* CLOCK_SRC (0x03) */
@@ -168,6 +169,13 @@
 #define NAU8540_TDM_OFFSET_EN		(0x1 << 14)
 #define NAU8540_TDM_TX_MASK		0xf
 
+/* ALC_CONTROL_3 (0x22) */
+#define NAU8540_ALC_CH1_EN		(0x1 << 12)
+#define NAU8540_ALC_CH2_EN		(0x1 << 13)
+#define NAU8540_ALC_CH3_EN		(0x1 << 14)
+#define NAU8540_ALC_CH4_EN		(0x1 << 15)
+#define NAU8540_ALC_CH_ALL_EN		(0xf << 12)
+
 /* ADC_SAMPLE_RATE (0x3A) */
 #define NAU8540_CH_SYNC		(0x1 << 14)
 #define NAU8540_ADC_OSR_MASK		0x3
@@ -181,6 +189,13 @@
 #define NAU8540_VMID_SEL_SFT		4
 #define NAU8540_VMID_SEL_MASK		(0x3 << NAU8540_VMID_SEL_SFT)
 
+/* MUTE (0x61) */
+#define NAU8540_PGA_CH1_MUTE		0x1
+#define NAU8540_PGA_CH2_MUTE		0x2
+#define NAU8540_PGA_CH3_MUTE		0x4
+#define NAU8540_PGA_CH4_MUTE		0x8
+#define NAU8540_PGA_CH_ALL_MUTE		0xf
+
 /* MIC_BIAS (0x67) */
 #define NAU8540_PU_PRE			(0x1 << 8)
 
diff --git a/sound/soc/codecs/nau8822.c b/sound/soc/codecs/nau8822.c
index ff3024899f456d..7199d734c79f2c 100644
--- a/sound/soc/codecs/nau8822.c
+++ b/sound/soc/codecs/nau8822.c
@@ -184,6 +184,7 @@ static int nau8822_eq_get(struct snd_kcontrol *kcontrol,
 	struct soc_bytes_ext *params = (void *)kcontrol->private_value;
 	int i, reg;
 	u16 reg_val, *val;
+	__be16 tmp;
 
 	val = (u16 *)ucontrol->value.bytes.data;
 	reg = NAU8822_REG_EQ1;
@@ -192,8 +193,8 @@ static int nau8822_eq_get(struct snd_kcontrol *kcontrol,
 		/* conversion of 16-bit integers between native CPU format
 		 * and big endian format
 		 */
-		reg_val = cpu_to_be16(reg_val);
-		memcpy(val + i, &reg_val, sizeof(reg_val));
+		tmp = cpu_to_be16(reg_val);
+		memcpy(val + i, &tmp, sizeof(tmp));
 	}
 
 	return 0;
@@ -216,6 +217,7 @@ static int nau8822_eq_put(struct snd_kcontrol *kcontrol,
 	void *data;
 	u16 *val, value;
 	int i, reg, ret;
+	__be16 *tmp;
 
 	data = kmemdup(ucontrol->value.bytes.data,
 		params->max, GFP_KERNEL | GFP_DMA);
@@ -228,7 +230,8 @@ static int nau8822_eq_put(struct snd_kcontrol *kcontrol,
 		/* conversion of 16-bit integers between native CPU format
 		 * and big endian format
 		 */
-		value = be16_to_cpu(*(val + i));
+		tmp = (__be16 *)(val + i);
+		value = be16_to_cpup(tmp);
 		ret = snd_soc_component_write(component, reg + i, value);
 		if (ret) {
 			dev_err(component->dev,
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 7938b52d741d8c..a0d01d71d8b56f 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -448,6 +448,7 @@ struct rt5645_priv {
 	struct regulator_bulk_data supplies[ARRAY_SIZE(rt5645_supply_names)];
 	struct rt5645_eq_param_s *eq_param;
 	struct timer_list btn_check_timer;
+	struct mutex jd_mutex;
 
 	int codec_type;
 	int sysclk;
@@ -3193,6 +3194,8 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse
 				rt5645_enable_push_button_irq(component, true);
 			}
 		} else {
+			if (rt5645->en_button_func)
+				rt5645_enable_push_button_irq(component, false);
 			snd_soc_dapm_disable_pin(dapm, "Mic Det Power");
 			snd_soc_dapm_sync(dapm);
 			rt5645->jack_type = SND_JACK_HEADPHONE;
@@ -3295,6 +3298,8 @@ static void rt5645_jack_detect_work(struct work_struct *work)
 	if (!rt5645->component)
 		return;
 
+	mutex_lock(&rt5645->jd_mutex);
+
 	switch (rt5645->pdata.jd_mode) {
 	case 0: /* Not using rt5645 JD */
 		if (rt5645->gpiod_hp_det) {
@@ -3321,7 +3326,7 @@ static void rt5645_jack_detect_work(struct work_struct *work)
 
 	if (!val && (rt5645->jack_type == 0)) { /* jack in */
 		report = rt5645_jack_detect(rt5645->component, 1);
-	} else if (!val && rt5645->jack_type != 0) {
+	} else if (!val && rt5645->jack_type == SND_JACK_HEADSET) {
 		/* for push button and jack out */
 		btn_type = 0;
 		if (snd_soc_component_read(rt5645->component, RT5645_INT_IRQ_ST) & 0x4) {
@@ -3377,6 +3382,8 @@ static void rt5645_jack_detect_work(struct work_struct *work)
 		rt5645_jack_detect(rt5645->component, 0);
 	}
 
+	mutex_unlock(&rt5645->jd_mutex);
+
 	snd_soc_jack_report(rt5645->hp_jack, report, SND_JACK_HEADPHONE);
 	snd_soc_jack_report(rt5645->mic_jack, report, SND_JACK_MICROPHONE);
 	if (rt5645->en_button_func)
@@ -4150,6 +4157,7 @@ static int rt5645_i2c_probe(struct i2c_client *i2c)
 	}
 	timer_setup(&rt5645->btn_check_timer, rt5645_btn_check_callback, 0);
 
+	mutex_init(&rt5645->jd_mutex);
 	INIT_DELAYED_WORK(&rt5645->jack_detect_work, rt5645_jack_detect_work);
 	INIT_DELAYED_WORK(&rt5645->rcclock_work, rt5645_rcclock_work);
 
diff --git a/sound/soc/codecs/rt712-sdca.c b/sound/soc/codecs/rt712-sdca.c
index 7077ff6ba1f4bc..6954fbe7ec5f3b 100644
--- a/sound/soc/codecs/rt712-sdca.c
+++ b/sound/soc/codecs/rt712-sdca.c
@@ -963,13 +963,6 @@ static int rt712_sdca_probe(struct snd_soc_component *component)
 	rt712_sdca_parse_dt(rt712, &rt712->slave->dev);
 	rt712->component = component;
 
-	if (!rt712->first_hw_init)
-		return 0;
-
-	ret = pm_runtime_resume(component->dev);
-	if (ret < 0 && ret != -EACCES)
-		return ret;
-
 	/* add SPK route */
 	if (rt712->hw_id != RT712_DEV_ID_713) {
 		snd_soc_add_component_controls(component,
@@ -980,6 +973,13 @@ static int rt712_sdca_probe(struct snd_soc_component *component)
 			rt712_sdca_spk_dapm_routes, ARRAY_SIZE(rt712_sdca_spk_dapm_routes));
 	}
 
+	if (!rt712->first_hw_init)
+		return 0;
+
+	ret = pm_runtime_resume(component->dev);
+	if (ret < 0 && ret != -EACCES)
+		return ret;
+
 	return 0;
 }
 
diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c
index 4efe95b60aaa73..5c09e441a93681 100644
--- a/sound/soc/codecs/tas2781-fmwlib.c
+++ b/sound/soc/codecs/tas2781-fmwlib.c
@@ -2189,11 +2189,11 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no,
 		goto out;
 	}
 
-	conf = &(tas_fmw->configs[cfg_no]);
 	for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) {
 		if (cfg_info[rca_conf_no]->active_dev & (1 << i)) {
-			if (tas_priv->tasdevice[i].cur_prog != prm_no
-				|| tas_priv->force_fwload_status) {
+			if (prm_no >= 0
+				&& (tas_priv->tasdevice[i].cur_prog != prm_no
+				|| tas_priv->force_fwload_status)) {
 				tas_priv->tasdevice[i].cur_conf = -1;
 				tas_priv->tasdevice[i].is_loading = true;
 				prog_status++;
@@ -2228,7 +2228,8 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no,
 	}
 
 	for (i = 0, status = 0; i < tas_priv->ndev; i++) {
-		if (tas_priv->tasdevice[i].cur_conf != cfg_no
+		if (cfg_no >= 0
+			&& tas_priv->tasdevice[i].cur_conf != cfg_no
 			&& (cfg_info[rca_conf_no]->active_dev & (1 << i))
 			&& (tas_priv->tasdevice[i].is_loaderr == false)) {
 			status++;
@@ -2238,6 +2239,7 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no,
 	}
 
 	if (status) {
+		conf = &(tas_fmw->configs[cfg_no]);
 		status = 0;
 		tasdevice_load_data(tas_priv, &(conf->dev_data));
 		for (i = 0; i < tas_priv->ndev; i++) {
@@ -2281,7 +2283,7 @@ int tasdevice_prmg_load(void *context, int prm_no)
 	}
 
 	for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) {
-		if (tas_priv->tasdevice[i].cur_prog != prm_no) {
+		if (prm_no >= 0 && tas_priv->tasdevice[i].cur_prog != prm_no) {
 			tas_priv->tasdevice[i].cur_conf = -1;
 			tas_priv->tasdevice[i].is_loading = true;
 			prog_status++;
@@ -2326,7 +2328,7 @@ int tasdevice_prmg_calibdata_load(void *context, int prm_no)
 	}
 
 	for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) {
-		if (tas_priv->tasdevice[i].cur_prog != prm_no) {
+		if (prm_no >= 0 && tas_priv->tasdevice[i].cur_prog != prm_no) {
 			tas_priv->tasdevice[i].cur_conf = -1;
 			tas_priv->tasdevice[i].is_loading = true;
 			prog_status++;
diff --git a/sound/soc/codecs/wm8974.c b/sound/soc/codecs/wm8974.c
index 044b6f604c090a..260bac695b20ab 100644
--- a/sound/soc/codecs/wm8974.c
+++ b/sound/soc/codecs/wm8974.c
@@ -186,7 +186,7 @@ SOC_DAPM_SINGLE("PCM Playback Switch", WM8974_MONOMIX, 0, 1, 0),
 
 /* Boost mixer */
 static const struct snd_kcontrol_new wm8974_boost_mixer[] = {
-SOC_DAPM_SINGLE("Aux Switch", WM8974_INPPGA, 6, 1, 1),
+SOC_DAPM_SINGLE("PGA Switch", WM8974_INPPGA, 6, 1, 1),
 };
 
 /* Input PGA */
@@ -246,8 +246,8 @@ static const struct snd_soc_dapm_route wm8974_dapm_routes[] = {
 
 	/* Boost Mixer */
 	{"ADC", NULL, "Boost Mixer"},
-	{"Boost Mixer", "Aux Switch", "Aux Input"},
-	{"Boost Mixer", NULL, "Input PGA"},
+	{"Boost Mixer", NULL, "Aux Input"},
+	{"Boost Mixer", "PGA Switch", "Input PGA"},
 	{"Boost Mixer", NULL, "MICP"},
 
 	/* Input PGA */
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 236b12b69ae517..c01e31175015cc 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1451,12 +1451,12 @@ static int wm_adsp_buffer_populate(struct wm_adsp_compr_buf *buf)
 		ret = wm_adsp_buffer_read(buf, caps->region_defs[i].base_offset,
 					  &region->base_addr);
 		if (ret < 0)
-			return ret;
+			goto err;
 
 		ret = wm_adsp_buffer_read(buf, caps->region_defs[i].size_offset,
 					  &offset);
 		if (ret < 0)
-			return ret;
+			goto err;
 
 		region->cumulative_size = offset;
 
@@ -1467,6 +1467,10 @@ static int wm_adsp_buffer_populate(struct wm_adsp_compr_buf *buf)
 	}
 
 	return 0;
+
+err:
+	kfree(buf->regions);
+	return ret;
 }
 
 static void wm_adsp_buffer_clear(struct wm_adsp_compr_buf *buf)
diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig
index 725c530a363607..be342ee03fb9cb 100644
--- a/sound/soc/fsl/Kconfig
+++ b/sound/soc/fsl/Kconfig
@@ -360,6 +360,7 @@ config SND_SOC_IMX_HDMI
 config SND_SOC_IMX_RPMSG
 	tristate "SoC Audio support for i.MX boards with rpmsg"
 	depends on RPMSG
+	depends on OF && I2C
 	select SND_SOC_IMX_PCM_RPMSG
 	select SND_SOC_IMX_AUDIO_RPMSG
 	help
diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index 79e7c6b98a754f..546bd4e333b5fb 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -673,6 +673,20 @@ static int fsl_sai_hw_params(struct snd_pcm_substream *substream,
 			   FSL_SAI_CR3_TRCE_MASK,
 			   FSL_SAI_CR3_TRCE((dl_cfg[dl_cfg_idx].mask[tx] & trce_mask)));
 
+	/*
+	 * When the TERE and FSD_MSTR enabled before configuring the word width
+	 * There will be no frame sync clock issue, because word width impact
+	 * the generation of frame sync clock.
+	 *
+	 * TERE enabled earlier only for i.MX8MP case for the hardware limitation,
+	 * We need to disable FSD_MSTR before configuring word width, then enable
+	 * FSD_MSTR bit for this specific case.
+	 */
+	if (sai->soc_data->mclk_with_tere && sai->mclk_direction_output &&
+	    !sai->is_consumer_mode)
+		regmap_update_bits(sai->regmap, FSL_SAI_xCR4(tx, ofs),
+				   FSL_SAI_CR4_FSD_MSTR, 0);
+
 	regmap_update_bits(sai->regmap, FSL_SAI_xCR4(tx, ofs),
 			   FSL_SAI_CR4_SYWD_MASK | FSL_SAI_CR4_FRSZ_MASK |
 			   FSL_SAI_CR4_CHMOD_MASK,
@@ -680,6 +694,13 @@ static int fsl_sai_hw_params(struct snd_pcm_substream *substream,
 	regmap_update_bits(sai->regmap, FSL_SAI_xCR5(tx, ofs),
 			   FSL_SAI_CR5_WNW_MASK | FSL_SAI_CR5_W0W_MASK |
 			   FSL_SAI_CR5_FBT_MASK, val_cr5);
+
+	/* Enable FSD_MSTR after configuring word width */
+	if (sai->soc_data->mclk_with_tere && sai->mclk_direction_output &&
+	    !sai->is_consumer_mode)
+		regmap_update_bits(sai->regmap, FSL_SAI_xCR4(tx, ofs),
+				   FSL_SAI_CR4_FSD_MSTR, FSL_SAI_CR4_FSD_MSTR);
+
 	regmap_write(sai->regmap, FSL_SAI_xMR(tx),
 		     ~0UL - ((1 << min(channels, slots)) - 1));
 
@@ -693,6 +714,9 @@ static int fsl_sai_hw_free(struct snd_pcm_substream *substream,
 	bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
 	unsigned int ofs = sai->soc_data->reg_offset;
 
+	/* Clear xMR to avoid channel swap with mclk_with_tere enabled case */
+	regmap_write(sai->regmap, FSL_SAI_xMR(tx), 0);
+
 	regmap_update_bits(sai->regmap, FSL_SAI_xCR3(tx, ofs),
 			   FSL_SAI_CR3_TRCE_MASK, 0);
 
diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c
index fa0a15263c66dc..f0fb33d719c251 100644
--- a/sound/soc/fsl/fsl_xcvr.c
+++ b/sound/soc/fsl/fsl_xcvr.c
@@ -358,7 +358,7 @@ static int fsl_xcvr_en_aud_pll(struct fsl_xcvr *xcvr, u32 freq)
 	struct device *dev = &xcvr->pdev->dev;
 	int ret;
 
-	freq = xcvr->soc_data->spdif_only ? freq / 10 : freq;
+	freq = xcvr->soc_data->spdif_only ? freq / 5 : freq;
 	clk_disable_unprepare(xcvr->phy_clk);
 	ret = clk_set_rate(xcvr->phy_clk, freq);
 	if (ret < 0) {
@@ -409,11 +409,21 @@ static int fsl_xcvr_prepare(struct snd_pcm_substream *substream,
 	bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
 	u32 m_ctl = 0, v_ctl = 0;
 	u32 r = substream->runtime->rate, ch = substream->runtime->channels;
-	u32 fout = 32 * r * ch * 10 * 2;
+	u32 fout = 32 * r * ch * 10;
 	int ret = 0;
 
 	switch (xcvr->mode) {
 	case FSL_XCVR_MODE_SPDIF:
+		if (xcvr->soc_data->spdif_only && tx) {
+			ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_TX_DPTH_CTRL_SET,
+						 FSL_XCVR_TX_DPTH_CTRL_BYPASS_FEM,
+						 FSL_XCVR_TX_DPTH_CTRL_BYPASS_FEM);
+			if (ret < 0) {
+				dev_err(dai->dev, "Failed to set bypass fem: %d\n", ret);
+				return ret;
+			}
+		}
+		fallthrough;
 	case FSL_XCVR_MODE_ARC:
 		if (tx) {
 			ret = fsl_xcvr_en_aud_pll(xcvr, fout);
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index ed14d9e4aa5333..42466b4b1ca45e 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -83,6 +83,7 @@ enum {
 #define BYT_RT5640_HSMIC2_ON_IN1	BIT(27)
 #define BYT_RT5640_JD_HP_ELITEP_1000G2	BIT(28)
 #define BYT_RT5640_USE_AMCR0F28		BIT(29)
+#define BYT_RT5640_SWAPPED_SPEAKERS	BIT(30)
 
 #define BYTCR_INPUT_DEFAULTS				\
 	(BYT_RT5640_IN3_MAP |				\
@@ -157,6 +158,8 @@ static void log_quirks(struct device *dev)
 		dev_info(dev, "quirk MONO_SPEAKER enabled\n");
 	if (byt_rt5640_quirk & BYT_RT5640_NO_SPEAKERS)
 		dev_info(dev, "quirk NO_SPEAKERS enabled\n");
+	if (byt_rt5640_quirk & BYT_RT5640_SWAPPED_SPEAKERS)
+		dev_info(dev, "quirk SWAPPED_SPEAKERS enabled\n");
 	if (byt_rt5640_quirk & BYT_RT5640_LINEOUT)
 		dev_info(dev, "quirk LINEOUT enabled\n");
 	if (byt_rt5640_quirk & BYT_RT5640_LINEOUT_AS_HP2)
@@ -894,6 +897,19 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_SSP0_AIF1 |
 					BYT_RT5640_MCLK_EN),
 	},
+	{
+		/* Medion Lifetab S10346 */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
+			DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"),
+			/* Above strings are much too generic, also match on BIOS date */
+			DMI_MATCH(DMI_BIOS_DATE, "10/22/2015"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_SWAPPED_SPEAKERS |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{	/* Mele PCG03 Mini PC */
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "Mini PC"),
@@ -1619,11 +1635,11 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 	const char *platform_name;
 	struct acpi_device *adev;
 	struct device *codec_dev;
+	const char *cfg_spk;
 	bool sof_parent;
 	int ret_val = 0;
 	int dai_index = 0;
-	int i, cfg_spk;
-	int aif;
+	int i, aif;
 
 	is_bytcr = false;
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
@@ -1783,13 +1799,16 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 	}
 
 	if (byt_rt5640_quirk & BYT_RT5640_NO_SPEAKERS) {
-		cfg_spk = 0;
+		cfg_spk = "0";
 		spk_type = "none";
 	} else if (byt_rt5640_quirk & BYT_RT5640_MONO_SPEAKER) {
-		cfg_spk = 1;
+		cfg_spk = "1";
 		spk_type = "mono";
+	} else if (byt_rt5640_quirk & BYT_RT5640_SWAPPED_SPEAKERS) {
+		cfg_spk = "swapped";
+		spk_type = "swapped";
 	} else {
-		cfg_spk = 2;
+		cfg_spk = "2";
 		spk_type = "stereo";
 	}
 
@@ -1804,7 +1823,7 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 		headset2_string = " cfg-hs2:in1";
 
 	snprintf(byt_rt5640_components, sizeof(byt_rt5640_components),
-		 "cfg-spk:%d cfg-mic:%s aif:%d%s%s", cfg_spk,
+		 "cfg-spk:%s cfg-mic:%s aif:%d%s%s", cfg_spk,
 		 map_name[BYT_RT5640_MAP(byt_rt5640_quirk)], aif,
 		 lineout_string, headset2_string);
 	byt_rt5640_card.components = byt_rt5640_components;
diff --git a/sound/soc/intel/boards/skl_hda_dsp_generic.c b/sound/soc/intel/boards/skl_hda_dsp_generic.c
index 6c6ef63cd5d9ef..6e172719c9795b 100644
--- a/sound/soc/intel/boards/skl_hda_dsp_generic.c
+++ b/sound/soc/intel/boards/skl_hda_dsp_generic.c
@@ -154,6 +154,8 @@ static int skl_hda_fill_card_info(struct snd_soc_acpi_mach_params *mach_params)
 		card->dapm_widgets = skl_hda_widgets;
 		card->num_dapm_widgets = ARRAY_SIZE(skl_hda_widgets);
 		if (!ctx->idisp_codec) {
+			card->dapm_routes = &skl_hda_map[IDISP_ROUTE_COUNT];
+			num_route -= IDISP_ROUTE_COUNT;
 			for (i = 0; i < IDISP_DAI_COUNT; i++) {
 				skl_hda_be_dai_links[i].codecs = &snd_soc_dummy_dlc;
 				skl_hda_be_dai_links[i].num_codecs = 1;
diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index 3312ad8a563b3f..4e428472977326 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -1546,7 +1546,7 @@ static int sof_card_dai_links_create(struct snd_soc_card *card)
 {
 	struct device *dev = card->dev;
 	struct snd_soc_acpi_mach *mach = dev_get_platdata(card->dev);
-	int sdw_be_num = 0, ssp_num = 0, dmic_num = 0, hdmi_num = 0, bt_num = 0;
+	int sdw_be_num = 0, ssp_num = 0, dmic_num = 0, bt_num = 0;
 	struct mc_private *ctx = snd_soc_card_get_drvdata(card);
 	struct snd_soc_acpi_mach_params *mach_params = &mach->mach_params;
 	const struct snd_soc_acpi_link_adr *adr_link = mach_params->links;
@@ -1564,6 +1564,7 @@ static int sof_card_dai_links_create(struct snd_soc_card *card)
 	char *codec_name, *codec_dai_name;
 	int i, j, be_id = 0;
 	int codec_index;
+	int hdmi_num;
 	int ret;
 
 	ret = get_dailink_info(dev, adr_link, &sdw_be_num, &codec_conf_num);
@@ -1584,14 +1585,13 @@ static int sof_card_dai_links_create(struct snd_soc_card *card)
 		ssp_num = hweight_long(ssp_mask);
 	}
 
-	if (mach_params->codec_mask & IDISP_CODEC_MASK) {
+	if (mach_params->codec_mask & IDISP_CODEC_MASK)
 		ctx->hdmi.idisp_codec = true;
 
-		if (sof_sdw_quirk & SOF_SDW_TGL_HDMI)
-			hdmi_num = SOF_TGL_HDMI_COUNT;
-		else
-			hdmi_num = SOF_PRE_TGL_HDMI_COUNT;
-	}
+	if (sof_sdw_quirk & SOF_SDW_TGL_HDMI)
+		hdmi_num = SOF_TGL_HDMI_COUNT;
+	else
+		hdmi_num = SOF_PRE_TGL_HDMI_COUNT;
 
 	/* enable dmic01 & dmic16k */
 	if (sof_sdw_quirk & SOF_SDW_PCH_DMIC || mach_params->dmic_num)
@@ -1601,7 +1601,8 @@ static int sof_card_dai_links_create(struct snd_soc_card *card)
 		bt_num = 1;
 
 	dev_dbg(dev, "sdw %d, ssp %d, dmic %d, hdmi %d, bt: %d\n",
-		sdw_be_num, ssp_num, dmic_num, hdmi_num, bt_num);
+		sdw_be_num, ssp_num, dmic_num,
+		ctx->hdmi.idisp_codec ? hdmi_num : 0, bt_num);
 
 	/* allocate BE dailinks */
 	num_links = sdw_be_num + ssp_num + dmic_num + hdmi_num + bt_num;
diff --git a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c
index 301b8142d554cb..9008b67682059c 100644
--- a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c
@@ -306,13 +306,13 @@ static const struct snd_soc_acpi_adr_device cs35l56_1_adr[] = {
 		.adr = 0x00013701FA355601ull,
 		.num_endpoints = 1,
 		.endpoints = &spk_r_endpoint,
-		.name_prefix = "cs35l56-8"
+		.name_prefix = "AMP8"
 	},
 	{
 		.adr = 0x00013601FA355601ull,
 		.num_endpoints = 1,
 		.endpoints = &spk_3_endpoint,
-		.name_prefix = "cs35l56-7"
+		.name_prefix = "AMP7"
 	}
 };
 
@@ -321,13 +321,13 @@ static const struct snd_soc_acpi_adr_device cs35l56_2_adr[] = {
 		.adr = 0x00023301FA355601ull,
 		.num_endpoints = 1,
 		.endpoints = &spk_l_endpoint,
-		.name_prefix = "cs35l56-1"
+		.name_prefix = "AMP1"
 	},
 	{
 		.adr = 0x00023201FA355601ull,
 		.num_endpoints = 1,
 		.endpoints = &spk_2_endpoint,
-		.name_prefix = "cs35l56-2"
+		.name_prefix = "AMP2"
 	}
 };
 
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index d0c02e8a67854c..174aae6e0398f2 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -240,8 +240,10 @@ static int skl_pcm_open(struct snd_pcm_substream *substream,
 	snd_pcm_set_sync(substream);
 
 	mconfig = skl_tplg_fe_get_cpr_module(dai, substream->stream);
-	if (!mconfig)
+	if (!mconfig) {
+		kfree(dma_params);
 		return -EINVAL;
+	}
 
 	skl_tplg_d0i3_get(skl, mconfig->d0i3_caps);
 
@@ -1462,6 +1464,7 @@ int skl_platform_register(struct device *dev)
 		dais = krealloc(skl->dais, sizeof(skl_fe_dai) +
 				sizeof(skl_platform_dai), GFP_KERNEL);
 		if (!dais) {
+			kfree(skl->dais);
 			ret = -ENOMEM;
 			goto err;
 		}
@@ -1474,8 +1477,10 @@ int skl_platform_register(struct device *dev)
 
 	ret = devm_snd_soc_register_component(dev, &skl_component,
 					 skl->dais, num_dais);
-	if (ret)
+	if (ret) {
+		kfree(skl->dais);
 		dev_err(dev, "soc component registration failed %d\n", ret);
+	}
 err:
 	return ret;
 }
diff --git a/sound/soc/intel/skylake/skl-sst-ipc.c b/sound/soc/intel/skylake/skl-sst-ipc.c
index 7a425271b08b16..fd9624ad5f72b0 100644
--- a/sound/soc/intel/skylake/skl-sst-ipc.c
+++ b/sound/soc/intel/skylake/skl-sst-ipc.c
@@ -1003,8 +1003,10 @@ int skl_ipc_get_large_config(struct sst_generic_ipc *ipc,
 
 	reply.size = (reply.header >> 32) & IPC_DATA_OFFSET_SZ_MASK;
 	buf = krealloc(reply.data, reply.size, GFP_KERNEL);
-	if (!buf)
+	if (!buf) {
+		kfree(reply.data);
 		return -ENOMEM;
+	}
 	*payload = buf;
 	*bytes = reply.size;
 
diff --git a/sound/soc/mediatek/mt8186/mt8186-mt6366-rt1019-rt5682s.c b/sound/soc/mediatek/mt8186/mt8186-mt6366-rt1019-rt5682s.c
index 6dfcfcf47cab39..f78197c8e582bb 100644
--- a/sound/soc/mediatek/mt8186/mt8186-mt6366-rt1019-rt5682s.c
+++ b/sound/soc/mediatek/mt8186/mt8186-mt6366-rt1019-rt5682s.c
@@ -1216,7 +1216,7 @@ static int mt8186_mt6366_rt1019_rt5682s_dev_probe(struct platform_device *pdev)
 	playback_codec = of_get_child_by_name(pdev->dev.of_node, "playback-codecs");
 	if (!playback_codec) {
 		ret = -EINVAL;
-		dev_err_probe(&pdev->dev, ret, "Property 'speaker-codecs' missing or invalid\n");
+		dev_err_probe(&pdev->dev, ret, "Property 'playback-codecs' missing or invalid\n");
 		goto err_playback_codec;
 	}
 
@@ -1230,7 +1230,7 @@ static int mt8186_mt6366_rt1019_rt5682s_dev_probe(struct platform_device *pdev)
 	for_each_card_prelinks(card, i, dai_link) {
 		ret = mt8186_mt6366_card_set_be_link(card, dai_link, playback_codec, "I2S3");
 		if (ret) {
-			dev_err_probe(&pdev->dev, ret, "%s set speaker_codec fail\n",
+			dev_err_probe(&pdev->dev, ret, "%s set playback_codec fail\n",
 				      dai_link->name);
 			goto err_probe;
 		}
diff --git a/sound/soc/qcom/sc8280xp.c b/sound/soc/qcom/sc8280xp.c
index d93b18f07be59a..39cb0b889aff91 100644
--- a/sound/soc/qcom/sc8280xp.c
+++ b/sound/soc/qcom/sc8280xp.c
@@ -27,6 +27,23 @@ struct sc8280xp_snd_data {
 static int sc8280xp_snd_init(struct snd_soc_pcm_runtime *rtd)
 {
 	struct sc8280xp_snd_data *data = snd_soc_card_get_drvdata(rtd->card);
+	struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, 0);
+	struct snd_soc_card *card = rtd->card;
+
+	switch (cpu_dai->id) {
+	case WSA_CODEC_DMA_RX_0:
+	case WSA_CODEC_DMA_RX_1:
+		/*
+		 * set limit of 0dB on Digital Volume for Speakers,
+		 * this can prevent damage of speakers to some extent without
+		 * active speaker protection
+		 */
+		snd_soc_limit_volume(card, "WSA_RX0 Digital Volume", 84);
+		snd_soc_limit_volume(card, "WSA_RX1 Digital Volume", 84);
+		break;
+	default:
+		break;
+	}
 
 	return qcom_snd_wcd_jack_setup(rtd, &data->jack, &data->jack_setup);
 }
diff --git a/sound/soc/rockchip/rockchip_i2s_tdm.c b/sound/soc/rockchip/rockchip_i2s_tdm.c
index 5c51dbef6e8645..860e66ec85e8a3 100644
--- a/sound/soc/rockchip/rockchip_i2s_tdm.c
+++ b/sound/soc/rockchip/rockchip_i2s_tdm.c
@@ -1757,7 +1757,7 @@ static struct platform_driver rockchip_i2s_tdm_driver = {
 	.remove_new = rockchip_i2s_tdm_remove,
 	.driver = {
 		.name = DRV_NAME,
-		.of_match_table = of_match_ptr(rockchip_i2s_tdm_match),
+		.of_match_table = rockchip_i2s_tdm_match,
 		.pm = &rockchip_i2s_tdm_pm_ops,
 	},
 };
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 4e2beda6f9bf2e..3844f777c87bbb 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -3670,7 +3670,7 @@ snd_soc_dapm_new_control_unlocked(struct snd_soc_dapm_context *dapm,
 		dapm_pinctrl_event(w, NULL, SND_SOC_DAPM_POST_PMD);
 		break;
 	case snd_soc_dapm_clock_supply:
-		w->clk = devm_clk_get(dapm->dev, w->name);
+		w->clk = devm_clk_get(dapm->dev, widget->name);
 		if (IS_ERR(w->clk)) {
 			ret = PTR_ERR(w->clk);
 			goto request_failed;
diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c
index 55b009d3c68154..2d25748ca70662 100644
--- a/sound/soc/soc-ops.c
+++ b/sound/soc/soc-ops.c
@@ -661,7 +661,7 @@ int snd_soc_limit_volume(struct snd_soc_card *card,
 	kctl = snd_soc_card_get_kcontrol(card, name);
 	if (kctl) {
 		struct soc_mixer_control *mc = (struct soc_mixer_control *)kctl->private_value;
-		if (max <= mc->max) {
+		if (max <= mc->max - mc->min) {
 			mc->platform_max = max;
 			ret = 0;
 		}
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 323e4d7b6adfe1..f6d1b2e11795fb 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -704,11 +704,6 @@ static int soc_pcm_clean(struct snd_soc_pcm_runtime *rtd,
 			if (snd_soc_dai_active(dai) == 0 &&
 			    (dai->rate || dai->channels || dai->sample_bits))
 				soc_pcm_set_dai_params(dai, NULL);
-
-			if (snd_soc_dai_stream_active(dai, substream->stream) ==  0) {
-				if (dai->driver->ops && !dai->driver->ops->mute_unmute_on_trigger)
-					snd_soc_dai_digital_mute(dai, 1, substream->stream);
-			}
 		}
 	}
 
@@ -947,8 +942,10 @@ static int soc_pcm_hw_clean(struct snd_soc_pcm_runtime *rtd,
 		if (snd_soc_dai_active(dai) == 1)
 			soc_pcm_set_dai_params(dai, NULL);
 
-		if (snd_soc_dai_stream_active(dai, substream->stream) == 1)
-			snd_soc_dai_digital_mute(dai, 1, substream->stream);
+		if (snd_soc_dai_stream_active(dai, substream->stream) == 1) {
+			if (dai->driver->ops && !dai->driver->ops->mute_unmute_on_trigger)
+				snd_soc_dai_digital_mute(dai, 1, substream->stream);
+		}
 	}
 
 	/* run the stream event */
diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c
index ba4ef290b6343f..2c7a5e7a364cf5 100644
--- a/sound/soc/sof/ipc3-topology.c
+++ b/sound/soc/sof/ipc3-topology.c
@@ -493,6 +493,7 @@ static int sof_ipc3_widget_setup_comp_mixer(struct snd_sof_widget *swidget)
 static int sof_ipc3_widget_setup_comp_pipeline(struct snd_sof_widget *swidget)
 {
 	struct snd_soc_component *scomp = swidget->scomp;
+	struct snd_sof_pipeline *spipe = swidget->spipe;
 	struct sof_ipc_pipe_new *pipeline;
 	struct snd_sof_widget *comp_swidget;
 	int ret;
@@ -545,6 +546,7 @@ static int sof_ipc3_widget_setup_comp_pipeline(struct snd_sof_widget *swidget)
 		swidget->dynamic_pipeline_widget);
 
 	swidget->core = pipeline->core;
+	spipe->core_mask |= BIT(pipeline->core);
 
 	return 0;
 
diff --git a/sound/soc/sof/ipc4-control.c b/sound/soc/sof/ipc4-control.c
index 938efaceb81cf1..b4cdcec33e1209 100644
--- a/sound/soc/sof/ipc4-control.c
+++ b/sound/soc/sof/ipc4-control.c
@@ -89,7 +89,7 @@ sof_ipc4_set_volume_data(struct snd_sof_dev *sdev, struct snd_sof_widget *swidge
 	struct sof_ipc4_control_data *cdata = scontrol->ipc_control_data;
 	struct sof_ipc4_gain *gain = swidget->private;
 	struct sof_ipc4_msg *msg = &cdata->msg;
-	struct sof_ipc4_gain_data data;
+	struct sof_ipc4_gain_params params;
 	bool all_channels_equal = true;
 	u32 value;
 	int ret, i;
@@ -109,20 +109,20 @@ sof_ipc4_set_volume_data(struct snd_sof_dev *sdev, struct snd_sof_widget *swidge
 	 */
 	for (i = 0; i < scontrol->num_channels; i++) {
 		if (all_channels_equal) {
-			data.channels = SOF_IPC4_GAIN_ALL_CHANNELS_MASK;
-			data.init_val = cdata->chanv[0].value;
+			params.channels = SOF_IPC4_GAIN_ALL_CHANNELS_MASK;
+			params.init_val = cdata->chanv[0].value;
 		} else {
-			data.channels = cdata->chanv[i].channel;
-			data.init_val = cdata->chanv[i].value;
+			params.channels = cdata->chanv[i].channel;
+			params.init_val = cdata->chanv[i].value;
 		}
 
 		/* set curve type and duration from topology */
-		data.curve_duration_l = gain->data.curve_duration_l;
-		data.curve_duration_h = gain->data.curve_duration_h;
-		data.curve_type = gain->data.curve_type;
+		params.curve_duration_l = gain->data.params.curve_duration_l;
+		params.curve_duration_h = gain->data.params.curve_duration_h;
+		params.curve_type = gain->data.params.curve_type;
 
-		msg->data_ptr = &data;
-		msg->data_size = sizeof(data);
+		msg->data_ptr = &params;
+		msg->data_size = sizeof(params);
 
 		ret = sof_ipc4_set_get_kcontrol_data(scontrol, true, lock);
 		msg->data_ptr = NULL;
diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index b24a64377f6874..e012b6e166accd 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -130,18 +130,18 @@ static const struct sof_topology_token comp_ext_tokens[] = {
 
 static const struct sof_topology_token gain_tokens[] = {
 	{SOF_TKN_GAIN_RAMP_TYPE, SND_SOC_TPLG_TUPLE_TYPE_WORD,
-		get_token_u32, offsetof(struct sof_ipc4_gain_data, curve_type)},
+		get_token_u32, offsetof(struct sof_ipc4_gain_params, curve_type)},
 	{SOF_TKN_GAIN_RAMP_DURATION,
 		SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32,
-		offsetof(struct sof_ipc4_gain_data, curve_duration_l)},
+		offsetof(struct sof_ipc4_gain_params, curve_duration_l)},
 	{SOF_TKN_GAIN_VAL, SND_SOC_TPLG_TUPLE_TYPE_WORD,
-		get_token_u32, offsetof(struct sof_ipc4_gain_data, init_val)},
+		get_token_u32, offsetof(struct sof_ipc4_gain_params, init_val)},
 };
 
 /* SRC */
 static const struct sof_topology_token src_tokens[] = {
 	{SOF_TKN_SRC_RATE_OUT, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32,
-		offsetof(struct sof_ipc4_src, sink_rate)},
+		offsetof(struct sof_ipc4_src_data, sink_rate)},
 };
 
 static const struct sof_token_info ipc4_token_list[SOF_TOKEN_COUNT] = {
@@ -656,6 +656,7 @@ static int sof_ipc4_widget_setup_comp_pipeline(struct snd_sof_widget *swidget)
 {
 	struct snd_soc_component *scomp = swidget->scomp;
 	struct sof_ipc4_pipeline *pipeline;
+	struct snd_sof_pipeline *spipe = swidget->spipe;
 	int ret;
 
 	pipeline = kzalloc(sizeof(*pipeline), GFP_KERNEL);
@@ -670,6 +671,7 @@ static int sof_ipc4_widget_setup_comp_pipeline(struct snd_sof_widget *swidget)
 	}
 
 	swidget->core = pipeline->core_id;
+	spipe->core_mask |= BIT(pipeline->core_id);
 
 	if (pipeline->use_chain_dma) {
 		dev_dbg(scomp->dev, "Set up chain DMA for %s\n", swidget->widget->name);
@@ -718,15 +720,15 @@ static int sof_ipc4_widget_setup_comp_pga(struct snd_sof_widget *swidget)
 
 	swidget->private = gain;
 
-	gain->data.channels = SOF_IPC4_GAIN_ALL_CHANNELS_MASK;
-	gain->data.init_val = SOF_IPC4_VOL_ZERO_DB;
+	gain->data.params.channels = SOF_IPC4_GAIN_ALL_CHANNELS_MASK;
+	gain->data.params.init_val = SOF_IPC4_VOL_ZERO_DB;
 
-	ret = sof_ipc4_get_audio_fmt(scomp, swidget, &gain->available_fmt, &gain->base_config);
+	ret = sof_ipc4_get_audio_fmt(scomp, swidget, &gain->available_fmt, &gain->data.base_config);
 	if (ret)
 		goto err;
 
-	ret = sof_update_ipc_object(scomp, &gain->data, SOF_GAIN_TOKENS, swidget->tuples,
-				    swidget->num_tuples, sizeof(gain->data), 1);
+	ret = sof_update_ipc_object(scomp, &gain->data.params, SOF_GAIN_TOKENS,
+				    swidget->tuples, swidget->num_tuples, sizeof(gain->data), 1);
 	if (ret) {
 		dev_err(scomp->dev, "Parsing gain tokens failed\n");
 		goto err;
@@ -734,8 +736,8 @@ static int sof_ipc4_widget_setup_comp_pga(struct snd_sof_widget *swidget)
 
 	dev_dbg(scomp->dev,
 		"pga widget %s: ramp type: %d, ramp duration %d, initial gain value: %#x\n",
-		swidget->widget->name, gain->data.curve_type, gain->data.curve_duration_l,
-		gain->data.init_val);
+		swidget->widget->name, gain->data.params.curve_type,
+		gain->data.params.curve_duration_l, gain->data.params.init_val);
 
 	ret = sof_ipc4_widget_setup_msg(swidget, &gain->msg);
 	if (ret)
@@ -797,6 +799,7 @@ err:
 static int sof_ipc4_widget_setup_comp_src(struct snd_sof_widget *swidget)
 {
 	struct snd_soc_component *scomp = swidget->scomp;
+	struct snd_sof_pipeline *spipe = swidget->spipe;
 	struct sof_ipc4_src *src;
 	int ret;
 
@@ -808,18 +811,21 @@ static int sof_ipc4_widget_setup_comp_src(struct snd_sof_widget *swidget)
 
 	swidget->private = src;
 
-	ret = sof_ipc4_get_audio_fmt(scomp, swidget, &src->available_fmt, &src->base_config);
+	ret = sof_ipc4_get_audio_fmt(scomp, swidget, &src->available_fmt,
+				     &src->data.base_config);
 	if (ret)
 		goto err;
 
-	ret = sof_update_ipc_object(scomp, src, SOF_SRC_TOKENS, swidget->tuples,
+	ret = sof_update_ipc_object(scomp, &src->data, SOF_SRC_TOKENS, swidget->tuples,
 				    swidget->num_tuples, sizeof(*src), 1);
 	if (ret) {
 		dev_err(scomp->dev, "Parsing SRC tokens failed\n");
 		goto err;
 	}
 
-	dev_dbg(scomp->dev, "SRC sink rate %d\n", src->sink_rate);
+	spipe->core_mask |= BIT(swidget->core);
+
+	dev_dbg(scomp->dev, "SRC sink rate %d\n", src->data.sink_rate);
 
 	ret = sof_ipc4_widget_setup_msg(swidget, &src->msg);
 	if (ret)
@@ -864,6 +870,7 @@ static int sof_ipc4_widget_setup_comp_process(struct snd_sof_widget *swidget)
 {
 	struct snd_soc_component *scomp = swidget->scomp;
 	struct sof_ipc4_fw_module *fw_module;
+	struct snd_sof_pipeline *spipe = swidget->spipe;
 	struct sof_ipc4_process *process;
 	void *cfg;
 	int ret;
@@ -920,6 +927,9 @@ static int sof_ipc4_widget_setup_comp_process(struct snd_sof_widget *swidget)
 
 	sof_ipc4_widget_update_kcontrol_module_id(swidget);
 
+	/* set pipeline core mask to keep track of the core the module is scheduled to run on */
+	spipe->core_mask |= BIT(swidget->core);
+
 	return 0;
 free_base_cfg_ext:
 	kfree(process->base_config_ext);
@@ -1816,7 +1826,7 @@ static int sof_ipc4_prepare_gain_module(struct snd_sof_widget *swidget,
 	u32 out_ref_rate, out_ref_channels, out_ref_valid_bits;
 	int ret;
 
-	ret = sof_ipc4_init_input_audio_fmt(sdev, swidget, &gain->base_config,
+	ret = sof_ipc4_init_input_audio_fmt(sdev, swidget, &gain->data.base_config,
 					    pipeline_params, available_fmt);
 	if (ret < 0)
 		return ret;
@@ -1826,7 +1836,7 @@ static int sof_ipc4_prepare_gain_module(struct snd_sof_widget *swidget,
 	out_ref_channels = SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT(in_fmt->fmt_cfg);
 	out_ref_valid_bits = SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH(in_fmt->fmt_cfg);
 
-	ret = sof_ipc4_init_output_audio_fmt(sdev, &gain->base_config, available_fmt,
+	ret = sof_ipc4_init_output_audio_fmt(sdev, &gain->data.base_config, available_fmt,
 					     out_ref_rate, out_ref_channels, out_ref_valid_bits);
 	if (ret < 0) {
 		dev_err(sdev->dev, "Failed to initialize output format for %s",
@@ -1835,7 +1845,7 @@ static int sof_ipc4_prepare_gain_module(struct snd_sof_widget *swidget,
 	}
 
 	/* update pipeline memory usage */
-	sof_ipc4_update_resource_usage(sdev, swidget, &gain->base_config);
+	sof_ipc4_update_resource_usage(sdev, swidget, &gain->data.base_config);
 
 	return 0;
 }
@@ -1891,7 +1901,7 @@ static int sof_ipc4_prepare_src_module(struct snd_sof_widget *swidget,
 	u32 out_ref_rate, out_ref_channels, out_ref_valid_bits;
 	int output_format_index, input_format_index;
 
-	input_format_index = sof_ipc4_init_input_audio_fmt(sdev, swidget, &src->base_config,
+	input_format_index = sof_ipc4_init_input_audio_fmt(sdev, swidget, &src->data.base_config,
 							   pipeline_params, available_fmt);
 	if (input_format_index < 0)
 		return input_format_index;
@@ -1921,7 +1931,7 @@ static int sof_ipc4_prepare_src_module(struct snd_sof_widget *swidget,
 	 */
 	out_ref_rate = params_rate(fe_params);
 
-	output_format_index = sof_ipc4_init_output_audio_fmt(sdev, &src->base_config,
+	output_format_index = sof_ipc4_init_output_audio_fmt(sdev, &src->data.base_config,
 							     available_fmt, out_ref_rate,
 							     out_ref_channels, out_ref_valid_bits);
 	if (output_format_index < 0) {
@@ -1931,10 +1941,10 @@ static int sof_ipc4_prepare_src_module(struct snd_sof_widget *swidget,
 	}
 
 	/* update pipeline memory usage */
-	sof_ipc4_update_resource_usage(sdev, swidget, &src->base_config);
+	sof_ipc4_update_resource_usage(sdev, swidget, &src->data.base_config);
 
 	out_audio_fmt = &available_fmt->output_pin_fmts[output_format_index].audio_fmt;
-	src->sink_rate = out_audio_fmt->sampling_frequency;
+	src->data.sink_rate = out_audio_fmt->sampling_frequency;
 
 	/* update pipeline_params for sink widgets */
 	return sof_ipc4_update_hw_params(sdev, pipeline_params, out_audio_fmt);
@@ -2314,9 +2324,8 @@ static int sof_ipc4_widget_setup(struct snd_sof_dev *sdev, struct snd_sof_widget
 	{
 		struct sof_ipc4_gain *gain = swidget->private;
 
-		ipc_size = sizeof(struct sof_ipc4_base_module_cfg) +
-			   sizeof(struct sof_ipc4_gain_data);
-		ipc_data = gain;
+		ipc_size = sizeof(gain->data);
+		ipc_data = &gain->data;
 
 		msg = &gain->msg;
 		break;
@@ -2335,8 +2344,8 @@ static int sof_ipc4_widget_setup(struct snd_sof_dev *sdev, struct snd_sof_widget
 	{
 		struct sof_ipc4_src *src = swidget->private;
 
-		ipc_size = sizeof(struct sof_ipc4_base_module_cfg) + sizeof(src->sink_rate);
-		ipc_data = src;
+		ipc_size = sizeof(src->data);
+		ipc_data = &src->data;
 
 		msg = &src->msg;
 		break;
diff --git a/sound/soc/sof/ipc4-topology.h b/sound/soc/sof/ipc4-topology.h
index 0a57b8ab3e08f0..dce174a190ddc6 100644
--- a/sound/soc/sof/ipc4-topology.h
+++ b/sound/soc/sof/ipc4-topology.h
@@ -361,7 +361,7 @@ struct sof_ipc4_control_msg_payload {
 } __packed;
 
 /**
- * struct sof_ipc4_gain_data - IPC gain blob
+ * struct sof_ipc4_gain_params - IPC gain parameters
  * @channels: Channels
  * @init_val: Initial value
  * @curve_type: Curve type
@@ -369,24 +369,32 @@ struct sof_ipc4_control_msg_payload {
  * @curve_duration_l: Curve duration low part
  * @curve_duration_h: Curve duration high part
  */
-struct sof_ipc4_gain_data {
+struct sof_ipc4_gain_params {
 	uint32_t channels;
 	uint32_t init_val;
 	uint32_t curve_type;
 	uint32_t reserved;
 	uint32_t curve_duration_l;
 	uint32_t curve_duration_h;
-} __aligned(8);
+} __packed __aligned(4);
 
 /**
- * struct sof_ipc4_gain - gain config data
+ * struct sof_ipc4_gain_data - IPC gain init blob
  * @base_config: IPC base config data
+ * @params: Initial parameters for the gain module
+ */
+struct sof_ipc4_gain_data {
+	struct sof_ipc4_base_module_cfg base_config;
+	struct sof_ipc4_gain_params params;
+} __packed __aligned(4);
+
+/**
+ * struct sof_ipc4_gain - gain config data
  * @data: IPC gain blob
  * @available_fmt: Available audio format
  * @msg: message structure for gain
  */
 struct sof_ipc4_gain {
-	struct sof_ipc4_base_module_cfg base_config;
 	struct sof_ipc4_gain_data data;
 	struct sof_ipc4_available_audio_format available_fmt;
 	struct sof_ipc4_msg msg;
@@ -404,16 +412,24 @@ struct sof_ipc4_mixer {
 	struct sof_ipc4_msg msg;
 };
 
-/**
- * struct sof_ipc4_src SRC config data
+/*
+ * struct sof_ipc4_src_data - IPC data for SRC
  * @base_config: IPC base config data
  * @sink_rate: Output rate for sink module
+ */
+struct sof_ipc4_src_data {
+	struct sof_ipc4_base_module_cfg base_config;
+	uint32_t sink_rate;
+} __packed __aligned(4);
+
+/**
+ * struct sof_ipc4_src - SRC config data
+ * @data: IPC base config data
  * @available_fmt: Available audio format
  * @msg: IPC4 message struct containing header and data info
  */
 struct sof_ipc4_src {
-	struct sof_ipc4_base_module_cfg base_config;
-	uint32_t sink_rate;
+	struct sof_ipc4_src_data data;
 	struct sof_ipc4_available_audio_format available_fmt;
 	struct sof_ipc4_msg msg;
 };
diff --git a/sound/soc/sof/sof-audio.c b/sound/soc/sof/sof-audio.c
index 563fe6f7789f73..77cc64ac71131b 100644
--- a/sound/soc/sof/sof-audio.c
+++ b/sound/soc/sof/sof-audio.c
@@ -46,6 +46,7 @@ static int sof_widget_free_unlocked(struct snd_sof_dev *sdev,
 				    struct snd_sof_widget *swidget)
 {
 	const struct sof_ipc_tplg_ops *tplg_ops = sof_ipc_get_ops(sdev, tplg);
+	struct snd_sof_pipeline *spipe = swidget->spipe;
 	struct snd_sof_widget *pipe_widget;
 	int err = 0;
 	int ret;
@@ -87,15 +88,22 @@ static int sof_widget_free_unlocked(struct snd_sof_dev *sdev,
 	}
 
 	/*
-	 * disable widget core. continue to route setup status and complete flag
-	 * even if this fails and return the appropriate error
+	 * decrement ref count for cores associated with all modules in the pipeline and clear
+	 * the complete flag
 	 */
-	ret = snd_sof_dsp_core_put(sdev, swidget->core);
-	if (ret < 0) {
-		dev_err(sdev->dev, "error: failed to disable target core: %d for widget %s\n",
-			swidget->core, swidget->widget->name);
-		if (!err)
-			err = ret;
+	if (swidget->id == snd_soc_dapm_scheduler) {
+		int i;
+
+		for_each_set_bit(i, &spipe->core_mask, sdev->num_cores) {
+			ret = snd_sof_dsp_core_put(sdev, i);
+			if (ret < 0) {
+				dev_err(sdev->dev, "failed to disable target core: %d for pipeline %s\n",
+					i, swidget->widget->name);
+				if (!err)
+					err = ret;
+			}
+		}
+		swidget->spipe->complete = 0;
 	}
 
 	/*
@@ -108,10 +116,6 @@ static int sof_widget_free_unlocked(struct snd_sof_dev *sdev,
 			err = ret;
 	}
 
-	/* clear pipeline complete */
-	if (swidget->id == snd_soc_dapm_scheduler)
-		swidget->spipe->complete = 0;
-
 	if (!err)
 		dev_dbg(sdev->dev, "widget %s freed\n", swidget->widget->name);
 
@@ -134,8 +138,10 @@ static int sof_widget_setup_unlocked(struct snd_sof_dev *sdev,
 				     struct snd_sof_widget *swidget)
 {
 	const struct sof_ipc_tplg_ops *tplg_ops = sof_ipc_get_ops(sdev, tplg);
+	struct snd_sof_pipeline *spipe = swidget->spipe;
 	bool use_count_decremented = false;
 	int ret;
+	int i;
 
 	/* skip if there is no private data */
 	if (!swidget->private)
@@ -166,19 +172,23 @@ static int sof_widget_setup_unlocked(struct snd_sof_dev *sdev,
 			goto use_count_dec;
 	}
 
-	/* enable widget core */
-	ret = snd_sof_dsp_core_get(sdev, swidget->core);
-	if (ret < 0) {
-		dev_err(sdev->dev, "error: failed to enable target core for widget %s\n",
-			swidget->widget->name);
-		goto pipe_widget_free;
+	/* update ref count for cores associated with all modules in the pipeline */
+	if (swidget->id == snd_soc_dapm_scheduler) {
+		for_each_set_bit(i, &spipe->core_mask, sdev->num_cores) {
+			ret = snd_sof_dsp_core_get(sdev, i);
+			if (ret < 0) {
+				dev_err(sdev->dev, "failed to enable target core %d for pipeline %s\n",
+					i, swidget->widget->name);
+				goto pipe_widget_free;
+			}
+		}
 	}
 
 	/* setup widget in the DSP */
 	if (tplg_ops && tplg_ops->widget_setup) {
 		ret = tplg_ops->widget_setup(sdev, swidget);
 		if (ret < 0)
-			goto core_put;
+			goto pipe_widget_free;
 	}
 
 	/* send config for DAI components */
@@ -208,15 +218,22 @@ static int sof_widget_setup_unlocked(struct snd_sof_dev *sdev,
 	return 0;
 
 widget_free:
-	/* widget use_count and core ref_count will both be decremented by sof_widget_free() */
+	/* widget use_count will be decremented by sof_widget_free() */
 	sof_widget_free_unlocked(sdev, swidget);
 	use_count_decremented = true;
-core_put:
-	if (!use_count_decremented)
-		snd_sof_dsp_core_put(sdev, swidget->core);
 pipe_widget_free:
-	if (swidget->id != snd_soc_dapm_scheduler)
+	if (swidget->id != snd_soc_dapm_scheduler) {
 		sof_widget_free_unlocked(sdev, swidget->spipe->pipe_widget);
+	} else {
+		int j;
+
+		/* decrement ref count for all cores that were updated previously */
+		for_each_set_bit(j, &spipe->core_mask, sdev->num_cores) {
+			if (j >= i)
+				break;
+			snd_sof_dsp_core_put(sdev, j);
+		}
+	}
 use_count_dec:
 	if (!use_count_decremented)
 		swidget->use_count--;
diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h
index 5d5eeb1a1a6f0d..a6d6bcd00ceece 100644
--- a/sound/soc/sof/sof-audio.h
+++ b/sound/soc/sof/sof-audio.h
@@ -480,6 +480,7 @@ struct snd_sof_widget {
  * @paused_count: Count of number of PCM's that have started and have currently paused this
 		  pipeline
  * @complete: flag used to indicate that pipeline set up is complete.
+ * @core_mask: Mask containing target cores for all modules in the pipeline
  * @list: List item in sdev pipeline_list
  */
 struct snd_sof_pipeline {
@@ -487,6 +488,7 @@ struct snd_sof_pipeline {
 	int started_count;
 	int paused_count;
 	int complete;
+	unsigned long core_mask;
 	struct list_head list;
 };
 
diff --git a/sound/soc/sof/sof-client.c b/sound/soc/sof/sof-client.c
index 9dce7f53b48213..54dca91255a0a5 100644
--- a/sound/soc/sof/sof-client.c
+++ b/sound/soc/sof/sof-client.c
@@ -176,7 +176,7 @@ int sof_register_clients(struct snd_sof_dev *sdev)
 		goto err_kernel_injector;
 	}
 
-	/* Platform depndent client device registration */
+	/* Platform dependent client device registration */
 
 	if (sof_ops(sdev) && sof_ops(sdev)->register_ipc_clients)
 		ret = sof_ops(sdev)->register_ipc_clients(sdev);
diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c
index a3a3af252259d9..37ec671a2d766f 100644
--- a/sound/soc/sof/topology.c
+++ b/sound/soc/sof/topology.c
@@ -1736,8 +1736,10 @@ static int sof_dai_load(struct snd_soc_component *scomp, int index,
 	/* perform pcm set op */
 	if (ipc_pcm_ops && ipc_pcm_ops->pcm_setup) {
 		ret = ipc_pcm_ops->pcm_setup(sdev, spcm);
-		if (ret < 0)
+		if (ret < 0) {
+			kfree(spcm);
 			return ret;
+		}
 	}
 
 	dai_drv->dobj.private = spcm;
diff --git a/sound/soc/ti/omap-mcbsp.c b/sound/soc/ti/omap-mcbsp.c
index 7643a54592f563..2110ffe5281cec 100644
--- a/sound/soc/ti/omap-mcbsp.c
+++ b/sound/soc/ti/omap-mcbsp.c
@@ -73,14 +73,16 @@ static int omap2_mcbsp_set_clks_src(struct omap_mcbsp *mcbsp, u8 fck_src_id)
 		return 0;
 	}
 
-	pm_runtime_put_sync(mcbsp->dev);
+	if (mcbsp->active)
+		pm_runtime_put_sync(mcbsp->dev);
 
 	r = clk_set_parent(mcbsp->fclk, fck_src);
 	if (r)
 		dev_err(mcbsp->dev, "CLKS: could not clk_set_parent() to %s\n",
 			src);
 
-	pm_runtime_get_sync(mcbsp->dev);
+	if (mcbsp->active)
+		pm_runtime_get_sync(mcbsp->dev);
 
 	clk_put(fck_src);
 
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index 898bc3baca7b99..c8d48566e17598 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -2978,6 +2978,7 @@ static int snd_bbfpro_controls_create(struct usb_mixer_interface *mixer)
 #define SND_DJM_850_IDX		0x2
 #define SND_DJM_900NXS2_IDX	0x3
 #define SND_DJM_750MK2_IDX	0x4
+#define SND_DJM_450_IDX		0x5
 
 
 #define SND_DJM_CTL(_name, suffix, _default_value, _windex) { \
@@ -3108,6 +3109,31 @@ static const struct snd_djm_ctl snd_djm_ctls_250mk2[] = {
 };
 
 
+// DJM-450
+static const u16 snd_djm_opts_450_cap1[] = {
+	0x0103, 0x0100, 0x0106, 0x0107, 0x0108, 0x0109, 0x010d, 0x010a };
+
+static const u16 snd_djm_opts_450_cap2[] = {
+	0x0203, 0x0200, 0x0206, 0x0207, 0x0208, 0x0209, 0x020d, 0x020a };
+
+static const u16 snd_djm_opts_450_cap3[] = {
+	0x030a, 0x0311, 0x0312, 0x0307, 0x0308, 0x0309, 0x030d };
+
+static const u16 snd_djm_opts_450_pb1[] = { 0x0100, 0x0101, 0x0104 };
+static const u16 snd_djm_opts_450_pb2[] = { 0x0200, 0x0201, 0x0204 };
+static const u16 snd_djm_opts_450_pb3[] = { 0x0300, 0x0301, 0x0304 };
+
+static const struct snd_djm_ctl snd_djm_ctls_450[] = {
+	SND_DJM_CTL("Capture Level", cap_level, 0, SND_DJM_WINDEX_CAPLVL),
+	SND_DJM_CTL("Ch1 Input",   450_cap1, 2, SND_DJM_WINDEX_CAP),
+	SND_DJM_CTL("Ch2 Input",   450_cap2, 2, SND_DJM_WINDEX_CAP),
+	SND_DJM_CTL("Ch3 Input",   450_cap3, 0, SND_DJM_WINDEX_CAP),
+	SND_DJM_CTL("Ch1 Output",   450_pb1, 0, SND_DJM_WINDEX_PB),
+	SND_DJM_CTL("Ch2 Output",   450_pb2, 1, SND_DJM_WINDEX_PB),
+	SND_DJM_CTL("Ch3 Output",   450_pb3, 2, SND_DJM_WINDEX_PB)
+};
+
+
 // DJM-750
 static const u16 snd_djm_opts_750_cap1[] = {
 	0x0101, 0x0103, 0x0106, 0x0107, 0x0108, 0x0109, 0x010a, 0x010f };
@@ -3203,6 +3229,7 @@ static const struct snd_djm_device snd_djm_devices[] = {
 	[SND_DJM_850_IDX] = SND_DJM_DEVICE(850),
 	[SND_DJM_900NXS2_IDX] = SND_DJM_DEVICE(900nxs2),
 	[SND_DJM_750MK2_IDX] = SND_DJM_DEVICE(750mk2),
+	[SND_DJM_450_IDX] = SND_DJM_DEVICE(450),
 };
 
 
@@ -3454,6 +3481,9 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer)
 	case USB_ID(0x2b73, 0x0017): /* Pioneer DJ DJM-250MK2 */
 		err = snd_djm_controls_create(mixer, SND_DJM_250MK2_IDX);
 		break;
+	case USB_ID(0x2b73, 0x0013): /* Pioneer DJ DJM-450 */
+		err = snd_djm_controls_create(mixer, SND_DJM_450_IDX);
+		break;
 	case USB_ID(0x08e4, 0x017f): /* Pioneer DJ DJM-750 */
 		err = snd_djm_controls_create(mixer, SND_DJM_750_IDX);
 		break;
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index ab2b938502ebed..07cc6a201579aa 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1387,7 +1387,7 @@ free_buf:
 
 static int snd_usb_motu_m_series_boot_quirk(struct usb_device *dev)
 {
-	msleep(2000);
+	msleep(4000);
 
 	return 0;
 }
@@ -1630,7 +1630,7 @@ int snd_usb_apply_boot_quirk_once(struct usb_device *dev,
 				  unsigned int id)
 {
 	switch (id) {
-	case USB_ID(0x07fd, 0x0008): /* MOTU M Series */
+	case USB_ID(0x07fd, 0x0008): /* MOTU M Series, 1st hardware version */
 		return snd_usb_motu_m_series_boot_quirk(dev);
 	}
 
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 5f6f84837a4903..7c7493cb571f97 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -79,13 +79,15 @@
 #define ARM_CPU_PART_CORTEX_A78AE	0xD42
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
+#define ARM_CPU_PART_CORTEX_A520	0xD80
 #define ARM_CPU_PART_CORTEX_A710	0xD47
 #define ARM_CPU_PART_CORTEX_A715	0xD4D
 #define ARM_CPU_PART_CORTEX_X2		0xD48
 #define ARM_CPU_PART_NEOVERSE_N2	0xD49
 #define ARM_CPU_PART_CORTEX_A78C	0xD4B
 
-#define APM_CPU_PART_POTENZA		0x000
+#define APM_CPU_PART_XGENE		0x000
+#define APM_CPU_VAR_POTENZA		0x00
 
 #define CAVIUM_CPU_PART_THUNDERX	0x0A1
 #define CAVIUM_CPU_PART_THUNDERX_81XX	0x0A2
@@ -148,6 +150,7 @@
 #define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
+#define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
 #define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
 #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index f7ddd73a8c0fa2..89d2fc872d9f5e 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -505,6 +505,38 @@ struct kvm_smccc_filter {
 #define KVM_HYPERCALL_EXIT_SMC		(1U << 0)
 #define KVM_HYPERCALL_EXIT_16BIT	(1U << 1)
 
+/*
+ * Get feature ID registers userspace writable mask.
+ *
+ * From DDI0487J.a, D19.2.66 ("ID_AA64MMFR2_EL1, AArch64 Memory Model
+ * Feature Register 2"):
+ *
+ * "The Feature ID space is defined as the System register space in
+ * AArch64 with op0==3, op1=={0, 1, 3}, CRn==0, CRm=={0-7},
+ * op2=={0-7}."
+ *
+ * This covers all currently known R/O registers that indicate
+ * anything useful feature wise, including the ID registers.
+ *
+ * If we ever need to introduce a new range, it will be described as
+ * such in the range field.
+ */
+#define KVM_ARM_FEATURE_ID_RANGE_IDX(op0, op1, crn, crm, op2)		\
+	({								\
+		__u64 __op1 = (op1) & 3;				\
+		__op1 -= (__op1 == 3);					\
+		(__op1 << 6 | ((crm) & 7) << 3 | (op2));		\
+	})
+
+#define KVM_ARM_FEATURE_ID_RANGE	0
+#define KVM_ARM_FEATURE_ID_RANGE_SIZE	(3 * 8 * 8)
+
+struct reg_mask_range {
+	__u64 addr;		/* Pointer to mask array */
+	__u32 range;		/* Requested range */
+	__u32 reserved[13];
+};
+
 #endif
 
 #endif /* __ARM_KVM_H__ */
diff --git a/tools/arch/arm64/include/uapi/asm/perf_regs.h b/tools/arch/arm64/include/uapi/asm/perf_regs.h
index fd157f46727e9a..86e556429e0eb6 100644
--- a/tools/arch/arm64/include/uapi/asm/perf_regs.h
+++ b/tools/arch/arm64/include/uapi/asm/perf_regs.h
@@ -36,11 +36,13 @@ enum perf_event_arm_regs {
 	PERF_REG_ARM64_LR,
 	PERF_REG_ARM64_SP,
 	PERF_REG_ARM64_PC,
+	PERF_REG_ARM64_MAX,
 
 	/* Extended/pseudo registers */
-	PERF_REG_ARM64_VG = 46, // SVE Vector Granule
-
-	PERF_REG_ARM64_MAX = PERF_REG_ARM64_PC + 1,
-	PERF_REG_ARM64_EXTENDED_MAX = PERF_REG_ARM64_VG + 1
+	PERF_REG_ARM64_VG = 46,				/* SVE Vector Granule */
+	PERF_REG_ARM64_EXTENDED_MAX
 };
+
+#define PERF_REG_EXTENDED_MASK	(1ULL << PERF_REG_ARM64_VG)
+
 #endif /* _ASM_ARM64_PERF_REGS_H */
diff --git a/tools/arch/arm64/tools/Makefile b/tools/arch/arm64/tools/Makefile
index 7f64b8bb510702..7b42feedf64719 100644
--- a/tools/arch/arm64/tools/Makefile
+++ b/tools/arch/arm64/tools/Makefile
@@ -22,7 +22,7 @@ endif
 arm64_tools_dir = $(top_srcdir)/arch/arm64/tools
 arm64_sysreg_tbl = $(arm64_tools_dir)/sysreg
 arm64_gen_sysreg = $(arm64_tools_dir)/gen-sysreg.awk
-arm64_generated_dir = $(top_srcdir)/tools/arch/arm64/include/generated
+arm64_generated_dir = $(OUTPUT)arch/arm64/include/generated
 arm64_sysreg_defs = $(arm64_generated_dir)/asm/sysreg-defs.h
 
 all: $(arm64_sysreg_defs)
diff --git a/tools/arch/parisc/include/uapi/asm/errno.h b/tools/arch/parisc/include/uapi/asm/errno.h
index 87245c584784ec..8d94739d75c67c 100644
--- a/tools/arch/parisc/include/uapi/asm/errno.h
+++ b/tools/arch/parisc/include/uapi/asm/errno.h
@@ -75,7 +75,6 @@
 
 /* We now return you to your regularly scheduled HPUX. */
 
-#define ENOSYM		215	/* symbol does not exist in executable */
 #define	ENOTSOCK	216	/* Socket operation on non-socket */
 #define	EDESTADDRREQ	217	/* Destination address required */
 #define	EMSGSIZE	218	/* Message too long */
@@ -101,7 +100,6 @@
 #define	ETIMEDOUT	238	/* Connection timed out */
 #define	ECONNREFUSED	239	/* Connection refused */
 #define	EREFUSED	ECONNREFUSED	/* for HP's NFS apparently */
-#define	EREMOTERELEASE	240	/* Remote peer released connection */
 #define	EHOSTDOWN	241	/* Host is down */
 #define	EHOSTUNREACH	242	/* No route to host */
 
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index a73cf01a160667..abe926d43cbe0a 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -159,6 +159,22 @@ struct kvm_s390_vm_cpu_subfunc {
 	__u8 reserved[1728];
 };
 
+#define KVM_S390_VM_CPU_PROCESSOR_UV_FEAT_GUEST	6
+#define KVM_S390_VM_CPU_MACHINE_UV_FEAT_GUEST	7
+
+#define KVM_S390_VM_CPU_UV_FEAT_NR_BITS	64
+struct kvm_s390_vm_cpu_uv_feat {
+	union {
+		struct {
+			__u64 : 4;
+			__u64 ap : 1;		/* bit 4 */
+			__u64 ap_intr : 1;	/* bit 5 */
+			__u64 : 58;
+		};
+		__u64 feat;
+	};
+};
+
 /* kvm attributes for crypto */
 #define KVM_S390_VM_CRYPTO_ENABLE_AES_KW	0
 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 798e60b5454b7e..4af140cf5719e6 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -198,7 +198,6 @@
 #define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
-#define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_XCOMPACTED		( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */
@@ -308,6 +307,11 @@
 #define X86_FEATURE_MSR_TSX_CTRL	(11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */
 #define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
 #define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
+#define X86_FEATURE_USER_SHSTK		(11*32+23) /* Shadow stack support for user mode applications */
+
+#define X86_FEATURE_SRSO		(11*32+24) /* "" AMD BTB untrain RETs */
+#define X86_FEATURE_SRSO_ALIAS		(11*32+25) /* "" AMD BTB untrain RETs through aliasing */
+#define X86_FEATURE_IBPB_ON_VMEXIT	(11*32+26) /* "" Issue an IBPB only on VMEXIT */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
@@ -380,6 +384,7 @@
 #define X86_FEATURE_OSPKE		(16*32+ 4) /* OS Protection Keys Enable */
 #define X86_FEATURE_WAITPKG		(16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */
 #define X86_FEATURE_AVX512_VBMI2	(16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
+#define X86_FEATURE_SHSTK		(16*32+ 7) /* "" Shadow stack */
 #define X86_FEATURE_GFNI		(16*32+ 8) /* Galois Field New Instructions */
 #define X86_FEATURE_VAES		(16*32+ 9) /* Vector AES */
 #define X86_FEATURE_VPCLMULQDQ		(16*32+10) /* Carry-Less Multiplication Double Quadword */
@@ -438,11 +443,16 @@
 
 /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* "" No Nested Data Breakpoints */
+#define X86_FEATURE_WRMSR_XX_BASE_NS	(20*32+ 1) /* "" WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
 #define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */
 #define X86_FEATURE_NULL_SEL_CLR_BASE	(20*32+ 6) /* "" Null Selector Clears Base */
 #define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* "" Automatic IBRS */
 #define X86_FEATURE_NO_SMM_CTL_MSR	(20*32+ 9) /* "" SMM_CTL MSR is not present */
 
+#define X86_FEATURE_SBPB		(20*32+27) /* "" Selective Branch Prediction Barrier */
+#define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */
+#define X86_FEATURE_SRSO_NO		(20*32+29) /* "" CPU is not affected by SRSO */
+
 /*
  * BUG word(s)
  */
@@ -484,5 +494,9 @@
 #define X86_BUG_RETBLEED		X86_BUG(27) /* CPU is affected by RETBleed */
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
+#define X86_BUG_GDS			X86_BUG(30) /* CPU is affected by Gather Data Sampling */
 
+/* BUG word 2 */
+#define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* AMD SRSO bug */
+#define X86_BUG_DIV0			X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index fafe9be7a6f4ff..702d93fdd10e8d 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -105,6 +105,18 @@
 # define DISABLE_TDX_GUEST	(1 << (X86_FEATURE_TDX_GUEST & 31))
 #endif
 
+#ifdef CONFIG_X86_USER_SHADOW_STACK
+#define DISABLE_USER_SHSTK	0
+#else
+#define DISABLE_USER_SHSTK	(1 << (X86_FEATURE_USER_SHSTK & 31))
+#endif
+
+#ifdef CONFIG_X86_KERNEL_IBT
+#define DISABLE_IBT	0
+#else
+#define DISABLE_IBT	(1 << (X86_FEATURE_IBT & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -120,7 +132,7 @@
 #define DISABLED_MASK9	(DISABLE_SGX)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
-			 DISABLE_CALL_DEPTH_TRACKING)
+			 DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK)
 #define DISABLED_MASK12	(DISABLE_LAM)
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
@@ -128,7 +140,7 @@
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
 			 DISABLE_ENQCMD)
 #define DISABLED_MASK17	0
-#define DISABLED_MASK18	0
+#define DISABLED_MASK18	(DISABLE_IBT)
 #define DISABLED_MASK19	0
 #define DISABLED_MASK20	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 1d111350197f31..1d51e1850ed03d 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -222,6 +222,7 @@
 #define MSR_INTEGRITY_CAPS_ARRAY_BIST          BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT)
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT	4
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST	BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT)
+#define MSR_INTEGRITY_CAPS_SAF_GEN_MASK	GENMASK_ULL(10, 9)
 
 #define MSR_LBR_NHM_FROM		0x00000680
 #define MSR_LBR_NHM_TO			0x000006c0
@@ -553,6 +554,7 @@
 #define MSR_AMD64_CPUID_FN_1		0xc0011004
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
+#define MSR_AMD64_TW_CFG		0xc0011023
 
 #define MSR_AMD64_DE_CFG		0xc0011029
 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT	 1
@@ -637,12 +639,21 @@
 /* AMD Last Branch Record MSRs */
 #define MSR_AMD64_LBR_SELECT			0xc000010e
 
+/* Zen4 */
+#define MSR_ZEN4_BP_CFG                 0xc001102e
+#define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5
+
+/* Fam 19h MSRs */
+#define MSR_F19H_UMC_PERF_CTL           0xc0010800
+#define MSR_F19H_UMC_PERF_CTR           0xc0010801
+
+/* Zen 2 */
+#define MSR_ZEN2_SPECTRAL_CHICKEN       0xc00110e3
+#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT   BIT_ULL(1)
+
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
 
-#define MSR_ZEN2_SPECTRAL_CHICKEN	0xc00110e3
-#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT	BIT_ULL(1)
-
 /* Fam 16h MSRs */
 #define MSR_F16H_L2I_PERF_CTL		0xc0010230
 #define MSR_F16H_L2I_PERF_CTR		0xc0010231
@@ -1112,12 +1123,16 @@
 #define MSR_IA32_VMX_MISC_INTEL_PT                 (1ULL << 14)
 #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
 #define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE   0x1F
-/* AMD-V MSRs */
 
+/* AMD-V MSRs */
 #define MSR_VM_CR                       0xc0010114
 #define MSR_VM_IGNNE                    0xc0010115
 #define MSR_VM_HSAVE_PA                 0xc0010117
 
+#define SVM_VM_CR_VALID_MASK		0x001fULL
+#define SVM_VM_CR_SVM_LOCK_MASK		0x0008ULL
+#define SVM_VM_CR_SVM_DIS_MASK		0x0010ULL
+
 /* Hardware Feedback Interface */
 #define MSR_IA32_HW_FEEDBACK_PTR        0x17d0
 #define MSR_IA32_HW_FEEDBACK_CONFIG     0x17d1
diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h
index e8d7ebbca1a4dc..384e2cc6ac190d 100644
--- a/tools/arch/x86/include/uapi/asm/prctl.h
+++ b/tools/arch/x86/include/uapi/asm/prctl.h
@@ -23,9 +23,21 @@
 #define ARCH_MAP_VDSO_32		0x2002
 #define ARCH_MAP_VDSO_64		0x2003
 
+/* Don't use 0x3001-0x3004 because of old glibcs */
+
 #define ARCH_GET_UNTAG_MASK		0x4001
 #define ARCH_ENABLE_TAGGED_ADDR		0x4002
 #define ARCH_GET_MAX_TAG_BITS		0x4003
 #define ARCH_FORCE_TAGGED_SVA		0x4004
 
+#define ARCH_SHSTK_ENABLE		0x5001
+#define ARCH_SHSTK_DISABLE		0x5002
+#define ARCH_SHSTK_LOCK			0x5003
+#define ARCH_SHSTK_UNLOCK		0x5004
+#define ARCH_SHSTK_STATUS		0x5005
+
+/* ARCH_SHSTK_ features bits */
+#define ARCH_SHSTK_SHSTK		(1ULL <<  0)
+#define ARCH_SHSTK_WRSS			(1ULL <<  1)
+
 #endif /* _ASM_X86_PRCTL_H */
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 264eeb9c46a9f5..318e2dad27e048 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -1421,7 +1421,7 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
 	if (error)
 		goto setval_error;
 
-	if (new_val->addr_family == ADDR_FAMILY_IPV6) {
+	if (new_val->addr_family & ADDR_FAMILY_IPV6) {
 		error = fprintf(nmfile, "\n[ipv6]\n");
 		if (error < 0)
 			goto setval_error;
@@ -1455,14 +1455,18 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
 	if (error < 0)
 		goto setval_error;
 
-	error = fprintf(nmfile, "gateway=%s\n", (char *)new_val->gate_way);
-	if (error < 0)
-		goto setval_error;
-
-	error = fprintf(nmfile, "dns=%s\n", (char *)new_val->dns_addr);
-	if (error < 0)
-		goto setval_error;
+	/* we do not want ipv4 addresses in ipv6 section and vice versa */
+	if (is_ipv6 != is_ipv4((char *)new_val->gate_way)) {
+		error = fprintf(nmfile, "gateway=%s\n", (char *)new_val->gate_way);
+		if (error < 0)
+			goto setval_error;
+	}
 
+	if (is_ipv6 != is_ipv4((char *)new_val->dns_addr)) {
+		error = fprintf(nmfile, "dns=%s\n", (char *)new_val->dns_addr);
+		if (error < 0)
+			goto setval_error;
+	}
 	fclose(nmfile);
 	fclose(ifcfg_file);
 
diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh
index ae5a7a8249a208..440a91b35823bf 100755
--- a/tools/hv/hv_set_ifconfig.sh
+++ b/tools/hv/hv_set_ifconfig.sh
@@ -53,7 +53,7 @@
 #                       or "manual" if no boot-time protocol should be used)
 #
 # address1=ipaddr1/plen
-# address=ipaddr2/plen
+# address2=ipaddr2/plen
 #
 # gateway=gateway1;gateway2
 #
@@ -61,7 +61,7 @@
 #
 # [ipv6]
 # address1=ipaddr1/plen
-# address2=ipaddr1/plen
+# address2=ipaddr2/plen
 #
 # gateway=gateway1;gateway2
 #
diff --git a/tools/include/asm-generic/unaligned.h b/tools/include/asm-generic/unaligned.h
index 156743d399aed2..2fd551915c2025 100644
--- a/tools/include/asm-generic/unaligned.h
+++ b/tools/include/asm-generic/unaligned.h
@@ -8,6 +8,7 @@
  */
 #pragma GCC diagnostic push
 #pragma GCC diagnostic ignored "-Wpacked"
+#pragma GCC diagnostic ignored "-Wattributes"
 
 #define __get_unaligned_t(type, ptr) ({						\
 	const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr);	\
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 76d94644539127..756b013fb8324b 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -816,15 +816,21 @@ __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
 __SYSCALL(__NR_futex_waitv, sys_futex_waitv)
 #define __NR_set_mempolicy_home_node 450
 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
-
 #define __NR_cachestat 451
 __SYSCALL(__NR_cachestat, sys_cachestat)
-
 #define __NR_fchmodat2 452
 __SYSCALL(__NR_fchmodat2, sys_fchmodat2)
+#define __NR_map_shadow_stack 453
+__SYSCALL(__NR_map_shadow_stack, sys_map_shadow_stack)
+#define __NR_futex_wake 454
+__SYSCALL(__NR_futex_wake, sys_futex_wake)
+#define __NR_futex_wait 455
+__SYSCALL(__NR_futex_wait, sys_futex_wait)
+#define __NR_futex_requeue 456
+__SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
 #undef __NR_syscalls
-#define __NR_syscalls 453
+#define __NR_syscalls 457
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 794c1d857677d9..de723566c5ae82 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -1134,6 +1134,26 @@ extern "C" {
 #define DRM_IOCTL_MODE_PAGE_FLIP	DRM_IOWR(0xB0, struct drm_mode_crtc_page_flip)
 #define DRM_IOCTL_MODE_DIRTYFB		DRM_IOWR(0xB1, struct drm_mode_fb_dirty_cmd)
 
+/**
+ * DRM_IOCTL_MODE_CREATE_DUMB - Create a new dumb buffer object.
+ *
+ * KMS dumb buffers provide a very primitive way to allocate a buffer object
+ * suitable for scanout and map it for software rendering. KMS dumb buffers are
+ * not suitable for hardware-accelerated rendering nor video decoding. KMS dumb
+ * buffers are not suitable to be displayed on any other device than the KMS
+ * device where they were allocated from. Also see
+ * :ref:`kms_dumb_buffer_objects`.
+ *
+ * The IOCTL argument is a struct drm_mode_create_dumb.
+ *
+ * User-space is expected to create a KMS dumb buffer via this IOCTL, then add
+ * it as a KMS framebuffer via &DRM_IOCTL_MODE_ADDFB and map it via
+ * &DRM_IOCTL_MODE_MAP_DUMB.
+ *
+ * &DRM_CAP_DUMB_BUFFER indicates whether this IOCTL is supported.
+ * &DRM_CAP_DUMB_PREFERRED_DEPTH and &DRM_CAP_DUMB_PREFER_SHADOW indicate
+ * driver preferences for dumb buffers.
+ */
 #define DRM_IOCTL_MODE_CREATE_DUMB DRM_IOWR(0xB2, struct drm_mode_create_dumb)
 #define DRM_IOCTL_MODE_MAP_DUMB    DRM_IOWR(0xB3, struct drm_mode_map_dumb)
 #define DRM_IOCTL_MODE_DESTROY_DUMB    DRM_IOWR(0xB4, struct drm_mode_destroy_dumb)
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 7000e5910a1d74..218edb0a96f8c0 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -38,13 +38,13 @@ extern "C" {
  */
 
 /**
- * DOC: uevents generated by i915 on it's device node
+ * DOC: uevents generated by i915 on its device node
  *
  * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch
- *	event from the gpu l3 cache. Additional information supplied is ROW,
+ *	event from the GPU L3 cache. Additional information supplied is ROW,
  *	BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep
- *	track of these events and if a specific cache-line seems to have a
- *	persistent error remap it with the l3 remapping tool supplied in
+ *	track of these events, and if a specific cache-line seems to have a
+ *	persistent error, remap it with the L3 remapping tool supplied in
  *	intel-gpu-tools.  The value supplied with the event is always 1.
  *
  * I915_ERROR_UEVENT - Generated upon error detection, currently only via
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index fd1fb0d5389d3a..7a8f4c2901873f 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -71,7 +71,8 @@ struct fscrypt_policy_v2 {
 	__u8 contents_encryption_mode;
 	__u8 filenames_encryption_mode;
 	__u8 flags;
-	__u8 __reserved[4];
+	__u8 log2_data_unit_size;
+	__u8 __reserved[3];
 	__u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
 };
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f089ab29097845..211b86de35ac53 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -264,6 +264,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_RISCV_SBI        35
 #define KVM_EXIT_RISCV_CSR        36
 #define KVM_EXIT_NOTIFY           37
+#define KVM_EXIT_LOONGARCH_IOCSR  38
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -336,6 +337,13 @@ struct kvm_run {
 			__u32 len;
 			__u8  is_write;
 		} mmio;
+		/* KVM_EXIT_LOONGARCH_IOCSR */
+		struct {
+			__u64 phys_addr;
+			__u8  data[8];
+			__u32 len;
+			__u8  is_write;
+		} iocsr_io;
 		/* KVM_EXIT_HYPERCALL */
 		struct {
 			__u64 nr;
@@ -1192,6 +1200,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_COUNTER_OFFSET 227
 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
+#define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1362,6 +1371,7 @@ struct kvm_dirty_tlb {
 #define KVM_REG_ARM64		0x6000000000000000ULL
 #define KVM_REG_MIPS		0x7000000000000000ULL
 #define KVM_REG_RISCV		0x8000000000000000ULL
+#define KVM_REG_LOONGARCH	0x9000000000000000ULL
 
 #define KVM_REG_SIZE_SHIFT	52
 #define KVM_REG_SIZE_MASK	0x00f0000000000000ULL
@@ -1418,9 +1428,16 @@ struct kvm_device_attr {
 	__u64	addr;		/* userspace address of attr data */
 };
 
-#define  KVM_DEV_VFIO_GROUP			1
-#define   KVM_DEV_VFIO_GROUP_ADD			1
-#define   KVM_DEV_VFIO_GROUP_DEL			2
+#define  KVM_DEV_VFIO_FILE			1
+
+#define   KVM_DEV_VFIO_FILE_ADD			1
+#define   KVM_DEV_VFIO_FILE_DEL			2
+
+/* KVM_DEV_VFIO_GROUP aliases are for compile time uapi compatibility */
+#define  KVM_DEV_VFIO_GROUP	KVM_DEV_VFIO_FILE
+
+#define   KVM_DEV_VFIO_GROUP_ADD	KVM_DEV_VFIO_FILE_ADD
+#define   KVM_DEV_VFIO_GROUP_DEL	KVM_DEV_VFIO_FILE_DEL
 #define   KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE		3
 
 enum kvm_device_type {
@@ -1555,6 +1572,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_ARM_MTE_COPY_TAGS	  _IOR(KVMIO,  0xb4, struct kvm_arm_copy_mte_tags)
 /* Available with KVM_CAP_COUNTER_OFFSET */
 #define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO,  0xb5, struct kvm_arm_counter_offset)
+#define KVM_ARM_GET_REG_WRITABLE_MASKS _IOR(KVMIO,  0xb6, struct reg_mask_range)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
index 8eb0d7b758d283..bb242fdcfe6b29 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/include/uapi/linux/mount.h
@@ -100,8 +100,9 @@ enum fsconfig_command {
 	FSCONFIG_SET_PATH	= 3,	/* Set parameter, supplying an object by path */
 	FSCONFIG_SET_PATH_EMPTY	= 4,	/* Set parameter, supplying an object by (empty) path */
 	FSCONFIG_SET_FD		= 5,	/* Set parameter, supplying an object by fd */
-	FSCONFIG_CMD_CREATE	= 6,	/* Invoke superblock creation */
+	FSCONFIG_CMD_CREATE	= 6,	/* Create new or reuse existing superblock */
 	FSCONFIG_CMD_RECONFIGURE = 7,	/* Invoke superblock reconfiguration */
+	FSCONFIG_CMD_CREATE_EXCL = 8,	/* Create new superblock, fail if reusing existing superblock */
 };
 
 /*
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index f5c48b61ab6224..649560c685f13b 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -219,4 +219,12 @@
  */
 #define VHOST_VDPA_RESUME		_IO(VHOST_VIRTIO, 0x7E)
 
+/* Get the group for the descriptor table including driver & device areas
+ * of a virtqueue: read index, write group in num.
+ * The virtqueue index is stored in the index field of vhost_vring_state.
+ * The group ID of the descriptor table for this specific virtqueue
+ * is returned via num field of vhost_vring_state.
+ */
+#define VHOST_VDPA_GET_VRING_DESC_GROUP	_IOWR(VHOST_VIRTIO, 0x7F,	\
+					      struct vhost_vring_state)
 #endif
diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps
index 64d139400db103..3110f84dd02944 100644
--- a/tools/net/ynl/Makefile.deps
+++ b/tools/net/ynl/Makefile.deps
@@ -18,4 +18,4 @@ CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h)
 CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h)
 CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h)
 CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h)
-CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_H,nfsd.h)
+CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_NETLINK_H,nfsd_netlink.h)
diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c
index 75b744b4798630..8e757e249dab84 100644
--- a/tools/net/ynl/generated/devlink-user.c
+++ b/tools/net/ynl/generated/devlink-user.c
@@ -15,7 +15,7 @@
 /* Enums */
 static const char * const devlink_op_strmap[] = {
 	[3] = "get",
-	[7] = "port-get",
+	// skip "port-get", duplicate reply value
 	[DEVLINK_CMD_PORT_NEW] = "port-new",
 	[13] = "sb-get",
 	[17] = "sb-pool-get",
@@ -121,6 +121,8 @@ const char *devlink_port_fn_opstate_str(enum devlink_port_fn_opstate value)
 static const char * const devlink_port_fn_attr_cap_strmap[] = {
 	[0] = "roce-bit",
 	[1] = "migratable-bit",
+	[2] = "ipsec-crypto-bit",
+	[3] = "ipsec-packet-bit",
 };
 
 const char *devlink_port_fn_attr_cap_str(enum devlink_port_fn_attr_cap value)
@@ -2397,6 +2399,7 @@ void devlink_port_set_req_free(struct devlink_port_set_req *req)
 
 int devlink_port_set(struct ynl_sock *ys, struct devlink_port_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -2414,7 +2417,7 @@ int devlink_port_set(struct ynl_sock *ys, struct devlink_port_set_req *req)
 	if (req->_present.port_function)
 		devlink_dl_port_function_put(nlh, DEVLINK_ATTR_PORT_FUNCTION, &req->port_function);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -2535,6 +2538,7 @@ void devlink_port_del_req_free(struct devlink_port_del_req *req)
 
 int devlink_port_del(struct ynl_sock *ys, struct devlink_port_del_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -2548,7 +2552,7 @@ int devlink_port_del(struct ynl_sock *ys, struct devlink_port_del_req *req)
 	if (req->_present.port_index)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -2566,6 +2570,7 @@ void devlink_port_split_req_free(struct devlink_port_split_req *req)
 
 int devlink_port_split(struct ynl_sock *ys, struct devlink_port_split_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -2581,7 +2586,7 @@ int devlink_port_split(struct ynl_sock *ys, struct devlink_port_split_req *req)
 	if (req->_present.port_split_count)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_SPLIT_COUNT, req->port_split_count);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -2600,6 +2605,7 @@ void devlink_port_unsplit_req_free(struct devlink_port_unsplit_req *req)
 int devlink_port_unsplit(struct ynl_sock *ys,
 			 struct devlink_port_unsplit_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -2613,7 +2619,7 @@ int devlink_port_unsplit(struct ynl_sock *ys,
 	if (req->_present.port_index)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -2924,6 +2930,7 @@ void devlink_sb_pool_set_req_free(struct devlink_sb_pool_set_req *req)
 int devlink_sb_pool_set(struct ynl_sock *ys,
 			struct devlink_sb_pool_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -2943,7 +2950,7 @@ int devlink_sb_pool_set(struct ynl_sock *ys,
 	if (req->_present.sb_pool_size)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_POOL_SIZE, req->sb_pool_size);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -3124,6 +3131,7 @@ devlink_sb_port_pool_set_req_free(struct devlink_sb_port_pool_set_req *req)
 int devlink_sb_port_pool_set(struct ynl_sock *ys,
 			     struct devlink_sb_port_pool_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -3143,7 +3151,7 @@ int devlink_sb_port_pool_set(struct ynl_sock *ys,
 	if (req->_present.sb_threshold)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_THRESHOLD, req->sb_threshold);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -3332,6 +3340,7 @@ devlink_sb_tc_pool_bind_set_req_free(struct devlink_sb_tc_pool_bind_set_req *req
 int devlink_sb_tc_pool_bind_set(struct ynl_sock *ys,
 				struct devlink_sb_tc_pool_bind_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -3355,7 +3364,7 @@ int devlink_sb_tc_pool_bind_set(struct ynl_sock *ys,
 	if (req->_present.sb_threshold)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_THRESHOLD, req->sb_threshold);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -3374,6 +3383,7 @@ void devlink_sb_occ_snapshot_req_free(struct devlink_sb_occ_snapshot_req *req)
 int devlink_sb_occ_snapshot(struct ynl_sock *ys,
 			    struct devlink_sb_occ_snapshot_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -3387,7 +3397,7 @@ int devlink_sb_occ_snapshot(struct ynl_sock *ys,
 	if (req->_present.sb_index)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -3407,6 +3417,7 @@ devlink_sb_occ_max_clear_req_free(struct devlink_sb_occ_max_clear_req *req)
 int devlink_sb_occ_max_clear(struct ynl_sock *ys,
 			     struct devlink_sb_occ_max_clear_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -3420,7 +3431,7 @@ int devlink_sb_occ_max_clear(struct ynl_sock *ys,
 	if (req->_present.sb_index)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -3542,6 +3553,7 @@ void devlink_eswitch_set_req_free(struct devlink_eswitch_set_req *req)
 int devlink_eswitch_set(struct ynl_sock *ys,
 			struct devlink_eswitch_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -3559,7 +3571,7 @@ int devlink_eswitch_set(struct ynl_sock *ys,
 	if (req->_present.eswitch_encap_mode)
 		mnl_attr_put_u8(nlh, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, req->eswitch_encap_mode);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -3893,6 +3905,7 @@ devlink_dpipe_table_counters_set_req_free(struct devlink_dpipe_table_counters_se
 int devlink_dpipe_table_counters_set(struct ynl_sock *ys,
 				     struct devlink_dpipe_table_counters_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -3908,7 +3921,7 @@ int devlink_dpipe_table_counters_set(struct ynl_sock *ys,
 	if (req->_present.dpipe_table_counters_enabled)
 		mnl_attr_put_u8(nlh, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED, req->dpipe_table_counters_enabled);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -3927,6 +3940,7 @@ void devlink_resource_set_req_free(struct devlink_resource_set_req *req)
 int devlink_resource_set(struct ynl_sock *ys,
 			 struct devlink_resource_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -3942,7 +3956,7 @@ int devlink_resource_set(struct ynl_sock *ys,
 	if (req->_present.resource_size)
 		mnl_attr_put_u64(nlh, DEVLINK_ATTR_RESOURCE_SIZE, req->resource_size);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -4317,6 +4331,7 @@ void devlink_param_set_req_free(struct devlink_param_set_req *req)
 
 int devlink_param_set(struct ynl_sock *ys, struct devlink_param_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -4334,7 +4349,7 @@ int devlink_param_set(struct ynl_sock *ys, struct devlink_param_set_req *req)
 	if (req->_present.param_value_cmode)
 		mnl_attr_put_u8(nlh, DEVLINK_ATTR_PARAM_VALUE_CMODE, req->param_value_cmode);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -4629,6 +4644,7 @@ void devlink_region_del_req_free(struct devlink_region_del_req *req)
 
 int devlink_region_del(struct ynl_sock *ys, struct devlink_region_del_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -4646,7 +4662,7 @@ int devlink_region_del(struct ynl_sock *ys, struct devlink_region_del_req *req)
 	if (req->_present.region_snapshot_id)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_REGION_SNAPSHOT_ID, req->region_snapshot_id);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -4920,6 +4936,7 @@ void devlink_port_param_set_req_free(struct devlink_port_param_set_req *req)
 int devlink_port_param_set(struct ynl_sock *ys,
 			   struct devlink_port_param_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -4933,7 +4950,7 @@ int devlink_port_param_set(struct ynl_sock *ys,
 	if (req->_present.port_index)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -5358,6 +5375,7 @@ devlink_health_reporter_set_req_free(struct devlink_health_reporter_set_req *req
 int devlink_health_reporter_set(struct ynl_sock *ys,
 				struct devlink_health_reporter_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -5379,7 +5397,7 @@ int devlink_health_reporter_set(struct ynl_sock *ys,
 	if (req->_present.health_reporter_auto_dump)
 		mnl_attr_put_u8(nlh, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP, req->health_reporter_auto_dump);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -5400,6 +5418,7 @@ devlink_health_reporter_recover_req_free(struct devlink_health_reporter_recover_
 int devlink_health_reporter_recover(struct ynl_sock *ys,
 				    struct devlink_health_reporter_recover_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -5415,7 +5434,7 @@ int devlink_health_reporter_recover(struct ynl_sock *ys,
 	if (req->_present.health_reporter_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -5436,6 +5455,7 @@ devlink_health_reporter_diagnose_req_free(struct devlink_health_reporter_diagnos
 int devlink_health_reporter_diagnose(struct ynl_sock *ys,
 				     struct devlink_health_reporter_diagnose_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -5451,7 +5471,7 @@ int devlink_health_reporter_diagnose(struct ynl_sock *ys,
 	if (req->_present.health_reporter_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -5554,6 +5574,7 @@ devlink_health_reporter_dump_clear_req_free(struct devlink_health_reporter_dump_
 int devlink_health_reporter_dump_clear(struct ynl_sock *ys,
 				       struct devlink_health_reporter_dump_clear_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -5569,7 +5590,7 @@ int devlink_health_reporter_dump_clear(struct ynl_sock *ys,
 	if (req->_present.health_reporter_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -5590,6 +5611,7 @@ void devlink_flash_update_req_free(struct devlink_flash_update_req *req)
 int devlink_flash_update(struct ynl_sock *ys,
 			 struct devlink_flash_update_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -5607,7 +5629,7 @@ int devlink_flash_update(struct ynl_sock *ys,
 	if (req->_present.flash_update_overwrite_mask)
 		mnl_attr_put(nlh, DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK, sizeof(struct nla_bitfield32), &req->flash_update_overwrite_mask);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -5778,6 +5800,7 @@ void devlink_trap_set_req_free(struct devlink_trap_set_req *req)
 
 int devlink_trap_set(struct ynl_sock *ys, struct devlink_trap_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -5793,7 +5816,7 @@ int devlink_trap_set(struct ynl_sock *ys, struct devlink_trap_set_req *req)
 	if (req->_present.trap_action)
 		mnl_attr_put_u8(nlh, DEVLINK_ATTR_TRAP_ACTION, req->trap_action);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -5966,6 +5989,7 @@ void devlink_trap_group_set_req_free(struct devlink_trap_group_set_req *req)
 int devlink_trap_group_set(struct ynl_sock *ys,
 			   struct devlink_trap_group_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -5983,7 +6007,7 @@ int devlink_trap_group_set(struct ynl_sock *ys,
 	if (req->_present.trap_policer_id)
 		mnl_attr_put_u32(nlh, DEVLINK_ATTR_TRAP_POLICER_ID, req->trap_policer_id);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -6150,6 +6174,7 @@ devlink_trap_policer_set_req_free(struct devlink_trap_policer_set_req *req)
 int devlink_trap_policer_set(struct ynl_sock *ys,
 			     struct devlink_trap_policer_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -6167,7 +6192,7 @@ int devlink_trap_policer_set(struct ynl_sock *ys,
 	if (req->_present.trap_policer_burst)
 		mnl_attr_put_u64(nlh, DEVLINK_ATTR_TRAP_POLICER_BURST, req->trap_policer_burst);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -6188,6 +6213,7 @@ devlink_health_reporter_test_req_free(struct devlink_health_reporter_test_req *r
 int devlink_health_reporter_test(struct ynl_sock *ys,
 				 struct devlink_health_reporter_test_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -6203,7 +6229,7 @@ int devlink_health_reporter_test(struct ynl_sock *ys,
 	if (req->_present.health_reporter_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -6382,6 +6408,7 @@ void devlink_rate_set_req_free(struct devlink_rate_set_req *req)
 
 int devlink_rate_set(struct ynl_sock *ys, struct devlink_rate_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -6405,7 +6432,7 @@ int devlink_rate_set(struct ynl_sock *ys, struct devlink_rate_set_req *req)
 	if (req->_present.rate_parent_node_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, req->rate_parent_node_name);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -6425,6 +6452,7 @@ void devlink_rate_new_req_free(struct devlink_rate_new_req *req)
 
 int devlink_rate_new(struct ynl_sock *ys, struct devlink_rate_new_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -6448,7 +6476,7 @@ int devlink_rate_new(struct ynl_sock *ys, struct devlink_rate_new_req *req)
 	if (req->_present.rate_parent_node_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, req->rate_parent_node_name);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -6467,6 +6495,7 @@ void devlink_rate_del_req_free(struct devlink_rate_del_req *req)
 
 int devlink_rate_del(struct ynl_sock *ys, struct devlink_rate_del_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -6480,7 +6509,7 @@ int devlink_rate_del(struct ynl_sock *ys, struct devlink_rate_del_req *req)
 	if (req->_present.rate_node_name_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -6643,6 +6672,7 @@ void devlink_linecard_set_req_free(struct devlink_linecard_set_req *req)
 int devlink_linecard_set(struct ynl_sock *ys,
 			 struct devlink_linecard_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -6658,7 +6688,7 @@ int devlink_linecard_set(struct ynl_sock *ys,
 	if (req->_present.linecard_type_len)
 		mnl_attr_put_strz(nlh, DEVLINK_ATTR_LINECARD_TYPE, req->linecard_type);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -6808,6 +6838,7 @@ void devlink_selftests_run_req_free(struct devlink_selftests_run_req *req)
 int devlink_selftests_run(struct ynl_sock *ys,
 			  struct devlink_selftests_run_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -6821,7 +6852,7 @@ int devlink_selftests_run(struct ynl_sock *ys,
 	if (req->_present.selftests)
 		devlink_dl_selftest_id_put(nlh, DEVLINK_ATTR_SELFTESTS, &req->selftests);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
diff --git a/tools/net/ynl/generated/ethtool-user.c b/tools/net/ynl/generated/ethtool-user.c
index 74b883a14958f4..660435639e2bf8 100644
--- a/tools/net/ynl/generated/ethtool-user.c
+++ b/tools/net/ynl/generated/ethtool-user.c
@@ -1843,6 +1843,7 @@ void ethtool_linkinfo_set_req_free(struct ethtool_linkinfo_set_req *req)
 int ethtool_linkinfo_set(struct ynl_sock *ys,
 			 struct ethtool_linkinfo_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -1862,7 +1863,7 @@ int ethtool_linkinfo_set(struct ynl_sock *ys,
 	if (req->_present.transceiver)
 		mnl_attr_put_u8(nlh, ETHTOOL_A_LINKINFO_TRANSCEIVER, req->transceiver);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -2067,6 +2068,7 @@ void ethtool_linkmodes_set_req_free(struct ethtool_linkmodes_set_req *req)
 int ethtool_linkmodes_set(struct ynl_sock *ys,
 			  struct ethtool_linkmodes_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -2094,7 +2096,7 @@ int ethtool_linkmodes_set(struct ynl_sock *ys,
 	if (req->_present.rate_matching)
 		mnl_attr_put_u8(nlh, ETHTOOL_A_LINKMODES_RATE_MATCHING, req->rate_matching);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -2398,6 +2400,7 @@ void ethtool_debug_set_req_free(struct ethtool_debug_set_req *req)
 
 int ethtool_debug_set(struct ynl_sock *ys, struct ethtool_debug_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -2409,7 +2412,7 @@ int ethtool_debug_set(struct ynl_sock *ys, struct ethtool_debug_set_req *req)
 	if (req->_present.msgmask)
 		ethtool_bitset_put(nlh, ETHTOOL_A_DEBUG_MSGMASK, &req->msgmask);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -2577,6 +2580,7 @@ void ethtool_wol_set_req_free(struct ethtool_wol_set_req *req)
 
 int ethtool_wol_set(struct ynl_sock *ys, struct ethtool_wol_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -2590,7 +2594,7 @@ int ethtool_wol_set(struct ynl_sock *ys, struct ethtool_wol_set_req *req)
 	if (req->_present.sopass_len)
 		mnl_attr_put(nlh, ETHTOOL_A_WOL_SOPASS, req->_present.sopass_len, req->sopass);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -3045,6 +3049,7 @@ void ethtool_privflags_set_req_free(struct ethtool_privflags_set_req *req)
 int ethtool_privflags_set(struct ynl_sock *ys,
 			  struct ethtool_privflags_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -3056,7 +3061,7 @@ int ethtool_privflags_set(struct ynl_sock *ys,
 	if (req->_present.flags)
 		ethtool_bitset_put(nlh, ETHTOOL_A_PRIVFLAGS_FLAGS, &req->flags);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -3273,6 +3278,7 @@ void ethtool_rings_set_req_free(struct ethtool_rings_set_req *req)
 
 int ethtool_rings_set(struct ynl_sock *ys, struct ethtool_rings_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -3312,7 +3318,7 @@ int ethtool_rings_set(struct ynl_sock *ys, struct ethtool_rings_set_req *req)
 	if (req->_present.tx_push_buf_len_max)
 		mnl_attr_put_u32(nlh, ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX, req->tx_push_buf_len_max);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -3495,6 +3501,7 @@ void ethtool_channels_set_req_free(struct ethtool_channels_set_req *req)
 int ethtool_channels_set(struct ynl_sock *ys,
 			 struct ethtool_channels_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -3520,7 +3527,7 @@ int ethtool_channels_set(struct ynl_sock *ys,
 	if (req->_present.combined_count)
 		mnl_attr_put_u32(nlh, ETHTOOL_A_CHANNELS_COMBINED_COUNT, req->combined_count);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -3798,6 +3805,7 @@ void ethtool_coalesce_set_req_free(struct ethtool_coalesce_set_req *req)
 int ethtool_coalesce_set(struct ynl_sock *ys,
 			 struct ethtool_coalesce_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -3861,7 +3869,7 @@ int ethtool_coalesce_set(struct ynl_sock *ys,
 	if (req->_present.tx_aggr_time_usecs)
 		mnl_attr_put_u32(nlh, ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, req->tx_aggr_time_usecs);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -4036,6 +4044,7 @@ void ethtool_pause_set_req_free(struct ethtool_pause_set_req *req)
 
 int ethtool_pause_set(struct ynl_sock *ys, struct ethtool_pause_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -4055,7 +4064,7 @@ int ethtool_pause_set(struct ynl_sock *ys, struct ethtool_pause_set_req *req)
 	if (req->_present.stats_src)
 		mnl_attr_put_u32(nlh, ETHTOOL_A_PAUSE_STATS_SRC, req->stats_src);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -4242,6 +4251,7 @@ void ethtool_eee_set_req_free(struct ethtool_eee_set_req *req)
 
 int ethtool_eee_set(struct ynl_sock *ys, struct ethtool_eee_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -4263,7 +4273,7 @@ int ethtool_eee_set(struct ynl_sock *ys, struct ethtool_eee_set_req *req)
 	if (req->_present.tx_lpi_timer)
 		mnl_attr_put_u32(nlh, ETHTOOL_A_EEE_TX_LPI_TIMER, req->tx_lpi_timer);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -4437,6 +4447,7 @@ void ethtool_cable_test_act_req_free(struct ethtool_cable_test_act_req *req)
 int ethtool_cable_test_act(struct ynl_sock *ys,
 			   struct ethtool_cable_test_act_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -4446,7 +4457,7 @@ int ethtool_cable_test_act(struct ynl_sock *ys,
 	if (req->_present.header)
 		ethtool_header_put(nlh, ETHTOOL_A_CABLE_TEST_HEADER, &req->header);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -4465,6 +4476,7 @@ ethtool_cable_test_tdr_act_req_free(struct ethtool_cable_test_tdr_act_req *req)
 int ethtool_cable_test_tdr_act(struct ynl_sock *ys,
 			       struct ethtool_cable_test_tdr_act_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -4474,7 +4486,7 @@ int ethtool_cable_test_tdr_act(struct ynl_sock *ys,
 	if (req->_present.header)
 		ethtool_header_put(nlh, ETHTOOL_A_CABLE_TEST_TDR_HEADER, &req->header);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -4782,6 +4794,7 @@ void ethtool_fec_set_req_free(struct ethtool_fec_set_req *req)
 
 int ethtool_fec_set(struct ynl_sock *ys, struct ethtool_fec_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -4799,7 +4812,7 @@ int ethtool_fec_set(struct ynl_sock *ys, struct ethtool_fec_set_req *req)
 	if (req->_present.stats)
 		ethtool_fec_stat_put(nlh, ETHTOOL_A_FEC_STATS, &req->stats);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -5235,6 +5248,7 @@ void ethtool_module_set_req_free(struct ethtool_module_set_req *req)
 
 int ethtool_module_set(struct ynl_sock *ys, struct ethtool_module_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -5248,7 +5262,7 @@ int ethtool_module_set(struct ynl_sock *ys, struct ethtool_module_set_req *req)
 	if (req->_present.power_mode)
 		mnl_attr_put_u8(nlh, ETHTOOL_A_MODULE_POWER_MODE, req->power_mode);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -5397,6 +5411,7 @@ void ethtool_pse_set_req_free(struct ethtool_pse_set_req *req)
 
 int ethtool_pse_set(struct ynl_sock *ys, struct ethtool_pse_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -5412,7 +5427,7 @@ int ethtool_pse_set(struct ynl_sock *ys, struct ethtool_pse_set_req *req)
 	if (req->_present.pw_d_status)
 		mnl_attr_put_u32(nlh, ETHTOOL_A_PODL_PSE_PW_D_STATUS, req->pw_d_status);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -5746,6 +5761,7 @@ void ethtool_plca_set_cfg_req_free(struct ethtool_plca_set_cfg_req *req)
 int ethtool_plca_set_cfg(struct ynl_sock *ys,
 			 struct ethtool_plca_set_cfg_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -5771,7 +5787,7 @@ int ethtool_plca_set_cfg(struct ynl_sock *ys,
 	if (req->_present.burst_tmr)
 		mnl_attr_put_u32(nlh, ETHTOOL_A_PLCA_BURST_TMR, req->burst_tmr);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -6124,6 +6140,7 @@ void ethtool_mm_set_req_free(struct ethtool_mm_set_req *req)
 
 int ethtool_mm_set(struct ynl_sock *ys, struct ethtool_mm_set_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -6143,7 +6160,7 @@ int ethtool_mm_set(struct ynl_sock *ys, struct ethtool_mm_set_req *req)
 	if (req->_present.tx_min_frag_size)
 		mnl_attr_put_u32(nlh, ETHTOOL_A_MM_TX_MIN_FRAG_SIZE, req->tx_min_frag_size);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
diff --git a/tools/net/ynl/generated/fou-user.c b/tools/net/ynl/generated/fou-user.c
index 4271b5d43c5867..f30bef23bc3101 100644
--- a/tools/net/ynl/generated/fou-user.c
+++ b/tools/net/ynl/generated/fou-user.c
@@ -72,6 +72,7 @@ void fou_add_req_free(struct fou_add_req *req)
 
 int fou_add(struct ynl_sock *ys, struct fou_add_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -99,7 +100,7 @@ int fou_add(struct ynl_sock *ys, struct fou_add_req *req)
 	if (req->_present.ifindex)
 		mnl_attr_put_u32(nlh, FOU_ATTR_IFINDEX, req->ifindex);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
@@ -117,6 +118,7 @@ void fou_del_req_free(struct fou_del_req *req)
 
 int fou_del(struct ynl_sock *ys, struct fou_del_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -140,7 +142,7 @@ int fou_del(struct ynl_sock *ys, struct fou_del_req *req)
 	if (req->_present.peer_v6_len)
 		mnl_attr_put(nlh, FOU_ATTR_PEER_V6, req->_present.peer_v6_len, req->peer_v6);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
diff --git a/tools/net/ynl/generated/handshake-user.c b/tools/net/ynl/generated/handshake-user.c
index 7c67765daf9021..6901f8462cca8b 100644
--- a/tools/net/ynl/generated/handshake-user.c
+++ b/tools/net/ynl/generated/handshake-user.c
@@ -295,6 +295,7 @@ void handshake_done_req_free(struct handshake_done_req *req)
 
 int handshake_done(struct ynl_sock *ys, struct handshake_done_req *req)
 {
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -308,7 +309,7 @@ int handshake_done(struct ynl_sock *ys, struct handshake_done_req *req)
 	for (unsigned int i = 0; i < req->n_remote_auth; i++)
 		mnl_attr_put_u32(nlh, HANDSHAKE_A_DONE_REMOTE_AUTH, req->remote_auth[i]);
 
-	err = ynl_exec(ys, nlh, NULL);
+	err = ynl_exec(ys, nlh, &yrs);
 	if (err < 0)
 		return -1;
 
diff --git a/tools/net/ynl/generated/nfsd-user.c b/tools/net/ynl/generated/nfsd-user.c
index fec6828680ce99..360b6448c6e917 100644
--- a/tools/net/ynl/generated/nfsd-user.c
+++ b/tools/net/ynl/generated/nfsd-user.c
@@ -50,9 +50,116 @@ struct ynl_policy_nest nfsd_rpc_status_nest = {
 /* Common nested types */
 /* ============== NFSD_CMD_RPC_STATUS_GET ============== */
 /* NFSD_CMD_RPC_STATUS_GET - dump */
-void nfsd_rpc_status_get_list_free(struct nfsd_rpc_status_get_list *rsp)
+int nfsd_rpc_status_get_rsp_dump_parse(const struct nlmsghdr *nlh, void *data)
 {
-	struct nfsd_rpc_status_get_list *next = rsp;
+	struct nfsd_rpc_status_get_rsp_dump *dst;
+	struct ynl_parse_arg *yarg = data;
+	unsigned int n_compound_ops = 0;
+	const struct nlattr *attr;
+	int i;
+
+	dst = yarg->data;
+
+	if (dst->compound_ops)
+		return ynl_error_parse(yarg, "attribute already present (rpc-status.compound-ops)");
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == NFSD_A_RPC_STATUS_XID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.xid = 1;
+			dst->xid = mnl_attr_get_u32(attr);
+		} else if (type == NFSD_A_RPC_STATUS_FLAGS) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.flags = 1;
+			dst->flags = mnl_attr_get_u32(attr);
+		} else if (type == NFSD_A_RPC_STATUS_PROG) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.prog = 1;
+			dst->prog = mnl_attr_get_u32(attr);
+		} else if (type == NFSD_A_RPC_STATUS_VERSION) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.version = 1;
+			dst->version = mnl_attr_get_u8(attr);
+		} else if (type == NFSD_A_RPC_STATUS_PROC) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.proc = 1;
+			dst->proc = mnl_attr_get_u32(attr);
+		} else if (type == NFSD_A_RPC_STATUS_SERVICE_TIME) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.service_time = 1;
+			dst->service_time = mnl_attr_get_u64(attr);
+		} else if (type == NFSD_A_RPC_STATUS_SADDR4) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.saddr4 = 1;
+			dst->saddr4 = mnl_attr_get_u32(attr);
+		} else if (type == NFSD_A_RPC_STATUS_DADDR4) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.daddr4 = 1;
+			dst->daddr4 = mnl_attr_get_u32(attr);
+		} else if (type == NFSD_A_RPC_STATUS_SADDR6) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = mnl_attr_get_payload_len(attr);
+			dst->_present.saddr6_len = len;
+			dst->saddr6 = malloc(len);
+			memcpy(dst->saddr6, mnl_attr_get_payload(attr), len);
+		} else if (type == NFSD_A_RPC_STATUS_DADDR6) {
+			unsigned int len;
+
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+
+			len = mnl_attr_get_payload_len(attr);
+			dst->_present.daddr6_len = len;
+			dst->daddr6 = malloc(len);
+			memcpy(dst->daddr6, mnl_attr_get_payload(attr), len);
+		} else if (type == NFSD_A_RPC_STATUS_SPORT) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.sport = 1;
+			dst->sport = mnl_attr_get_u16(attr);
+		} else if (type == NFSD_A_RPC_STATUS_DPORT) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.dport = 1;
+			dst->dport = mnl_attr_get_u16(attr);
+		} else if (type == NFSD_A_RPC_STATUS_COMPOUND_OPS) {
+			n_compound_ops++;
+		}
+	}
+
+	if (n_compound_ops) {
+		dst->compound_ops = calloc(n_compound_ops, sizeof(*dst->compound_ops));
+		dst->n_compound_ops = n_compound_ops;
+		i = 0;
+		mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+			if (mnl_attr_get_type(attr) == NFSD_A_RPC_STATUS_COMPOUND_OPS) {
+				dst->compound_ops[i] = mnl_attr_get_u32(attr);
+				i++;
+			}
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+void
+nfsd_rpc_status_get_rsp_list_free(struct nfsd_rpc_status_get_rsp_list *rsp)
+{
+	struct nfsd_rpc_status_get_rsp_list *next = rsp;
 
 	while ((void *)next != YNL_LIST_END) {
 		rsp = next;
@@ -65,15 +172,16 @@ void nfsd_rpc_status_get_list_free(struct nfsd_rpc_status_get_list *rsp)
 	}
 }
 
-struct nfsd_rpc_status_get_list *nfsd_rpc_status_get_dump(struct ynl_sock *ys)
+struct nfsd_rpc_status_get_rsp_list *
+nfsd_rpc_status_get_dump(struct ynl_sock *ys)
 {
 	struct ynl_dump_state yds = {};
 	struct nlmsghdr *nlh;
 	int err;
 
 	yds.ys = ys;
-	yds.alloc_sz = sizeof(struct nfsd_rpc_status_get_list);
-	yds.cb = nfsd_rpc_status_get_rsp_parse;
+	yds.alloc_sz = sizeof(struct nfsd_rpc_status_get_rsp_list);
+	yds.cb = nfsd_rpc_status_get_rsp_dump_parse;
 	yds.rsp_cmd = NFSD_CMD_RPC_STATUS_GET;
 	yds.rsp_policy = &nfsd_rpc_status_nest;
 
@@ -86,7 +194,7 @@ struct nfsd_rpc_status_get_list *nfsd_rpc_status_get_dump(struct ynl_sock *ys)
 	return yds.first;
 
 free_list:
-	nfsd_rpc_status_get_list_free(yds.first);
+	nfsd_rpc_status_get_rsp_list_free(yds.first);
 	return NULL;
 }
 
diff --git a/tools/net/ynl/generated/nfsd-user.h b/tools/net/ynl/generated/nfsd-user.h
index b6b69501031a07..989c6e209ced0a 100644
--- a/tools/net/ynl/generated/nfsd-user.h
+++ b/tools/net/ynl/generated/nfsd-user.h
@@ -21,13 +21,47 @@ const char *nfsd_op_str(int op);
 /* Common nested types */
 /* ============== NFSD_CMD_RPC_STATUS_GET ============== */
 /* NFSD_CMD_RPC_STATUS_GET - dump */
-struct nfsd_rpc_status_get_list {
-	struct nfsd_rpc_status_get_list *next;
-	struct nfsd_rpc_status_get_rsp obj __attribute__ ((aligned (8)));
+struct nfsd_rpc_status_get_rsp_dump {
+	struct {
+		__u32 xid:1;
+		__u32 flags:1;
+		__u32 prog:1;
+		__u32 version:1;
+		__u32 proc:1;
+		__u32 service_time:1;
+		__u32 saddr4:1;
+		__u32 daddr4:1;
+		__u32 saddr6_len;
+		__u32 daddr6_len;
+		__u32 sport:1;
+		__u32 dport:1;
+	} _present;
+
+	__u32 xid /* big-endian */;
+	__u32 flags;
+	__u32 prog;
+	__u8 version;
+	__u32 proc;
+	__s64 service_time;
+	__u32 saddr4 /* big-endian */;
+	__u32 daddr4 /* big-endian */;
+	void *saddr6;
+	void *daddr6;
+	__u16 sport /* big-endian */;
+	__u16 dport /* big-endian */;
+	unsigned int n_compound_ops;
+	__u32 *compound_ops;
+};
+
+struct nfsd_rpc_status_get_rsp_list {
+	struct nfsd_rpc_status_get_rsp_list *next;
+	struct nfsd_rpc_status_get_rsp_dump obj __attribute__((aligned(8)));
 };
 
-void nfsd_rpc_status_get_list_free(struct nfsd_rpc_status_get_list *rsp);
+void
+nfsd_rpc_status_get_rsp_list_free(struct nfsd_rpc_status_get_rsp_list *rsp);
 
-struct nfsd_rpc_status_get_list *nfsd_rpc_status_get_dump(struct ynl_sock *ys);
+struct nfsd_rpc_status_get_rsp_list *
+nfsd_rpc_status_get_dump(struct ynl_sock *ys);
 
 #endif /* _LINUX_NFSD_GEN_H */
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 13427436bfb77b..8337aa6de25e9b 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -3,6 +3,7 @@
 
 import argparse
 import collections
+import filecmp
 import os
 import re
 import shutil
@@ -1168,7 +1169,7 @@ class CodeWriter:
         if out_file is None:
             self._out = os.sys.stdout
         else:
-            self._out = tempfile.TemporaryFile('w+')
+            self._out = tempfile.NamedTemporaryFile('w+')
             self._out_file = out_file
 
     def __del__(self):
@@ -1177,6 +1178,10 @@ class CodeWriter:
     def close_out_file(self):
         if self._out == os.sys.stdout:
             return
+        # Avoid modifying the file if contents didn't change
+        self._out.flush()
+        if os.path.isfile(self._out_file) and filecmp.cmp(self._out.name, self._out_file, shallow=False):
+            return
         with open(self._out_file, 'w+') as out_file:
             self._out.seek(0)
             shutil.copyfileobj(self._out, out_file)
@@ -1500,6 +1505,12 @@ def put_op_name(family, cw):
     cw.block_start(line=f"static const char * const {map_name}[] =")
     for op_name, op in family.msgs.items():
         if op.rsp_value:
+            # Make sure we don't add duplicated entries, if multiple commands
+            # produce the same response in legacy families.
+            if family.rsp_by_value[op.rsp_value] != op:
+                cw.p(f'// skip "{op_name}", duplicate reply value')
+                continue
+
             if op.req_value == op.rsp_value:
                 cw.p(f'[{op.enum_name}] = "{op_name}",')
             else:
@@ -1698,14 +1709,14 @@ def print_req(ri):
     ret_ok = '0'
     ret_err = '-1'
     direction = "request"
-    local_vars = ['struct nlmsghdr *nlh;',
+    local_vars = ['struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };',
+                  'struct nlmsghdr *nlh;',
                   'int err;']
 
     if 'reply' in ri.op[ri.op_mode]:
         ret_ok = 'rsp'
         ret_err = 'NULL'
-        local_vars += [f'{type_name(ri, rdir(direction))} *rsp;',
-                       'struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };']
+        local_vars += [f'{type_name(ri, rdir(direction))} *rsp;']
 
     print_prototype(ri, direction, terminate=False)
     ri.cw.block_start()
@@ -1721,7 +1732,6 @@ def print_req(ri):
         attr.attr_put(ri, "req")
     ri.cw.nl()
 
-    parse_arg = "NULL"
     if 'reply' in ri.op[ri.op_mode]:
         ri.cw.p('rsp = calloc(1, sizeof(*rsp));')
         ri.cw.p('yrs.yarg.data = rsp;')
@@ -1731,8 +1741,7 @@ def print_req(ri):
         else:
             ri.cw.p(f'yrs.rsp_cmd = {ri.op.rsp_value};')
         ri.cw.nl()
-        parse_arg = '&yrs'
-    ri.cw.p(f"err = ynl_exec(ys, nlh, {parse_arg});")
+    ri.cw.p("err = ynl_exec(ys, nlh, &yrs);")
     ri.cw.p('if (err < 0)')
     if 'reply' in ri.op[ri.op_mode]:
         ri.cw.p('goto err_free;')
diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h
index 649ebdef9c3fa0..1685d7ea6a9f70 100644
--- a/tools/objtool/noreturns.h
+++ b/tools/objtool/noreturns.h
@@ -6,7 +6,6 @@
  *
  * Yes, this is unfortunate.  A better solution is in the works.
  */
-NORETURN(__invalid_creds)
 NORETURN(__kunit_abort)
 NORETURN(__module_put_and_kthread_exit)
 NORETURN(__reiserfs_panic)
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 1da7f4b91b4f8a..dc42de1785cee7 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,3 +1,5 @@
+arch/arm64/tools/gen-sysreg.awk
+arch/arm64/tools/sysreg
 tools/perf
 tools/arch
 tools/scripts
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index d88da787e815b5..058c9aecf6087d 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -434,6 +434,21 @@ export INSTALL SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
+arm64_gen_sysreg_dir := $(srctree)/tools/arch/arm64/tools
+ifneq ($(OUTPUT),)
+  arm64_gen_sysreg_outdir := $(OUTPUT)
+else
+  arm64_gen_sysreg_outdir := $(CURDIR)
+endif
+
+arm64-sysreg-defs: FORCE
+	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir)
+
+arm64-sysreg-defs-clean:
+	$(call QUIET_CLEAN,arm64-sysreg-defs)
+	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir) \
+		clean > /dev/null
+
 beauty_linux_dir := $(srctree)/tools/perf/trace/beauty/include/linux/
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
 asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
@@ -450,15 +465,6 @@ drm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/drm_ioctl.sh
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(beauty_ioctl_outdir)' ] || mkdir -p '$(beauty_ioctl_outdir)')
 
-arm64_gen_sysreg_dir := $(srctree)/tools/arch/arm64/tools
-
-arm64-sysreg-defs: FORCE
-	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir)
-
-arm64-sysreg-defs-clean:
-	$(call QUIET_CLEAN,arm64-sysreg-defs)
-	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) clean > /dev/null
-
 $(drm_ioctl_array): $(drm_hdr_dir)/drm.h $(drm_hdr_dir)/i915_drm.h $(drm_ioctl_tbl)
 	$(Q)$(SHELL) '$(drm_ioctl_tbl)' $(drm_hdr_dir) > $@
 
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 80be0e98ea0c54..116ff501bf9263 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -367,3 +367,7 @@
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	n64	cachestat			sys_cachestat
 452	n64	fchmodat2			sys_fchmodat2
+453	n64	map_shadow_stack		sys_map_shadow_stack
+454	n64	futex_wake			sys_futex_wake
+455	n64	futex_wait			sys_futex_wait
+456	n64	futex_requeue			sys_futex_requeue
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index e1412519b4ad9a..7fab411378f2dd 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -539,3 +539,7 @@
 450 	nospu	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
 452	common	fchmodat2			sys_fchmodat2
+453	common	map_shadow_stack		sys_ni_syscall
+454	common	futex_wake			sys_futex_wake
+455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index cc0bc144b66162..86fec9b080f61b 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -455,3 +455,7 @@
 450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node
 451  common	cachestat		sys_cachestat			sys_cachestat
 452  common	fchmodat2		sys_fchmodat2			sys_fchmodat2
+453  common	map_shadow_stack	sys_map_shadow_stack		sys_map_shadow_stack
+454  common	futex_wake		sys_futex_wake			sys_futex_wake
+455  common	futex_wait		sys_futex_wait			sys_futex_wait
+456  common	futex_requeue		sys_futex_requeue		sys_futex_requeue
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 2a62eaf30d69a3..8cb8bf68721cf6 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -375,6 +375,9 @@
 451	common	cachestat		sys_cachestat
 452	common	fchmodat2		sys_fchmodat2
 453	64	map_shadow_stack	sys_map_shadow_stack
+454	common	futex_wake		sys_futex_wake
+455	common	futex_wait		sys_futex_wait
+456	common	futex_requeue		sys_futex_requeue
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/builtin-kwork.c b/tools/perf/builtin-kwork.c
index f007a9b27065f8..0092b9b39611d7 100644
--- a/tools/perf/builtin-kwork.c
+++ b/tools/perf/builtin-kwork.c
@@ -1643,7 +1643,7 @@ static int top_print_work(struct perf_kwork *kwork __maybe_unused, struct kwork_
 	/*
 	 * pid
 	 */
-	ret += printf(" %*ld ", PRINT_PID_WIDTH, work->id);
+	ret += printf(" %*" PRIu64 " ", PRINT_PID_WIDTH, work->id);
 
 	/*
 	 * tgid
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index a343823c8ddfc9..61c2c96cc0701b 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -434,6 +434,11 @@ static void json_print_metric(void *ps __maybe_unused, const char *group,
 	strbuf_release(&buf);
 }
 
+static bool json_skip_duplicate_pmus(void *ps __maybe_unused)
+{
+	return false;
+}
+
 static bool default_skip_duplicate_pmus(void *ps)
 {
 	struct print_state *print_state = ps;
@@ -503,6 +508,7 @@ int cmd_list(int argc, const char **argv)
 			.print_end = json_print_end,
 			.print_event = json_print_event,
 			.print_metric = json_print_metric,
+			.skip_duplicate_pmus = json_skip_duplicate_pmus,
 		};
 		ps = &json_ps;
 	} else {
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
index e2848a9d48487b..afcdad58ef89c2 100644
--- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json
@@ -231,6 +231,7 @@
         "MetricName": "slots_lost_misspeculation_fraction",
         "MetricExpr": "100 * ((OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots))",
         "BriefDescription": "Fraction of slots lost due to misspeculation",
+        "DefaultMetricgroupName": "TopdownL1",
         "MetricGroup": "Default;TopdownL1",
         "ScaleUnit": "1percent of slots"
     },
@@ -238,6 +239,7 @@
         "MetricName": "retired_fraction",
         "MetricExpr": "100 * (OP_RETIRED / (CPU_CYCLES * #slots))",
         "BriefDescription": "Fraction of slots retiring, useful work",
+        "DefaultMetricgroupName": "TopdownL1",
         "MetricGroup": "Default;TopdownL1",
 	"ScaleUnit": "1percent of slots"
     },
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index 39b74d83c7c4a7..cfcb7e2c3813f2 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -383,6 +383,7 @@ struct ucred {
 #define SOL_MPTCP	284
 #define SOL_MCTP	285
 #define SOL_SMC		286
+#define SOL_VSOCK	287
 
 /* IPX options */
 #define IPX_TYPE	1
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index fb661c48992fe5..988473bf907aee 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -347,7 +347,7 @@ CFLAGS_rbtree.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET
 CFLAGS_libstring.o     += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_hweight.o       += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_header.o        += -include $(OUTPUT)PERF-VERSION-FILE
-CFLAGS_arm-spe.o       += -I$(srctree)/tools/arch/arm64/include/ -I$(srctree)/tools/arch/arm64/include/generated/
+CFLAGS_arm-spe.o       += -I$(srctree)/tools/arch/arm64/include/ -I$(OUTPUT)arch/arm64/include/generated/
 
 $(OUTPUT)util/argv_split.o: ../lib/argv_split.c FORCE
 	$(call rule_mkdir)
diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c
index e105245eb905d2..f1716c089c9912 100644
--- a/tools/perf/util/bpf_lock_contention.c
+++ b/tools/perf/util/bpf_lock_contention.c
@@ -12,6 +12,7 @@
 #include <linux/zalloc.h>
 #include <linux/string.h>
 #include <bpf/bpf.h>
+#include <inttypes.h>
 
 #include "bpf_skel/lock_contention.skel.h"
 #include "bpf_skel/lock_data.h"
@@ -250,7 +251,7 @@ static const char *lock_contention_get_name(struct lock_contention *con,
 		if (cgrp)
 			return cgrp->name;
 
-		snprintf(name_buf, sizeof(name_buf), "cgroup:%lu", cgrp_id);
+		snprintf(name_buf, sizeof(name_buf), "cgroup:%" PRIu64 "", cgrp_id);
 		return name_buf;
 	}
 
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 0484736d9fe440..ca3e0404f18720 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -225,7 +225,7 @@ static struct metric *metric__new(const struct pmu_metric *pm,
 
 	m->pmu = pm->pmu ?: "cpu";
 	m->metric_name = pm->metric_name;
-	m->default_metricgroup_name = pm->default_metricgroup_name;
+	m->default_metricgroup_name = pm->default_metricgroup_name ?: "";
 	m->modifier = NULL;
 	if (modifier) {
 		m->modifier = strdup(modifier);
diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py
index 4a356a70678554..40ad221e88811b 100755
--- a/tools/power/pm-graph/sleepgraph.py
+++ b/tools/power/pm-graph/sleepgraph.py
@@ -4151,7 +4151,7 @@ def parseKernelLog(data):
 			elif(re.match('Enabling non-boot CPUs .*', msg)):
 				# start of first cpu resume
 				cpu_start = ktime
-			elif(re.match('smpboot: CPU (?P<cpu>[0-9]*) is now offline', msg)) \
+			elif(re.match('smpboot: CPU (?P<cpu>[0-9]*) is now offline', msg) \
 				or re.match('psci: CPU(?P<cpu>[0-9]*) killed.*', msg)):
 				# end of a cpu suspend, start of the next
 				m = re.match('smpboot: CPU (?P<cpu>[0-9]*) is now offline', msg)
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 9a10512e340787..7a334377f92b97 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -211,9 +211,6 @@ int *fd_instr_count_percpu;
 struct timeval interval_tv = { 5, 0 };
 struct timespec interval_ts = { 5, 0 };
 
-/* Save original CPU model */
-unsigned int model_orig;
-
 unsigned int num_iterations;
 unsigned int header_iterations;
 unsigned int debug;
@@ -224,24 +221,16 @@ unsigned int rapl_joules;
 unsigned int summary_only;
 unsigned int list_header_only;
 unsigned int dump_only;
-unsigned int do_snb_cstates;
-unsigned int do_knl_cstates;
-unsigned int do_slm_cstates;
-unsigned int use_c1_residency_msr;
 unsigned int has_aperf;
 unsigned int has_epb;
 unsigned int has_turbo;
 unsigned int is_hybrid;
-unsigned int do_irtl_snb;
-unsigned int do_irtl_hsw;
 unsigned int units = 1000000;	/* MHz etc */
 unsigned int genuine_intel;
 unsigned int authentic_amd;
 unsigned int hygon_genuine;
 unsigned int max_level, max_extended_level;
 unsigned int has_invariant_tsc;
-unsigned int do_nhm_platform_info;
-unsigned int no_MSR_MISC_PWR_MGMT;
 unsigned int aperf_mperf_multiplier = 1;
 double bclk;
 double base_hz;
@@ -250,7 +239,6 @@ double tsc_tweak = 1.0;
 unsigned int show_pkg_only;
 unsigned int show_core_only;
 char *output_buffer, *outp;
-unsigned int do_rapl;
 unsigned int do_dts;
 unsigned int do_ptm;
 unsigned int do_ipc;
@@ -261,65 +249,686 @@ unsigned int gfx_cur_mhz;
 unsigned int gfx_act_mhz;
 unsigned int tj_max;
 unsigned int tj_max_override;
-int tcc_offset_bits;
 double rapl_power_units, rapl_time_units;
 double rapl_dram_energy_units, rapl_energy_units;
 double rapl_joule_counter_range;
-unsigned int do_core_perf_limit_reasons;
-unsigned int has_automatic_cstate_conversion;
-unsigned int dis_cstate_prewake;
-unsigned int do_gfx_perf_limit_reasons;
-unsigned int do_ring_perf_limit_reasons;
 unsigned int crystal_hz;
 unsigned long long tsc_hz;
 int base_cpu;
-double discover_bclk(unsigned int family, unsigned int model);
 unsigned int has_hwp;		/* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */
 			/* IA32_HWP_REQUEST, IA32_HWP_STATUS */
 unsigned int has_hwp_notify;	/* IA32_HWP_INTERRUPT */
 unsigned int has_hwp_activity_window;	/* IA32_HWP_REQUEST[bits 41:32] */
 unsigned int has_hwp_epp;	/* IA32_HWP_REQUEST[bits 31:24] */
 unsigned int has_hwp_pkg;	/* IA32_HWP_REQUEST_PKG */
-unsigned int has_misc_feature_control;
 unsigned int first_counter_read = 1;
 int ignore_stdin;
 
-#define RAPL_PKG		(1 << 0)
-					/* 0x610 MSR_PKG_POWER_LIMIT */
-					/* 0x611 MSR_PKG_ENERGY_STATUS */
-#define RAPL_PKG_PERF_STATUS	(1 << 1)
-					/* 0x613 MSR_PKG_PERF_STATUS */
-#define RAPL_PKG_POWER_INFO	(1 << 2)
-					/* 0x614 MSR_PKG_POWER_INFO */
-
-#define RAPL_DRAM		(1 << 3)
-					/* 0x618 MSR_DRAM_POWER_LIMIT */
-					/* 0x619 MSR_DRAM_ENERGY_STATUS */
-#define RAPL_DRAM_PERF_STATUS	(1 << 4)
-					/* 0x61b MSR_DRAM_PERF_STATUS */
-#define RAPL_DRAM_POWER_INFO	(1 << 5)
-					/* 0x61c MSR_DRAM_POWER_INFO */
-
-#define RAPL_CORES_POWER_LIMIT	(1 << 6)
-					/* 0x638 MSR_PP0_POWER_LIMIT */
-#define RAPL_CORE_POLICY	(1 << 7)
-					/* 0x63a MSR_PP0_POLICY */
-
-#define RAPL_GFX		(1 << 8)
-					/* 0x640 MSR_PP1_POWER_LIMIT */
-					/* 0x641 MSR_PP1_ENERGY_STATUS */
-					/* 0x642 MSR_PP1_POLICY */
-
-#define RAPL_CORES_ENERGY_STATUS	(1 << 9)
-					/* 0x639 MSR_PP0_ENERGY_STATUS */
-#define RAPL_PER_CORE_ENERGY	(1 << 10)
-					/* Indicates cores energy collection is per-core,
-					 * not per-package. */
-#define RAPL_AMD_F17H		(1 << 11)
-					/* 0xc0010299 MSR_RAPL_PWR_UNIT */
-					/* 0xc001029a MSR_CORE_ENERGY_STAT */
-					/* 0xc001029b MSR_PKG_ENERGY_STAT */
-#define RAPL_CORES (RAPL_CORES_ENERGY_STATUS | RAPL_CORES_POWER_LIMIT)
+int get_msr(int cpu, off_t offset, unsigned long long *msr);
+
+/* Model specific support Start */
+
+/* List of features that may diverge among different platforms */
+struct platform_features {
+	bool has_msr_misc_feature_control;	/* MSR_MISC_FEATURE_CONTROL */
+	bool has_msr_misc_pwr_mgmt;	/* MSR_MISC_PWR_MGMT */
+	bool has_nhm_msrs;	/* MSR_PLATFORM_INFO, MSR_IA32_TEMPERATURE_TARGET, MSR_SMI_COUNT, MSR_PKG_CST_CONFIG_CONTROL, MSR_IA32_POWER_CTL, TRL MSRs */
+	bool has_config_tdp;	/* MSR_CONFIG_TDP_NOMINAL/LEVEL_1/LEVEL_2/CONTROL, MSR_TURBO_ACTIVATION_RATIO */
+	int bclk_freq;		/* CPU base clock */
+	int crystal_freq;	/* Crystal clock to use when not available from CPUID.15 */
+	int supported_cstates;	/* Core cstates and Package cstates supported */
+	int cst_limit;		/* MSR_PKG_CST_CONFIG_CONTROL */
+	bool has_cst_auto_convension;	/* AUTOMATIC_CSTATE_CONVERSION bit in MSR_PKG_CST_CONFIG_CONTROL */
+	bool has_irtl_msrs;	/* MSR_PKGC3/PKGC6/PKGC7/PKGC8/PKGC9/PKGC10_IRTL */
+	bool has_msr_core_c1_res;	/* MSR_CORE_C1_RES */
+	bool has_msr_module_c6_res_ms;	/* MSR_MODULE_C6_RES_MS */
+	bool has_msr_c6_demotion_policy_config;	/* MSR_CC6_DEMOTION_POLICY_CONFIG/MSR_MC6_DEMOTION_POLICY_CONFIG */
+	bool has_msr_atom_pkg_c6_residency;	/* MSR_ATOM_PKG_C6_RESIDENCY */
+	bool has_msr_knl_core_c6_residency;	/* MSR_KNL_CORE_C6_RESIDENCY */
+	bool has_ext_cst_msrs;	/* MSR_PKG_WEIGHTED_CORE_C0_RES/MSR_PKG_ANY_CORE_C0_RES/MSR_PKG_ANY_GFXE_C0_RES/MSR_PKG_BOTH_CORE_GFXE_C0_RES */
+	bool has_cst_prewake_bit;	/* Cstate prewake bit in MSR_IA32_POWER_CTL */
+	int trl_msrs;		/* MSR_TURBO_RATIO_LIMIT/LIMIT1/LIMIT2/SECONDARY, Atom TRL MSRs */
+	int plr_msrs;		/* MSR_CORE/GFX/RING_PERF_LIMIT_REASONS */
+	int rapl_msrs;		/* RAPL PKG/DRAM/CORE/GFX MSRs, AMD RAPL MSRs */
+	bool has_per_core_rapl;	/* Indicates cores energy collection is per-core, not per-package. AMD specific for now */
+	bool has_rapl_divisor;	/* Divisor for Energy unit raw value from MSR_RAPL_POWER_UNIT */
+	bool has_fixed_rapl_unit;	/* Fixed Energy Unit used for DRAM RAPL Domain */
+	int rapl_quirk_tdp;	/* Hardcoded TDP value when cannot be retrieved from hardware */
+	int tcc_offset_bits;	/* TCC Offset bits in MSR_IA32_TEMPERATURE_TARGET */
+	bool enable_tsc_tweak;	/* Use CPU Base freq instead of TSC freq for aperf/mperf counter */
+	bool need_perf_multiplier;	/* mperf/aperf multiplier */
+};
+
+struct platform_data {
+	unsigned int model;
+	const struct platform_features *features;
+};
+
+/* For BCLK */
+enum bclk_freq {
+	BCLK_100MHZ = 1,
+	BCLK_133MHZ,
+	BCLK_SLV,
+};
+
+#define SLM_BCLK_FREQS 5
+double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0 };
+
+double slm_bclk(void)
+{
+	unsigned long long msr = 3;
+	unsigned int i;
+	double freq;
+
+	if (get_msr(base_cpu, MSR_FSB_FREQ, &msr))
+		fprintf(outf, "SLM BCLK: unknown\n");
+
+	i = msr & 0xf;
+	if (i >= SLM_BCLK_FREQS) {
+		fprintf(outf, "SLM BCLK[%d] invalid\n", i);
+		i = 3;
+	}
+	freq = slm_freq_table[i];
+
+	if (!quiet)
+		fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq);
+
+	return freq;
+}
+
+/* For Package cstate limit */
+enum package_cstate_limit {
+	CST_LIMIT_NHM = 1,
+	CST_LIMIT_SNB,
+	CST_LIMIT_HSW,
+	CST_LIMIT_SKX,
+	CST_LIMIT_ICX,
+	CST_LIMIT_SLV,
+	CST_LIMIT_AMT,
+	CST_LIMIT_KNL,
+	CST_LIMIT_GMT,
+};
+
+/* For Turbo Ratio Limit MSRs */
+enum turbo_ratio_limit_msrs {
+	TRL_BASE = BIT(0),
+	TRL_LIMIT1 = BIT(1),
+	TRL_LIMIT2 = BIT(2),
+	TRL_ATOM = BIT(3),
+	TRL_KNL = BIT(4),
+	TRL_CORECOUNT = BIT(5),
+};
+
+/* For Perf Limit Reason MSRs */
+enum perf_limit_reason_msrs {
+	PLR_CORE = BIT(0),
+	PLR_GFX = BIT(1),
+	PLR_RING = BIT(2),
+};
+
+/* For RAPL MSRs */
+enum rapl_msrs {
+	RAPL_PKG_POWER_LIMIT = BIT(0),	/* 0x610 MSR_PKG_POWER_LIMIT */
+	RAPL_PKG_ENERGY_STATUS = BIT(1),	/* 0x611 MSR_PKG_ENERGY_STATUS */
+	RAPL_PKG_PERF_STATUS = BIT(2),	/* 0x613 MSR_PKG_PERF_STATUS */
+	RAPL_PKG_POWER_INFO = BIT(3),	/* 0x614 MSR_PKG_POWER_INFO */
+	RAPL_DRAM_POWER_LIMIT = BIT(4),	/* 0x618 MSR_DRAM_POWER_LIMIT */
+	RAPL_DRAM_ENERGY_STATUS = BIT(5),	/* 0x619 MSR_DRAM_ENERGY_STATUS */
+	RAPL_DRAM_PERF_STATUS = BIT(6),	/* 0x61b MSR_DRAM_PERF_STATUS */
+	RAPL_DRAM_POWER_INFO = BIT(7),	/* 0x61c MSR_DRAM_POWER_INFO */
+	RAPL_CORE_POWER_LIMIT = BIT(8),	/* 0x638 MSR_PP0_POWER_LIMIT */
+	RAPL_CORE_ENERGY_STATUS = BIT(9),	/* 0x639 MSR_PP0_ENERGY_STATUS */
+	RAPL_CORE_POLICY = BIT(10),	/* 0x63a MSR_PP0_POLICY */
+	RAPL_GFX_POWER_LIMIT = BIT(11),	/* 0x640 MSR_PP1_POWER_LIMIT */
+	RAPL_GFX_ENERGY_STATUS = BIT(12),	/* 0x641 MSR_PP1_ENERGY_STATUS */
+	RAPL_GFX_POLICY = BIT(13),	/* 0x642 MSR_PP1_POLICY */
+	RAPL_AMD_PWR_UNIT = BIT(14),	/* 0xc0010299 MSR_AMD_RAPL_POWER_UNIT */
+	RAPL_AMD_CORE_ENERGY_STAT = BIT(15),	/* 0xc001029a MSR_AMD_CORE_ENERGY_STATUS */
+	RAPL_AMD_PKG_ENERGY_STAT = BIT(16),	/* 0xc001029b MSR_AMD_PKG_ENERGY_STATUS */
+};
+
+#define RAPL_PKG	(RAPL_PKG_ENERGY_STATUS | RAPL_PKG_POWER_LIMIT)
+#define RAPL_DRAM	(RAPL_DRAM_ENERGY_STATUS | RAPL_DRAM_POWER_LIMIT)
+#define RAPL_CORE	(RAPL_CORE_ENERGY_STATUS | RAPL_CORE_POWER_LIMIT)
+#define RAPL_GFX	(RAPL_GFX_POWER_LIMIT | RAPL_GFX_ENERGY_STATUS)
+
+#define RAPL_PKG_ALL	(RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO)
+#define RAPL_DRAM_ALL	(RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_DRAM_POWER_INFO)
+#define RAPL_CORE_ALL	(RAPL_CORE | RAPL_CORE_POLICY)
+#define RAPL_GFX_ALL	(RAPL_GFX | RAPL_GFX_POLIGY)
+
+#define RAPL_AMD_F17H	(RAPL_AMD_PWR_UNIT | RAPL_AMD_CORE_ENERGY_STAT | RAPL_AMD_PKG_ENERGY_STAT)
+
+/* For Cstates */
+enum cstates {
+	CC1 = BIT(0),
+	CC3 = BIT(1),
+	CC6 = BIT(2),
+	CC7 = BIT(3),
+	PC2 = BIT(4),
+	PC3 = BIT(5),
+	PC6 = BIT(6),
+	PC7 = BIT(7),
+	PC8 = BIT(8),
+	PC9 = BIT(9),
+	PC10 = BIT(10),
+};
+
+static const struct platform_features nhm_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_133MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | PC3 | PC6,
+	.cst_limit = CST_LIMIT_NHM,
+	.trl_msrs = TRL_BASE,
+};
+
+static const struct platform_features nhx_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_133MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | PC3 | PC6,
+	.cst_limit = CST_LIMIT_NHM,
+};
+
+static const struct platform_features snb_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_SNB,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features snx_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_SNB,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM_ALL,
+};
+
+static const struct platform_features ivb_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_SNB,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features ivx_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_SNB,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE | TRL_LIMIT1,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM_ALL,
+};
+
+static const struct platform_features hsw_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.plr_msrs = PLR_CORE | PLR_GFX | PLR_RING,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features hsx_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE | TRL_LIMIT1 | TRL_LIMIT2,
+	.plr_msrs = PLR_CORE | PLR_RING,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+	.has_fixed_rapl_unit = 1,
+};
+
+static const struct platform_features hswl_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.plr_msrs = PLR_CORE | PLR_GFX | PLR_RING,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features hswg_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.plr_msrs = PLR_CORE | PLR_GFX | PLR_RING,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features bdw_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features bdwg_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features bdx_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | PC2 | PC3 | PC6,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.has_cst_auto_convension = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+	.has_fixed_rapl_unit = 1,
+};
+
+static const struct platform_features skl_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.crystal_freq = 24000000,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.has_ext_cst_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.tcc_offset_bits = 6,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX,
+	.enable_tsc_tweak = 1,
+};
+
+static const struct platform_features cnl_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.has_msr_core_c1_res = 1,
+	.has_ext_cst_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.tcc_offset_bits = 6,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX,
+	.enable_tsc_tweak = 1,
+};
+
+static const struct platform_features adl_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC8 | PC10,
+	.cst_limit = CST_LIMIT_HSW,
+	.has_irtl_msrs = 1,
+	.has_msr_core_c1_res = 1,
+	.has_ext_cst_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.tcc_offset_bits = 6,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX,
+	.enable_tsc_tweak = 1,
+};
+
+static const struct platform_features skx_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | PC2 | PC6,
+	.cst_limit = CST_LIMIT_SKX,
+	.has_irtl_msrs = 1,
+	.has_cst_auto_convension = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+	.has_fixed_rapl_unit = 1,
+};
+
+static const struct platform_features icx_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | PC2 | PC6,
+	.cst_limit = CST_LIMIT_ICX,
+	.has_irtl_msrs = 1,
+	.has_cst_prewake_bit = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+	.has_fixed_rapl_unit = 1,
+};
+
+static const struct platform_features spr_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | PC2 | PC6,
+	.cst_limit = CST_LIMIT_SKX,
+	.has_msr_core_c1_res = 1,
+	.has_irtl_msrs = 1,
+	.has_cst_prewake_bit = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+};
+
+static const struct platform_features srf_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | PC2 | PC6,
+	.cst_limit = CST_LIMIT_SKX,
+	.has_msr_core_c1_res = 1,
+	.has_msr_module_c6_res_ms = 1,
+	.has_irtl_msrs = 1,
+	.has_cst_prewake_bit = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+};
+
+static const struct platform_features grr_features = {
+	.has_msr_misc_feature_control = 1,
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6,
+	.cst_limit = CST_LIMIT_SKX,
+	.has_msr_core_c1_res = 1,
+	.has_msr_module_c6_res_ms = 1,
+	.has_irtl_msrs = 1,
+	.has_cst_prewake_bit = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+};
+
+static const struct platform_features slv_features = {
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_SLV,
+	.supported_cstates = CC1 | CC6 | PC6,
+	.cst_limit = CST_LIMIT_SLV,
+	.has_msr_core_c1_res = 1,
+	.has_msr_module_c6_res_ms = 1,
+	.has_msr_c6_demotion_policy_config = 1,
+	.has_msr_atom_pkg_c6_residency = 1,
+	.trl_msrs = TRL_ATOM,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE,
+	.has_rapl_divisor = 1,
+	.rapl_quirk_tdp = 30,
+};
+
+static const struct platform_features slvd_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_SLV,
+	.supported_cstates = CC1 | CC6 | PC3 | PC6,
+	.cst_limit = CST_LIMIT_SLV,
+	.has_msr_atom_pkg_c6_residency = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG | RAPL_CORE,
+	.rapl_quirk_tdp = 30,
+};
+
+static const struct platform_features amt_features = {
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_133MHZ,
+	.supported_cstates = CC1 | CC3 | CC6 | PC3 | PC6,
+	.cst_limit = CST_LIMIT_AMT,
+	.trl_msrs = TRL_BASE,
+};
+
+static const struct platform_features gmt_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.crystal_freq = 19200000,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_GMT,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features gmtd_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.crystal_freq = 25000000,
+	.supported_cstates = CC1 | CC6 | PC2 | PC6,
+	.cst_limit = CST_LIMIT_GMT,
+	.has_irtl_msrs = 1,
+	.has_msr_core_c1_res = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_CORE_ENERGY_STATUS,
+};
+
+static const struct platform_features gmtp_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.crystal_freq = 19200000,
+	.supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_GMT,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG | RAPL_PKG_POWER_INFO,
+};
+
+static const struct platform_features tmt_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10,
+	.cst_limit = CST_LIMIT_GMT,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX,
+	.enable_tsc_tweak = 1,
+};
+
+static const struct platform_features tmtd_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6,
+	.cst_limit = CST_LIMIT_GMT,
+	.has_irtl_msrs = 1,
+	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
+	.rapl_msrs = RAPL_PKG_ALL,
+};
+
+static const struct platform_features knl_features = {
+	.has_msr_misc_pwr_mgmt = 1,
+	.has_nhm_msrs = 1,
+	.has_config_tdp = 1,
+	.bclk_freq = BCLK_100MHZ,
+	.supported_cstates = CC1 | CC6 | PC3 | PC6,
+	.cst_limit = CST_LIMIT_KNL,
+	.has_msr_knl_core_c6_residency = 1,
+	.trl_msrs = TRL_KNL,
+	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL,
+	.has_fixed_rapl_unit = 1,
+	.need_perf_multiplier = 1,
+};
+
+static const struct platform_features default_features = {
+};
+
+static const struct platform_features amd_features_with_rapl = {
+	.rapl_msrs = RAPL_AMD_F17H,
+	.has_per_core_rapl = 1,
+	.rapl_quirk_tdp = 280,	/* This is the max stock TDP of HEDT/Server Fam17h+ chips */
+};
+
+static const struct platform_data turbostat_pdata[] = {
+	{ INTEL_FAM6_NEHALEM, &nhm_features },
+	{ INTEL_FAM6_NEHALEM_G, &nhm_features },
+	{ INTEL_FAM6_NEHALEM_EP, &nhm_features },
+	{ INTEL_FAM6_NEHALEM_EX, &nhx_features },
+	{ INTEL_FAM6_WESTMERE, &nhm_features },
+	{ INTEL_FAM6_WESTMERE_EP, &nhm_features },
+	{ INTEL_FAM6_WESTMERE_EX, &nhx_features },
+	{ INTEL_FAM6_SANDYBRIDGE, &snb_features },
+	{ INTEL_FAM6_SANDYBRIDGE_X, &snx_features },
+	{ INTEL_FAM6_IVYBRIDGE, &ivb_features },
+	{ INTEL_FAM6_IVYBRIDGE_X, &ivx_features },
+	{ INTEL_FAM6_HASWELL, &hsw_features },
+	{ INTEL_FAM6_HASWELL_X, &hsx_features },
+	{ INTEL_FAM6_HASWELL_L, &hswl_features },
+	{ INTEL_FAM6_HASWELL_G, &hswg_features },
+	{ INTEL_FAM6_BROADWELL, &bdw_features },
+	{ INTEL_FAM6_BROADWELL_G, &bdwg_features },
+	{ INTEL_FAM6_BROADWELL_X, &bdx_features },
+	{ INTEL_FAM6_BROADWELL_D, &bdx_features },
+	{ INTEL_FAM6_SKYLAKE_L, &skl_features },
+	{ INTEL_FAM6_SKYLAKE, &skl_features },
+	{ INTEL_FAM6_SKYLAKE_X, &skx_features },
+	{ INTEL_FAM6_KABYLAKE_L, &skl_features },
+	{ INTEL_FAM6_KABYLAKE, &skl_features },
+	{ INTEL_FAM6_COMETLAKE, &skl_features },
+	{ INTEL_FAM6_COMETLAKE_L, &skl_features },
+	{ INTEL_FAM6_CANNONLAKE_L, &cnl_features },
+	{ INTEL_FAM6_ICELAKE_X, &icx_features },
+	{ INTEL_FAM6_ICELAKE_D, &icx_features },
+	{ INTEL_FAM6_ICELAKE_L, &cnl_features },
+	{ INTEL_FAM6_ICELAKE_NNPI, &cnl_features },
+	{ INTEL_FAM6_ROCKETLAKE, &cnl_features },
+	{ INTEL_FAM6_TIGERLAKE_L, &cnl_features },
+	{ INTEL_FAM6_TIGERLAKE, &cnl_features },
+	{ INTEL_FAM6_SAPPHIRERAPIDS_X, &spr_features },
+	{ INTEL_FAM6_EMERALDRAPIDS_X, &spr_features },
+	{ INTEL_FAM6_GRANITERAPIDS_X, &spr_features },
+	{ INTEL_FAM6_LAKEFIELD, &cnl_features },
+	{ INTEL_FAM6_ALDERLAKE, &adl_features },
+	{ INTEL_FAM6_ALDERLAKE_L, &adl_features },
+	{ INTEL_FAM6_RAPTORLAKE, &adl_features },
+	{ INTEL_FAM6_RAPTORLAKE_P, &adl_features },
+	{ INTEL_FAM6_RAPTORLAKE_S, &adl_features },
+	{ INTEL_FAM6_METEORLAKE, &cnl_features },
+	{ INTEL_FAM6_METEORLAKE_L, &cnl_features },
+	{ INTEL_FAM6_ARROWLAKE, &cnl_features },
+	{ INTEL_FAM6_LUNARLAKE_M, &cnl_features },
+	{ INTEL_FAM6_ATOM_SILVERMONT, &slv_features },
+	{ INTEL_FAM6_ATOM_SILVERMONT_D, &slvd_features },
+	{ INTEL_FAM6_ATOM_AIRMONT, &amt_features },
+	{ INTEL_FAM6_ATOM_GOLDMONT, &gmt_features },
+	{ INTEL_FAM6_ATOM_GOLDMONT_D, &gmtd_features },
+	{ INTEL_FAM6_ATOM_GOLDMONT_PLUS, &gmtp_features },
+	{ INTEL_FAM6_ATOM_TREMONT_D, &tmtd_features },
+	{ INTEL_FAM6_ATOM_TREMONT, &tmt_features },
+	{ INTEL_FAM6_ATOM_TREMONT_L, &tmt_features },
+	{ INTEL_FAM6_ATOM_GRACEMONT, &adl_features },
+	{ INTEL_FAM6_ATOM_CRESTMONT_X, &srf_features },
+	{ INTEL_FAM6_ATOM_CRESTMONT, &grr_features },
+	{ INTEL_FAM6_XEON_PHI_KNL, &knl_features },
+	{ INTEL_FAM6_XEON_PHI_KNM, &knl_features },
+	/*
+	 * Missing support for
+	 * INTEL_FAM6_ICELAKE
+	 * INTEL_FAM6_ATOM_SILVERMONT_MID
+	 * INTEL_FAM6_ATOM_AIRMONT_MID
+	 * INTEL_FAM6_ATOM_AIRMONT_NP
+	 */
+	{ 0, NULL },
+};
+
+static const struct platform_features *platform;
+
+void probe_platform_features(unsigned int family, unsigned int model)
+{
+	int i;
+
+	platform = &default_features;
+
+	if (authentic_amd || hygon_genuine) {
+		if (max_extended_level >= 0x80000007) {
+			unsigned int eax, ebx, ecx, edx;
+
+			__cpuid(0x80000007, eax, ebx, ecx, edx);
+			/* RAPL (Fam 17h+) */
+			if ((edx & (1 << 14)) && family >= 0x17)
+				platform = &amd_features_with_rapl;
+		}
+		return;
+	}
+
+	if (!genuine_intel || family != 6)
+		return;
+
+	for (i = 0; turbostat_pdata[i].features; i++) {
+		if (turbostat_pdata[i].model == model) {
+			platform = turbostat_pdata[i].features;
+			return;
+		}
+	}
+}
+
+/* Model specific support End */
+
 #define	TJMAX_DEFAULT	100
 
 /* MSRs that are not yet in the kernel-provided header. */
@@ -333,8 +942,8 @@ int backwards_count;
 char *progname;
 
 #define CPU_SUBSET_MAXCPUS	1024	/* need to use before probe... */
-cpu_set_t *cpu_present_set, *cpu_affinity_set, *cpu_subset;
-size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size;
+cpu_set_t *cpu_present_set, *cpu_effective_set, *cpu_allowed_set, *cpu_affinity_set, *cpu_subset;
+size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affinity_setsize, cpu_subset_size;
 #define MAX_ADDED_COUNTERS 8
 #define MAX_ADDED_THREAD_COUNTERS 24
 #define BITMASK_SIZE 32
@@ -355,12 +964,11 @@ struct thread_data {
 	unsigned int x2apic_id;
 	unsigned int flags;
 	bool is_atom;
-#define CPU_IS_FIRST_THREAD_IN_CORE	0x2
-#define CPU_IS_FIRST_CORE_IN_PACKAGE	0x4
 	unsigned long long counter[MAX_ADDED_THREAD_COUNTERS];
 } *thread_even, *thread_odd;
 
 struct core_data {
+	int base_cpu;
 	unsigned long long c3;
 	unsigned long long c6;
 	unsigned long long c7;
@@ -373,6 +981,7 @@ struct core_data {
 } *core_even, *core_odd;
 
 struct pkg_data {
+	int base_cpu;
 	unsigned long long pc2;
 	unsigned long long pc3;
 	unsigned long long pc6;
@@ -456,7 +1065,7 @@ off_t idx_to_offset(int idx)
 
 	switch (idx) {
 	case IDX_PKG_ENERGY:
-		if (do_rapl & RAPL_AMD_F17H)
+		if (platform->rapl_msrs & RAPL_AMD_F17H)
 			offset = MSR_PKG_ENERGY_STAT;
 		else
 			offset = MSR_PKG_ENERGY_STATUS;
@@ -516,17 +1125,17 @@ int idx_valid(int idx)
 {
 	switch (idx) {
 	case IDX_PKG_ENERGY:
-		return do_rapl & (RAPL_PKG | RAPL_AMD_F17H);
+		return platform->rapl_msrs & (RAPL_PKG | RAPL_AMD_F17H);
 	case IDX_DRAM_ENERGY:
-		return do_rapl & RAPL_DRAM;
+		return platform->rapl_msrs & RAPL_DRAM;
 	case IDX_PP0_ENERGY:
-		return do_rapl & RAPL_CORES_ENERGY_STATUS;
+		return platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS;
 	case IDX_PP1_ENERGY:
-		return do_rapl & RAPL_GFX;
+		return platform->rapl_msrs & RAPL_GFX;
 	case IDX_PKG_PERF:
-		return do_rapl & RAPL_PKG_PERF_STATUS;
+		return platform->rapl_msrs & RAPL_PKG_PERF_STATUS;
 	case IDX_DRAM_PERF:
-		return do_rapl & RAPL_DRAM_PERF_STATUS;
+		return platform->rapl_msrs & RAPL_DRAM_PERF_STATUS;
 	default:
 		return 0;
 	}
@@ -563,6 +1172,9 @@ struct topo_params {
 	int num_die;
 	int num_cpus;
 	int num_cores;
+	int allowed_packages;
+	int allowed_cpus;
+	int allowed_cores;
 	int max_cpu_num;
 	int max_node_num;
 	int nodes_per_pkg;
@@ -575,7 +1187,7 @@ struct timeval tv_even, tv_odd, tv_delta;
 int *irq_column_2_cpu;		/* /proc/interrupts column numbers */
 int *irqs_per_cpu;		/* indexed by cpu_num */
 
-void setup_all_buffers(void);
+void setup_all_buffers(bool startup);
 
 char *sys_lpi_file;
 char *sys_lpi_file_sysfs = "/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us";
@@ -586,6 +1198,11 @@ int cpu_is_not_present(int cpu)
 	return !CPU_ISSET_S(cpu, cpu_present_setsize, cpu_present_set);
 }
 
+int cpu_is_not_allowed(int cpu)
+{
+	return !CPU_ISSET_S(cpu, cpu_allowed_setsize, cpu_allowed_set);
+}
+
 /*
  * run func(thread, core, package) in topology order
  * skip non-present cpus
@@ -603,10 +1220,9 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk
 					struct thread_data *t;
 					struct core_data *c;
 					struct pkg_data *p;
-
 					t = GET_THREAD(thread_base, thread_no, core_no, node_no, pkg_no);
 
-					if (cpu_is_not_present(t->cpu_id))
+					if (cpu_is_not_allowed(t->cpu_id))
 						continue;
 
 					c = GET_CORE(core_base, core_no, node_no, pkg_no);
@@ -622,6 +1238,25 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk
 	return 0;
 }
 
+int is_cpu_first_thread_in_core(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	UNUSED(p);
+
+	return ((int)t->cpu_id == c->base_cpu || c->base_cpu < 0);
+}
+
+int is_cpu_first_core_in_package(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	UNUSED(c);
+
+	return ((int)t->cpu_id == p->base_cpu || p->base_cpu < 0);
+}
+
+int is_cpu_first_thread_in_package(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	return is_cpu_first_thread_in_core(t, c, p) && is_cpu_first_core_in_package(t, c, p);
+}
+
 int cpu_migrate(int cpu)
 {
 	CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
@@ -904,11 +1539,11 @@ void print_header(char *delim)
 	if (DO_BIC(BIC_CORE_THROT_CNT))
 		outp += sprintf(outp, "%sCoreThr", (printed++ ? delim : ""));
 
-	if (do_rapl && !rapl_joules) {
-		if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+	if (platform->rapl_msrs && !rapl_joules) {
+		if (DO_BIC(BIC_CorWatt) && platform->has_per_core_rapl)
 			outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
-	} else if (do_rapl && rapl_joules) {
-		if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+	} else if (platform->rapl_msrs && rapl_joules) {
+		if (DO_BIC(BIC_Cor_J) && platform->has_per_core_rapl)
 			outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
 	}
 
@@ -966,10 +1601,10 @@ void print_header(char *delim)
 	if (DO_BIC(BIC_SYS_LPI))
 		outp += sprintf(outp, "%sSYS%%LPI", (printed++ ? delim : ""));
 
-	if (do_rapl && !rapl_joules) {
+	if (platform->rapl_msrs && !rapl_joules) {
 		if (DO_BIC(BIC_PkgWatt))
 			outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : ""));
-		if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
+		if (DO_BIC(BIC_CorWatt) && !platform->has_per_core_rapl)
 			outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFXWatt))
 			outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : ""));
@@ -979,10 +1614,10 @@ void print_header(char *delim)
 			outp += sprintf(outp, "%sPKG_%%", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_RAM__))
 			outp += sprintf(outp, "%sRAM_%%", (printed++ ? delim : ""));
-	} else if (do_rapl && rapl_joules) {
+	} else if (platform->rapl_msrs && rapl_joules) {
 		if (DO_BIC(BIC_Pkg_J))
 			outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : ""));
-		if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
+		if (DO_BIC(BIC_Cor_J) && !platform->has_per_core_rapl)
 			outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFX_J))
 			outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : ""));
@@ -1106,11 +1741,11 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	int printed = 0;
 
 	/* if showing only 1st thread in core and this isn't one, bail out */
-	if (show_core_only && !(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+	if (show_core_only && !is_cpu_first_thread_in_core(t, c, p))
 		return 0;
 
 	/* if showing only 1st thread in pkg and this isn't one, bail out */
-	if (show_pkg_only && !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (show_pkg_only && !is_cpu_first_core_in_package(t, c, p))
 		return 0;
 
 	/*if not summary line and --cpu is used */
@@ -1244,7 +1879,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->c1 / tsc);
 
 	/* print per-core data only for 1st thread in core */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+	if (!is_cpu_first_thread_in_core(t, c, p))
 		goto done;
 
 	if (DO_BIC(BIC_CPU_c3))
@@ -1284,14 +1919,14 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	fmt8 = "%s%.2f";
 
-	if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+	if (DO_BIC(BIC_CorWatt) && platform->has_per_core_rapl)
 		outp +=
 		    sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
-	if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+	if (DO_BIC(BIC_Cor_J) && platform->has_per_core_rapl)
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units);
 
 	/* print per-package data only for 1st core in package */
-	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_core_in_package(t, c, p))
 		goto done;
 
 	/* PkgTmp */
@@ -1352,7 +1987,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 		outp +=
 		    sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float);
 
-	if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
+	if (DO_BIC(BIC_CorWatt) && !platform->has_per_core_rapl)
 		outp +=
 		    sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float);
 	if (DO_BIC(BIC_GFXWatt))
@@ -1364,7 +1999,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 			    p->energy_dram * rapl_dram_energy_units / interval_float);
 	if (DO_BIC(BIC_Pkg_J))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units);
-	if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
+	if (DO_BIC(BIC_Cor_J) && !platform->has_per_core_rapl)
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units);
 	if (DO_BIC(BIC_GFX_J))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units);
@@ -1527,7 +2162,7 @@ void delta_core(struct core_data *new, struct core_data *old)
 
 int soft_c1_residency_display(int bic)
 {
-	if (!DO_BIC(BIC_CPU_c1) || use_c1_residency_msr)
+	if (!DO_BIC(BIC_CPU_c1) || platform->has_msr_core_c1_res)
 		return 0;
 
 	return DO_BIC_READ(bic);
@@ -1567,7 +2202,8 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d
 
 	old->c1 = new->c1 - old->c1;
 
-	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || soft_c1_residency_display(BIC_Avg_MHz)) {
+	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || DO_BIC(BIC_IPC)
+	    || soft_c1_residency_display(BIC_Avg_MHz)) {
 		if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) {
 			old->aperf = new->aperf - old->aperf;
 			old->mperf = new->mperf - old->mperf;
@@ -1576,7 +2212,7 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d
 		}
 	}
 
-	if (use_c1_residency_msr) {
+	if (platform->has_msr_core_c1_res) {
 		/*
 		 * Some models have a dedicated C1 residency MSR,
 		 * which should be more accurate than the derivation below.
@@ -1626,7 +2262,7 @@ int delta_cpu(struct thread_data *t, struct core_data *c,
 	int retval = 0;
 
 	/* calculate core delta only for 1st thread in core */
-	if (t->flags & CPU_IS_FIRST_THREAD_IN_CORE)
+	if (is_cpu_first_thread_in_core(t, c, p))
 		delta_core(c, c2);
 
 	/* always calculate thread delta */
@@ -1635,7 +2271,7 @@ int delta_cpu(struct thread_data *t, struct core_data *c,
 		return retval;
 
 	/* calculate package delta only for 1st core in package */
-	if (t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)
+	if (is_cpu_first_core_in_package(t, c, p))
 		retval = delta_package(p, p2);
 
 	return retval;
@@ -1663,9 +2299,6 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	t->irq_count = 0;
 	t->smi_count = 0;
 
-	/* tells format_counters to dump all fields from this set */
-	t->flags = CPU_IS_FIRST_THREAD_IN_CORE | CPU_IS_FIRST_CORE_IN_PACKAGE;
-
 	c->c3 = 0;
 	c->c6 = 0;
 	c->c7 = 0;
@@ -1749,7 +2382,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	}
 
 	/* sum per-core values only for 1st thread in core */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+	if (!is_cpu_first_thread_in_core(t, c, p))
 		return 0;
 
 	average.cores.c3 += c->c3;
@@ -1769,7 +2402,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	}
 
 	/* sum per-pkg values only for 1st core in pkg */
-	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_core_in_package(t, c, p))
 		return 0;
 
 	if (DO_BIC(BIC_Totl_c0))
@@ -1834,40 +2467,40 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data
 	/* Use the global time delta for the average. */
 	average.threads.tv_delta = tv_delta;
 
-	average.threads.tsc /= topo.num_cpus;
-	average.threads.aperf /= topo.num_cpus;
-	average.threads.mperf /= topo.num_cpus;
-	average.threads.instr_count /= topo.num_cpus;
-	average.threads.c1 /= topo.num_cpus;
+	average.threads.tsc /= topo.allowed_cpus;
+	average.threads.aperf /= topo.allowed_cpus;
+	average.threads.mperf /= topo.allowed_cpus;
+	average.threads.instr_count /= topo.allowed_cpus;
+	average.threads.c1 /= topo.allowed_cpus;
 
 	if (average.threads.irq_count > 9999999)
 		sums_need_wide_columns = 1;
 
-	average.cores.c3 /= topo.num_cores;
-	average.cores.c6 /= topo.num_cores;
-	average.cores.c7 /= topo.num_cores;
-	average.cores.mc6_us /= topo.num_cores;
+	average.cores.c3 /= topo.allowed_cores;
+	average.cores.c6 /= topo.allowed_cores;
+	average.cores.c7 /= topo.allowed_cores;
+	average.cores.mc6_us /= topo.allowed_cores;
 
 	if (DO_BIC(BIC_Totl_c0))
-		average.packages.pkg_wtd_core_c0 /= topo.num_packages;
+		average.packages.pkg_wtd_core_c0 /= topo.allowed_packages;
 	if (DO_BIC(BIC_Any_c0))
-		average.packages.pkg_any_core_c0 /= topo.num_packages;
+		average.packages.pkg_any_core_c0 /= topo.allowed_packages;
 	if (DO_BIC(BIC_GFX_c0))
-		average.packages.pkg_any_gfxe_c0 /= topo.num_packages;
+		average.packages.pkg_any_gfxe_c0 /= topo.allowed_packages;
 	if (DO_BIC(BIC_CPUGFX))
-		average.packages.pkg_both_core_gfxe_c0 /= topo.num_packages;
+		average.packages.pkg_both_core_gfxe_c0 /= topo.allowed_packages;
 
-	average.packages.pc2 /= topo.num_packages;
+	average.packages.pc2 /= topo.allowed_packages;
 	if (DO_BIC(BIC_Pkgpc3))
-		average.packages.pc3 /= topo.num_packages;
+		average.packages.pc3 /= topo.allowed_packages;
 	if (DO_BIC(BIC_Pkgpc6))
-		average.packages.pc6 /= topo.num_packages;
+		average.packages.pc6 /= topo.allowed_packages;
 	if (DO_BIC(BIC_Pkgpc7))
-		average.packages.pc7 /= topo.num_packages;
+		average.packages.pc7 /= topo.allowed_packages;
 
-	average.packages.pc8 /= topo.num_packages;
-	average.packages.pc9 /= topo.num_packages;
-	average.packages.pc10 /= topo.num_packages;
+	average.packages.pc8 /= topo.allowed_packages;
+	average.packages.pc9 /= topo.allowed_packages;
+	average.packages.pc10 /= topo.allowed_packages;
 
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
@@ -1877,7 +2510,7 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data
 				sums_need_wide_columns = 1;
 			continue;
 		}
-		average.threads.counter[i] /= topo.num_cpus;
+		average.threads.counter[i] /= topo.allowed_cpus;
 	}
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
@@ -1886,7 +2519,7 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data
 			if (average.cores.counter[i] > 9999999)
 				sums_need_wide_columns = 1;
 		}
-		average.cores.counter[i] /= topo.num_cores;
+		average.cores.counter[i] /= topo.allowed_cores;
 	}
 	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
@@ -1895,7 +2528,7 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data
 			if (average.packages.counter[i] > 9999999)
 				sums_need_wide_columns = 1;
 		}
-		average.packages.counter[i] /= topo.num_packages;
+		average.packages.counter[i] /= topo.allowed_packages;
 	}
 }
 
@@ -2092,7 +2725,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 retry:
 	t->tsc = rdtsc();	/* we are running on local CPU of interest */
 
-	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || soft_c1_residency_display(BIC_Avg_MHz)) {
+	if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || DO_BIC(BIC_IPC)
+	    || soft_c1_residency_display(BIC_Avg_MHz)) {
 		unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
 
 		/*
@@ -2158,7 +2792,7 @@ retry:
 			return -5;
 		t->smi_count = msr & 0xFFFFFFFF;
 	}
-	if (DO_BIC(BIC_CPU_c1) && use_c1_residency_msr) {
+	if (DO_BIC(BIC_CPU_c1) && platform->has_msr_core_c1_res) {
 		if (get_msr(cpu, MSR_CORE_C1_RES, &t->c1))
 			return -6;
 	}
@@ -2169,7 +2803,7 @@ retry:
 	}
 
 	/* collect core counters only for 1st thread in core */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
+	if (!is_cpu_first_thread_in_core(t, c, p))
 		goto done;
 
 	if (DO_BIC(BIC_CPU_c3) || soft_c1_residency_display(BIC_CPU_c3)) {
@@ -2177,10 +2811,10 @@ retry:
 			return -6;
 	}
 
-	if ((DO_BIC(BIC_CPU_c6) || soft_c1_residency_display(BIC_CPU_c6)) && !do_knl_cstates) {
+	if ((DO_BIC(BIC_CPU_c6) || soft_c1_residency_display(BIC_CPU_c6)) && !platform->has_msr_knl_core_c6_residency) {
 		if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6))
 			return -7;
-	} else if (do_knl_cstates || soft_c1_residency_display(BIC_CPU_c6)) {
+	} else if (platform->has_msr_knl_core_c6_residency && soft_c1_residency_display(BIC_CPU_c6)) {
 		if (get_msr(cpu, MSR_KNL_CORE_C6_RESIDENCY, &c->c6))
 			return -7;
 	}
@@ -2212,7 +2846,7 @@ retry:
 	if (DO_BIC(BIC_CORE_THROT_CNT))
 		get_core_throt_cnt(cpu, &c->core_throt_cnt);
 
-	if (do_rapl & RAPL_AMD_F17H) {
+	if (platform->rapl_msrs & RAPL_AMD_F17H) {
 		if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr))
 			return -14;
 		c->core_energy = msr & 0xFFFFFFFF;
@@ -2224,7 +2858,7 @@ retry:
 	}
 
 	/* collect package counters only for 1st core in package */
-	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_core_in_package(t, c, p))
 		goto done;
 
 	if (DO_BIC(BIC_Totl_c0)) {
@@ -2247,7 +2881,7 @@ retry:
 		if (get_msr(cpu, MSR_PKG_C3_RESIDENCY, &p->pc3))
 			return -9;
 	if (DO_BIC(BIC_Pkgpc6)) {
-		if (do_slm_cstates) {
+		if (platform->has_msr_atom_pkg_c6_residency) {
 			if (get_msr(cpu, MSR_ATOM_PKG_C6_RESIDENCY, &p->pc6))
 				return -10;
 		} else {
@@ -2277,37 +2911,37 @@ retry:
 	if (DO_BIC(BIC_SYS_LPI))
 		p->sys_lpi = cpuidle_cur_sys_lpi_us;
 
-	if (do_rapl & RAPL_PKG) {
+	if (platform->rapl_msrs & RAPL_PKG) {
 		if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr))
 			return -13;
 		p->energy_pkg = msr;
 	}
-	if (do_rapl & RAPL_CORES_ENERGY_STATUS) {
+	if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) {
 		if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr))
 			return -14;
 		p->energy_cores = msr;
 	}
-	if (do_rapl & RAPL_DRAM) {
+	if (platform->rapl_msrs & RAPL_DRAM) {
 		if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr))
 			return -15;
 		p->energy_dram = msr;
 	}
-	if (do_rapl & RAPL_GFX) {
+	if (platform->rapl_msrs & RAPL_GFX) {
 		if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr))
 			return -16;
 		p->energy_gfx = msr;
 	}
-	if (do_rapl & RAPL_PKG_PERF_STATUS) {
+	if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS) {
 		if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr))
 			return -16;
 		p->rapl_pkg_perf_status = msr;
 	}
-	if (do_rapl & RAPL_DRAM_PERF_STATUS) {
+	if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS) {
 		if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr))
 			return -16;
 		p->rapl_dram_perf_status = msr;
 	}
-	if (do_rapl & RAPL_AMD_F17H) {
+	if (platform->rapl_msrs & RAPL_AMD_F17H) {
 		if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr))
 			return -13;
 		p->energy_pkg = msr;
@@ -2414,18 +3048,58 @@ int icx_pkg_cstate_limits[16] =
 	PCLRSV, PCLRSV
 };
 
-static void calculate_tsc_tweak()
+void probe_cst_limit(void)
 {
-	tsc_tweak = base_hz / tsc_hz;
-}
+	unsigned long long msr;
+	int *pkg_cstate_limits;
+
+	if (!platform->has_nhm_msrs)
+		return;
+
+	switch (platform->cst_limit) {
+	case CST_LIMIT_NHM:
+		pkg_cstate_limits = nhm_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_SNB:
+		pkg_cstate_limits = snb_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_HSW:
+		pkg_cstate_limits = hsw_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_SKX:
+		pkg_cstate_limits = skx_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_ICX:
+		pkg_cstate_limits = icx_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_SLV:
+		pkg_cstate_limits = slv_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_AMT:
+		pkg_cstate_limits = amt_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_KNL:
+		pkg_cstate_limits = phi_pkg_cstate_limits;
+		break;
+	case CST_LIMIT_GMT:
+		pkg_cstate_limits = glm_pkg_cstate_limits;
+		break;
+	default:
+		return;
+	}
 
-void prewake_cstate_probe(unsigned int family, unsigned int model);
+	get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
+	pkg_cstate_limit = pkg_cstate_limits[msr & 0xF];
+}
 
-static void dump_nhm_platform_info(void)
+static void dump_platform_info(void)
 {
 	unsigned long long msr;
 	unsigned int ratio;
 
+	if (!platform->has_nhm_msrs)
+		return;
+
 	get_msr(base_cpu, MSR_PLATFORM_INFO, &msr);
 
 	fprintf(outf, "cpu%d: MSR_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr);
@@ -2435,19 +3109,27 @@ static void dump_nhm_platform_info(void)
 
 	ratio = (msr >> 8) & 0xFF;
 	fprintf(outf, "%d * %.1f = %.1f MHz base frequency\n", ratio, bclk, ratio * bclk);
+}
+
+static void dump_power_ctl(void)
+{
+	unsigned long long msr;
+
+	if (!platform->has_nhm_msrs)
+		return;
 
 	get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr);
 	fprintf(outf, "cpu%d: MSR_IA32_POWER_CTL: 0x%08llx (C1E auto-promotion: %sabled)\n",
 		base_cpu, msr, msr & 0x2 ? "EN" : "DIS");
 
 	/* C-state Pre-wake Disable (CSTATE_PREWAKE_DISABLE) */
-	if (dis_cstate_prewake)
+	if (platform->has_cst_prewake_bit)
 		fprintf(outf, "C-state Pre-wake: %sabled\n", msr & 0x40000000 ? "DIS" : "EN");
 
 	return;
 }
 
-static void dump_hsw_turbo_ratio_limits(void)
+static void dump_turbo_ratio_limit2(void)
 {
 	unsigned long long msr;
 	unsigned int ratio;
@@ -2466,7 +3148,7 @@ static void dump_hsw_turbo_ratio_limits(void)
 	return;
 }
 
-static void dump_ivt_turbo_ratio_limits(void)
+static void dump_turbo_ratio_limit1(void)
 {
 	unsigned long long msr;
 	unsigned int ratio;
@@ -2509,29 +3191,7 @@ static void dump_ivt_turbo_ratio_limits(void)
 	return;
 }
 
-int has_turbo_ratio_group_limits(int family, int model)
-{
-
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_SKYLAKE_X:
-	case INTEL_FAM6_ICELAKE_X:
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:
-	case INTEL_FAM6_ATOM_GOLDMONT_D:
-	case INTEL_FAM6_ATOM_TREMONT_D:
-		return 1;
-	default:
-		return 0;
-	}
-}
-
-static void dump_turbo_ratio_limits(int trl_msr_offset, int family, int model)
+static void dump_turbo_ratio_limits(int trl_msr_offset)
 {
 	unsigned long long msr, core_counts;
 	int shift;
@@ -2540,7 +3200,7 @@ static void dump_turbo_ratio_limits(int trl_msr_offset, int family, int model)
 	fprintf(outf, "cpu%d: MSR_%sTURBO_RATIO_LIMIT: 0x%08llx\n",
 		base_cpu, trl_msr_offset == MSR_SECONDARY_TURBO_RATIO_LIMIT ? "SECONDARY_" : "", msr);
 
-	if (has_turbo_ratio_group_limits(family, model)) {
+	if (platform->trl_msrs & TRL_CORECOUNT) {
 		get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &core_counts);
 		fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", base_cpu, core_counts);
 	} else {
@@ -2657,10 +3317,13 @@ static void dump_knl_turbo_ratio_limits(void)
 				ratio[i], bclk, ratio[i] * bclk, cores[i]);
 }
 
-static void dump_nhm_cst_cfg(void)
+static void dump_cst_cfg(void)
 {
 	unsigned long long msr;
 
+	if (!platform->has_nhm_msrs)
+		return;
+
 	get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
 
 	fprintf(outf, "cpu%d: MSR_PKG_CST_CONFIG_CONTROL: 0x%08llx", base_cpu, msr);
@@ -2673,7 +3336,7 @@ static void dump_nhm_cst_cfg(void)
 		(msr & (1 << 15)) ? "" : "UN", (unsigned int)msr & 0xF, pkg_cstate_limit_strings[pkg_cstate_limit]);
 
 #define AUTOMATIC_CSTATE_CONVERSION		(1UL << 16)
-	if (has_automatic_cstate_conversion) {
+	if (platform->has_cst_auto_convension) {
 		fprintf(outf, ", automatic c-state conversion=%s", (msr & AUTOMATIC_CSTATE_CONVERSION) ? "on" : "off");
 	}
 
@@ -2730,39 +3393,50 @@ void print_irtl(void)
 {
 	unsigned long long msr;
 
-	get_msr(base_cpu, MSR_PKGC3_IRTL, &msr);
-	fprintf(outf, "cpu%d: MSR_PKGC3_IRTL: 0x%08llx (", base_cpu, msr);
-	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
-		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
-
-	get_msr(base_cpu, MSR_PKGC6_IRTL, &msr);
-	fprintf(outf, "cpu%d: MSR_PKGC6_IRTL: 0x%08llx (", base_cpu, msr);
-	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
-		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	if (!platform->has_irtl_msrs)
+		return;
 
-	get_msr(base_cpu, MSR_PKGC7_IRTL, &msr);
-	fprintf(outf, "cpu%d: MSR_PKGC7_IRTL: 0x%08llx (", base_cpu, msr);
-	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
-		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	if (platform->supported_cstates & PC3) {
+		get_msr(base_cpu, MSR_PKGC3_IRTL, &msr);
+		fprintf(outf, "cpu%d: MSR_PKGC3_IRTL: 0x%08llx (", base_cpu, msr);
+		fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+			(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	}
 
-	if (!do_irtl_hsw)
-		return;
+	if (platform->supported_cstates & PC6) {
+		get_msr(base_cpu, MSR_PKGC6_IRTL, &msr);
+		fprintf(outf, "cpu%d: MSR_PKGC6_IRTL: 0x%08llx (", base_cpu, msr);
+		fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+			(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	}
 
-	get_msr(base_cpu, MSR_PKGC8_IRTL, &msr);
-	fprintf(outf, "cpu%d: MSR_PKGC8_IRTL: 0x%08llx (", base_cpu, msr);
-	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
-		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	if (platform->supported_cstates & PC7) {
+		get_msr(base_cpu, MSR_PKGC7_IRTL, &msr);
+		fprintf(outf, "cpu%d: MSR_PKGC7_IRTL: 0x%08llx (", base_cpu, msr);
+		fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+			(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	}
 
-	get_msr(base_cpu, MSR_PKGC9_IRTL, &msr);
-	fprintf(outf, "cpu%d: MSR_PKGC9_IRTL: 0x%08llx (", base_cpu, msr);
-	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
-		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	if (platform->supported_cstates & PC8) {
+		get_msr(base_cpu, MSR_PKGC8_IRTL, &msr);
+		fprintf(outf, "cpu%d: MSR_PKGC8_IRTL: 0x%08llx (", base_cpu, msr);
+		fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+			(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	}
 
-	get_msr(base_cpu, MSR_PKGC10_IRTL, &msr);
-	fprintf(outf, "cpu%d: MSR_PKGC10_IRTL: 0x%08llx (", base_cpu, msr);
-	fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
-		(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	if (platform->supported_cstates & PC9) {
+		get_msr(base_cpu, MSR_PKGC9_IRTL, &msr);
+		fprintf(outf, "cpu%d: MSR_PKGC9_IRTL: 0x%08llx (", base_cpu, msr);
+		fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+			(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	}
 
+	if (platform->supported_cstates & PC10) {
+		get_msr(base_cpu, MSR_PKGC10_IRTL, &msr);
+		fprintf(outf, "cpu%d: MSR_PKGC10_IRTL: 0x%08llx (", base_cpu, msr);
+		fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+			(msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+	}
 }
 
 void free_fd_percpu(void)
@@ -2785,6 +3459,14 @@ void free_all_buffers(void)
 	cpu_present_set = NULL;
 	cpu_present_setsize = 0;
 
+	CPU_FREE(cpu_effective_set);
+	cpu_effective_set = NULL;
+	cpu_effective_setsize = 0;
+
+	CPU_FREE(cpu_allowed_set);
+	cpu_allowed_set = NULL;
+	cpu_allowed_setsize = 0;
+
 	CPU_FREE(cpu_affinity_set);
 	cpu_affinity_set = NULL;
 	cpu_affinity_setsize = 0;
@@ -2927,6 +3609,59 @@ int get_physical_node_id(struct cpu_topology *thiscpu)
 	return -1;
 }
 
+static int parse_cpu_str(char *cpu_str, cpu_set_t *cpu_set, int cpu_set_size)
+{
+	unsigned int start, end;
+	char *next = cpu_str;
+
+	while (next && *next) {
+
+		if (*next == '-')	/* no negative cpu numbers */
+			return 1;
+
+		start = strtoul(next, &next, 10);
+
+		if (start >= CPU_SUBSET_MAXCPUS)
+			return 1;
+		CPU_SET_S(start, cpu_set_size, cpu_set);
+
+		if (*next == '\0' || *next == '\n')
+			break;
+
+		if (*next == ',') {
+			next += 1;
+			continue;
+		}
+
+		if (*next == '-') {
+			next += 1;	/* start range */
+		} else if (*next == '.') {
+			next += 1;
+			if (*next == '.')
+				next += 1;	/* start range */
+			else
+				return 1;
+		}
+
+		end = strtoul(next, &next, 10);
+		if (end <= start)
+			return 1;
+
+		while (++start <= end) {
+			if (start >= CPU_SUBSET_MAXCPUS)
+				return 1;
+			CPU_SET_S(start, cpu_set_size, cpu_set);
+		}
+
+		if (*next == ',')
+			next += 1;
+		else if (*next != '\0' && *next != '\n')
+			return 1;
+	}
+
+	return 0;
+}
+
 int get_thread_siblings(struct cpu_topology *thiscpu)
 {
 	char path[80], character;
@@ -2998,7 +3733,7 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *,
 
 					t = GET_THREAD(thread_base, thread_no, core_no, node_no, pkg_no);
 
-					if (cpu_is_not_present(t->cpu_id))
+					if (cpu_is_not_allowed(t->cpu_id))
 						continue;
 
 					t2 = GET_THREAD(thread_base2, thread_no, core_no, node_no, pkg_no);
@@ -3050,11 +3785,51 @@ int for_all_proc_cpus(int (func) (int))
 	return 0;
 }
 
+#define PATH_EFFECTIVE_CPUS	"/sys/fs/cgroup/cpuset.cpus.effective"
+
+static char cpu_effective_str[1024];
+
+static int update_effective_str(bool startup)
+{
+	FILE *fp;
+	char *pos;
+	char buf[1024];
+	int ret;
+
+	if (cpu_effective_str[0] == '\0' && !startup)
+		return 0;
+
+	fp = fopen(PATH_EFFECTIVE_CPUS, "r");
+	if (!fp)
+		return 0;
+
+	pos = fgets(buf, 1024, fp);
+	if (!pos)
+		err(1, "%s: file read failed\n", PATH_EFFECTIVE_CPUS);
+
+	fclose(fp);
+
+	ret = strncmp(cpu_effective_str, buf, 1024);
+	if (!ret)
+		return 0;
+
+	strncpy(cpu_effective_str, buf, 1024);
+	return 1;
+}
+
+static void update_effective_set(bool startup)
+{
+	update_effective_str(startup);
+
+	if (parse_cpu_str(cpu_effective_str, cpu_effective_set, cpu_effective_setsize))
+		err(1, "%s: cpu str malformat %s\n", PATH_EFFECTIVE_CPUS, cpu_effective_str);
+}
+
 void re_initialize(void)
 {
 	free_all_buffers();
-	setup_all_buffers();
-	fprintf(outf, "turbostat: re-initialized with num_cpus %d\n", topo.num_cpus);
+	setup_all_buffers(false);
+	fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus, topo.allowed_cpus);
 }
 
 void set_max_cpu_num(void)
@@ -3191,8 +3966,8 @@ int snapshot_gfx_rc6_ms(void)
 /*
  * snapshot_gfx_mhz()
  *
- * record snapshot of
- * /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz
+ * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz
+ * when /sys/class/drm/card0/gt_cur_freq_mhz is not available.
  *
  * return 1 if config change requires a restart, else return 0
  */
@@ -3201,9 +3976,11 @@ int snapshot_gfx_mhz(void)
 	static FILE *fp;
 	int retval;
 
-	if (fp == NULL)
-		fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r");
-	else {
+	if (fp == NULL) {
+		fp = fopen("/sys/class/drm/card0/gt_cur_freq_mhz", "r");
+		if (!fp)
+			fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r");
+	} else {
 		rewind(fp);
 		fflush(fp);
 	}
@@ -3218,8 +3995,8 @@ int snapshot_gfx_mhz(void)
 /*
  * snapshot_gfx_cur_mhz()
  *
- * record snapshot of
- * /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz
+ * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz
+ * when /sys/class/drm/card0/gt_act_freq_mhz is not available.
  *
  * return 1 if config change requires a restart, else return 0
  */
@@ -3228,9 +4005,11 @@ int snapshot_gfx_act_mhz(void)
 	static FILE *fp;
 	int retval;
 
-	if (fp == NULL)
-		fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r");
-	else {
+	if (fp == NULL) {
+		fp = fopen("/sys/class/drm/card0/gt_act_freq_mhz", "r");
+		if (!fp)
+			fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r");
+	} else {
 		rewind(fp);
 		fflush(fp);
 	}
@@ -3562,6 +4341,10 @@ restart:
 			re_initialize();
 			goto restart;
 		}
+		if (update_effective_str(false)) {
+			re_initialize();
+			goto restart;
+		}
 		do_sleep();
 		if (snapshot_proc_sysfs_files())
 			goto restart;
@@ -3674,395 +4457,31 @@ void check_permissions(void)
 		exit(-6);
 }
 
-/*
- * NHM adds support for additional MSRs:
- *
- * MSR_SMI_COUNT                   0x00000034
- *
- * MSR_PLATFORM_INFO               0x000000ce
- * MSR_PKG_CST_CONFIG_CONTROL     0x000000e2
- *
- * MSR_MISC_PWR_MGMT               0x000001aa
- *
- * MSR_PKG_C3_RESIDENCY            0x000003f8
- * MSR_PKG_C6_RESIDENCY            0x000003f9
- * MSR_CORE_C3_RESIDENCY           0x000003fc
- * MSR_CORE_C6_RESIDENCY           0x000003fd
- *
- * Side effect:
- * sets global pkg_cstate_limit to decode MSR_PKG_CST_CONFIG_CONTROL
- * sets has_misc_feature_control
- */
-int probe_nhm_msrs(unsigned int family, unsigned int model)
+void probe_bclk(void)
 {
 	unsigned long long msr;
 	unsigned int base_ratio;
-	int *pkg_cstate_limits;
 
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	bclk = discover_bclk(family, model);
+	if (!platform->has_nhm_msrs)
+		return;
 
-	switch (model) {
-	case INTEL_FAM6_NEHALEM:	/* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */
-	case INTEL_FAM6_NEHALEM_EX:	/* Nehalem-EX Xeon - Beckton */
-		pkg_cstate_limits = nhm_pkg_cstate_limits;
-		break;
-	case INTEL_FAM6_SANDYBRIDGE:	/* SNB */
-	case INTEL_FAM6_SANDYBRIDGE_X:	/* SNB Xeon */
-	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
-	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
-		pkg_cstate_limits = snb_pkg_cstate_limits;
-		has_misc_feature_control = 1;
-		break;
-	case INTEL_FAM6_HASWELL:	/* HSW */
-	case INTEL_FAM6_HASWELL_G:	/* HSW */
-	case INTEL_FAM6_HASWELL_X:	/* HSX */
-	case INTEL_FAM6_HASWELL_L:	/* HSW */
-	case INTEL_FAM6_BROADWELL:	/* BDW */
-	case INTEL_FAM6_BROADWELL_G:	/* BDW */
-	case INTEL_FAM6_BROADWELL_X:	/* BDX */
-	case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-		pkg_cstate_limits = hsw_pkg_cstate_limits;
-		has_misc_feature_control = 1;
-		break;
-	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:	/* SPR */
-		pkg_cstate_limits = skx_pkg_cstate_limits;
-		has_misc_feature_control = 1;
-		break;
-	case INTEL_FAM6_ICELAKE_X:	/* ICX */
-		pkg_cstate_limits = icx_pkg_cstate_limits;
-		has_misc_feature_control = 1;
-		break;
-	case INTEL_FAM6_ATOM_SILVERMONT:	/* BYT */
-		no_MSR_MISC_PWR_MGMT = 1;
-		/* FALLTHRU */
-	case INTEL_FAM6_ATOM_SILVERMONT_D:	/* AVN */
-		pkg_cstate_limits = slv_pkg_cstate_limits;
-		break;
-	case INTEL_FAM6_ATOM_AIRMONT:	/* AMT */
-		pkg_cstate_limits = amt_pkg_cstate_limits;
-		no_MSR_MISC_PWR_MGMT = 1;
-		break;
-	case INTEL_FAM6_XEON_PHI_KNL:	/* PHI */
-		pkg_cstate_limits = phi_pkg_cstate_limits;
-		break;
-	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
-	case INTEL_FAM6_ATOM_GOLDMONT_D:	/* DNV */
-	case INTEL_FAM6_ATOM_TREMONT:	/* EHL */
-	case INTEL_FAM6_ATOM_TREMONT_D:	/* JVL */
-		pkg_cstate_limits = glm_pkg_cstate_limits;
-		break;
-	default:
-		return 0;
-	}
-	get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
-	pkg_cstate_limit = pkg_cstate_limits[msr & 0xF];
+	if (platform->bclk_freq == BCLK_100MHZ)
+		bclk = 100.00;
+	else if (platform->bclk_freq == BCLK_133MHZ)
+		bclk = 133.33;
+	else if (platform->bclk_freq == BCLK_SLV)
+		bclk = slm_bclk();
+	else
+		return;
 
 	get_msr(base_cpu, MSR_PLATFORM_INFO, &msr);
 	base_ratio = (msr >> 8) & 0xFF;
 
 	base_hz = base_ratio * bclk * 1000000;
 	has_base_hz = 1;
-	return 1;
-}
-
-/*
- * SLV client has support for unique MSRs:
- *
- * MSR_CC6_DEMOTION_POLICY_CONFIG
- * MSR_MC6_DEMOTION_POLICY_CONFIG
- */
-
-int has_slv_msrs(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_SILVERMONT:
-	case INTEL_FAM6_ATOM_SILVERMONT_MID:
-	case INTEL_FAM6_ATOM_AIRMONT_MID:
-		return 1;
-	}
-	return 0;
-}
-
-int is_dnv(unsigned int family, unsigned int model)
-{
-
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_GOLDMONT_D:
-		return 1;
-	}
-	return 0;
-}
-
-int is_bdx(unsigned int family, unsigned int model)
-{
-
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_BROADWELL_X:
-		return 1;
-	}
-	return 0;
-}
-
-int is_skx(unsigned int family, unsigned int model)
-{
-
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_SKYLAKE_X:
-		return 1;
-	}
-	return 0;
-}
-
-int is_icx(unsigned int family, unsigned int model)
-{
-
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ICELAKE_X:
-		return 1;
-	}
-	return 0;
-}
-
-int is_spr(unsigned int family, unsigned int model)
-{
-
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:
-		return 1;
-	}
-	return 0;
-}
-
-int is_ehl(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_TREMONT:
-		return 1;
-	}
-	return 0;
-}
-
-int is_jvl(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_TREMONT_D:
-		return 1;
-	}
-	return 0;
-}
-
-int has_turbo_ratio_limit(unsigned int family, unsigned int model)
-{
-	if (has_slv_msrs(family, model))
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-		/* Nehalem compatible, but do not include turbo-ratio limit support */
-	case INTEL_FAM6_NEHALEM_EX:	/* Nehalem-EX Xeon - Beckton */
-	case INTEL_FAM6_XEON_PHI_KNL:	/* PHI - Knights Landing (different MSR definition) */
-		return 0;
-	default:
-		return 1;
-	}
-}
-
-int has_atom_turbo_ratio_limit(unsigned int family, unsigned int model)
-{
-	if (has_slv_msrs(family, model))
-		return 1;
-
-	return 0;
-}
-
-int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
 
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
-	case INTEL_FAM6_HASWELL_X:	/* HSW Xeon */
-		return 1;
-	default:
-		return 0;
-	}
-}
-
-int has_hsw_turbo_ratio_limit(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_HASWELL_X:	/* HSW Xeon */
-		return 1;
-	default:
-		return 0;
-	}
-}
-
-int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_XEON_PHI_KNL:	/* Knights Landing */
-		return 1;
-	default:
-		return 0;
-	}
-}
-
-int has_glm_turbo_ratio_limit(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_SKYLAKE_X:
-	case INTEL_FAM6_ICELAKE_X:
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:
-		return 1;
-	default:
-		return 0;
-	}
-}
-
-int has_config_tdp(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
-	case INTEL_FAM6_HASWELL:	/* HSW */
-	case INTEL_FAM6_HASWELL_X:	/* HSX */
-	case INTEL_FAM6_HASWELL_L:	/* HSW */
-	case INTEL_FAM6_HASWELL_G:	/* HSW */
-	case INTEL_FAM6_BROADWELL:	/* BDW */
-	case INTEL_FAM6_BROADWELL_G:	/* BDW */
-	case INTEL_FAM6_BROADWELL_X:	/* BDX */
-	case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
-	case INTEL_FAM6_ICELAKE_X:	/* ICX */
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:	/* SPR */
-	case INTEL_FAM6_XEON_PHI_KNL:	/* Knights Landing */
-		return 1;
-	default:
-		return 0;
-	}
-}
-
-/*
- * tcc_offset_bits:
- * 0: Tcc Offset not supported (Default)
- * 6: Bit 29:24 of MSR_PLATFORM_INFO
- * 4: Bit 27:24 of MSR_PLATFORM_INFO
- */
-void check_tcc_offset(int model)
-{
-	unsigned long long msr;
-
-	if (!genuine_intel)
-		return;
-
-	switch (model) {
-	case INTEL_FAM6_SKYLAKE_L:
-	case INTEL_FAM6_SKYLAKE:
-	case INTEL_FAM6_KABYLAKE_L:
-	case INTEL_FAM6_KABYLAKE:
-	case INTEL_FAM6_ICELAKE_L:
-	case INTEL_FAM6_ICELAKE:
-	case INTEL_FAM6_TIGERLAKE_L:
-	case INTEL_FAM6_TIGERLAKE:
-	case INTEL_FAM6_COMETLAKE:
-		if (!get_msr(base_cpu, MSR_PLATFORM_INFO, &msr)) {
-			msr = (msr >> 30) & 1;
-			if (msr)
-				tcc_offset_bits = 6;
-		}
-		return;
-	default:
-		return;
-	}
+	if (platform->enable_tsc_tweak)
+		tsc_tweak = base_hz / tsc_hz;
 }
 
 static void remove_underbar(char *s)
@@ -4078,44 +4497,37 @@ static void remove_underbar(char *s)
 	*to = 0;
 }
 
-static void dump_turbo_ratio_info(unsigned int family, unsigned int model)
+static void dump_turbo_ratio_info(void)
 {
 	if (!has_turbo)
 		return;
 
-	if (has_hsw_turbo_ratio_limit(family, model))
-		dump_hsw_turbo_ratio_limits();
+	if (!platform->has_nhm_msrs)
+		return;
+
+	if (platform->trl_msrs & TRL_LIMIT2)
+		dump_turbo_ratio_limit2();
 
-	if (has_ivt_turbo_ratio_limit(family, model))
-		dump_ivt_turbo_ratio_limits();
+	if (platform->trl_msrs & TRL_LIMIT1)
+		dump_turbo_ratio_limit1();
 
-	if (has_turbo_ratio_limit(family, model)) {
-		dump_turbo_ratio_limits(MSR_TURBO_RATIO_LIMIT, family, model);
+	if (platform->trl_msrs & TRL_BASE) {
+		dump_turbo_ratio_limits(MSR_TURBO_RATIO_LIMIT);
 
 		if (is_hybrid)
-			dump_turbo_ratio_limits(MSR_SECONDARY_TURBO_RATIO_LIMIT, family, model);
+			dump_turbo_ratio_limits(MSR_SECONDARY_TURBO_RATIO_LIMIT);
 	}
 
-	if (has_atom_turbo_ratio_limit(family, model))
+	if (platform->trl_msrs & TRL_ATOM)
 		dump_atom_turbo_ratio_limits();
 
-	if (has_knl_turbo_ratio_limit(family, model))
+	if (platform->trl_msrs & TRL_KNL)
 		dump_knl_turbo_ratio_limits();
 
-	if (has_config_tdp(family, model))
+	if (platform->has_config_tdp)
 		dump_config_tdp();
 }
 
-static void dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
-{
-	if (!do_nhm_platform_info)
-		return;
-
-	dump_nhm_platform_info();
-	dump_turbo_ratio_info(family, model);
-	dump_nhm_cst_cfg();
-}
-
 static int read_sysfs_int(char *path)
 {
 	FILE *input;
@@ -4152,7 +4564,7 @@ static void dump_sysfs_file(char *path)
 	fprintf(outf, "%s: %s", strrchr(path, '/') + 1, cpuidle_buf);
 }
 
-static void intel_uncore_frequency_probe(void)
+static void probe_intel_uncore_frequency(void)
 {
 	int i, j;
 	char path[128];
@@ -4163,6 +4575,10 @@ static void intel_uncore_frequency_probe(void)
 	if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00", R_OK))
 		return;
 
+	/* Cluster level sysfs not supported yet. */
+	if (!access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00", R_OK))
+		return;
+
 	if (!access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK))
 		BIC_PRESENT(BIC_UNCORE_MHZ);
 
@@ -4194,6 +4610,20 @@ static void intel_uncore_frequency_probe(void)
 	}
 }
 
+static void probe_graphics(void)
+{
+	if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK))
+		BIC_PRESENT(BIC_GFX_rc6);
+
+	if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK) ||
+	    !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
+		BIC_PRESENT(BIC_GFXMHz);
+
+	if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK) ||
+	    !access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK))
+		BIC_PRESENT(BIC_GFXACTMHz);
+}
+
 static void dump_sysfs_cstate_config(void)
 {
 	char path[64];
@@ -4310,7 +4740,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	cpu = t->cpu_id;
 
 	/* EPB is per-package */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_thread_in_package(t, c, p))
 		return 0;
 
 	if (cpu_migrate(cpu)) {
@@ -4359,7 +4789,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	cpu = t->cpu_id;
 
 	/* MSR_HWP_CAPABILITIES is per-package */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_thread_in_package(t, c, p))
 		return 0;
 
 	if (cpu_migrate(cpu)) {
@@ -4442,7 +4872,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 	cpu = t->cpu_id;
 
 	/* per-package */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_thread_in_package(t, c, p))
 		return 0;
 
 	if (cpu_migrate(cpu)) {
@@ -4450,7 +4880,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 		return -1;
 	}
 
-	if (do_core_perf_limit_reasons) {
+	if (platform->plr_msrs & PLR_CORE) {
 		get_msr(cpu, MSR_CORE_PERF_LIMIT_REASONS, &msr);
 		fprintf(outf, "cpu%d: MSR_CORE_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
 		fprintf(outf, " (Active: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)",
@@ -4483,7 +4913,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 			(msr & 1 << 17) ? "ThermStatus, " : "", (msr & 1 << 16) ? "PROCHOT, " : "");
 
 	}
-	if (do_gfx_perf_limit_reasons) {
+	if (platform->plr_msrs & PLR_GFX) {
 		get_msr(cpu, MSR_GFX_PERF_LIMIT_REASONS, &msr);
 		fprintf(outf, "cpu%d: MSR_GFX_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
 		fprintf(outf, " (Active: %s%s%s%s%s%s%s%s)",
@@ -4503,7 +4933,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 			(msr & 1 << 25) ? "GFXPwr, " : "",
 			(msr & 1 << 26) ? "PkgPwrL1, " : "", (msr & 1 << 27) ? "PkgPwrL2, " : "");
 	}
-	if (do_ring_perf_limit_reasons) {
+	if (platform->plr_msrs & PLR_RING) {
 		get_msr(cpu, MSR_RING_PERF_LIMIT_REASONS, &msr);
 		fprintf(outf, "cpu%d: MSR_RING_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
 		fprintf(outf, " (Active: %s%s%s%s%s%s)",
@@ -4525,208 +4955,74 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 #define	RAPL_POWER_GRANULARITY	0x7FFF	/* 15 bit power granularity */
 #define	RAPL_TIME_GRANULARITY	0x3F	/* 6 bit time granularity */
 
-double get_tdp_intel(unsigned int model)
+double get_quirk_tdp(void)
 {
-	unsigned long long msr;
+	if (platform->rapl_quirk_tdp)
+		return platform->rapl_quirk_tdp;
 
-	if (do_rapl & RAPL_PKG_POWER_INFO)
-		if (!get_msr(base_cpu, MSR_PKG_POWER_INFO, &msr))
-			return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_SILVERMONT:
-	case INTEL_FAM6_ATOM_SILVERMONT_D:
-		return 30.0;
-	default:
-		return 135.0;
-	}
+	return 135.0;
 }
 
-double get_tdp_amd(unsigned int family)
+double get_tdp_intel(void)
 {
-	UNUSED(family);
+	unsigned long long msr;
 
-	/* This is the max stock TDP of HEDT/Server Fam17h+ chips */
-	return 280.0;
+	if (platform->rapl_msrs & RAPL_PKG_POWER_INFO)
+		if (!get_msr(base_cpu, MSR_PKG_POWER_INFO, &msr))
+			return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units;
+	return get_quirk_tdp();
 }
 
-/*
- * rapl_dram_energy_units_probe()
- * Energy units are either hard-coded, or come from RAPL Energy Unit MSR.
- */
-static double rapl_dram_energy_units_probe(int model, double rapl_energy_units)
+double get_tdp_amd(void)
 {
-	/* only called for genuine_intel, family 6 */
-
-	switch (model) {
-	case INTEL_FAM6_HASWELL_X:	/* HSX */
-	case INTEL_FAM6_BROADWELL_X:	/* BDX */
-	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
-	case INTEL_FAM6_XEON_PHI_KNL:	/* KNL */
-	case INTEL_FAM6_ICELAKE_X:	/* ICX */
-		return (rapl_dram_energy_units = 15.3 / 1000000);
-	default:
-		return (rapl_energy_units);
-	}
+	return get_quirk_tdp();
 }
 
-void rapl_probe_intel(unsigned int family, unsigned int model)
+void rapl_probe_intel(void)
 {
 	unsigned long long msr;
 	unsigned int time_unit;
 	double tdp;
 
-	if (family != 6)
-		return;
-
-	switch (model) {
-	case INTEL_FAM6_SANDYBRIDGE:
-	case INTEL_FAM6_IVYBRIDGE:
-	case INTEL_FAM6_HASWELL:	/* HSW */
-	case INTEL_FAM6_HASWELL_L:	/* HSW */
-	case INTEL_FAM6_HASWELL_G:	/* HSW */
-	case INTEL_FAM6_BROADWELL:	/* BDW */
-	case INTEL_FAM6_BROADWELL_G:	/* BDW */
-		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO;
-		if (rapl_joules) {
-			BIC_PRESENT(BIC_Pkg_J);
-			BIC_PRESENT(BIC_Cor_J);
-			BIC_PRESENT(BIC_GFX_J);
-		} else {
-			BIC_PRESENT(BIC_PkgWatt);
-			BIC_PRESENT(BIC_CorWatt);
-			BIC_PRESENT(BIC_GFXWatt);
-		}
-		break;
-	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
-		do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO;
-		if (rapl_joules)
-			BIC_PRESENT(BIC_Pkg_J);
-		else
-			BIC_PRESENT(BIC_PkgWatt);
-		break;
-	case INTEL_FAM6_ATOM_TREMONT:	/* EHL */
-		do_rapl =
-		    RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS
-		    | RAPL_GFX | RAPL_PKG_POWER_INFO;
-		if (rapl_joules) {
-			BIC_PRESENT(BIC_Pkg_J);
-			BIC_PRESENT(BIC_Cor_J);
-			BIC_PRESENT(BIC_RAM_J);
-			BIC_PRESENT(BIC_GFX_J);
-		} else {
-			BIC_PRESENT(BIC_PkgWatt);
-			BIC_PRESENT(BIC_CorWatt);
-			BIC_PRESENT(BIC_RAMWatt);
-			BIC_PRESENT(BIC_GFXWatt);
-		}
-		break;
-	case INTEL_FAM6_ATOM_TREMONT_D:	/* JVL */
-		do_rapl = RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
-		BIC_PRESENT(BIC_PKG__);
-		if (rapl_joules)
-			BIC_PRESENT(BIC_Pkg_J);
-		else
-			BIC_PRESENT(BIC_PkgWatt);
-		break;
-	case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-		do_rapl =
-		    RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS
-		    | RAPL_GFX | RAPL_PKG_POWER_INFO;
-		BIC_PRESENT(BIC_PKG__);
-		BIC_PRESENT(BIC_RAM__);
-		if (rapl_joules) {
+	if (rapl_joules) {
+		if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS)
 			BIC_PRESENT(BIC_Pkg_J);
+		if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS)
 			BIC_PRESENT(BIC_Cor_J);
+		if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS)
 			BIC_PRESENT(BIC_RAM_J);
+		if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS)
 			BIC_PRESENT(BIC_GFX_J);
-		} else {
+	} else {
+		if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS)
 			BIC_PRESENT(BIC_PkgWatt);
+		if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS)
 			BIC_PRESENT(BIC_CorWatt);
+		if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS)
 			BIC_PRESENT(BIC_RAMWatt);
+		if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS)
 			BIC_PRESENT(BIC_GFXWatt);
-		}
-		break;
-	case INTEL_FAM6_HASWELL_X:	/* HSX */
-	case INTEL_FAM6_BROADWELL_X:	/* BDX */
-	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
-	case INTEL_FAM6_ICELAKE_X:	/* ICX */
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:	/* SPR */
-	case INTEL_FAM6_XEON_PHI_KNL:	/* KNL */
-		do_rapl =
-		    RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS |
-		    RAPL_PKG_POWER_INFO;
-		BIC_PRESENT(BIC_PKG__);
-		BIC_PRESENT(BIC_RAM__);
-		if (rapl_joules) {
-			BIC_PRESENT(BIC_Pkg_J);
-			BIC_PRESENT(BIC_RAM_J);
-		} else {
-			BIC_PRESENT(BIC_PkgWatt);
-			BIC_PRESENT(BIC_RAMWatt);
-		}
-		break;
-	case INTEL_FAM6_SANDYBRIDGE_X:
-	case INTEL_FAM6_IVYBRIDGE_X:
-		do_rapl =
-		    RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_PKG_PERF_STATUS |
-		    RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO;
-		BIC_PRESENT(BIC_PKG__);
-		BIC_PRESENT(BIC_RAM__);
-		if (rapl_joules) {
-			BIC_PRESENT(BIC_Pkg_J);
-			BIC_PRESENT(BIC_Cor_J);
-			BIC_PRESENT(BIC_RAM_J);
-		} else {
-			BIC_PRESENT(BIC_PkgWatt);
-			BIC_PRESENT(BIC_CorWatt);
-			BIC_PRESENT(BIC_RAMWatt);
-		}
-		break;
-	case INTEL_FAM6_ATOM_SILVERMONT:	/* BYT */
-	case INTEL_FAM6_ATOM_SILVERMONT_D:	/* AVN */
-		do_rapl = RAPL_PKG | RAPL_CORES;
-		if (rapl_joules) {
-			BIC_PRESENT(BIC_Pkg_J);
-			BIC_PRESENT(BIC_Cor_J);
-		} else {
-			BIC_PRESENT(BIC_PkgWatt);
-			BIC_PRESENT(BIC_CorWatt);
-		}
-		break;
-	case INTEL_FAM6_ATOM_GOLDMONT_D:	/* DNV */
-		do_rapl =
-		    RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS |
-		    RAPL_PKG_POWER_INFO | RAPL_CORES_ENERGY_STATUS;
+	}
+
+	if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS)
 		BIC_PRESENT(BIC_PKG__);
+	if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS)
 		BIC_PRESENT(BIC_RAM__);
-		if (rapl_joules) {
-			BIC_PRESENT(BIC_Pkg_J);
-			BIC_PRESENT(BIC_Cor_J);
-			BIC_PRESENT(BIC_RAM_J);
-		} else {
-			BIC_PRESENT(BIC_PkgWatt);
-			BIC_PRESENT(BIC_CorWatt);
-			BIC_PRESENT(BIC_RAMWatt);
-		}
-		break;
-	default:
-		return;
-	}
 
 	/* units on package 0, verify later other packages match */
 	if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr))
 		return;
 
 	rapl_power_units = 1.0 / (1 << (msr & 0xF));
-	if (model == INTEL_FAM6_ATOM_SILVERMONT)
+	if (platform->has_rapl_divisor)
 		rapl_energy_units = 1.0 * (1 << (msr >> 8 & 0x1F)) / 1000000;
 	else
 		rapl_energy_units = 1.0 / (1 << (msr >> 8 & 0x1F));
 
-	rapl_dram_energy_units = rapl_dram_energy_units_probe(model, rapl_energy_units);
+	if (platform->has_fixed_rapl_unit)
+		rapl_dram_energy_units = (15.3 / 1000000);
+	else
+		rapl_dram_energy_units = rapl_energy_units;
 
 	time_unit = msr >> 16 & 0xF;
 	if (time_unit == 0)
@@ -4734,32 +5030,18 @@ void rapl_probe_intel(unsigned int family, unsigned int model)
 
 	rapl_time_units = 1.0 / (1 << (time_unit));
 
-	tdp = get_tdp_intel(model);
+	tdp = get_tdp_intel();
 
 	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
 	if (!quiet)
 		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
 }
 
-void rapl_probe_amd(unsigned int family, unsigned int model)
+void rapl_probe_amd(void)
 {
 	unsigned long long msr;
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int has_rapl = 0;
 	double tdp;
 
-	UNUSED(model);
-
-	if (max_extended_level >= 0x80000007) {
-		__cpuid(0x80000007, eax, ebx, ecx, edx);
-		/* RAPL (Fam 17h+) */
-		has_rapl = edx & (1 << 14);
-	}
-
-	if (!has_rapl || family < 0x17)
-		return;
-
-	do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
 	if (rapl_joules) {
 		BIC_PRESENT(BIC_Pkg_J);
 		BIC_PRESENT(BIC_Cor_J);
@@ -4775,128 +5057,13 @@ void rapl_probe_amd(unsigned int family, unsigned int model)
 	rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f));
 	rapl_power_units = ldexp(1.0, -(msr & 0xf));
 
-	tdp = get_tdp_amd(family);
+	tdp = get_tdp_amd();
 
 	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
 	if (!quiet)
 		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
 }
 
-/*
- * rapl_probe()
- *
- * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units
- */
-void rapl_probe(unsigned int family, unsigned int model)
-{
-	if (genuine_intel)
-		rapl_probe_intel(family, model);
-	if (authentic_amd || hygon_genuine)
-		rapl_probe_amd(family, model);
-}
-
-void perf_limit_reasons_probe(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return;
-
-	if (family != 6)
-		return;
-
-	switch (model) {
-	case INTEL_FAM6_HASWELL:	/* HSW */
-	case INTEL_FAM6_HASWELL_L:	/* HSW */
-	case INTEL_FAM6_HASWELL_G:	/* HSW */
-		do_gfx_perf_limit_reasons = 1;
-		/* FALLTHRU */
-	case INTEL_FAM6_HASWELL_X:	/* HSX */
-		do_core_perf_limit_reasons = 1;
-		do_ring_perf_limit_reasons = 1;
-	default:
-		return;
-	}
-}
-
-void automatic_cstate_conversion_probe(unsigned int family, unsigned int model)
-{
-	if (family != 6)
-		return;
-
-	switch (model) {
-	case INTEL_FAM6_BROADWELL_X:
-	case INTEL_FAM6_SKYLAKE_X:
-		has_automatic_cstate_conversion = 1;
-	}
-}
-
-void prewake_cstate_probe(unsigned int family, unsigned int model)
-{
-	if (is_icx(family, model) || is_spr(family, model))
-		dis_cstate_prewake = 1;
-}
-
-int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p)
-{
-	unsigned long long msr;
-	unsigned int dts, dts2;
-	int cpu;
-
-	UNUSED(c);
-	UNUSED(p);
-
-	if (!(do_dts || do_ptm))
-		return 0;
-
-	cpu = t->cpu_id;
-
-	/* DTS is per-core, no need to print for each thread */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
-		return 0;
-
-	if (cpu_migrate(cpu)) {
-		fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu);
-		return -1;
-	}
-
-	if (do_ptm && (t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) {
-		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
-			return 0;
-
-		dts = (msr >> 16) & 0x7F;
-		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n", cpu, msr, tj_max - dts);
-
-		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &msr))
-			return 0;
-
-		dts = (msr >> 16) & 0x7F;
-		dts2 = (msr >> 8) & 0x7F;
-		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
-			cpu, msr, tj_max - dts, tj_max - dts2);
-	}
-
-	if (do_dts && debug) {
-		unsigned int resolution;
-
-		if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr))
-			return 0;
-
-		dts = (msr >> 16) & 0x7F;
-		resolution = (msr >> 27) & 0xF;
-		fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n",
-			cpu, msr, tj_max - dts, resolution);
-
-		if (get_msr(cpu, MSR_IA32_THERM_INTERRUPT, &msr))
-			return 0;
-
-		dts = (msr >> 16) & 0x7F;
-		dts2 = (msr >> 8) & 0x7F;
-		fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
-			cpu, msr, tj_max - dts, tj_max - dts2);
-	}
-
-	return 0;
-}
-
 void print_power_limit_msr(int cpu, unsigned long long msr, char *label)
 {
 	fprintf(outf, "cpu%d: %s: %sabled (%0.3f Watts, %f sec, clamp %sabled)\n",
@@ -4918,11 +5085,11 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	UNUSED(c);
 	UNUSED(p);
 
-	if (!do_rapl)
+	if (!platform->rapl_msrs)
 		return 0;
 
 	/* RAPL counters are per package, so print only for 1st thread/package */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_thread_in_package(t, c, p))
 		return 0;
 
 	cpu = t->cpu_id;
@@ -4931,7 +5098,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		return -1;
 	}
 
-	if (do_rapl & RAPL_AMD_F17H) {
+	if (platform->rapl_msrs & RAPL_AMD_F17H) {
 		msr_name = "MSR_RAPL_PWR_UNIT";
 		if (get_msr(cpu, MSR_RAPL_PWR_UNIT, &msr))
 			return -1;
@@ -4944,7 +5111,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	fprintf(outf, "cpu%d: %s: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr_name, msr,
 		rapl_power_units, rapl_energy_units, rapl_time_units);
 
-	if (do_rapl & RAPL_PKG_POWER_INFO) {
+	if (platform->rapl_msrs & RAPL_PKG_POWER_INFO) {
 
 		if (get_msr(cpu, MSR_PKG_POWER_INFO, &msr))
 			return -5;
@@ -4957,7 +5124,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			((msr >> 48) & RAPL_TIME_GRANULARITY) * rapl_time_units);
 
 	}
-	if (do_rapl & RAPL_PKG) {
+	if (platform->rapl_msrs & RAPL_PKG) {
 
 		if (get_msr(cpu, MSR_PKG_POWER_LIMIT, &msr))
 			return -9;
@@ -4981,7 +5148,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			cpu, ((msr >> 0) & 0x1FFF) * rapl_power_units, (msr >> 31) & 1 ? "" : "UN");
 	}
 
-	if (do_rapl & RAPL_DRAM_POWER_INFO) {
+	if (platform->rapl_msrs & RAPL_DRAM_POWER_INFO) {
 		if (get_msr(cpu, MSR_DRAM_POWER_INFO, &msr))
 			return -6;
 
@@ -4992,7 +5159,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			((msr >> 32) & RAPL_POWER_GRANULARITY) * rapl_power_units,
 			((msr >> 48) & RAPL_TIME_GRANULARITY) * rapl_time_units);
 	}
-	if (do_rapl & RAPL_DRAM) {
+	if (platform->rapl_msrs & RAPL_DRAM) {
 		if (get_msr(cpu, MSR_DRAM_POWER_LIMIT, &msr))
 			return -9;
 		fprintf(outf, "cpu%d: MSR_DRAM_POWER_LIMIT: 0x%08llx (%slocked)\n",
@@ -5000,20 +5167,20 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 
 		print_power_limit_msr(cpu, msr, "DRAM Limit");
 	}
-	if (do_rapl & RAPL_CORE_POLICY) {
+	if (platform->rapl_msrs & RAPL_CORE_POLICY) {
 		if (get_msr(cpu, MSR_PP0_POLICY, &msr))
 			return -7;
 
 		fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF);
 	}
-	if (do_rapl & RAPL_CORES_POWER_LIMIT) {
+	if (platform->rapl_msrs & RAPL_CORE_POWER_LIMIT) {
 		if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr))
 			return -9;
 		fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n",
 			cpu, msr, (msr >> 31) & 1 ? "" : "UN");
 		print_power_limit_msr(cpu, msr, "Cores Limit");
 	}
-	if (do_rapl & RAPL_GFX) {
+	if (platform->rapl_msrs & RAPL_GFX) {
 		if (get_msr(cpu, MSR_PP1_POLICY, &msr))
 			return -8;
 
@@ -5029,217 +5196,24 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 }
 
 /*
- * SNB adds support for additional MSRs:
+ * probe_rapl()
  *
- * MSR_PKG_C7_RESIDENCY            0x000003fa
- * MSR_CORE_C7_RESIDENCY           0x000003fe
- * MSR_PKG_C2_RESIDENCY            0x0000060d
+ * sets rapl_power_units, rapl_energy_units, rapl_time_units
  */
-
-int has_snb_msrs(unsigned int family, unsigned int model)
+void probe_rapl(void)
 {
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_SANDYBRIDGE:
-	case INTEL_FAM6_SANDYBRIDGE_X:
-	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
-	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
-	case INTEL_FAM6_HASWELL:	/* HSW */
-	case INTEL_FAM6_HASWELL_X:	/* HSW */
-	case INTEL_FAM6_HASWELL_L:	/* HSW */
-	case INTEL_FAM6_HASWELL_G:	/* HSW */
-	case INTEL_FAM6_BROADWELL:	/* BDW */
-	case INTEL_FAM6_BROADWELL_G:	/* BDW */
-	case INTEL_FAM6_BROADWELL_X:	/* BDX */
-	case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
-	case INTEL_FAM6_ICELAKE_X:	/* ICX */
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:	/* SPR */
-	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
-	case INTEL_FAM6_ATOM_GOLDMONT_D:	/* DNV */
-	case INTEL_FAM6_ATOM_TREMONT:	/* EHL */
-	case INTEL_FAM6_ATOM_TREMONT_D:	/* JVL */
-		return 1;
-	}
-	return 0;
-}
-
-/*
- * HSW ULT added support for C8/C9/C10 MSRs:
- *
- * MSR_PKG_C8_RESIDENCY		0x00000630
- * MSR_PKG_C9_RESIDENCY		0x00000631
- * MSR_PKG_C10_RESIDENCY	0x00000632
- *
- * MSR_PKGC8_IRTL		0x00000633
- * MSR_PKGC9_IRTL		0x00000634
- * MSR_PKGC10_IRTL		0x00000635
- *
- */
-int has_c8910_msrs(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_HASWELL_L:	/* HSW */
-	case INTEL_FAM6_BROADWELL:	/* BDW */
-	case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
-	case INTEL_FAM6_ATOM_TREMONT:	/* EHL */
-		return 1;
-	}
-	return 0;
-}
-
-/*
- * SKL adds support for additional MSRS:
- *
- * MSR_PKG_WEIGHTED_CORE_C0_RES    0x00000658
- * MSR_PKG_ANY_CORE_C0_RES         0x00000659
- * MSR_PKG_ANY_GFXE_C0_RES         0x0000065A
- * MSR_PKG_BOTH_CORE_GFXE_C0_RES   0x0000065B
- */
-int has_skl_msrs(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-		return 1;
-	}
-	return 0;
-}
-
-int is_slm(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_ATOM_SILVERMONT:	/* BYT */
-	case INTEL_FAM6_ATOM_SILVERMONT_D:	/* AVN */
-		return 1;
-	}
-	return 0;
-}
-
-int is_knl(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_XEON_PHI_KNL:	/* KNL */
-		return 1;
-	}
-	return 0;
-}
-
-int is_cnl(unsigned int family, unsigned int model)
-{
-	if (!genuine_intel)
-		return 0;
-
-	if (family != 6)
-		return 0;
-
-	switch (model) {
-	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
-		return 1;
-	}
-
-	return 0;
-}
-
-unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model)
-{
-	if (is_knl(family, model))
-		return 1024;
-	return 1;
-}
-
-#define SLM_BCLK_FREQS 5
-double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0 };
-
-double slm_bclk(void)
-{
-	unsigned long long msr = 3;
-	unsigned int i;
-	double freq;
-
-	if (get_msr(base_cpu, MSR_FSB_FREQ, &msr))
-		fprintf(outf, "SLM BCLK: unknown\n");
-
-	i = msr & 0xf;
-	if (i >= SLM_BCLK_FREQS) {
-		fprintf(outf, "SLM BCLK[%d] invalid\n", i);
-		i = 3;
-	}
-	freq = slm_freq_table[i];
-
-	if (!quiet)
-		fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq);
-
-	return freq;
-}
-
-double discover_bclk(unsigned int family, unsigned int model)
-{
-	if (has_snb_msrs(family, model) || is_knl(family, model))
-		return 100.00;
-	else if (is_slm(family, model))
-		return slm_bclk();
-	else
-		return 133.33;
-}
-
-int get_cpu_type(struct thread_data *t, struct core_data *c, struct pkg_data *p)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	UNUSED(c);
-	UNUSED(p);
-
-	if (!genuine_intel)
-		return 0;
+	if (!platform->rapl_msrs)
+		return;
 
-	if (cpu_migrate(t->cpu_id)) {
-		fprintf(outf, "Could not migrate to CPU %d\n", t->cpu_id);
-		return -1;
-	}
+	if (genuine_intel)
+		rapl_probe_intel();
+	if (authentic_amd || hygon_genuine)
+		rapl_probe_amd();
 
-	if (max_level < 0x1a)
-		return 0;
+	if (quiet)
+		return;
 
-	__cpuid(0x1a, eax, ebx, ecx, edx);
-	eax = (eax >> 24) & 0xFF;
-	if (eax == 0x20)
-		t->is_atom = true;
-	return 0;
+	for_all_cpus(print_rapl, ODD_COUNTERS);
 }
 
 /*
@@ -5268,7 +5242,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 		return 0;
 
 	/* this is a per-package concept */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+	if (!is_cpu_first_thread_in_package(t, c, p))
 		return 0;
 
 	cpu = t->cpu_id;
@@ -5284,7 +5258,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 	}
 
 	/* Temperature Target MSR is Nehalem and newer only */
-	if (!do_nhm_platform_info)
+	if (!platform->has_nhm_msrs)
 		goto guess;
 
 	if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
@@ -5293,20 +5267,18 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 	tcc_default = (msr >> 16) & 0xFF;
 
 	if (!quiet) {
-		switch (tcc_offset_bits) {
-		case 4:
-			tcc_offset = (msr >> 24) & 0xF;
-			fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n",
-				cpu, msr, tcc_default - tcc_offset, tcc_default, tcc_offset);
-			break;
-		case 6:
-			tcc_offset = (msr >> 24) & 0x3F;
+		int bits = platform->tcc_offset_bits;
+		unsigned long long enabled = 0;
+
+		if (bits && !get_msr(base_cpu, MSR_PLATFORM_INFO, &enabled))
+			enabled = (enabled >> 30) & 1;
+
+		if (bits && enabled) {
+			tcc_offset = (msr >> 24) & GENMASK(bits - 1, 0);
 			fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n",
 				cpu, msr, tcc_default - tcc_offset, tcc_default, tcc_offset);
-			break;
-		default:
+		} else {
 			fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n", cpu, msr, tcc_default);
-			break;
 		}
 	}
 
@@ -5324,6 +5296,108 @@ guess:
 	return 0;
 }
 
+int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	unsigned long long msr;
+	unsigned int dts, dts2;
+	int cpu;
+
+	UNUSED(c);
+	UNUSED(p);
+
+	if (!(do_dts || do_ptm))
+		return 0;
+
+	cpu = t->cpu_id;
+
+	/* DTS is per-core, no need to print for each thread */
+	if (!is_cpu_first_thread_in_core(t, c, p))
+		return 0;
+
+	if (cpu_migrate(cpu)) {
+		fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu);
+		return -1;
+	}
+
+	if (do_ptm && is_cpu_first_core_in_package(t, c, p)) {
+		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
+			return 0;
+
+		dts = (msr >> 16) & 0x7F;
+		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n", cpu, msr, tj_max - dts);
+
+		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &msr))
+			return 0;
+
+		dts = (msr >> 16) & 0x7F;
+		dts2 = (msr >> 8) & 0x7F;
+		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
+			cpu, msr, tj_max - dts, tj_max - dts2);
+	}
+
+	if (do_dts && debug) {
+		unsigned int resolution;
+
+		if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr))
+			return 0;
+
+		dts = (msr >> 16) & 0x7F;
+		resolution = (msr >> 27) & 0xF;
+		fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n",
+			cpu, msr, tj_max - dts, resolution);
+
+		if (get_msr(cpu, MSR_IA32_THERM_INTERRUPT, &msr))
+			return 0;
+
+		dts = (msr >> 16) & 0x7F;
+		dts2 = (msr >> 8) & 0x7F;
+		fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
+			cpu, msr, tj_max - dts, tj_max - dts2);
+	}
+
+	return 0;
+}
+
+void probe_thermal(void)
+{
+	if (!access("/sys/devices/system/cpu/cpu0/thermal_throttle/core_throttle_count", R_OK))
+		BIC_PRESENT(BIC_CORE_THROT_CNT);
+	else
+		BIC_NOT_PRESENT(BIC_CORE_THROT_CNT);
+
+	for_all_cpus(set_temperature_target, ODD_COUNTERS);
+
+	if (quiet)
+		return;
+
+	for_all_cpus(print_thermal, ODD_COUNTERS);
+}
+
+int get_cpu_type(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	unsigned int eax, ebx, ecx, edx;
+
+	UNUSED(c);
+	UNUSED(p);
+
+	if (!genuine_intel)
+		return 0;
+
+	if (cpu_migrate(t->cpu_id)) {
+		fprintf(outf, "Could not migrate to CPU %d\n", t->cpu_id);
+		return -1;
+	}
+
+	if (max_level < 0x1a)
+		return 0;
+
+	__cpuid(0x1a, eax, ebx, ecx, edx);
+	eax = (eax >> 24) & 0xFF;
+	if (eax == 0x20)
+		t->is_atom = true;
+	return 0;
+}
+
 void decode_feature_control_msr(void)
 {
 	unsigned long long msr;
@@ -5354,7 +5428,7 @@ void decode_misc_feature_control(void)
 {
 	unsigned long long msr;
 
-	if (!has_misc_feature_control)
+	if (!platform->has_msr_misc_feature_control)
 		return;
 
 	if (!get_msr(base_cpu, MSR_MISC_FEATURE_CONTROL, &msr))
@@ -5375,10 +5449,7 @@ void decode_misc_pwr_mgmt_msr(void)
 {
 	unsigned long long msr;
 
-	if (!do_nhm_platform_info)
-		return;
-
-	if (no_MSR_MISC_PWR_MGMT)
+	if (!platform->has_msr_misc_pwr_mgmt)
 		return;
 
 	if (!get_msr(base_cpu, MSR_MISC_PWR_MGMT, &msr))
@@ -5397,6 +5468,9 @@ void decode_c6_demotion_policy_msr(void)
 {
 	unsigned long long msr;
 
+	if (!platform->has_msr_c6_demotion_policy_config)
+		return;
+
 	if (!get_msr(base_cpu, MSR_CC6_DEMOTION_POLICY_CONFIG, &msr))
 		fprintf(outf, "cpu%d: MSR_CC6_DEMOTION_POLICY_CONFIG: 0x%08llx (%sable-CC6-Demotion)\n",
 			base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS");
@@ -5406,67 +5480,6 @@ void decode_c6_demotion_policy_msr(void)
 			base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS");
 }
 
-/*
- * When models are the same, for the purpose of turbostat, reuse
- */
-unsigned int intel_model_duplicates(unsigned int model)
-{
-
-	switch (model) {
-	case INTEL_FAM6_NEHALEM_EP:	/* Core i7, Xeon 5500 series - Bloomfield, Gainstown NHM-EP */
-	case INTEL_FAM6_NEHALEM:	/* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */
-	case 0x1F:		/* Core i7 and i5 Processor - Nehalem */
-	case INTEL_FAM6_WESTMERE:	/* Westmere Client - Clarkdale, Arrandale */
-	case INTEL_FAM6_WESTMERE_EP:	/* Westmere EP - Gulftown */
-		return INTEL_FAM6_NEHALEM;
-
-	case INTEL_FAM6_NEHALEM_EX:	/* Nehalem-EX Xeon - Beckton */
-	case INTEL_FAM6_WESTMERE_EX:	/* Westmere-EX Xeon - Eagleton */
-		return INTEL_FAM6_NEHALEM_EX;
-
-	case INTEL_FAM6_XEON_PHI_KNM:
-		return INTEL_FAM6_XEON_PHI_KNL;
-
-	case INTEL_FAM6_BROADWELL_X:
-	case INTEL_FAM6_BROADWELL_D:	/* BDX-DE */
-		return INTEL_FAM6_BROADWELL_X;
-
-	case INTEL_FAM6_SKYLAKE_L:
-	case INTEL_FAM6_SKYLAKE:
-	case INTEL_FAM6_KABYLAKE_L:
-	case INTEL_FAM6_KABYLAKE:
-	case INTEL_FAM6_COMETLAKE_L:
-	case INTEL_FAM6_COMETLAKE:
-		return INTEL_FAM6_SKYLAKE_L;
-
-	case INTEL_FAM6_ICELAKE_L:
-	case INTEL_FAM6_ICELAKE_NNPI:
-	case INTEL_FAM6_TIGERLAKE_L:
-	case INTEL_FAM6_TIGERLAKE:
-	case INTEL_FAM6_ROCKETLAKE:
-	case INTEL_FAM6_LAKEFIELD:
-	case INTEL_FAM6_ALDERLAKE:
-	case INTEL_FAM6_ALDERLAKE_L:
-	case INTEL_FAM6_ATOM_GRACEMONT:
-	case INTEL_FAM6_RAPTORLAKE:
-	case INTEL_FAM6_RAPTORLAKE_P:
-	case INTEL_FAM6_RAPTORLAKE_S:
-	case INTEL_FAM6_METEORLAKE:
-	case INTEL_FAM6_METEORLAKE_L:
-		return INTEL_FAM6_CANNONLAKE_L;
-
-	case INTEL_FAM6_ATOM_TREMONT_L:
-		return INTEL_FAM6_ATOM_TREMONT;
-
-	case INTEL_FAM6_ICELAKE_D:
-		return INTEL_FAM6_ICELAKE_X;
-
-	case INTEL_FAM6_EMERALDRAPIDS_X:
-		return INTEL_FAM6_SAPPHIRERAPIDS_X;
-	}
-	return model;
-}
-
 void print_dev_latency(void)
 {
 	char *path = "/dev/cpu_dma_latency";
@@ -5510,6 +5523,101 @@ void linux_perf_init(void)
 	BIC_PRESENT(BIC_IPC);
 }
 
+void probe_cstates(void)
+{
+	probe_cst_limit();
+
+	if (platform->supported_cstates & CC1)
+		BIC_PRESENT(BIC_CPU_c1);
+
+	if (platform->supported_cstates & CC3)
+		BIC_PRESENT(BIC_CPU_c3);
+
+	if (platform->supported_cstates & CC6)
+		BIC_PRESENT(BIC_CPU_c6);
+
+	if (platform->supported_cstates & CC7)
+		BIC_PRESENT(BIC_CPU_c7);
+
+	if (platform->supported_cstates & PC2 && (pkg_cstate_limit >= PCL__2))
+		BIC_PRESENT(BIC_Pkgpc2);
+
+	if (platform->supported_cstates & PC3 && (pkg_cstate_limit >= PCL__3))
+		BIC_PRESENT(BIC_Pkgpc3);
+
+	if (platform->supported_cstates & PC6 && (pkg_cstate_limit >= PCL__6))
+		BIC_PRESENT(BIC_Pkgpc6);
+
+	if (platform->supported_cstates & PC7 && (pkg_cstate_limit >= PCL__7))
+		BIC_PRESENT(BIC_Pkgpc7);
+
+	if (platform->supported_cstates & PC8 && (pkg_cstate_limit >= PCL__8))
+		BIC_PRESENT(BIC_Pkgpc8);
+
+	if (platform->supported_cstates & PC9 && (pkg_cstate_limit >= PCL__9))
+		BIC_PRESENT(BIC_Pkgpc9);
+
+	if (platform->supported_cstates & PC10 && (pkg_cstate_limit >= PCL_10))
+		BIC_PRESENT(BIC_Pkgpc10);
+
+	if (platform->has_msr_module_c6_res_ms)
+		BIC_PRESENT(BIC_Mod_c6);
+
+	if (platform->has_ext_cst_msrs) {
+		BIC_PRESENT(BIC_Totl_c0);
+		BIC_PRESENT(BIC_Any_c0);
+		BIC_PRESENT(BIC_GFX_c0);
+		BIC_PRESENT(BIC_CPUGFX);
+	}
+
+	if (quiet)
+		return;
+
+	dump_power_ctl();
+	dump_cst_cfg();
+	decode_c6_demotion_policy_msr();
+	print_dev_latency();
+	dump_sysfs_cstate_config();
+	print_irtl();
+}
+
+void probe_lpi(void)
+{
+	if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK))
+		BIC_PRESENT(BIC_CPU_LPI);
+	else
+		BIC_NOT_PRESENT(BIC_CPU_LPI);
+
+	if (!access(sys_lpi_file_sysfs, R_OK)) {
+		sys_lpi_file = sys_lpi_file_sysfs;
+		BIC_PRESENT(BIC_SYS_LPI);
+	} else if (!access(sys_lpi_file_debugfs, R_OK)) {
+		sys_lpi_file = sys_lpi_file_debugfs;
+		BIC_PRESENT(BIC_SYS_LPI);
+	} else {
+		sys_lpi_file_sysfs = NULL;
+		BIC_NOT_PRESENT(BIC_SYS_LPI);
+	}
+
+}
+
+void probe_pstates(void)
+{
+	probe_bclk();
+
+	if (quiet)
+		return;
+
+	dump_platform_info();
+	dump_turbo_ratio_info();
+	dump_sysfs_pstate_config();
+	decode_misc_pwr_mgmt_msr();
+
+	for_all_cpus(print_hwp, ODD_COUNTERS);
+	for_all_cpus(print_epb, ODD_COUNTERS);
+	for_all_cpus(print_perf_limit, ODD_COUNTERS);
+}
+
 void process_cpuid()
 {
 	unsigned int eax, ebx, ecx, edx;
@@ -5569,10 +5677,8 @@ void process_cpuid()
 			edx_flags & (1 << 22) ? "ACPI-TM" : "-",
 			edx_flags & (1 << 28) ? "HT" : "-", edx_flags & (1 << 29) ? "TM" : "-");
 	}
-	if (genuine_intel) {
-		model_orig = model;
-		model = intel_model_duplicates(model);
-	}
+
+	probe_platform_features(family, model);
 
 	if (!(edx_flags & (1 << 5)))
 		errx(1, "CPUID: no MSR");
@@ -5656,26 +5762,12 @@ void process_cpuid()
 		__cpuid(0x15, eax_crystal, ebx_tsc, crystal_hz, edx);
 
 		if (ebx_tsc != 0) {
-
 			if (!quiet && (ebx != 0))
 				fprintf(outf, "CPUID(0x15): eax_crystal: %d ebx_tsc: %d ecx_crystal_hz: %d\n",
 					eax_crystal, ebx_tsc, crystal_hz);
 
 			if (crystal_hz == 0)
-				switch (model) {
-				case INTEL_FAM6_SKYLAKE_L:	/* SKL */
-					crystal_hz = 24000000;	/* 24.0 MHz */
-					break;
-				case INTEL_FAM6_ATOM_GOLDMONT_D:	/* DNV */
-					crystal_hz = 25000000;	/* 25.0 MHz */
-					break;
-				case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-				case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
-					crystal_hz = 19200000;	/* 19.2 MHz */
-					break;
-				default:
-					crystal_hz = 0;
-				}
+				crystal_hz = platform->crystal_freq;
 
 			if (crystal_hz) {
 				tsc_hz = (unsigned long long)crystal_hz *ebx_tsc / eax_crystal;
@@ -5700,147 +5792,33 @@ void process_cpuid()
 	}
 
 	if (has_aperf)
-		aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model);
+		aperf_mperf_multiplier = platform->need_perf_multiplier ? 1024 : 1;
 
 	BIC_PRESENT(BIC_IRQ);
 	BIC_PRESENT(BIC_TSC_MHz);
+}
 
-	if (probe_nhm_msrs(family, model)) {
-		do_nhm_platform_info = 1;
-		BIC_PRESENT(BIC_CPU_c1);
-		BIC_PRESENT(BIC_CPU_c3);
-		BIC_PRESENT(BIC_CPU_c6);
-		BIC_PRESENT(BIC_SMI);
-	}
-	do_snb_cstates = has_snb_msrs(family, model);
-
-	if (do_snb_cstates)
-		BIC_PRESENT(BIC_CPU_c7);
-
-	do_irtl_snb = has_snb_msrs(family, model);
-	if (do_snb_cstates && (pkg_cstate_limit >= PCL__2))
-		BIC_PRESENT(BIC_Pkgpc2);
-	if (pkg_cstate_limit >= PCL__3)
-		BIC_PRESENT(BIC_Pkgpc3);
-	if (pkg_cstate_limit >= PCL__6)
-		BIC_PRESENT(BIC_Pkgpc6);
-	if (do_snb_cstates && (pkg_cstate_limit >= PCL__7))
-		BIC_PRESENT(BIC_Pkgpc7);
-	if (has_slv_msrs(family, model)) {
-		BIC_NOT_PRESENT(BIC_Pkgpc2);
-		BIC_NOT_PRESENT(BIC_Pkgpc3);
-		BIC_PRESENT(BIC_Pkgpc6);
-		BIC_NOT_PRESENT(BIC_Pkgpc7);
-		BIC_PRESENT(BIC_Mod_c6);
-		use_c1_residency_msr = 1;
-	}
-	if (is_jvl(family, model)) {
-		BIC_NOT_PRESENT(BIC_CPU_c3);
-		BIC_NOT_PRESENT(BIC_CPU_c7);
-		BIC_NOT_PRESENT(BIC_Pkgpc2);
-		BIC_NOT_PRESENT(BIC_Pkgpc3);
-		BIC_NOT_PRESENT(BIC_Pkgpc6);
-		BIC_NOT_PRESENT(BIC_Pkgpc7);
-	}
-	if (is_dnv(family, model)) {
-		BIC_PRESENT(BIC_CPU_c1);
-		BIC_NOT_PRESENT(BIC_CPU_c3);
-		BIC_NOT_PRESENT(BIC_Pkgpc3);
-		BIC_NOT_PRESENT(BIC_CPU_c7);
-		BIC_NOT_PRESENT(BIC_Pkgpc7);
-		use_c1_residency_msr = 1;
-	}
-	if (is_skx(family, model) || is_icx(family, model) || is_spr(family, model)) {
-		BIC_NOT_PRESENT(BIC_CPU_c3);
-		BIC_NOT_PRESENT(BIC_Pkgpc3);
-		BIC_NOT_PRESENT(BIC_CPU_c7);
-		BIC_NOT_PRESENT(BIC_Pkgpc7);
-	}
-	if (is_bdx(family, model)) {
-		BIC_NOT_PRESENT(BIC_CPU_c7);
-		BIC_NOT_PRESENT(BIC_Pkgpc7);
-	}
-	if (has_c8910_msrs(family, model)) {
-		if (pkg_cstate_limit >= PCL__8)
-			BIC_PRESENT(BIC_Pkgpc8);
-		if (pkg_cstate_limit >= PCL__9)
-			BIC_PRESENT(BIC_Pkgpc9);
-		if (pkg_cstate_limit >= PCL_10)
-			BIC_PRESENT(BIC_Pkgpc10);
-	}
-	do_irtl_hsw = has_c8910_msrs(family, model);
-	if (has_skl_msrs(family, model)) {
-		BIC_PRESENT(BIC_Totl_c0);
-		BIC_PRESENT(BIC_Any_c0);
-		BIC_PRESENT(BIC_GFX_c0);
-		BIC_PRESENT(BIC_CPUGFX);
-	}
-	do_slm_cstates = is_slm(family, model);
-	do_knl_cstates = is_knl(family, model);
-
-	if (do_slm_cstates || do_knl_cstates || is_cnl(family, model) || is_ehl(family, model))
-		BIC_NOT_PRESENT(BIC_CPU_c3);
-
-	if (!quiet)
-		decode_misc_pwr_mgmt_msr();
-
-	if (!quiet && has_slv_msrs(family, model))
-		decode_c6_demotion_policy_msr();
-
-	rapl_probe(family, model);
-	perf_limit_reasons_probe(family, model);
-	automatic_cstate_conversion_probe(family, model);
-
-	check_tcc_offset(model_orig);
-
-	if (!quiet)
-		dump_cstate_pstate_config_info(family, model);
-	intel_uncore_frequency_probe();
-
-	if (!quiet)
-		print_dev_latency();
-	if (!quiet)
-		dump_sysfs_cstate_config();
-	if (!quiet)
-		dump_sysfs_pstate_config();
+void probe_pm_features(void)
+{
+	probe_pstates();
 
-	if (has_skl_msrs(family, model) || is_ehl(family, model))
-		calculate_tsc_tweak();
+	probe_cstates();
 
-	if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK))
-		BIC_PRESENT(BIC_GFX_rc6);
+	probe_lpi();
 
-	if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
-		BIC_PRESENT(BIC_GFXMHz);
+	probe_intel_uncore_frequency();
 
-	if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK))
-		BIC_PRESENT(BIC_GFXACTMHz);
+	probe_graphics();
 
-	if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK))
-		BIC_PRESENT(BIC_CPU_LPI);
-	else
-		BIC_NOT_PRESENT(BIC_CPU_LPI);
+	probe_rapl();
 
-	if (!access("/sys/devices/system/cpu/cpu0/thermal_throttle/core_throttle_count", R_OK))
-		BIC_PRESENT(BIC_CORE_THROT_CNT);
-	else
-		BIC_NOT_PRESENT(BIC_CORE_THROT_CNT);
+	probe_thermal();
 
-	if (!access(sys_lpi_file_sysfs, R_OK)) {
-		sys_lpi_file = sys_lpi_file_sysfs;
-		BIC_PRESENT(BIC_SYS_LPI);
-	} else if (!access(sys_lpi_file_debugfs, R_OK)) {
-		sys_lpi_file = sys_lpi_file_debugfs;
-		BIC_PRESENT(BIC_SYS_LPI);
-	} else {
-		sys_lpi_file_sysfs = NULL;
-		BIC_NOT_PRESENT(BIC_SYS_LPI);
-	}
+	if (platform->has_nhm_msrs)
+		BIC_PRESENT(BIC_SMI);
 
 	if (!quiet)
 		decode_misc_feature_control();
-
-	return;
 }
 
 /*
@@ -5855,7 +5833,7 @@ int dir_filter(const struct dirent *dirp)
 		return 0;
 }
 
-void topology_probe()
+void topology_probe(bool startup)
 {
 	int i;
 	int max_core_id = 0;
@@ -5888,14 +5866,62 @@ void topology_probe()
 	for_all_proc_cpus(mark_cpu_present);
 
 	/*
-	 * Validate that all cpus in cpu_subset are also in cpu_present_set
+	 * Allocate and initialize cpu_effective_set
+	 */
+	cpu_effective_set = CPU_ALLOC((topo.max_cpu_num + 1));
+	if (cpu_effective_set == NULL)
+		err(3, "CPU_ALLOC");
+	cpu_effective_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
+	CPU_ZERO_S(cpu_effective_setsize, cpu_effective_set);
+	update_effective_set(startup);
+
+	/*
+	 * Allocate and initialize cpu_allowed_set
+	 */
+	cpu_allowed_set = CPU_ALLOC((topo.max_cpu_num + 1));
+	if (cpu_allowed_set == NULL)
+		err(3, "CPU_ALLOC");
+	cpu_allowed_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
+	CPU_ZERO_S(cpu_allowed_setsize, cpu_allowed_set);
+
+	/*
+	 * Validate and update cpu_allowed_set.
+	 *
+	 * Make sure all cpus in cpu_subset are also in cpu_present_set during startup.
+	 * Give a warning when cpus in cpu_subset become unavailable at runtime.
+	 * Give a warning when cpus are not effective because of cgroup setting.
+	 *
+	 * cpu_allowed_set is the intersection of cpu_present_set/cpu_effective_set/cpu_subset.
 	 */
 	for (i = 0; i < CPU_SUBSET_MAXCPUS; ++i) {
-		if (CPU_ISSET_S(i, cpu_subset_size, cpu_subset))
-			if (!CPU_ISSET_S(i, cpu_present_setsize, cpu_present_set))
-				err(1, "cpu%d not present", i);
+		if (cpu_subset && !CPU_ISSET_S(i, cpu_subset_size, cpu_subset))
+			continue;
+
+		if (!CPU_ISSET_S(i, cpu_present_setsize, cpu_present_set)) {
+			if (cpu_subset) {
+				/* cpus in cpu_subset must be in cpu_present_set during startup */
+				if (startup)
+					err(1, "cpu%d not present", i);
+				else
+					fprintf(stderr, "cpu%d not present\n", i);
+			}
+			continue;
+		}
+
+		if (CPU_COUNT_S(cpu_effective_setsize, cpu_effective_set)) {
+			if (!CPU_ISSET_S(i, cpu_effective_setsize, cpu_effective_set)) {
+				fprintf(stderr, "cpu%d not effective\n", i);
+				continue;
+			}
+		}
+
+		CPU_SET_S(i, cpu_allowed_setsize, cpu_allowed_set);
 	}
 
+	if (!CPU_COUNT_S(cpu_allowed_setsize, cpu_allowed_set))
+		err(-ENODEV, "No valid cpus found");
+	sched_setaffinity(0, cpu_allowed_setsize, cpu_allowed_set);
+
 	/*
 	 * Allocate and initialize cpu_affinity_set
 	 */
@@ -6009,15 +6035,19 @@ void allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_
 	if (*c == NULL)
 		goto error;
 
-	for (i = 0; i < num_cores; i++)
+	for (i = 0; i < num_cores; i++) {
 		(*c)[i].core_id = -1;
+		(*c)[i].base_cpu = -1;
+	}
 
 	*p = calloc(topo.num_packages, sizeof(struct pkg_data));
 	if (*p == NULL)
 		goto error;
 
-	for (i = 0; i < topo.num_packages; i++)
+	for (i = 0; i < topo.num_packages; i++) {
 		(*p)[i].package_id = i;
+		(*p)[i].base_cpu = -1;
+	}
 
 	return;
 error:
@@ -6050,10 +6080,11 @@ void init_counter(struct thread_data *thread_base, struct core_data *core_base,
 	p = GET_PKG(pkg_base, pkg_id);
 
 	t->cpu_id = cpu_id;
-	if (thread_id == 0) {
-		t->flags |= CPU_IS_FIRST_THREAD_IN_CORE;
-		if (cpu_is_first_core_in_package(cpu_id))
-			t->flags |= CPU_IS_FIRST_CORE_IN_PACKAGE;
+	if (!cpu_is_not_allowed(cpu_id)) {
+		if (c->base_cpu < 0)
+			c->base_cpu = t->cpu_id;
+		if (p->base_cpu < 0)
+			p->base_cpu = t->cpu_id;
 	}
 
 	c->core_id = core_id;
@@ -6093,59 +6124,64 @@ void allocate_irq_buffers(void)
 		err(-1, "calloc %d", topo.max_cpu_num + 1);
 }
 
-void setup_all_buffers(void)
+int update_topo(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	topo.allowed_cpus++;
+	if ((int)t->cpu_id == c->base_cpu)
+		topo.allowed_cores++;
+	if ((int)t->cpu_id == p->base_cpu)
+		topo.allowed_packages++;
+
+	return 0;
+}
+
+void topology_update(void)
 {
-	topology_probe();
+	topo.allowed_cpus = 0;
+	topo.allowed_cores = 0;
+	topo.allowed_packages = 0;
+	for_all_cpus(update_topo, ODD_COUNTERS);
+}
+void setup_all_buffers(bool startup)
+{
+	topology_probe(startup);
 	allocate_irq_buffers();
 	allocate_fd_percpu();
 	allocate_counters(&thread_even, &core_even, &package_even);
 	allocate_counters(&thread_odd, &core_odd, &package_odd);
 	allocate_output_buffer();
 	for_all_proc_cpus(initialize_counters);
+	topology_update();
 }
 
 void set_base_cpu(void)
 {
-	base_cpu = sched_getcpu();
-	if (base_cpu < 0)
-		err(-ENODEV, "No valid cpus found");
+	int i;
 
-	if (debug > 1)
-		fprintf(outf, "base_cpu = %d\n", base_cpu);
+	for (i = 0; i < topo.max_cpu_num + 1; ++i) {
+		if (cpu_is_not_allowed(i))
+			continue;
+		base_cpu = i;
+		if (debug > 1)
+			fprintf(outf, "base_cpu = %d\n", base_cpu);
+		return;
+	}
+	err(-ENODEV, "No valid cpus found");
 }
 
 void turbostat_init()
 {
-	setup_all_buffers();
+	setup_all_buffers(true);
 	set_base_cpu();
 	check_dev_msr();
 	check_permissions();
 	process_cpuid();
+	probe_pm_features();
 	linux_perf_init();
 
-	if (!quiet)
-		for_all_cpus(print_hwp, ODD_COUNTERS);
-
-	if (!quiet)
-		for_all_cpus(print_epb, ODD_COUNTERS);
-
-	if (!quiet)
-		for_all_cpus(print_perf_limit, ODD_COUNTERS);
-
-	if (!quiet)
-		for_all_cpus(print_rapl, ODD_COUNTERS);
-
-	for_all_cpus(set_temperature_target, ODD_COUNTERS);
-
 	for_all_cpus(get_cpu_type, ODD_COUNTERS);
 	for_all_cpus(get_cpu_type, EVEN_COUNTERS);
 
-	if (!quiet)
-		for_all_cpus(print_thermal, ODD_COUNTERS);
-
-	if (!quiet && do_irtl_snb)
-		print_irtl();
-
 	if (DO_BIC(BIC_IPC))
 		(void)get_instr_count_fd(base_cpu);
 }
@@ -6160,8 +6196,6 @@ int fork_it(char **argv)
 	first_counter_read = 0;
 	if (status)
 		exit(status);
-	/* clear affinity side-effect of get_counters() */
-	sched_setaffinity(0, cpu_present_setsize, cpu_present_set);
 	gettimeofday(&tv_even, (struct timezone *)NULL);
 
 	child_pid = fork();
@@ -6225,7 +6259,7 @@ int get_and_dump_counters(void)
 
 void print_version()
 {
-	fprintf(outf, "turbostat version 2023.03.17 - Len Brown <lenb@kernel.org>\n");
+	fprintf(outf, "turbostat version 2023.11.07 - Len Brown <lenb@kernel.org>\n");
 }
 
 #define COMMAND_LINE_SIZE 2048
@@ -6508,9 +6542,6 @@ void probe_sysfs(void)
  */
 void parse_cpu_command(char *optarg)
 {
-	unsigned int start, end;
-	char *next;
-
 	if (!strcmp(optarg, "core")) {
 		if (cpu_subset)
 			goto error;
@@ -6533,52 +6564,8 @@ void parse_cpu_command(char *optarg)
 
 	CPU_ZERO_S(cpu_subset_size, cpu_subset);
 
-	next = optarg;
-
-	while (next && *next) {
-
-		if (*next == '-')	/* no negative cpu numbers */
-			goto error;
-
-		start = strtoul(next, &next, 10);
-
-		if (start >= CPU_SUBSET_MAXCPUS)
-			goto error;
-		CPU_SET_S(start, cpu_subset_size, cpu_subset);
-
-		if (*next == '\0')
-			break;
-
-		if (*next == ',') {
-			next += 1;
-			continue;
-		}
-
-		if (*next == '-') {
-			next += 1;	/* start range */
-		} else if (*next == '.') {
-			next += 1;
-			if (*next == '.')
-				next += 1;	/* start range */
-			else
-				goto error;
-		}
-
-		end = strtoul(next, &next, 10);
-		if (end <= start)
-			goto error;
-
-		while (++start <= end) {
-			if (start >= CPU_SUBSET_MAXCPUS)
-				goto error;
-			CPU_SET_S(start, cpu_subset_size, cpu_subset);
-		}
-
-		if (*next == ',')
-			next += 1;
-		else if (*next != '\0')
-			goto error;
-	}
+	if (parse_cpu_str(optarg, cpu_subset, cpu_subset_size))
+		goto error;
 
 	return;
 
@@ -6719,6 +6706,19 @@ void cmdline(int argc, char **argv)
 
 int main(int argc, char **argv)
 {
+	int fd, ret;
+
+	fd = open("/sys/fs/cgroup/cgroup.procs", O_WRONLY);
+	if (fd < 0)
+		goto skip_cgroup_setting;
+
+	ret = write(fd, "0\n", 2);
+	if (ret == -1)
+		perror("Can't update cgroup\n");
+
+	close(fd);
+
+skip_cgroup_setting:
 	outf = stderr;
 	cmdline(argc, argv);
 
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
index 90f3c9802ffb80..95dc58b94178bf 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -62,5 +62,6 @@ cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o
 cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o
 cxl_core-y += config_check.o
 cxl_core-y += cxl_core_test.o
+cxl_core-y += cxl_core_exports.o
 
 obj-m += test/
diff --git a/tools/testing/cxl/cxl_core_exports.c b/tools/testing/cxl/cxl_core_exports.c
new file mode 100644
index 00000000000000..077e6883921df2
--- /dev/null
+++ b/tools/testing/cxl/cxl_core_exports.c
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+
+#include "cxl.h"
+
+/* Exporting of cxl_core symbols that are only used by cxl_test */
+EXPORT_SYMBOL_NS_GPL(cxl_num_decoders_committed, CXL);
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index b8854629990227..f4e517a0c7740f 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -669,10 +669,11 @@ static int mock_decoder_commit(struct cxl_decoder *cxld)
 		return 0;
 
 	dev_dbg(&port->dev, "%s commit\n", dev_name(&cxld->dev));
-	if (port->commit_end + 1 != id) {
+	if (cxl_num_decoders_committed(port) != id) {
 		dev_dbg(&port->dev,
 			"%s: out of order commit, expected decoder%d.%d\n",
-			dev_name(&cxld->dev), port->id, port->commit_end + 1);
+			dev_name(&cxld->dev), port->id,
+			cxl_num_decoders_committed(port));
 		return -EBUSY;
 	}
 
diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c
index fd26189d53be8e..b8419f460368a4 100644
--- a/tools/testing/nvdimm/test/ndtest.c
+++ b/tools/testing/nvdimm/test/ndtest.c
@@ -924,7 +924,7 @@ static __init int ndtest_init(void)
 
 	nfit_test_setup(ndtest_resource_lookup, NULL);
 
-	rc = class_regster(&ndtest_dimm_class);
+	rc = class_register(&ndtest_dimm_class);
 	if (rc)
 		goto err_register;
 
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 3b2061d1c1a527..8247a7c69c36d7 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -155,12 +155,10 @@ ifneq ($(KBUILD_OUTPUT),)
   abs_objtree := $(realpath $(abs_objtree))
   BUILD := $(abs_objtree)/kselftest
   KHDR_INCLUDES := -isystem ${abs_objtree}/usr/include
-  KHDR_DIR := ${abs_objtree}/usr/include
 else
   BUILD := $(CURDIR)
   abs_srctree := $(shell cd $(top_srcdir) && pwd)
   KHDR_INCLUDES := -isystem ${abs_srctree}/usr/include
-  KHDR_DIR := ${abs_srctree}/usr/include
   DEFAULT_INSTALL_HDR_PATH := 1
 endif
 
@@ -174,7 +172,7 @@ export KHDR_INCLUDES
 # all isn't the first target in the file.
 .DEFAULT_GOAL := all
 
-all: kernel_header_files
+all:
 	@ret=1;							\
 	for TARGET in $(TARGETS); do				\
 		BUILD_TARGET=$$BUILD/$$TARGET;			\
@@ -185,23 +183,6 @@ all: kernel_header_files
 		ret=$$((ret * $$?));				\
 	done; exit $$ret;
 
-kernel_header_files:
-	@ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null;                          \
-	if [ $$? -ne 0 ]; then                                                     \
-            RED='\033[1;31m';                                                  \
-            NOCOLOR='\033[0m';                                                 \
-            echo;                                                              \
-            echo -e "$${RED}error$${NOCOLOR}: missing kernel header files.";   \
-            echo "Please run this and try again:";                             \
-            echo;                                                              \
-            echo "    cd $(top_srcdir)";                                       \
-            echo "    make headers";                                           \
-            echo;                                                              \
-	    exit 1;                                                                \
-	fi
-
-.PHONY: kernel_header_files
-
 run_tests: all
 	@for TARGET in $(TARGETS); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c
index 21e482b23f5028..23df154fcdd77b 100644
--- a/tools/testing/selftests/alsa/mixer-test.c
+++ b/tools/testing/selftests/alsa/mixer-test.c
@@ -138,7 +138,7 @@ static void find_controls(void)
 			err = snd_ctl_elem_info(card_data->handle,
 						ctl_data->info);
 			if (err < 0) {
-				ksft_print_msg("%s getting info for %d\n",
+				ksft_print_msg("%s getting info for %s\n",
 					       snd_strerror(err),
 					       ctl_data->name);
 			}
diff --git a/tools/testing/selftests/arm64/fp/za-fork.c b/tools/testing/selftests/arm64/fp/za-fork.c
index b86cb1049497f3..587b9464822261 100644
--- a/tools/testing/selftests/arm64/fp/za-fork.c
+++ b/tools/testing/selftests/arm64/fp/za-fork.c
@@ -85,7 +85,7 @@ int main(int argc, char **argv)
 	 */
 	ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0);
 	if (ret >= 0) {
-		ksft_test_result(fork_test(), "fork_test");
+		ksft_test_result(fork_test(), "fork_test\n");
 
 	} else {
 		ksft_print_msg("SME not supported\n");
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index a5e246f7b20274..91907b321f9134 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -39,9 +39,7 @@ struct bpf_testmod_struct_arg_4 {
 	int b;
 };
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "Global functions as their definitions will be in bpf_testmod.ko BTF");
+__bpf_hook_start();
 
 noinline int
 bpf_testmod_test_struct_arg_1(struct bpf_testmod_struct_arg_2 a, int b, int c) {
@@ -335,7 +333,7 @@ noinline int bpf_fentry_shadow_test(int a)
 }
 EXPORT_SYMBOL_GPL(bpf_fentry_shadow_test);
 
-__diag_pop();
+__bpf_hook_end();
 
 static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
 	.attr = { .name = "bpf_testmod", .mode = 0666, },
diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64
index 2e70a604827845..49a29dbc191072 100644
--- a/tools/testing/selftests/bpf/config.x86_64
+++ b/tools/testing/selftests/bpf/config.x86_64
@@ -50,7 +50,6 @@ CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_XXHASH=y
 CONFIG_DCB=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_CREDENTIALS=y
 CONFIG_DEBUG_INFO_BTF=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_DEBUG_MEMORY_INIT=y
diff --git a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
index 1a9eeefda9a870..8bf497a9843e1b 100644
--- a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
+++ b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
@@ -326,20 +326,14 @@ static int map_create(__u32 type, const char *name, struct bpf_map_create_opts *
 
 static int create_hash(void)
 {
-	struct bpf_map_create_opts map_opts = {
-		.sz = sizeof(map_opts),
-		.map_flags = BPF_F_NO_PREALLOC,
-	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = BPF_F_NO_PREALLOC);
 
 	return map_create(BPF_MAP_TYPE_HASH, "hash", &map_opts);
 }
 
 static int create_percpu_hash(void)
 {
-	struct bpf_map_create_opts map_opts = {
-		.sz = sizeof(map_opts),
-		.map_flags = BPF_F_NO_PREALLOC,
-	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = BPF_F_NO_PREALLOC);
 
 	return map_create(BPF_MAP_TYPE_PERCPU_HASH, "percpu_hash", &map_opts);
 }
@@ -356,21 +350,17 @@ static int create_percpu_hash_prealloc(void)
 
 static int create_lru_hash(__u32 type, __u32 map_flags)
 {
-	struct bpf_map_create_opts map_opts = {
-		.sz = sizeof(map_opts),
-		.map_flags = map_flags,
-	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = map_flags);
 
 	return map_create(type, "lru_hash", &map_opts);
 }
 
 static int create_hash_of_maps(void)
 {
-	struct bpf_map_create_opts map_opts = {
-		.sz = sizeof(map_opts),
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts,
 		.map_flags = BPF_F_NO_PREALLOC,
 		.inner_map_fd = create_small_hash(),
-	};
+	);
 	int ret;
 
 	ret = map_create_opts(BPF_MAP_TYPE_HASH_OF_MAPS, "hash_of_maps",
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c b/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
index e02feb5fae97dd..574d9a0cdc8e4a 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
@@ -4,6 +4,7 @@
 #include <test_progs.h>
 #include <bpf/libbpf.h>
 #include <bpf/btf.h>
+#include "iters_css_task.skel.h"
 #include "cgroup_iter.skel.h"
 #include "cgroup_helpers.h"
 
@@ -263,6 +264,35 @@ close_cgrp:
 	close(cgrp_fd);
 }
 
+static void test_walk_self_only_css_task(void)
+{
+	struct iters_css_task *skel;
+	int err;
+
+	skel = iters_css_task__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.cgroup_id_printer, true);
+
+	err = iters_css_task__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	err = join_cgroup(cg_path[CHILD2]);
+	if (!ASSERT_OK(err, "join_cgroup"))
+		goto cleanup;
+
+	skel->bss->target_pid = getpid();
+	snprintf(expected_output, sizeof(expected_output),
+		PROLOGUE "%8llu\n" EPILOGUE, cg_id[CHILD2]);
+	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[CHILD2],
+		BPF_CGROUP_ITER_SELF_ONLY, "test_walk_self_only_css_task");
+	ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt");
+cleanup:
+	iters_css_task__destroy(skel);
+}
+
 void test_cgroup_iter(void)
 {
 	struct cgroup_iter *skel = NULL;
@@ -293,6 +323,9 @@ void test_cgroup_iter(void)
 		test_walk_self_only(skel);
 	if (test__start_subtest("cgroup_iter__dead_self_only"))
 		test_walk_dead_self_only(skel);
+	if (test__start_subtest("cgroup_iter__self_only_css_task"))
+		test_walk_self_only_css_task();
+
 out:
 	cgroup_iter__destroy(skel);
 	cleanup_cgroups();
diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c
index c2425791c9232f..bf84d4a1d9ae2c 100644
--- a/tools/testing/selftests/bpf/prog_tests/iters.c
+++ b/tools/testing/selftests/bpf/prog_tests/iters.c
@@ -294,6 +294,7 @@ void test_iters(void)
 	RUN_TESTS(iters_state_safety);
 	RUN_TESTS(iters_looping);
 	RUN_TESTS(iters);
+	RUN_TESTS(iters_css_task);
 
 	if (env.has_testmod)
 		RUN_TESTS(iters_testmod_seq);
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index f75f84d0b3d798..7c2241fae19a6e 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -524,6 +524,37 @@ out:
 	test_sockmap_pass_prog__destroy(pass);
 }
 
+static void test_sockmap_unconnected_unix(void)
+{
+	int err, map, stream = 0, dgram = 0, zero = 0;
+	struct test_sockmap_pass_prog *skel;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	stream = xsocket(AF_UNIX, SOCK_STREAM, 0);
+	if (stream < 0)
+		return;
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		close(stream);
+		return;
+	}
+
+	err = bpf_map_update_elem(map, &zero, &stream, BPF_ANY);
+	ASSERT_ERR(err, "bpf_map_update_elem(stream)");
+
+	err = bpf_map_update_elem(map, &zero, &dgram, BPF_ANY);
+	ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+
+	close(stream);
+	close(dgram);
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
@@ -566,4 +597,7 @@ void test_sockmap_basic(void)
 		test_sockmap_skb_verdict_fionread(false);
 	if (test__start_subtest("sockmap skb_verdict msg_f_peek"))
 		test_sockmap_skb_verdict_peek();
+
+	if (test__start_subtest("sockmap unconnected af_unix"))
+		test_sockmap_unconnected_unix();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index a934d430c20c13..a92807bfcd1349 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1337,7 +1337,8 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
 }
 
 static void pairs_redir_to_connected(int cli0, int peer0, int cli1, int peer1,
-				     int sock_mapfd, int verd_mapfd, enum redir_mode mode)
+				     int sock_mapfd, int nop_mapfd,
+				     int verd_mapfd, enum redir_mode mode)
 {
 	const char *log_prefix = redir_mode_str(mode);
 	unsigned int pass;
@@ -1351,6 +1352,12 @@ static void pairs_redir_to_connected(int cli0, int peer0, int cli1, int peer1,
 	if (err)
 		return;
 
+	if (nop_mapfd >= 0) {
+		err = add_to_sockmap(nop_mapfd, cli0, cli1);
+		if (err)
+			return;
+	}
+
 	n = write(cli1, "a", 1);
 	if (n < 0)
 		FAIL_ERRNO("%s: write", log_prefix);
@@ -1387,7 +1394,7 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd,
 		goto close0;
 	c1 = sfd[0], p1 = sfd[1];
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, mode);
 
 	xclose(c1);
 	xclose(p1);
@@ -1677,7 +1684,7 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
 	if (err)
 		goto close_cli0;
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, mode);
 
 	xclose(c1);
 	xclose(p1);
@@ -1735,7 +1742,7 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
 	if (err)
 		goto close;
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, mode);
 
 	xclose(c1);
 	xclose(p1);
@@ -1770,8 +1777,10 @@ static void inet_unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
 	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
 }
 
-static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
-					int verd_mapfd, enum redir_mode mode)
+static void unix_inet_redir_to_connected(int family, int type,
+					int sock_mapfd, int nop_mapfd,
+					int verd_mapfd,
+					enum redir_mode mode)
 {
 	int c0, c1, p0, p1;
 	int sfd[2];
@@ -1785,7 +1794,8 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
 		goto close_cli0;
 	c1 = sfd[0], p1 = sfd[1];
 
-	pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, verd_mapfd, mode);
+	pairs_redir_to_connected(c0, p0, c1, p1,
+				 sock_mapfd, nop_mapfd, verd_mapfd, mode);
 
 	xclose(c1);
 	xclose(p1);
@@ -1799,6 +1809,7 @@ static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel,
 					    struct bpf_map *inner_map, int family)
 {
 	int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	int nop_map = bpf_map__fd(skel->maps.nop_map);
 	int verdict_map = bpf_map__fd(skel->maps.verdict_map);
 	int sock_map = bpf_map__fd(inner_map);
 	int err;
@@ -1808,14 +1819,32 @@ static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel,
 		return;
 
 	skel->bss->test_ingress = false;
-	unix_inet_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, -1, verdict_map,
 				     REDIR_EGRESS);
-	unix_inet_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, -1, verdict_map,
+				     REDIR_EGRESS);
+
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, nop_map, verdict_map,
+				     REDIR_EGRESS);
+	unix_inet_redir_to_connected(family, SOCK_STREAM,
+				     sock_map, nop_map, verdict_map,
 				     REDIR_EGRESS);
 	skel->bss->test_ingress = true;
-	unix_inet_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, -1, verdict_map,
+				     REDIR_INGRESS);
+	unix_inet_redir_to_connected(family, SOCK_STREAM,
+				     sock_map, -1, verdict_map,
+				     REDIR_INGRESS);
+
+	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+				     sock_map, nop_map, verdict_map,
 				     REDIR_INGRESS);
-	unix_inet_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
+	unix_inet_redir_to_connected(family, SOCK_STREAM,
+				     sock_map, nop_map, verdict_map,
 				     REDIR_INGRESS);
 
 	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index fc6b2954e8f50a..59993fc9c0d7e2 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <unistd.h>
 #include <test_progs.h>
 #include <network_helpers.h>
+#include "tailcall_poke.skel.h"
+
 
 /* test_tailcall_1 checks basic functionality by patching multiple locations
  * in a single program for a single tail call slot with nop->jmp, jmp->nop
@@ -1105,6 +1108,85 @@ out:
 	bpf_object__close(tgt_obj);
 }
 
+#define JMP_TABLE "/sys/fs/bpf/jmp_table"
+
+static int poke_thread_exit;
+
+static void *poke_update(void *arg)
+{
+	__u32 zero = 0, prog1_fd, prog2_fd, map_fd;
+	struct tailcall_poke *call = arg;
+
+	map_fd = bpf_map__fd(call->maps.jmp_table);
+	prog1_fd = bpf_program__fd(call->progs.call1);
+	prog2_fd = bpf_program__fd(call->progs.call2);
+
+	while (!poke_thread_exit) {
+		bpf_map_update_elem(map_fd, &zero, &prog1_fd, BPF_ANY);
+		bpf_map_update_elem(map_fd, &zero, &prog2_fd, BPF_ANY);
+	}
+
+	return NULL;
+}
+
+/*
+ * We are trying to hit prog array update during another program load
+ * that shares the same prog array map.
+ *
+ * For that we share the jmp_table map between two skeleton instances
+ * by pinning the jmp_table to same path. Then first skeleton instance
+ * periodically updates jmp_table in 'poke update' thread while we load
+ * the second skeleton instance in the main thread.
+ */
+static void test_tailcall_poke(void)
+{
+	struct tailcall_poke *call, *test;
+	int err, cnt = 10;
+	pthread_t thread;
+
+	unlink(JMP_TABLE);
+
+	call = tailcall_poke__open_and_load();
+	if (!ASSERT_OK_PTR(call, "tailcall_poke__open"))
+		return;
+
+	err = bpf_map__pin(call->maps.jmp_table, JMP_TABLE);
+	if (!ASSERT_OK(err, "bpf_map__pin"))
+		goto out;
+
+	err = pthread_create(&thread, NULL, poke_update, call);
+	if (!ASSERT_OK(err, "new toggler"))
+		goto out;
+
+	while (cnt--) {
+		test = tailcall_poke__open();
+		if (!ASSERT_OK_PTR(test, "tailcall_poke__open"))
+			break;
+
+		err = bpf_map__set_pin_path(test->maps.jmp_table, JMP_TABLE);
+		if (!ASSERT_OK(err, "bpf_map__pin")) {
+			tailcall_poke__destroy(test);
+			break;
+		}
+
+		bpf_program__set_autoload(test->progs.test, true);
+		bpf_program__set_autoload(test->progs.call1, false);
+		bpf_program__set_autoload(test->progs.call2, false);
+
+		err = tailcall_poke__load(test);
+		tailcall_poke__destroy(test);
+		if (!ASSERT_OK(err, "tailcall_poke__load"))
+			break;
+	}
+
+	poke_thread_exit = 1;
+	ASSERT_OK(pthread_join(thread, NULL), "pthread_join");
+
+out:
+	bpf_map__unpin(call->maps.jmp_table, JMP_TABLE);
+	tailcall_poke__destroy(call);
+}
+
 void test_tailcalls(void)
 {
 	if (test__start_subtest("tailcall_1"))
@@ -1139,4 +1221,6 @@ void test_tailcalls(void)
 		test_tailcall_bpf2bpf_fentry_fexit();
 	if (test__start_subtest("tailcall_bpf2bpf_fentry_entry"))
 		test_tailcall_bpf2bpf_fentry_entry();
+	if (test__start_subtest("tailcall_poke"))
+		test_tailcall_poke();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index 6ee22c3b251ad0..518f143c5b0fec 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -24,6 +24,7 @@
 
 #include "test_progs.h"
 #include "network_helpers.h"
+#include "netlink_helpers.h"
 #include "test_tc_neigh_fib.skel.h"
 #include "test_tc_neigh.skel.h"
 #include "test_tc_peer.skel.h"
@@ -110,11 +111,17 @@ static void netns_setup_namespaces_nofail(const char *verb)
 	}
 }
 
+enum dev_mode {
+	MODE_VETH,
+	MODE_NETKIT,
+};
+
 struct netns_setup_result {
-	int ifindex_veth_src;
-	int ifindex_veth_src_fwd;
-	int ifindex_veth_dst;
-	int ifindex_veth_dst_fwd;
+	enum dev_mode dev_mode;
+	int ifindex_src;
+	int ifindex_src_fwd;
+	int ifindex_dst;
+	int ifindex_dst_fwd;
 };
 
 static int get_ifaddr(const char *name, char *ifaddr)
@@ -137,58 +144,110 @@ static int get_ifaddr(const char *name, char *ifaddr)
 	return 0;
 }
 
+static int create_netkit(int mode, char *prim, char *peer)
+{
+	struct rtattr *linkinfo, *data, *peer_info;
+	struct rtnl_handle rth = { .fd = -1 };
+	const char *type = "netkit";
+	struct {
+		struct nlmsghdr n;
+		struct ifinfomsg i;
+		char buf[1024];
+	} req = {};
+	int err;
+
+	err = rtnl_open(&rth, 0);
+	if (!ASSERT_OK(err, "open_rtnetlink"))
+		return err;
+
+	memset(&req, 0, sizeof(req));
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
+	req.n.nlmsg_type = RTM_NEWLINK;
+	req.i.ifi_family = AF_UNSPEC;
+
+	addattr_l(&req.n, sizeof(req), IFLA_IFNAME, prim, strlen(prim));
+	linkinfo = addattr_nest(&req.n, sizeof(req), IFLA_LINKINFO);
+	addattr_l(&req.n, sizeof(req), IFLA_INFO_KIND, type, strlen(type));
+	data = addattr_nest(&req.n, sizeof(req), IFLA_INFO_DATA);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode);
+	peer_info = addattr_nest(&req.n, sizeof(req), IFLA_NETKIT_PEER_INFO);
+	req.n.nlmsg_len += sizeof(struct ifinfomsg);
+	addattr_l(&req.n, sizeof(req), IFLA_IFNAME, peer, strlen(peer));
+	addattr_nest_end(&req.n, peer_info);
+	addattr_nest_end(&req.n, data);
+	addattr_nest_end(&req.n, linkinfo);
+
+	err = rtnl_talk(&rth, &req.n, NULL);
+	ASSERT_OK(err, "talk_rtnetlink");
+	rtnl_close(&rth);
+	return err;
+}
+
 static int netns_setup_links_and_routes(struct netns_setup_result *result)
 {
 	struct nstoken *nstoken = NULL;
-	char veth_src_fwd_addr[IFADDR_STR_LEN+1] = {};
-
-	SYS(fail, "ip link add veth_src type veth peer name veth_src_fwd");
-	SYS(fail, "ip link add veth_dst type veth peer name veth_dst_fwd");
+	char src_fwd_addr[IFADDR_STR_LEN+1] = {};
+	int err;
 
-	SYS(fail, "ip link set veth_dst_fwd address " MAC_DST_FWD);
-	SYS(fail, "ip link set veth_dst address " MAC_DST);
+	if (result->dev_mode == MODE_VETH) {
+		SYS(fail, "ip link add src type veth peer name src_fwd");
+		SYS(fail, "ip link add dst type veth peer name dst_fwd");
+
+		SYS(fail, "ip link set dst_fwd address " MAC_DST_FWD);
+		SYS(fail, "ip link set dst address " MAC_DST);
+	} else if (result->dev_mode == MODE_NETKIT) {
+		err = create_netkit(NETKIT_L3, "src", "src_fwd");
+		if (!ASSERT_OK(err, "create_ifindex_src"))
+			goto fail;
+		err = create_netkit(NETKIT_L3, "dst", "dst_fwd");
+		if (!ASSERT_OK(err, "create_ifindex_dst"))
+			goto fail;
+	}
 
-	if (get_ifaddr("veth_src_fwd", veth_src_fwd_addr))
+	if (get_ifaddr("src_fwd", src_fwd_addr))
 		goto fail;
 
-	result->ifindex_veth_src = if_nametoindex("veth_src");
-	if (!ASSERT_GT(result->ifindex_veth_src, 0, "ifindex_veth_src"))
+	result->ifindex_src = if_nametoindex("src");
+	if (!ASSERT_GT(result->ifindex_src, 0, "ifindex_src"))
 		goto fail;
 
-	result->ifindex_veth_src_fwd = if_nametoindex("veth_src_fwd");
-	if (!ASSERT_GT(result->ifindex_veth_src_fwd, 0, "ifindex_veth_src_fwd"))
+	result->ifindex_src_fwd = if_nametoindex("src_fwd");
+	if (!ASSERT_GT(result->ifindex_src_fwd, 0, "ifindex_src_fwd"))
 		goto fail;
 
-	result->ifindex_veth_dst = if_nametoindex("veth_dst");
-	if (!ASSERT_GT(result->ifindex_veth_dst, 0, "ifindex_veth_dst"))
+	result->ifindex_dst = if_nametoindex("dst");
+	if (!ASSERT_GT(result->ifindex_dst, 0, "ifindex_dst"))
 		goto fail;
 
-	result->ifindex_veth_dst_fwd = if_nametoindex("veth_dst_fwd");
-	if (!ASSERT_GT(result->ifindex_veth_dst_fwd, 0, "ifindex_veth_dst_fwd"))
+	result->ifindex_dst_fwd = if_nametoindex("dst_fwd");
+	if (!ASSERT_GT(result->ifindex_dst_fwd, 0, "ifindex_dst_fwd"))
 		goto fail;
 
-	SYS(fail, "ip link set veth_src netns " NS_SRC);
-	SYS(fail, "ip link set veth_src_fwd netns " NS_FWD);
-	SYS(fail, "ip link set veth_dst_fwd netns " NS_FWD);
-	SYS(fail, "ip link set veth_dst netns " NS_DST);
+	SYS(fail, "ip link set src netns " NS_SRC);
+	SYS(fail, "ip link set src_fwd netns " NS_FWD);
+	SYS(fail, "ip link set dst_fwd netns " NS_FWD);
+	SYS(fail, "ip link set dst netns " NS_DST);
 
 	/** setup in 'src' namespace */
 	nstoken = open_netns(NS_SRC);
 	if (!ASSERT_OK_PTR(nstoken, "setns src"))
 		goto fail;
 
-	SYS(fail, "ip addr add " IP4_SRC "/32 dev veth_src");
-	SYS(fail, "ip addr add " IP6_SRC "/128 dev veth_src nodad");
-	SYS(fail, "ip link set dev veth_src up");
+	SYS(fail, "ip addr add " IP4_SRC "/32 dev src");
+	SYS(fail, "ip addr add " IP6_SRC "/128 dev src nodad");
+	SYS(fail, "ip link set dev src up");
 
-	SYS(fail, "ip route add " IP4_DST "/32 dev veth_src scope global");
-	SYS(fail, "ip route add " IP4_NET "/16 dev veth_src scope global");
-	SYS(fail, "ip route add " IP6_DST "/128 dev veth_src scope global");
+	SYS(fail, "ip route add " IP4_DST "/32 dev src scope global");
+	SYS(fail, "ip route add " IP4_NET "/16 dev src scope global");
+	SYS(fail, "ip route add " IP6_DST "/128 dev src scope global");
 
-	SYS(fail, "ip neigh add " IP4_DST " dev veth_src lladdr %s",
-	    veth_src_fwd_addr);
-	SYS(fail, "ip neigh add " IP6_DST " dev veth_src lladdr %s",
-	    veth_src_fwd_addr);
+	if (result->dev_mode == MODE_VETH) {
+		SYS(fail, "ip neigh add " IP4_DST " dev src lladdr %s",
+		    src_fwd_addr);
+		SYS(fail, "ip neigh add " IP6_DST " dev src lladdr %s",
+		    src_fwd_addr);
+	}
 
 	close_netns(nstoken);
 
@@ -201,15 +260,15 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 	 * needs v4 one in order to start ARP probing. IP4_NET route is added
 	 * to the endpoints so that the ARP processing will reply.
 	 */
-	SYS(fail, "ip addr add " IP4_SLL "/32 dev veth_src_fwd");
-	SYS(fail, "ip addr add " IP4_DLL "/32 dev veth_dst_fwd");
-	SYS(fail, "ip link set dev veth_src_fwd up");
-	SYS(fail, "ip link set dev veth_dst_fwd up");
+	SYS(fail, "ip addr add " IP4_SLL "/32 dev src_fwd");
+	SYS(fail, "ip addr add " IP4_DLL "/32 dev dst_fwd");
+	SYS(fail, "ip link set dev src_fwd up");
+	SYS(fail, "ip link set dev dst_fwd up");
 
-	SYS(fail, "ip route add " IP4_SRC "/32 dev veth_src_fwd scope global");
-	SYS(fail, "ip route add " IP6_SRC "/128 dev veth_src_fwd scope global");
-	SYS(fail, "ip route add " IP4_DST "/32 dev veth_dst_fwd scope global");
-	SYS(fail, "ip route add " IP6_DST "/128 dev veth_dst_fwd scope global");
+	SYS(fail, "ip route add " IP4_SRC "/32 dev src_fwd scope global");
+	SYS(fail, "ip route add " IP6_SRC "/128 dev src_fwd scope global");
+	SYS(fail, "ip route add " IP4_DST "/32 dev dst_fwd scope global");
+	SYS(fail, "ip route add " IP6_DST "/128 dev dst_fwd scope global");
 
 	close_netns(nstoken);
 
@@ -218,16 +277,18 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 	if (!ASSERT_OK_PTR(nstoken, "setns dst"))
 		goto fail;
 
-	SYS(fail, "ip addr add " IP4_DST "/32 dev veth_dst");
-	SYS(fail, "ip addr add " IP6_DST "/128 dev veth_dst nodad");
-	SYS(fail, "ip link set dev veth_dst up");
+	SYS(fail, "ip addr add " IP4_DST "/32 dev dst");
+	SYS(fail, "ip addr add " IP6_DST "/128 dev dst nodad");
+	SYS(fail, "ip link set dev dst up");
 
-	SYS(fail, "ip route add " IP4_SRC "/32 dev veth_dst scope global");
-	SYS(fail, "ip route add " IP4_NET "/16 dev veth_dst scope global");
-	SYS(fail, "ip route add " IP6_SRC "/128 dev veth_dst scope global");
+	SYS(fail, "ip route add " IP4_SRC "/32 dev dst scope global");
+	SYS(fail, "ip route add " IP4_NET "/16 dev dst scope global");
+	SYS(fail, "ip route add " IP6_SRC "/128 dev dst scope global");
 
-	SYS(fail, "ip neigh add " IP4_SRC " dev veth_dst lladdr " MAC_DST_FWD);
-	SYS(fail, "ip neigh add " IP6_SRC " dev veth_dst lladdr " MAC_DST_FWD);
+	if (result->dev_mode == MODE_VETH) {
+		SYS(fail, "ip neigh add " IP4_SRC " dev dst lladdr " MAC_DST_FWD);
+		SYS(fail, "ip neigh add " IP6_SRC " dev dst lladdr " MAC_DST_FWD);
+	}
 
 	close_netns(nstoken);
 
@@ -293,23 +354,23 @@ static int netns_load_bpf(const struct bpf_program *src_prog,
 			  const struct bpf_program *chk_prog,
 			  const struct netns_setup_result *setup_result)
 {
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src_fwd);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_src_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd);
 	int err;
 
-	/* tc qdisc add dev veth_src_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_src_fwd, setup_result->ifindex_veth_src_fwd);
-	/* tc filter add dev veth_src_fwd ingress bpf da src_prog */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS, src_prog, 0);
-	/* tc filter add dev veth_src_fwd egress bpf da chk_prog */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS, chk_prog, 0);
+	/* tc qdisc add dev src_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_src_fwd, setup_result->ifindex_src_fwd);
+	/* tc filter add dev src_fwd ingress bpf da src_prog */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS, src_prog, 0);
+	/* tc filter add dev src_fwd egress bpf da chk_prog */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS, chk_prog, 0);
 
-	/* tc qdisc add dev veth_dst_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd);
-	/* tc filter add dev veth_dst_fwd ingress bpf da dst_prog */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, dst_prog, 0);
-	/* tc filter add dev veth_dst_fwd egress bpf da chk_prog */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, chk_prog, 0);
+	/* tc qdisc add dev dst_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd);
+	/* tc filter add dev dst_fwd ingress bpf da dst_prog */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, dst_prog, 0);
+	/* tc filter add dev dst_fwd egress bpf da chk_prog */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, chk_prog, 0);
 
 	return 0;
 fail:
@@ -539,10 +600,10 @@ done:
 static int netns_load_dtime_bpf(struct test_tc_dtime *skel,
 				const struct netns_setup_result *setup_result)
 {
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src_fwd);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_src_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_src);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_dst);
 	struct nstoken *nstoken;
 	int err;
 
@@ -550,58 +611,58 @@ static int netns_load_dtime_bpf(struct test_tc_dtime *skel,
 	nstoken = open_netns(NS_SRC);
 	if (!ASSERT_OK_PTR(nstoken, "setns " NS_SRC))
 		return -1;
-	/* tc qdisc add dev veth_src clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_src, setup_result->ifindex_veth_src);
-	/* tc filter add dev veth_src ingress bpf da ingress_host */
-	XGRESS_FILTER_ADD(&qdisc_veth_src, BPF_TC_INGRESS, skel->progs.ingress_host, 0);
-	/* tc filter add dev veth_src egress bpf da egress_host */
-	XGRESS_FILTER_ADD(&qdisc_veth_src, BPF_TC_EGRESS, skel->progs.egress_host, 0);
+	/* tc qdisc add dev src clsact */
+	QDISC_CLSACT_CREATE(&qdisc_src, setup_result->ifindex_src);
+	/* tc filter add dev src ingress bpf da ingress_host */
+	XGRESS_FILTER_ADD(&qdisc_src, BPF_TC_INGRESS, skel->progs.ingress_host, 0);
+	/* tc filter add dev src egress bpf da egress_host */
+	XGRESS_FILTER_ADD(&qdisc_src, BPF_TC_EGRESS, skel->progs.egress_host, 0);
 	close_netns(nstoken);
 
 	/* setup ns_dst tc progs */
 	nstoken = open_netns(NS_DST);
 	if (!ASSERT_OK_PTR(nstoken, "setns " NS_DST))
 		return -1;
-	/* tc qdisc add dev veth_dst clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_dst, setup_result->ifindex_veth_dst);
-	/* tc filter add dev veth_dst ingress bpf da ingress_host */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst, BPF_TC_INGRESS, skel->progs.ingress_host, 0);
-	/* tc filter add dev veth_dst egress bpf da egress_host */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst, BPF_TC_EGRESS, skel->progs.egress_host, 0);
+	/* tc qdisc add dev dst clsact */
+	QDISC_CLSACT_CREATE(&qdisc_dst, setup_result->ifindex_dst);
+	/* tc filter add dev dst ingress bpf da ingress_host */
+	XGRESS_FILTER_ADD(&qdisc_dst, BPF_TC_INGRESS, skel->progs.ingress_host, 0);
+	/* tc filter add dev dst egress bpf da egress_host */
+	XGRESS_FILTER_ADD(&qdisc_dst, BPF_TC_EGRESS, skel->progs.egress_host, 0);
 	close_netns(nstoken);
 
 	/* setup ns_fwd tc progs */
 	nstoken = open_netns(NS_FWD);
 	if (!ASSERT_OK_PTR(nstoken, "setns " NS_FWD))
 		return -1;
-	/* tc qdisc add dev veth_dst_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd);
-	/* tc filter add dev veth_dst_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS,
+	/* tc qdisc add dev dst_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd);
+	/* tc filter add dev dst_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS,
 			  skel->progs.ingress_fwdns_prio100, 100);
-	/* tc filter add dev veth_dst_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS,
+	/* tc filter add dev dst_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS,
 			  skel->progs.ingress_fwdns_prio101, 101);
-	/* tc filter add dev veth_dst_fwd egress prio 100 bpf da egress_fwdns_prio100 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS,
+	/* tc filter add dev dst_fwd egress prio 100 bpf da egress_fwdns_prio100 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS,
 			  skel->progs.egress_fwdns_prio100, 100);
-	/* tc filter add dev veth_dst_fwd egress prio 101 bpf da egress_fwdns_prio101 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS,
+	/* tc filter add dev dst_fwd egress prio 101 bpf da egress_fwdns_prio101 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS,
 			  skel->progs.egress_fwdns_prio101, 101);
 
-	/* tc qdisc add dev veth_src_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_src_fwd, setup_result->ifindex_veth_src_fwd);
-	/* tc filter add dev veth_src_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS,
+	/* tc qdisc add dev src_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_src_fwd, setup_result->ifindex_src_fwd);
+	/* tc filter add dev src_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS,
 			  skel->progs.ingress_fwdns_prio100, 100);
-	/* tc filter add dev veth_src_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS,
+	/* tc filter add dev src_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS,
 			  skel->progs.ingress_fwdns_prio101, 101);
-	/* tc filter add dev veth_src_fwd egress prio 100 bpf da egress_fwdns_prio100 */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS,
+	/* tc filter add dev src_fwd egress prio 100 bpf da egress_fwdns_prio100 */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS,
 			  skel->progs.egress_fwdns_prio100, 100);
-	/* tc filter add dev veth_src_fwd egress prio 101 bpf da egress_fwdns_prio101 */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS,
+	/* tc filter add dev src_fwd egress prio 101 bpf da egress_fwdns_prio101 */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS,
 			  skel->progs.egress_fwdns_prio101, 101);
 	close_netns(nstoken);
 	return 0;
@@ -777,8 +838,8 @@ static void test_tc_redirect_dtime(struct netns_setup_result *setup_result)
 	if (!ASSERT_OK_PTR(skel, "test_tc_dtime__open"))
 		return;
 
-	skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd;
-	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+	skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd;
 
 	err = test_tc_dtime__load(skel);
 	if (!ASSERT_OK(err, "test_tc_dtime__load"))
@@ -868,8 +929,8 @@ static void test_tc_redirect_neigh(struct netns_setup_result *setup_result)
 	if (!ASSERT_OK_PTR(skel, "test_tc_neigh__open"))
 		goto done;
 
-	skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd;
-	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+	skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd;
 
 	err = test_tc_neigh__load(skel);
 	if (!ASSERT_OK(err, "test_tc_neigh__load"))
@@ -904,8 +965,8 @@ static void test_tc_redirect_peer(struct netns_setup_result *setup_result)
 	if (!ASSERT_OK_PTR(skel, "test_tc_peer__open"))
 		goto done;
 
-	skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd;
-	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+	skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd;
 
 	err = test_tc_peer__load(skel);
 	if (!ASSERT_OK(err, "test_tc_peer__load"))
@@ -996,7 +1057,7 @@ static int tun_relay_loop(int src_fd, int target_fd)
 static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result)
 {
 	LIBBPF_OPTS(bpf_tc_hook, qdisc_tun_fwd);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd);
 	struct test_tc_peer *skel = NULL;
 	struct nstoken *nstoken = NULL;
 	int err;
@@ -1045,7 +1106,7 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result)
 		goto fail;
 
 	skel->rodata->IFINDEX_SRC = ifindex;
-	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd;
 
 	err = test_tc_peer__load(skel);
 	if (!ASSERT_OK(err, "test_tc_peer__load"))
@@ -1053,19 +1114,19 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result)
 
 	/* Load "tc_src_l3" to the tun_fwd interface to redirect packets
 	 * towards dst, and "tc_dst" to redirect packets
-	 * and "tc_chk" on veth_dst_fwd to drop non-redirected packets.
+	 * and "tc_chk" on dst_fwd to drop non-redirected packets.
 	 */
 	/* tc qdisc add dev tun_fwd clsact */
 	QDISC_CLSACT_CREATE(&qdisc_tun_fwd, ifindex);
 	/* tc filter add dev tun_fwd ingress bpf da tc_src_l3 */
 	XGRESS_FILTER_ADD(&qdisc_tun_fwd, BPF_TC_INGRESS, skel->progs.tc_src_l3, 0);
 
-	/* tc qdisc add dev veth_dst_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd);
-	/* tc filter add dev veth_dst_fwd ingress bpf da tc_dst_l3 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, skel->progs.tc_dst_l3, 0);
-	/* tc filter add dev veth_dst_fwd egress bpf da tc_chk */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, skel->progs.tc_chk, 0);
+	/* tc qdisc add dev dst_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd);
+	/* tc filter add dev dst_fwd ingress bpf da tc_dst_l3 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, skel->progs.tc_dst_l3, 0);
+	/* tc filter add dev dst_fwd egress bpf da tc_chk */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, skel->progs.tc_chk, 0);
 
 	/* Setup route and neigh tables */
 	SYS(fail, "ip -netns " NS_SRC " addr add dev tun_src " IP4_TUN_SRC "/24");
@@ -1074,17 +1135,17 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result)
 	SYS(fail, "ip -netns " NS_SRC " addr add dev tun_src " IP6_TUN_SRC "/64 nodad");
 	SYS(fail, "ip -netns " NS_FWD " addr add dev tun_fwd " IP6_TUN_FWD "/64 nodad");
 
-	SYS(fail, "ip -netns " NS_SRC " route del " IP4_DST "/32 dev veth_src scope global");
+	SYS(fail, "ip -netns " NS_SRC " route del " IP4_DST "/32 dev src scope global");
 	SYS(fail, "ip -netns " NS_SRC " route add " IP4_DST "/32 via " IP4_TUN_FWD
 	    " dev tun_src scope global");
-	SYS(fail, "ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev veth_dst scope global");
-	SYS(fail, "ip -netns " NS_SRC " route del " IP6_DST "/128 dev veth_src scope global");
+	SYS(fail, "ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev dst scope global");
+	SYS(fail, "ip -netns " NS_SRC " route del " IP6_DST "/128 dev src scope global");
 	SYS(fail, "ip -netns " NS_SRC " route add " IP6_DST "/128 via " IP6_TUN_FWD
 	    " dev tun_src scope global");
-	SYS(fail, "ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev veth_dst scope global");
+	SYS(fail, "ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev dst scope global");
 
-	SYS(fail, "ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD);
-	SYS(fail, "ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD);
+	SYS(fail, "ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev dst lladdr " MAC_DST_FWD);
+	SYS(fail, "ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev dst lladdr " MAC_DST_FWD);
 
 	if (!ASSERT_OK(set_forwarding(false), "disable forwarding"))
 		goto fail;
@@ -1106,9 +1167,9 @@ fail:
 		close_netns(nstoken);
 }
 
-#define RUN_TEST(name)                                                                      \
+#define RUN_TEST(name, mode)                                                                \
 	({                                                                                  \
-		struct netns_setup_result setup_result;                                     \
+		struct netns_setup_result setup_result = { .dev_mode = mode, };             \
 		if (test__start_subtest(#name))                                             \
 			if (ASSERT_OK(netns_setup_namespaces("add"), "setup namespaces")) { \
 				if (ASSERT_OK(netns_setup_links_and_routes(&setup_result),  \
@@ -1122,11 +1183,13 @@ static void *test_tc_redirect_run_tests(void *arg)
 {
 	netns_setup_namespaces_nofail("delete");
 
-	RUN_TEST(tc_redirect_peer);
-	RUN_TEST(tc_redirect_peer_l3);
-	RUN_TEST(tc_redirect_neigh);
-	RUN_TEST(tc_redirect_neigh_fib);
-	RUN_TEST(tc_redirect_dtime);
+	RUN_TEST(tc_redirect_peer, MODE_VETH);
+	RUN_TEST(tc_redirect_peer, MODE_NETKIT);
+	RUN_TEST(tc_redirect_peer_l3, MODE_VETH);
+	RUN_TEST(tc_redirect_peer_l3, MODE_NETKIT);
+	RUN_TEST(tc_redirect_neigh, MODE_VETH);
+	RUN_TEST(tc_redirect_neigh_fib, MODE_VETH);
+	RUN_TEST(tc_redirect_dtime, MODE_VETH);
 	return NULL;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
index 214d9f4a94a538..ea933fd151c389 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
@@ -8,7 +8,8 @@
 #include <sys/types.h>
 #include <test_progs.h>
 
-#define TDIR "/sys/kernel/debug"
+/* TDIR must be in a location we can create a directory in. */
+#define TDIR "/tmp/test_bpffs_testdir"
 
 static int read_iter(char *file)
 {
@@ -43,8 +44,11 @@ static int fn(void)
 	if (!ASSERT_OK(err, "mount /"))
 		goto out;
 
-	err = umount(TDIR);
-	if (!ASSERT_OK(err, "umount " TDIR))
+	err =  mkdir(TDIR, 0777);
+	/* If the directory already exists we can carry on. It may be left over
+	 * from a previous run.
+	 */
+	if ((err && errno != EEXIST) && !ASSERT_OK(err, "mkdir " TDIR))
 		goto out;
 
 	err = mount("none", TDIR, "tmpfs", 0, NULL);
@@ -138,6 +142,7 @@ out:
 	rmdir(TDIR "/fs1");
 	rmdir(TDIR "/fs2");
 	umount(TDIR);
+	rmdir(TDIR);
 	exit(err);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index e3e68c97b40cfd..5cfa7a6316b63c 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -31,6 +31,7 @@
 #include "verifier_helper_restricted.skel.h"
 #include "verifier_helper_value_access.skel.h"
 #include "verifier_int_ptr.skel.h"
+#include "verifier_iterating_callbacks.skel.h"
 #include "verifier_jeq_infer_not_null.skel.h"
 #include "verifier_ld_ind.skel.h"
 #include "verifier_ldsx.skel.h"
@@ -46,6 +47,7 @@
 #include "verifier_movsx.skel.h"
 #include "verifier_netfilter_ctx.skel.h"
 #include "verifier_netfilter_retcode.skel.h"
+#include "verifier_precision.skel.h"
 #include "verifier_prevent_map_lookup.skel.h"
 #include "verifier_raw_stack.skel.h"
 #include "verifier_raw_tp_writable.skel.h"
@@ -138,6 +140,7 @@ void test_verifier_helper_packet_access(void) { RUN(verifier_helper_packet_acces
 void test_verifier_helper_restricted(void)    { RUN(verifier_helper_restricted); }
 void test_verifier_helper_value_access(void)  { RUN(verifier_helper_value_access); }
 void test_verifier_int_ptr(void)              { RUN(verifier_int_ptr); }
+void test_verifier_iterating_callbacks(void)  { RUN(verifier_iterating_callbacks); }
 void test_verifier_jeq_infer_not_null(void)   { RUN(verifier_jeq_infer_not_null); }
 void test_verifier_ld_ind(void)               { RUN(verifier_ld_ind); }
 void test_verifier_ldsx(void)                  { RUN(verifier_ldsx); }
@@ -153,6 +156,7 @@ void test_verifier_meta_access(void)          { RUN(verifier_meta_access); }
 void test_verifier_movsx(void)                 { RUN(verifier_movsx); }
 void test_verifier_netfilter_ctx(void)        { RUN(verifier_netfilter_ctx); }
 void test_verifier_netfilter_retcode(void)    { RUN(verifier_netfilter_retcode); }
+void test_verifier_precision(void)            { RUN(verifier_precision); }
 void test_verifier_prevent_map_lookup(void)   { RUN(verifier_prevent_map_lookup); }
 void test_verifier_raw_stack(void)            { RUN(verifier_raw_stack); }
 void test_verifier_raw_tp_writable(void)      { RUN(verifier_raw_tp_writable); }
diff --git a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c
index 4ce76eb064c41c..d461746fd3c1e7 100644
--- a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c
+++ b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c
@@ -15,13 +15,16 @@ static int empty_callback(__u32 index, void *data)
 	return 0;
 }
 
+static int outer_loop(__u32 index, void *data)
+{
+	bpf_loop(nr_loops, empty_callback, NULL, 0);
+	__sync_add_and_fetch(&hits, nr_loops);
+	return 0;
+}
+
 SEC("fentry/" SYS_PREFIX "sys_getpgid")
 int benchmark(void *ctx)
 {
-	for (int i = 0; i < 1000; i++) {
-		bpf_loop(nr_loops, empty_callback, NULL, 0);
-
-		__sync_add_and_fetch(&hits, nr_loops);
-	}
+	bpf_loop(1000, outer_loop, NULL, 0);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/cb_refs.c b/tools/testing/selftests/bpf/progs/cb_refs.c
index 76d661b20e87d0..56c764df819679 100644
--- a/tools/testing/selftests/bpf/progs/cb_refs.c
+++ b/tools/testing/selftests/bpf/progs/cb_refs.c
@@ -33,6 +33,7 @@ int underflow_prog(void *ctx)
 	if (!p)
 		return 0;
 	bpf_for_each_map_elem(&array_map, cb1, &p, 0);
+	bpf_kfunc_call_test_release(p);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c
index 4c39e920dac223..8c0ef2742208ae 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_fail.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c
@@ -171,6 +171,7 @@ int reject_with_rbtree_add_throw(void *ctx)
 		return 0;
 	bpf_spin_lock(&lock);
 	bpf_rbtree_add(&rbtree, &f->node, rbless);
+	bpf_spin_unlock(&lock);
 	return 0;
 }
 
@@ -214,6 +215,7 @@ int reject_with_cb_reference(void *ctx)
 	if (!f)
 		return 0;
 	bpf_loop(5, subprog_cb_ref, NULL, 0);
+	bpf_obj_drop(f);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/iters_css_task.c b/tools/testing/selftests/bpf/progs/iters_css_task.c
index 5089ce384a1c7a..9ac758649cb8cc 100644
--- a/tools/testing/selftests/bpf/progs/iters_css_task.c
+++ b/tools/testing/selftests/bpf/progs/iters_css_task.c
@@ -10,6 +10,7 @@
 
 char _license[] SEC("license") = "GPL";
 
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
 struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
 void bpf_cgroup_release(struct cgroup *p) __ksym;
 
@@ -45,3 +46,57 @@ int BPF_PROG(iter_css_task_for_each, struct vm_area_struct *vma,
 
 	return -EPERM;
 }
+
+static inline u64 cgroup_id(struct cgroup *cgrp)
+{
+	return cgrp->kn->id;
+}
+
+SEC("?iter/cgroup")
+int cgroup_id_printer(struct bpf_iter__cgroup *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct cgroup *cgrp = ctx->cgroup;
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+
+	/* epilogue */
+	if (cgrp == NULL) {
+		BPF_SEQ_PRINTF(seq, "epilogue\n");
+		return 0;
+	}
+
+	/* prologue */
+	if (ctx->meta->seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "prologue\n");
+
+	BPF_SEQ_PRINTF(seq, "%8llu\n", cgroup_id(cgrp));
+
+	css = &cgrp->self;
+	css_task_cnt = 0;
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) {
+		if (task->pid == target_pid)
+			css_task_cnt++;
+	}
+
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int BPF_PROG(iter_css_task_for_each_sleep)
+{
+	u64 cgrp_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp = bpf_cgroup_from_id(cgrp_id);
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+
+	if (cgrp == NULL)
+		return 0;
+	css = &cgrp->self;
+
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) {
+
+	}
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_task_failure.c b/tools/testing/selftests/bpf/progs/iters_task_failure.c
index c3bf96a67dba9d..6b1588d7065273 100644
--- a/tools/testing/selftests/bpf/progs/iters_task_failure.c
+++ b/tools/testing/selftests/bpf/progs/iters_task_failure.c
@@ -84,8 +84,8 @@ int BPF_PROG(iter_css_lock_and_unlock)
 	return 0;
 }
 
-SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
-__failure __msg("css_task_iter is only allowed in bpf_lsm and bpf iter-s")
+SEC("?fentry/" SYS_PREFIX "sys_getpgid")
+__failure __msg("css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs")
 int BPF_PROG(iter_css_task_for_each)
 {
 	u64 cg_id = bpf_get_current_cgroup_id();
diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index e02cfd38074695..40df2cc26eaf9d 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -24,9 +24,11 @@ struct task_struct {};
 #define STACK_TABLE_EPOCH_SHIFT 20
 #define STROBE_MAX_STR_LEN 1
 #define STROBE_MAX_CFGS 32
+#define READ_MAP_VAR_PAYLOAD_CAP					\
+	((1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN)
 #define STROBE_MAX_PAYLOAD						\
 	(STROBE_MAX_STRS * STROBE_MAX_STR_LEN +				\
-	STROBE_MAX_MAPS * (1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN)
+	 STROBE_MAX_MAPS * READ_MAP_VAR_PAYLOAD_CAP)
 
 struct strobe_value_header {
 	/*
@@ -355,7 +357,7 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg,
 					     size_t idx, void *tls_base,
 					     struct strobe_value_generic *value,
 					     struct strobemeta_payload *data,
-					     void *payload)
+					     size_t off)
 {
 	void *location;
 	uint64_t len;
@@ -366,7 +368,7 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg,
 		return 0;
 
 	bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location);
-	len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, value->ptr);
+	len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, value->ptr);
 	/*
 	 * if bpf_probe_read_user_str returns error (<0), due to casting to
 	 * unsinged int, it will become big number, so next check is
@@ -378,14 +380,14 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg,
 		return 0;
 
 	data->str_lens[idx] = len;
-	return len;
+	return off + len;
 }
 
-static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
-					  size_t idx, void *tls_base,
-					  struct strobe_value_generic *value,
-					  struct strobemeta_payload *data,
-					  void *payload)
+static __always_inline uint64_t read_map_var(struct strobemeta_cfg *cfg,
+					     size_t idx, void *tls_base,
+					     struct strobe_value_generic *value,
+					     struct strobemeta_payload *data,
+					     size_t off)
 {
 	struct strobe_map_descr* descr = &data->map_descrs[idx];
 	struct strobe_map_raw map;
@@ -397,11 +399,11 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 
 	location = calc_location(&cfg->map_locs[idx], tls_base);
 	if (!location)
-		return payload;
+		return off;
 
 	bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location);
 	if (bpf_probe_read_user(&map, sizeof(struct strobe_map_raw), value->ptr))
-		return payload;
+		return off;
 
 	descr->id = map.id;
 	descr->cnt = map.cnt;
@@ -410,10 +412,10 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 		data->req_meta_valid = 1;
 	}
 
-	len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, map.tag);
+	len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, map.tag);
 	if (len <= STROBE_MAX_STR_LEN) {
 		descr->tag_len = len;
-		payload += len;
+		off += len;
 	}
 
 #ifdef NO_UNROLL
@@ -426,22 +428,22 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 			break;
 
 		descr->key_lens[i] = 0;
-		len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN,
+		len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN,
 					      map.entries[i].key);
 		if (len <= STROBE_MAX_STR_LEN) {
 			descr->key_lens[i] = len;
-			payload += len;
+			off += len;
 		}
 		descr->val_lens[i] = 0;
-		len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN,
+		len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN,
 					      map.entries[i].val);
 		if (len <= STROBE_MAX_STR_LEN) {
 			descr->val_lens[i] = len;
-			payload += len;
+			off += len;
 		}
 	}
 
-	return payload;
+	return off;
 }
 
 #ifdef USE_BPF_LOOP
@@ -455,14 +457,20 @@ struct read_var_ctx {
 	struct strobemeta_payload *data;
 	void *tls_base;
 	struct strobemeta_cfg *cfg;
-	void *payload;
+	size_t payload_off;
 	/* value gets mutated */
 	struct strobe_value_generic *value;
 	enum read_type type;
 };
 
-static int read_var_callback(__u32 index, struct read_var_ctx *ctx)
+static int read_var_callback(__u64 index, struct read_var_ctx *ctx)
 {
+	/* lose precision info for ctx->payload_off, verifier won't track
+	 * double xor, barrier_var() is needed to force clang keep both xors.
+	 */
+	ctx->payload_off ^= index;
+	barrier_var(ctx->payload_off);
+	ctx->payload_off ^= index;
 	switch (ctx->type) {
 	case READ_INT_VAR:
 		if (index >= STROBE_MAX_INTS)
@@ -472,14 +480,18 @@ static int read_var_callback(__u32 index, struct read_var_ctx *ctx)
 	case READ_MAP_VAR:
 		if (index >= STROBE_MAX_MAPS)
 			return 1;
-		ctx->payload = read_map_var(ctx->cfg, index, ctx->tls_base,
-					    ctx->value, ctx->data, ctx->payload);
+		if (ctx->payload_off > sizeof(ctx->data->payload) - READ_MAP_VAR_PAYLOAD_CAP)
+			return 1;
+		ctx->payload_off = read_map_var(ctx->cfg, index, ctx->tls_base,
+						ctx->value, ctx->data, ctx->payload_off);
 		break;
 	case READ_STR_VAR:
 		if (index >= STROBE_MAX_STRS)
 			return 1;
-		ctx->payload += read_str_var(ctx->cfg, index, ctx->tls_base,
-					     ctx->value, ctx->data, ctx->payload);
+		if (ctx->payload_off > sizeof(ctx->data->payload) - STROBE_MAX_STR_LEN)
+			return 1;
+		ctx->payload_off = read_str_var(ctx->cfg, index, ctx->tls_base,
+						ctx->value, ctx->data, ctx->payload_off);
 		break;
 	}
 	return 0;
@@ -501,7 +513,8 @@ static void *read_strobe_meta(struct task_struct *task,
 	pid_t pid = bpf_get_current_pid_tgid() >> 32;
 	struct strobe_value_generic value = {0};
 	struct strobemeta_cfg *cfg;
-	void *tls_base, *payload;
+	size_t payload_off;
+	void *tls_base;
 
 	cfg = bpf_map_lookup_elem(&strobemeta_cfgs, &pid);
 	if (!cfg)
@@ -509,7 +522,7 @@ static void *read_strobe_meta(struct task_struct *task,
 
 	data->int_vals_set_mask = 0;
 	data->req_meta_valid = 0;
-	payload = data->payload;
+	payload_off = 0;
 	/*
 	 * we don't have struct task_struct definition, it should be:
 	 * tls_base = (void *)task->thread.fsbase;
@@ -522,7 +535,7 @@ static void *read_strobe_meta(struct task_struct *task,
 		.tls_base = tls_base,
 		.value = &value,
 		.data = data,
-		.payload = payload,
+		.payload_off = 0,
 	};
 	int err;
 
@@ -540,6 +553,11 @@ static void *read_strobe_meta(struct task_struct *task,
 	err = bpf_loop(STROBE_MAX_MAPS, read_var_callback, &ctx, 0);
 	if (err != STROBE_MAX_MAPS)
 		return NULL;
+
+	payload_off = ctx.payload_off;
+	/* this should not really happen, here only to satisfy verifer */
+	if (payload_off > sizeof(data->payload))
+		payload_off = sizeof(data->payload);
 #else
 #ifdef NO_UNROLL
 #pragma clang loop unroll(disable)
@@ -555,7 +573,7 @@ static void *read_strobe_meta(struct task_struct *task,
 #pragma unroll
 #endif /* NO_UNROLL */
 	for (int i = 0; i < STROBE_MAX_STRS; ++i) {
-		payload += read_str_var(cfg, i, tls_base, &value, data, payload);
+		payload_off = read_str_var(cfg, i, tls_base, &value, data, payload_off);
 	}
 #ifdef NO_UNROLL
 #pragma clang loop unroll(disable)
@@ -563,7 +581,7 @@ static void *read_strobe_meta(struct task_struct *task,
 #pragma unroll
 #endif /* NO_UNROLL */
 	for (int i = 0; i < STROBE_MAX_MAPS; ++i) {
-		payload = read_map_var(cfg, i, tls_base, &value, data, payload);
+		payload_off = read_map_var(cfg, i, tls_base, &value, data, payload_off);
 	}
 #endif /* USE_BPF_LOOP */
 
@@ -571,7 +589,7 @@ static void *read_strobe_meta(struct task_struct *task,
 	 * return pointer right after end of payload, so it's possible to
 	 * calculate exact amount of useful data that needs to be sent
 	 */
-	return payload;
+	return &data->payload[payload_off];
 }
 
 SEC("raw_tracepoint/kfree_skb")
diff --git a/tools/testing/selftests/bpf/progs/tailcall_poke.c b/tools/testing/selftests/bpf/progs/tailcall_poke.c
new file mode 100644
index 00000000000000..c78b94b75e83e6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_poke.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+SEC("?fentry/bpf_fentry_test1")
+int BPF_PROG(test, int a)
+{
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(call1, int a)
+{
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(call2, int a)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
index 3ddcb3777912c2..2a2a942737d7a8 100644
--- a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
+++ b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
@@ -7,7 +7,8 @@
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
      (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) ||       \
-     defined(__TARGET_ARCH_s390)) && __clang_major__ >= 18
+     defined(__TARGET_ARCH_s390) || defined(__TARGET_ARCH_loongarch)) && \
+     __clang_major__ >= 18
 const volatile int skip = 0;
 #else
 const volatile int skip = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
index 464d35bd57c708..b7250eb9c30cca 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
@@ -15,6 +15,13 @@ struct {
 } sock_map SEC(".maps");
 
 struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __u64);
+} nop_map SEC(".maps");
+
+struct {
 	__uint(type, BPF_MAP_TYPE_SOCKHASH);
 	__uint(max_entries, 2);
 	__type(key, __u32);
diff --git a/tools/testing/selftests/bpf/progs/verifier_bswap.c b/tools/testing/selftests/bpf/progs/verifier_bswap.c
index 107525fb4a6a33..e61755656e8d73 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bswap.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bswap.c
@@ -6,7 +6,8 @@
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
 	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
-        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
+	defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \
+	defined(__TARGET_ARCH_loongarch)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_cfg.c b/tools/testing/selftests/bpf/progs/verifier_cfg.c
index df7697b94007b1..c1f55e1d80a426 100644
--- a/tools/testing/selftests/bpf/progs/verifier_cfg.c
+++ b/tools/testing/selftests/bpf/progs/verifier_cfg.c
@@ -97,4 +97,66 @@ l0_%=:	r2 = r0;					\
 "	::: __clobber_all);
 }
 
+SEC("socket")
+__description("conditional loop (2)")
+__success
+__failure_unpriv __msg_unpriv("back-edge from insn 10 to 11")
+__naked void conditional_loop2(void)
+{
+	asm volatile ("					\
+	r9 = 2 ll;					\
+	r3 = 0x20 ll;					\
+	r4 = 0x35 ll;					\
+	r8 = r4;					\
+	goto l1_%=;					\
+l0_%=:	r9 -= r3;					\
+	r9 -= r4;					\
+	r9 -= r8;					\
+l1_%=:	r8 += r4;					\
+	if r8 < 0x64 goto l0_%=;			\
+	r0 = r9;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unconditional loop after conditional jump")
+__failure __msg("infinite loop detected")
+__failure_unpriv __msg_unpriv("back-edge from insn 3 to 2")
+__naked void uncond_loop_after_cond_jmp(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	if r0 > 0 goto l1_%=;				\
+l0_%=:	r0 = 1;						\
+	goto l0_%=;					\
+l1_%=:	exit;						\
+"	::: __clobber_all);
+}
+
+
+__naked __noinline __used
+static unsigned long never_ending_subprog()
+{
+	asm volatile ("					\
+	r0 = r1;					\
+	goto -1;					\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unconditional loop after conditional jump")
+/* infinite loop is detected *after* check_cfg() */
+__failure __msg("infinite loop detected")
+__naked void uncond_loop_in_subprog_after_cond_jmp(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	if r0 > 0 goto l1_%=;				\
+l0_%=:	r0 += 1;					\
+	call never_ending_subprog;			\
+l1_%=:	exit;						\
+"	::: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
index 9f202eda952fdc..d1edbcff9a1858 100644
--- a/tools/testing/selftests/bpf/progs/verifier_gotol.c
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -6,7 +6,8 @@
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
 	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
-        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
+	defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \
+	defined(__TARGET_ARCH_loongarch)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
new file mode 100644
index 00000000000000..5905e036e0eaca
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 8);
+	__type(key, __u32);
+	__type(value, __u64);
+} map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_USER_RINGBUF);
+	__uint(max_entries, 8);
+} ringbuf SEC(".maps");
+
+struct vm_area_struct;
+struct bpf_map;
+
+struct buf_context {
+	char *buf;
+};
+
+struct num_context {
+	__u64 i;
+	__u64 j;
+};
+
+__u8 choice_arr[2] = { 0, 1 };
+
+static int unsafe_on_2nd_iter_cb(__u32 idx, struct buf_context *ctx)
+{
+	if (idx == 0) {
+		ctx->buf = (char *)(0xDEAD);
+		return 0;
+	}
+
+	if (bpf_probe_read_user(ctx->buf, 8, (void *)(0xBADC0FFEE)))
+		return 1;
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("R1 type=scalar expected=fp")
+int unsafe_on_2nd_iter(void *unused)
+{
+	char buf[4];
+	struct buf_context loop_ctx = { .buf = buf };
+
+	bpf_loop(100, unsafe_on_2nd_iter_cb, &loop_ctx, 0);
+	return 0;
+}
+
+static int unsafe_on_zero_iter_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i = 0;
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=32 size=1")
+int unsafe_on_zero_iter(void *unused)
+{
+	struct num_context loop_ctx = { .i = 32 };
+
+	bpf_loop(100, unsafe_on_zero_iter_cb, &loop_ctx, 0);
+	return choice_arr[loop_ctx.i];
+}
+
+static int widening_cb(__u32 idx, struct num_context *ctx)
+{
+	++ctx->i;
+	return 0;
+}
+
+SEC("?raw_tp")
+__success
+int widening(void *unused)
+{
+	struct num_context loop_ctx = { .i = 0, .j = 1 };
+
+	bpf_loop(100, widening_cb, &loop_ctx, 0);
+	/* loop_ctx.j is not changed during callback iteration,
+	 * verifier should not apply widening to it.
+	 */
+	return choice_arr[loop_ctx.j];
+}
+
+static int loop_detection_cb(__u32 idx, struct num_context *ctx)
+{
+	for (;;) {}
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("infinite loop detected")
+int loop_detection(void *unused)
+{
+	struct num_context loop_ctx = { .i = 0 };
+
+	bpf_loop(100, loop_detection_cb, &loop_ctx, 0);
+	return 0;
+}
+
+static __always_inline __u64 oob_state_machine(struct num_context *ctx)
+{
+	switch (ctx->i) {
+	case 0:
+		ctx->i = 1;
+		break;
+	case 1:
+		ctx->i = 32;
+		break;
+	}
+	return 0;
+}
+
+static __u64 for_each_map_elem_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data)
+{
+	return oob_state_machine(data);
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=32 size=1")
+int unsafe_for_each_map_elem(void *unused)
+{
+	struct num_context loop_ctx = { .i = 0 };
+
+	bpf_for_each_map_elem(&map, for_each_map_elem_cb, &loop_ctx, 0);
+	return choice_arr[loop_ctx.i];
+}
+
+static __u64 ringbuf_drain_cb(struct bpf_dynptr *dynptr, void *data)
+{
+	return oob_state_machine(data);
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=32 size=1")
+int unsafe_ringbuf_drain(void *unused)
+{
+	struct num_context loop_ctx = { .i = 0 };
+
+	bpf_user_ringbuf_drain(&ringbuf, ringbuf_drain_cb, &loop_ctx, 0);
+	return choice_arr[loop_ctx.i];
+}
+
+static __u64 find_vma_cb(struct task_struct *task, struct vm_area_struct *vma, void *data)
+{
+	return oob_state_machine(data);
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=32 size=1")
+int unsafe_find_vma(void *unused)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct num_context loop_ctx = { .i = 0 };
+
+	bpf_find_vma(task, 0, find_vma_cb, &loop_ctx, 0);
+	return choice_arr[loop_ctx.i];
+}
+
+static int iter_limit_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i++;
+	return 0;
+}
+
+SEC("?raw_tp")
+__success
+int bpf_loop_iter_limit_ok(void *unused)
+{
+	struct num_context ctx = { .i = 0 };
+
+	bpf_loop(1, iter_limit_cb, &ctx, 0);
+	return choice_arr[ctx.i];
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=2 size=1")
+int bpf_loop_iter_limit_overflow(void *unused)
+{
+	struct num_context ctx = { .i = 0 };
+
+	bpf_loop(2, iter_limit_cb, &ctx, 0);
+	return choice_arr[ctx.i];
+}
+
+static int iter_limit_level2a_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i += 100;
+	return 0;
+}
+
+static int iter_limit_level2b_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i += 10;
+	return 0;
+}
+
+static int iter_limit_level1_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i += 1;
+	bpf_loop(1, iter_limit_level2a_cb, ctx, 0);
+	bpf_loop(1, iter_limit_level2b_cb, ctx, 0);
+	return 0;
+}
+
+/* Check that path visiting every callback function once had been
+ * reached by verifier. Variables 'ctx{1,2}i' below serve as flags,
+ * with each decimal digit corresponding to a callback visit marker.
+ */
+SEC("socket")
+__success __retval(111111)
+int bpf_loop_iter_limit_nested(void *unused)
+{
+	struct num_context ctx1 = { .i = 0 };
+	struct num_context ctx2 = { .i = 0 };
+	__u64 a, b, c;
+
+	bpf_loop(1, iter_limit_level1_cb, &ctx1, 0);
+	bpf_loop(1, iter_limit_level1_cb, &ctx2, 0);
+	a = ctx1.i;
+	b = ctx2.i;
+	/* Force 'ctx1.i' and 'ctx2.i' precise. */
+	c = choice_arr[(a + b) % 2];
+	/* This makes 'c' zero, but neither clang nor verifier know it. */
+	c /= 10;
+	/* Make sure that verifier does not visit 'impossible' states:
+	 * enumerate all possible callback visit masks.
+	 */
+	if (a != 0 && a != 1 && a != 11 && a != 101 && a != 111 &&
+	    b != 0 && b != 1 && b != 11 && b != 101 && b != 111)
+		asm volatile ("r0 /= 0;" ::: "r0");
+	return 1000 * a + b + c;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
index 37552532963735..d4427d8e12174b 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ldsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -6,7 +6,8 @@
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
 	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
-        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
+	defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \
+	defined(__TARGET_ARCH_loongarch)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_loops1.c b/tools/testing/selftests/bpf/progs/verifier_loops1.c
index 5bc86af80a9ad4..71735dbf33d4f8 100644
--- a/tools/testing/selftests/bpf/progs/verifier_loops1.c
+++ b/tools/testing/selftests/bpf/progs/verifier_loops1.c
@@ -75,9 +75,10 @@ l0_%=:	r0 += 1;					\
 "	::: __clobber_all);
 }
 
-SEC("tracepoint")
+SEC("socket")
 __description("bounded loop, start in the middle")
-__failure __msg("back-edge")
+__success
+__failure_unpriv __msg_unpriv("back-edge")
 __naked void loop_start_in_the_middle(void)
 {
 	asm volatile ("					\
@@ -136,7 +137,9 @@ l0_%=:	exit;						\
 
 SEC("tracepoint")
 __description("bounded recursion")
-__failure __msg("back-edge")
+__failure
+/* verifier limitation in detecting max stack depth */
+__msg("the call stack of 8 frames is too deep !")
 __naked void bounded_recursion(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c
index b2a04d1179d0b9..cbb9d6714f537c 100644
--- a/tools/testing/selftests/bpf/progs/verifier_movsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c
@@ -6,7 +6,8 @@
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
 	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
-        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
+	defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \
+	defined(__TARGET_ARCH_loongarch)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c
new file mode 100644
index 00000000000000..6b564d4c09866a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_precision.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 SUSE LLC */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0xfffffff8 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (87) r2 = -r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 8")
+__naked int bpf_neg(void)
+{
+	asm volatile (
+		"r2 = 8;"
+		"r2 = -r2;"
+		"if r2 != -8 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (d4) r2 = le16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_to_le(void)
+{
+	asm volatile (
+		"r2 = 0;"
+		"r2 = le16 r2;"
+		"if r2 != 0 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (dc) r2 = be16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_to_be(void)
+{
+	asm volatile (
+		"r2 = 0;"
+		"r2 = be16 r2;"
+		"if r2 != 0 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+	defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
+	__clang_major__ >= 18
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (d7) r2 = bswap16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_bswap(void)
+{
+	asm volatile (
+		"r2 = 0;"
+		"r2 = bswap16 r2;"
+		"if r2 != 0 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+#endif /* v4 instruction */
+
+SEC("?raw_tp")
+__success __log_level(2)
+/*
+ * Without the bug fix there will be no history between "last_idx 3 first_idx 3"
+ * and "parent state regs=" lines. "R0_w=6" parts are here to help anchor
+ * expected log messages to the one specific mark_chain_precision operation.
+ *
+ * This is quite fragile: if verifier checkpointing heuristic changes, this
+ * might need adjusting.
+ */
+__msg("2: (07) r0 += 1                       ; R0_w=6")
+__msg("3: (35) if r0 >= 0xa goto pc+1")
+__msg("mark_precise: frame0: last_idx 3 first_idx 3 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r0 stack= before 2: (07) r0 += 1")
+__msg("mark_precise: frame0: regs=r0 stack= before 1: (07) r0 += 1")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (05) goto pc-4")
+__msg("mark_precise: frame0: regs=r0 stack= before 3: (35) if r0 >= 0xa goto pc+1")
+__msg("mark_precise: frame0: parent state regs= stack=:  R0_rw=P4")
+__msg("3: R0_w=6")
+__naked int state_loop_first_last_equal(void)
+{
+	asm volatile (
+		"r0 = 0;"
+	"l0_%=:"
+		"r0 += 1;"
+		"r0 += 1;"
+		/* every few iterations we'll have a checkpoint here with
+		 * first_idx == last_idx, potentially confusing precision
+		 * backtracking logic
+		 */
+		"if r0 >= 10 goto l1_%=;"	/* checkpoint + mark_precise */
+		"goto l0_%=;"
+	"l1_%=:"
+		"exit;"
+		::: __clobber_common
+	);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_sdiv.c b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
index 8fc5174808b2bc..2a2271cf029410 100644
--- a/tools/testing/selftests/bpf/progs/verifier_sdiv.c
+++ b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
@@ -6,7 +6,8 @@
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
 	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
-        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
+	defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \
+	defined(__TARGET_ARCH_loongarch)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
index db6b3143338b61..f61d623b1ce8df 100644
--- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
@@ -119,15 +119,41 @@ __naked int global_subprog_result_precise(void)
 
 SEC("?raw_tp")
 __success __log_level(2)
+/* First simulated path does not include callback body,
+ * r1 and r4 are always precise for bpf_loop() calls.
+ */
+__msg("9: (85) call bpf_loop#181")
+__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
+__msg("mark_precise: frame0: parent state regs=r4 stack=:")
+__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9")
+__msg("mark_precise: frame0: regs=r4 stack= before 8: (b7) r4 = 0")
+__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
+__msg("mark_precise: frame0: parent state regs=r1 stack=:")
+__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9")
+__msg("mark_precise: frame0: regs=r1 stack= before 8: (b7) r4 = 0")
+__msg("mark_precise: frame0: regs=r1 stack= before 7: (b7) r3 = 0")
+__msg("mark_precise: frame0: regs=r1 stack= before 6: (bf) r2 = r8")
+__msg("mark_precise: frame0: regs=r1 stack= before 5: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3")
+/* r6 precision propagation */
 __msg("14: (0f) r1 += r6")
-__msg("mark_precise: frame0: last_idx 14 first_idx 10")
+__msg("mark_precise: frame0: last_idx 14 first_idx 9")
 __msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7")
 __msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4")
 __msg("mark_precise: frame0: regs=r6 stack= before 11: (25) if r6 > 0x3 goto pc+4")
 __msg("mark_precise: frame0: regs=r6 stack= before 10: (bf) r6 = r0")
-__msg("mark_precise: frame0: parent state regs=r0 stack=:")
-__msg("mark_precise: frame0: last_idx 18 first_idx 0")
-__msg("mark_precise: frame0: regs=r0 stack= before 18: (95) exit")
+__msg("mark_precise: frame0: regs=r0 stack= before 9: (85) call bpf_loop")
+/* State entering callback body popped from states stack */
+__msg("from 9 to 17: frame1:")
+__msg("17: frame1: R1=scalar() R2=0 R10=fp0 cb")
+__msg("17: (b7) r0 = 0")
+__msg("18: (95) exit")
+__msg("returning from callee:")
+__msg("to caller at 9:")
+__msg("frame 0: propagating r1,r4")
+__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r1,r4 stack= before 18: (95) exit")
+__msg("from 18 to 9: safe")
 __naked int callback_result_precise(void)
 {
 	asm volatile (
@@ -233,20 +259,36 @@ __naked int parent_callee_saved_reg_precise_global(void)
 
 SEC("?raw_tp")
 __success __log_level(2)
+/* First simulated path does not include callback body */
 __msg("12: (0f) r1 += r6")
-__msg("mark_precise: frame0: last_idx 12 first_idx 10")
+__msg("mark_precise: frame0: last_idx 12 first_idx 9")
 __msg("mark_precise: frame0: regs=r6 stack= before 11: (bf) r1 = r7")
 __msg("mark_precise: frame0: regs=r6 stack= before 10: (27) r6 *= 4")
+__msg("mark_precise: frame0: regs=r6 stack= before 9: (85) call bpf_loop")
 __msg("mark_precise: frame0: parent state regs=r6 stack=:")
-__msg("mark_precise: frame0: last_idx 16 first_idx 0")
-__msg("mark_precise: frame0: regs=r6 stack= before 16: (95) exit")
-__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0")
-__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop#181")
+__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9")
 __msg("mark_precise: frame0: regs=r6 stack= before 8: (b7) r4 = 0")
 __msg("mark_precise: frame0: regs=r6 stack= before 7: (b7) r3 = 0")
 __msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r2 = r8")
 __msg("mark_precise: frame0: regs=r6 stack= before 5: (b7) r1 = 1")
 __msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3")
+/* State entering callback body popped from states stack */
+__msg("from 9 to 15: frame1:")
+__msg("15: frame1: R1=scalar() R2=0 R10=fp0 cb")
+__msg("15: (b7) r0 = 0")
+__msg("16: (95) exit")
+__msg("returning from callee:")
+__msg("to caller at 9:")
+/* r1, r4 are always precise for bpf_loop(),
+ * r6 was marked before backtracking to callback body.
+ */
+__msg("frame 0: propagating r1,r4,r6")
+__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r1,r4,r6 stack= before 16: (95) exit")
+__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0")
+__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop")
+__msg("mark_precise: frame0: parent state regs= stack=:")
+__msg("from 16 to 9: safe")
 __naked int parent_callee_saved_reg_precise_with_callback(void)
 {
 	asm volatile (
@@ -373,22 +415,38 @@ __naked int parent_stack_slot_precise_global(void)
 
 SEC("?raw_tp")
 __success __log_level(2)
+/* First simulated path does not include callback body */
 __msg("14: (0f) r1 += r6")
-__msg("mark_precise: frame0: last_idx 14 first_idx 11")
+__msg("mark_precise: frame0: last_idx 14 first_idx 10")
 __msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7")
 __msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4")
 __msg("mark_precise: frame0: regs=r6 stack= before 11: (79) r6 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-8 before 10: (85) call bpf_loop")
 __msg("mark_precise: frame0: parent state regs= stack=-8:")
-__msg("mark_precise: frame0: last_idx 18 first_idx 0")
-__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit")
-__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0")
-__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181")
+__msg("mark_precise: frame0: last_idx 9 first_idx 0 subseq_idx 10")
 __msg("mark_precise: frame0: regs= stack=-8 before 9: (b7) r4 = 0")
 __msg("mark_precise: frame0: regs= stack=-8 before 8: (b7) r3 = 0")
 __msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r2 = r8")
 __msg("mark_precise: frame0: regs= stack=-8 before 6: (bf) r1 = r6")
 __msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -8) = r6")
 __msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3")
+/* State entering callback body popped from states stack */
+__msg("from 10 to 17: frame1:")
+__msg("17: frame1: R1=scalar() R2=0 R10=fp0 cb")
+__msg("17: (b7) r0 = 0")
+__msg("18: (95) exit")
+__msg("returning from callee:")
+__msg("to caller at 10:")
+/* r1, r4 are always precise for bpf_loop(),
+ * fp-8 was marked before backtracking to callback body.
+ */
+__msg("frame 0: propagating r1,r4,fp-8")
+__msg("mark_precise: frame0: last_idx 10 first_idx 10 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r1,r4 stack=-8 before 18: (95) exit")
+__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0")
+__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181")
+__msg("mark_precise: frame0: parent state regs= stack=:")
+__msg("from 18 to 10: safe")
 __naked int parent_stack_slot_precise_with_callback(void)
 {
 	asm volatile (
diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
index e959336c7a7304..80f620602d50ff 100644
--- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
@@ -53,6 +53,8 @@
 #define DEFAULT_TTL 64
 #define MAX_ALLOWED_PORTS 8
 
+#define MAX_PACKET_OFF 0xffff
+
 #define swap(a, b) \
 	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
 
@@ -183,63 +185,76 @@ static __always_inline __u32 tcp_clock_ms(void)
 }
 
 struct tcpopt_context {
-	__u8 *ptr;
-	__u8 *end;
+	void *data;
 	void *data_end;
 	__be32 *tsecr;
 	__u8 wscale;
 	bool option_timestamp;
 	bool option_sack;
+	__u32 off;
 };
 
-static int tscookie_tcpopt_parse(struct tcpopt_context *ctx)
+static __always_inline u8 *next(struct tcpopt_context *ctx, __u32 sz)
 {
-	__u8 opcode, opsize;
+	__u64 off = ctx->off;
+	__u8 *data;
 
-	if (ctx->ptr >= ctx->end)
-		return 1;
-	if (ctx->ptr >= ctx->data_end)
-		return 1;
+	/* Verifier forbids access to packet when offset exceeds MAX_PACKET_OFF */
+	if (off > MAX_PACKET_OFF - sz)
+		return NULL;
 
-	opcode = ctx->ptr[0];
+	data = ctx->data + off;
+	barrier_var(data);
+	if (data + sz >= ctx->data_end)
+		return NULL;
 
-	if (opcode == TCPOPT_EOL)
-		return 1;
-	if (opcode == TCPOPT_NOP) {
-		++ctx->ptr;
-		return 0;
-	}
+	ctx->off += sz;
+	return data;
+}
 
-	if (ctx->ptr + 1 >= ctx->end)
-		return 1;
-	if (ctx->ptr + 1 >= ctx->data_end)
+static int tscookie_tcpopt_parse(struct tcpopt_context *ctx)
+{
+	__u8 *opcode, *opsize, *wscale, *tsecr;
+	__u32 off = ctx->off;
+
+	opcode = next(ctx, 1);
+	if (!opcode)
 		return 1;
-	opsize = ctx->ptr[1];
-	if (opsize < 2)
+
+	if (*opcode == TCPOPT_EOL)
 		return 1;
+	if (*opcode == TCPOPT_NOP)
+		return 0;
 
-	if (ctx->ptr + opsize > ctx->end)
+	opsize = next(ctx, 1);
+	if (!opsize || *opsize < 2)
 		return 1;
 
-	switch (opcode) {
+	switch (*opcode) {
 	case TCPOPT_WINDOW:
-		if (opsize == TCPOLEN_WINDOW && ctx->ptr + TCPOLEN_WINDOW <= ctx->data_end)
-			ctx->wscale = ctx->ptr[2] < TCP_MAX_WSCALE ? ctx->ptr[2] : TCP_MAX_WSCALE;
+		wscale = next(ctx, 1);
+		if (!wscale)
+			return 1;
+		if (*opsize == TCPOLEN_WINDOW)
+			ctx->wscale = *wscale < TCP_MAX_WSCALE ? *wscale : TCP_MAX_WSCALE;
 		break;
 	case TCPOPT_TIMESTAMP:
-		if (opsize == TCPOLEN_TIMESTAMP && ctx->ptr + TCPOLEN_TIMESTAMP <= ctx->data_end) {
+		tsecr = next(ctx, 4);
+		if (!tsecr)
+			return 1;
+		if (*opsize == TCPOLEN_TIMESTAMP) {
 			ctx->option_timestamp = true;
 			/* Client's tsval becomes our tsecr. */
-			*ctx->tsecr = get_unaligned((__be32 *)(ctx->ptr + 2));
+			*ctx->tsecr = get_unaligned((__be32 *)tsecr);
 		}
 		break;
 	case TCPOPT_SACK_PERM:
-		if (opsize == TCPOLEN_SACK_PERM)
+		if (*opsize == TCPOLEN_SACK_PERM)
 			ctx->option_sack = true;
 		break;
 	}
 
-	ctx->ptr += opsize;
+	ctx->off = off + *opsize;
 
 	return 0;
 }
@@ -256,16 +271,21 @@ static int tscookie_tcpopt_parse_batch(__u32 index, void *context)
 
 static __always_inline bool tscookie_init(struct tcphdr *tcp_header,
 					  __u16 tcp_len, __be32 *tsval,
-					  __be32 *tsecr, void *data_end)
+					  __be32 *tsecr, void *data, void *data_end)
 {
 	struct tcpopt_context loop_ctx = {
-		.ptr = (__u8 *)(tcp_header + 1),
-		.end = (__u8 *)tcp_header + tcp_len,
+		.data = data,
 		.data_end = data_end,
 		.tsecr = tsecr,
 		.wscale = TS_OPT_WSCALE_MASK,
 		.option_timestamp = false,
 		.option_sack = false,
+		/* Note: currently verifier would track .off as unbound scalar.
+		 *       In case if verifier would at some point get smarter and
+		 *       compute bounded value for this var, beware that it might
+		 *       hinder bpf_loop() convergence validation.
+		 */
+		.off = (__u8 *)(tcp_header + 1) - (__u8 *)data,
 	};
 	u32 cookie;
 
@@ -635,7 +655,7 @@ static __always_inline int syncookie_handle_syn(struct header_pointers *hdr,
 	cookie = (__u32)value;
 
 	if (tscookie_init((void *)hdr->tcp, hdr->tcp_len,
-			  &tsopt_buf[0], &tsopt_buf[1], data_end))
+			  &tsopt_buf[0], &tsopt_buf[1], data, data_end))
 		tsopt = tsopt_buf;
 
 	/* Check that there is enough space for a SYNACK. It also covers
diff --git a/tools/testing/selftests/bpf/verifier/bpf_st_mem.c b/tools/testing/selftests/bpf/verifier/bpf_st_mem.c
index 3af2501082b29b..b616575c3b00a5 100644
--- a/tools/testing/selftests/bpf/verifier/bpf_st_mem.c
+++ b/tools/testing/selftests/bpf/verifier/bpf_st_mem.c
@@ -65,3 +65,35 @@
 	.expected_attach_type = BPF_SK_LOOKUP,
 	.runs = -1,
 },
+{
+	"BPF_ST_MEM stack imm sign",
+	/* Check if verifier correctly reasons about sign of an
+	 * immediate spilled to stack by BPF_ST instruction.
+	 *
+	 *   fp[-8] = -44;
+	 *   r0 = fp[-8];
+	 *   if r0 s< 0 goto ret0;
+	 *   r0 = -1;
+	 *   exit;
+	 * ret0:
+	 *   r0 = 0;
+	 *   exit;
+	 */
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, -44),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+	BPF_JMP_IMM(BPF_JSLT, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, -1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	/* Use prog type that requires return value in range [0, 1] */
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+	.result = VERBOSE_ACCEPT,
+	.runs = -1,
+	.errstr = "0: (7a) *(u64 *)(r10 -8) = -44        ; R10=fp0 fp-8_w=-44\
+	2: (c5) if r0 s< 0x0 goto pc+2\
+	R0_w=-44",
+},
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 1bdf2b43e49eaf..3d5cd51071f047 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -442,7 +442,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.errstr = "back-edge from insn 0 to 0",
+	.errstr = "the call stack of 9 frames is too deep",
 	.result = REJECT,
 },
 {
@@ -799,7 +799,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.errstr = "back-edge",
+	.errstr = "the call stack of 9 frames is too deep",
 	.result = REJECT,
 },
 {
@@ -811,7 +811,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.errstr = "back-edge",
+	.errstr = "the call stack of 9 frames is too deep",
 	.result = REJECT,
 },
 {
diff --git a/tools/testing/selftests/bpf/verifier/ld_imm64.c b/tools/testing/selftests/bpf/verifier/ld_imm64.c
index f9297900cea6d4..78f19c255f20b4 100644
--- a/tools/testing/selftests/bpf/verifier/ld_imm64.c
+++ b/tools/testing/selftests/bpf/verifier/ld_imm64.c
@@ -9,8 +9,8 @@
 	BPF_MOV64_IMM(BPF_REG_0, 2),
 	BPF_EXIT_INSN(),
 	},
-	.errstr = "invalid BPF_LD_IMM insn",
-	.errstr_unpriv = "R1 pointer comparison",
+	.errstr = "jump into the middle of ldimm64 insn 1",
+	.errstr_unpriv = "jump into the middle of ldimm64 insn 1",
 	.result = REJECT,
 },
 {
@@ -23,8 +23,8 @@
 	BPF_LD_IMM64(BPF_REG_0, 1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr = "invalid BPF_LD_IMM insn",
-	.errstr_unpriv = "R1 pointer comparison",
+	.errstr = "jump into the middle of ldimm64 insn 1",
+	.errstr_unpriv = "jump into the middle of ldimm64 insn 1",
 	.result = REJECT,
 },
 {
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index 17c0f92ff16029..c3ba40d0b9de46 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -430,7 +430,7 @@ static void print_usage(void)
 
 static void read_args(int argc, char *argv[])
 {
-	char opt;
+	int opt;
 
 	while ((opt = getopt(argc, argv, "mh")) != -1) {
 		switch (opt) {
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 591ca9637b23e8..b604c570309a7f 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -908,8 +908,9 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr)
 	struct xdp_info *meta = data - sizeof(struct xdp_info);
 
 	if (meta->count != pkt->pkt_nb) {
-		ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%d]\n",
-			       __func__, pkt->pkt_nb, meta->count);
+		ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%llu]\n",
+			       __func__, pkt->pkt_nb,
+			       (unsigned long long)meta->count);
 		return false;
 	}
 
@@ -926,11 +927,13 @@ static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 exp
 
 	if (addr >= umem->num_frames * umem->frame_size ||
 	    addr + len > umem->num_frames * umem->frame_size) {
-		ksft_print_msg("Frag invalid addr: %llx len: %u\n", addr, len);
+		ksft_print_msg("Frag invalid addr: %llx len: %u\n",
+			       (unsigned long long)addr, len);
 		return false;
 	}
 	if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) {
-		ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n", addr, len);
+		ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n",
+			       (unsigned long long)addr, len);
 		return false;
 	}
 
@@ -1029,7 +1032,8 @@ static int complete_pkts(struct xsk_socket_info *xsk, int batch_size)
 			u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1);
 
 			ksft_print_msg("[%s] Too many packets completed\n", __func__);
-			ksft_print_msg("Last completion address: %llx\n", addr);
+			ksft_print_msg("Last completion address: %llx\n",
+				       (unsigned long long)addr);
 			return TEST_FAILURE;
 		}
 
@@ -1513,8 +1517,9 @@ static int validate_tx_invalid_descs(struct ifobject *ifobject)
 	}
 
 	if (stats.tx_invalid_descs != ifobject->xsk->pkt_stream->nb_pkts / 2) {
-		ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%u] expected [%u]\n",
-			       __func__, stats.tx_invalid_descs,
+		ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%llu] expected [%u]\n",
+			       __func__,
+			       (unsigned long long)stats.tx_invalid_descs,
 			       ifobject->xsk->pkt_stream->nb_pkts);
 		return TEST_FAILURE;
 	}
diff --git a/tools/testing/selftests/hid/config.common b/tools/testing/selftests/hid/config.common
index 0617275d93cc70..0f456dbab62f37 100644
--- a/tools/testing/selftests/hid/config.common
+++ b/tools/testing/selftests/hid/config.common
@@ -46,7 +46,6 @@ CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_XXHASH=y
 CONFIG_DCB=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_CREDENTIALS=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_DEFAULT_FQ_CODEL=y
diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
index 050e9751321cff..ad9202335656cc 100644
--- a/tools/testing/selftests/iommu/iommufd_utils.h
+++ b/tools/testing/selftests/iommu/iommufd_utils.h
@@ -293,15 +293,13 @@ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length,
 				    __u64 bitmap_size, __u32 flags,
 				    struct __test_metadata *_metadata)
 {
-	unsigned long i, count, nbits = bitmap_size * BITS_PER_BYTE;
+	unsigned long i, nbits = bitmap_size * BITS_PER_BYTE;
 	unsigned long nr = nbits / 2;
 	__u64 out_dirty = 0;
 
 	/* Mark all even bits as dirty in the mock domain */
-	for (count = 0, i = 0; i < nbits; count += !(i % 2), i++)
-		if (!(i % 2))
-			set_bit(i, (unsigned long *)bitmap);
-	ASSERT_EQ(nr, count);
+	for (i = 0; i < nbits; i += 2)
+		set_bit(i, (unsigned long *)bitmap);
 
 	test_cmd_mock_domain_set_dirty(fd, hwpt_id, length, iova, page_size,
 				       bitmap, &out_dirty);
@@ -311,9 +309,10 @@ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length,
 	memset(bitmap, 0, bitmap_size);
 	test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap,
 				  flags);
-	for (count = 0, i = 0; i < nbits; count += !(i % 2), i++)
+	/* Beware ASSERT_EQ() is two statements -- braces are not redundant! */
+	for (i = 0; i < nbits; i++) {
 		ASSERT_EQ(!(i % 2), test_bit(i, (unsigned long *)bitmap));
-	ASSERT_EQ(count, out_dirty);
+	}
 
 	memset(bitmap, 0, bitmap_size);
 	test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap,
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index a5963ab9215b94..3e0c36b8ddd56e 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -17,15 +17,6 @@ else
 	ARCH_DIR := $(ARCH)
 endif
 
-ifeq ($(ARCH),arm64)
-arm64_tools_dir := $(top_srcdir)/tools/arch/arm64/tools/
-GEN_HDRS := $(top_srcdir)/tools/arch/arm64/include/generated/
-CFLAGS += -I$(GEN_HDRS)
-
-$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*)
-	$(MAKE) -C $(arm64_tools_dir)
-endif
-
 LIBKVM += lib/assert.c
 LIBKVM += lib/elf.c
 LIBKVM += lib/guest_modes.c
@@ -223,7 +214,7 @@ else
 LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include
 endif
 CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
-	-Wno-gnu-variable-sized-type-not-at-end -MD\
+	-Wno-gnu-variable-sized-type-not-at-end -MD -MP \
 	-fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \
 	-fno-builtin-strnlen \
 	-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
@@ -233,6 +224,22 @@ CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
 ifeq ($(ARCH),s390)
 	CFLAGS += -march=z10
 endif
+ifeq ($(ARCH),arm64)
+tools_dir := $(top_srcdir)/tools
+arm64_tools_dir := $(tools_dir)/arch/arm64/tools/
+
+ifneq ($(abs_objdir),)
+arm64_hdr_outdir := $(abs_objdir)/tools/
+else
+arm64_hdr_outdir := $(tools_dir)/
+endif
+
+GEN_HDRS := $(arm64_hdr_outdir)arch/arm64/include/generated/
+CFLAGS += -I$(GEN_HDRS)
+
+$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*)
+	$(MAKE) -C $(arm64_tools_dir) OUTPUT=$(arm64_hdr_outdir)
+endif
 
 no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \
         $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c
index be7bf522443478..8274ef04301f67 100644
--- a/tools/testing/selftests/kvm/get-reg-list.c
+++ b/tools/testing/selftests/kvm/get-reg-list.c
@@ -71,11 +71,12 @@ static const char *config_name(struct vcpu_reg_list *c)
 	for_each_sublist(c, s) {
 		if (!strcmp(s->name, "base"))
 			continue;
-		strcat(c->name + len, s->name);
-		len += strlen(s->name) + 1;
-		c->name[len - 1] = '+';
+		if (len)
+			c->name[len++] = '+';
+		strcpy(c->name + len, s->name);
+		len += strlen(s->name);
 	}
-	c->name[len - 1] = '\0';
+	c->name[len] = '\0';
 
 	return c->name;
 }
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 6bedaea9539515..25de4b8bc3472e 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -458,8 +458,9 @@ void print_reg(const char *prefix, __u64 id)
 		reg_size = "KVM_REG_SIZE_U128";
 		break;
 	default:
-		printf("\tKVM_REG_RISCV | (%lld << KVM_REG_SIZE_SHIFT) | 0x%llx /* UNKNOWN */,",
-		       (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id & REG_MASK);
+		printf("\tKVM_REG_RISCV | (%lld << KVM_REG_SIZE_SHIFT) | 0x%llx /* UNKNOWN */,\n",
+		       (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id & ~REG_MASK);
+		return;
 	}
 
 	switch (id & KVM_REG_RISCV_TYPE_MASK) {
@@ -496,8 +497,9 @@ void print_reg(const char *prefix, __u64 id)
 				reg_size, sbi_ext_id_to_str(prefix, id));
 		break;
 	default:
-		printf("\tKVM_REG_RISCV | %s | 0x%llx /* UNKNOWN */,",
-				reg_size, id & REG_MASK);
+		printf("\tKVM_REG_RISCV | %s | 0x%llx /* UNKNOWN */,\n",
+				reg_size, id & ~REG_MASK);
+		return;
 	}
 }
 
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
index 18ac5c1952a3a3..83e25bccc139de 100644
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
@@ -259,7 +259,7 @@ int main(int argc, char **argv)
 	__TEST_REQUIRE(token == MAGIC_TOKEN,
 		       "This test must be run with the magic token %d.\n"
 		       "This is done by nx_huge_pages_test.sh, which\n"
-		       "also handles environment setup for the test.");
+		       "also handles environment setup for the test.", MAGIC_TOKEN);
 
 	run_test(reclaim_period_ms, false, reboot_permissions);
 	run_test(reclaim_period_ms, true, reboot_permissions);
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 118e0964bda946..aa646e0661f36c 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -44,26 +44,10 @@ endif
 selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST))))
 top_srcdir = $(selfdir)/../../..
 
-ifeq ("$(origin O)", "command line")
-  KBUILD_OUTPUT := $(O)
+ifeq ($(KHDR_INCLUDES),)
+KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include
 endif
 
-ifneq ($(KBUILD_OUTPUT),)
-  # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot
-  # expand a shell special character '~'. We use a somewhat tedious way here.
-  abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd)
-  $(if $(abs_objtree),, \
-    $(error failed to create output directory "$(KBUILD_OUTPUT)"))
-  # $(realpath ...) resolves symlinks
-  abs_objtree := $(realpath $(abs_objtree))
-  KHDR_DIR := ${abs_objtree}/usr/include
-else
-  abs_srctree := $(shell cd $(top_srcdir) && pwd)
-  KHDR_DIR := ${abs_srctree}/usr/include
-endif
-
-KHDR_INCLUDES := -isystem $(KHDR_DIR)
-
 # The following are built by lib.mk common compile rules.
 # TEST_CUSTOM_PROGS should be used by tests that require
 # custom build rule and prevent common build rule use.
@@ -74,25 +58,7 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS))
 TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED))
 TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
 
-all: kernel_header_files $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) \
-     $(TEST_GEN_FILES)
-
-kernel_header_files:
-	@ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null;                      \
-	if [ $$? -ne 0 ]; then                                                 \
-            RED='\033[1;31m';                                                  \
-            NOCOLOR='\033[0m';                                                 \
-            echo;                                                              \
-            echo -e "$${RED}error$${NOCOLOR}: missing kernel header files.";   \
-            echo "Please run this and try again:";                             \
-            echo;                                                              \
-            echo "    cd $(top_srcdir)";                                       \
-            echo "    make headers";                                           \
-            echo;                                                              \
-	    exit 1; \
-	fi
-
-.PHONY: kernel_header_files
+all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
 
 define RUN_TESTS
 	BASE_DIR="$(selfdir)";			\
diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore
index cc920c79ff1c32..4ff10ea6146179 100644
--- a/tools/testing/selftests/mm/.gitignore
+++ b/tools/testing/selftests/mm/.gitignore
@@ -45,3 +45,4 @@ mdwe_test
 gup_longterm
 mkdirty
 va_high_addr_switch
+hugetlb_fault_after_madv
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 78dfec8bc676fa..dede0bcf97a383 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -60,7 +60,7 @@ TEST_GEN_FILES += mrelease_test
 TEST_GEN_FILES += mremap_dontunmap
 TEST_GEN_FILES += mremap_test
 TEST_GEN_FILES += on-fault-limit
-TEST_GEN_PROGS += pagemap_ioctl
+TEST_GEN_FILES += pagemap_ioctl
 TEST_GEN_FILES += thuge-gen
 TEST_GEN_FILES += transhuge-stress
 TEST_GEN_FILES += uffd-stress
@@ -72,7 +72,7 @@ TEST_GEN_FILES += mdwe_test
 TEST_GEN_FILES += hugetlb_fault_after_madv
 
 ifneq ($(ARCH),arm64)
-TEST_GEN_PROGS += soft-dirty
+TEST_GEN_FILES += soft-dirty
 endif
 
 ifeq ($(ARCH),x86_64)
diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c
index 7324ce5363c0c9..6f2f839904416c 100644
--- a/tools/testing/selftests/mm/cow.c
+++ b/tools/testing/selftests/mm/cow.c
@@ -1680,6 +1680,8 @@ int main(int argc, char **argv)
 {
 	int err;
 
+	ksft_print_header();
+
 	pagesize = getpagesize();
 	thpsize = read_pmd_pagesize();
 	if (thpsize)
@@ -1689,7 +1691,6 @@ int main(int argc, char **argv)
 						    ARRAY_SIZE(hugetlbsizes));
 	detect_huge_zeropage();
 
-	ksft_print_header();
 	ksft_set_plan(ARRAY_SIZE(anon_test_cases) * tests_per_anon_test_case() +
 		      ARRAY_SIZE(anon_thp_test_cases) * tests_per_anon_thp_test_case() +
 		      ARRAY_SIZE(non_anon_test_cases) * tests_per_non_anon_test_case());
diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c
index 0161fb49fc6ef1..d59517ed3d48bd 100644
--- a/tools/testing/selftests/mm/pagemap_ioctl.c
+++ b/tools/testing/selftests/mm/pagemap_ioctl.c
@@ -36,6 +36,7 @@ int pagemap_fd;
 int uffd;
 int page_size;
 int hpage_size;
+const char *progname;
 
 #define LEN(region)	((region.end - region.start)/page_size)
 
@@ -94,19 +95,19 @@ int init_uffd(void)
 
 	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY);
 	if (uffd == -1)
-		ksft_exit_fail_msg("uffd syscall failed\n");
+		return uffd;
 
 	uffdio_api.api = UFFD_API;
 	uffdio_api.features = UFFD_FEATURE_WP_UNPOPULATED | UFFD_FEATURE_WP_ASYNC |
 			      UFFD_FEATURE_WP_HUGETLBFS_SHMEM;
 	if (ioctl(uffd, UFFDIO_API, &uffdio_api))
-		ksft_exit_fail_msg("UFFDIO_API\n");
+		return -1;
 
 	if (!(uffdio_api.api & UFFDIO_REGISTER_MODE_WP) ||
 	    !(uffdio_api.features & UFFD_FEATURE_WP_UNPOPULATED) ||
 	    !(uffdio_api.features & UFFD_FEATURE_WP_ASYNC) ||
 	    !(uffdio_api.features & UFFD_FEATURE_WP_HUGETLBFS_SHMEM))
-		ksft_exit_fail_msg("UFFDIO_API error %llu\n", uffdio_api.api);
+		return -1;
 
 	return 0;
 }
@@ -1149,17 +1150,17 @@ int sanity_tests(void)
 	munmap(mem, mem_size);
 
 	/* 9. Memory mapped file */
-	fd = open(__FILE__, O_RDONLY);
+	fd = open(progname, O_RDONLY);
 	if (fd < 0)
-		ksft_exit_fail_msg("%s Memory mapped file\n");
+		ksft_exit_fail_msg("%s Memory mapped file\n", __func__);
 
-	ret = stat(__FILE__, &sbuf);
+	ret = stat(progname, &sbuf);
 	if (ret < 0)
 		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
 
 	fmem = mmap(NULL, sbuf.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
 	if (fmem == MAP_FAILED)
-		ksft_exit_fail_msg("error nomem %ld %s\n", errno, strerror(errno));
+		ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno));
 
 	tmp_buf = malloc(sbuf.st_size);
 	memcpy(tmp_buf, fmem, sbuf.st_size);
@@ -1189,7 +1190,7 @@ int sanity_tests(void)
 
 	fmem = mmap(NULL, buf_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
 	if (fmem == MAP_FAILED)
-		ksft_exit_fail_msg("error nomem %ld %s\n", errno, strerror(errno));
+		ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno));
 
 	wp_init(fmem, buf_size);
 	wp_addr_range(fmem, buf_size);
@@ -1472,13 +1473,19 @@ static void transact_test(int page_size)
 			      extra_thread_faults);
 }
 
-int main(void)
+int main(int argc, char *argv[])
 {
 	int mem_size, shmid, buf_size, fd, i, ret;
 	char *mem, *map, *fmem;
 	struct stat sbuf;
 
+	progname = argv[0];
+
 	ksft_print_header();
+
+	if (init_uffd())
+		return ksft_exit_pass();
+
 	ksft_set_plan(115);
 
 	page_size = getpagesize();
@@ -1488,9 +1495,6 @@ int main(void)
 	if (pagemap_fd < 0)
 		return -EINVAL;
 
-	if (init_uffd())
-		ksft_exit_fail_msg("uffd init failed\n");
-
 	/* 1. Sanity testing */
 	sanity_tests_sd();
 
@@ -1595,7 +1599,7 @@ int main(void)
 
 	fmem = mmap(NULL, sbuf.st_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
 	if (fmem == MAP_FAILED)
-		ksft_exit_fail_msg("error nomem %ld %s\n", errno, strerror(errno));
+		ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno));
 
 	wp_init(fmem, sbuf.st_size);
 	wp_addr_range(fmem, sbuf.st_size);
@@ -1623,7 +1627,7 @@ int main(void)
 
 	fmem = mmap(NULL, buf_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
 	if (fmem == MAP_FAILED)
-		ksft_exit_fail_msg("error nomem %ld %s\n", errno, strerror(errno));
+		ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno));
 
 	wp_init(fmem, buf_size);
 	wp_addr_range(fmem, buf_size);
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index cc16f6ca853332..00757445278eda 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -223,9 +223,12 @@ CATEGORY="hugetlb" run_test ./hugepage-mremap
 CATEGORY="hugetlb" run_test ./hugepage-vmemmap
 CATEGORY="hugetlb" run_test ./hugetlb-madvise
 
+nr_hugepages_tmp=$(cat /proc/sys/vm/nr_hugepages)
 # For this test, we need one and just one huge page
 echo 1 > /proc/sys/vm/nr_hugepages
 CATEGORY="hugetlb" run_test ./hugetlb_fault_after_madv
+# Restore the previous number of huge pages, since further tests rely on it
+echo "$nr_hugepages_tmp" > /proc/sys/vm/nr_hugepages
 
 if test_selected "hugetlb"; then
 	echo "NOTE: These hugetlb tests provide minimal coverage.  Use"
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 5b2aca4c5f1007..9e5bf59a20bff4 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -91,6 +91,7 @@ TEST_PROGS += test_bridge_neigh_suppress.sh
 TEST_PROGS += test_vxlan_nolocalbypass.sh
 TEST_PROGS += test_bridge_backup_port.sh
 TEST_PROGS += fdb_flush.sh
+TEST_PROGS += vlan_hw_filter.sh
 
 TEST_FILES := settings
 
diff --git a/tools/testing/selftests/net/af_unix/diag_uid.c b/tools/testing/selftests/net/af_unix/diag_uid.c
index 5b88f7129fea44..79a3dd75590e89 100644
--- a/tools/testing/selftests/net/af_unix/diag_uid.c
+++ b/tools/testing/selftests/net/af_unix/diag_uid.c
@@ -148,7 +148,6 @@ void receive_response(struct __test_metadata *_metadata,
 		.msg_iov = &iov,
 		.msg_iovlen = 1
 	};
-	struct unix_diag_req *udr;
 	struct nlmsghdr *nlh;
 	int ret;
 
diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c
index 24b21b15ed3fb0..6ff3e732f449f9 100644
--- a/tools/testing/selftests/net/cmsg_sender.c
+++ b/tools/testing/selftests/net/cmsg_sender.c
@@ -416,9 +416,9 @@ int main(int argc, char *argv[])
 {
 	struct addrinfo hints, *ai;
 	struct iovec iov[1];
+	unsigned char *buf;
 	struct msghdr msg;
 	char cbuf[1024];
-	char *buf;
 	int err;
 	int fd;
 
diff --git a/tools/testing/selftests/net/ipsec.c b/tools/testing/selftests/net/ipsec.c
index 9a8229abfa026a..be4a30a0d02aef 100644
--- a/tools/testing/selftests/net/ipsec.c
+++ b/tools/testing/selftests/net/ipsec.c
@@ -2263,7 +2263,7 @@ static int check_results(void)
 
 int main(int argc, char **argv)
 {
-	unsigned int nr_process = 1;
+	long nr_process = 1;
 	int route_sock = -1, ret = KSFT_SKIP;
 	int test_desc_fd[2];
 	uint32_t route_seq;
@@ -2284,7 +2284,7 @@ int main(int argc, char **argv)
 			exit_usage(argv);
 		}
 
-		if (nr_process > MAX_PROCESSES || !nr_process) {
+		if (nr_process > MAX_PROCESSES || nr_process < 1) {
 			printk("nr_process should be between [1; %u]",
 					MAX_PROCESSES);
 			exit_usage(argv);
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index c7f9ebeebc2c5b..d2043ec3bf6d69 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -18,6 +18,7 @@
 
 #include <sys/ioctl.h>
 #include <sys/poll.h>
+#include <sys/random.h>
 #include <sys/sendfile.h>
 #include <sys/stat.h>
 #include <sys/socket.h>
@@ -1125,15 +1126,11 @@ again:
 
 static void init_rng(void)
 {
-	int fd = open("/dev/urandom", O_RDONLY);
 	unsigned int foo;
 
-	if (fd > 0) {
-		int ret = read(fd, &foo, sizeof(foo));
-
-		if (ret < 0)
-			srand(fd + foo);
-		close(fd);
+	if (getrandom(&foo, sizeof(foo), 0) == -1) {
+		perror("getrandom");
+		exit(1);
 	}
 
 	srand(foo);
diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
index 8672d898f8cdad..218aac46732125 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_inq.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c
@@ -18,6 +18,7 @@
 #include <time.h>
 
 #include <sys/ioctl.h>
+#include <sys/random.h>
 #include <sys/socket.h>
 #include <sys/types.h>
 #include <sys/wait.h>
@@ -519,15 +520,11 @@ static int client(int unixfd)
 
 static void init_rng(void)
 {
-	int fd = open("/dev/urandom", O_RDONLY);
 	unsigned int foo;
 
-	if (fd > 0) {
-		int ret = read(fd, &foo, sizeof(foo));
-
-		if (ret < 0)
-			srand(fd + foo);
-		close(fd);
+	if (getrandom(&foo, sizeof(foo), 0) == -1) {
+		perror("getrandom");
+		exit(1);
 	}
 
 	srand(foo);
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 75a2438efdf373..24a57b3ae2155d 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -2776,7 +2776,7 @@ backup_tests()
 	fi
 
 	if reset "mpc backup" &&
-	   continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then
+	   continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup
 		speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
@@ -2785,7 +2785,7 @@ backup_tests()
 	fi
 
 	if reset "mpc backup both sides" &&
-	   continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then
+	   continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then
 		pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup
 		speed=slow \
@@ -2795,7 +2795,7 @@ backup_tests()
 	fi
 
 	if reset "mpc switch to backup" &&
-	   continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then
+	   continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow
 		sflags=backup speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
@@ -2804,7 +2804,7 @@ backup_tests()
 	fi
 
 	if reset "mpc switch to backup both sides" &&
-	   continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then
+	   continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then
 		pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow
 		sflags=backup speed=slow \
@@ -3240,7 +3240,7 @@ fastclose_tests()
 	if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then
 		test_linkfail=1024 fastclose=server \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 0 0 0
+		chk_join_nr 0 0 0 0 0 0 1
 		chk_fclose_nr 1 1 invert
 		chk_rst_nr 1 1
 	fi
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index f838dd370f6af3..b3b2dc5a630cf2 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -2048,7 +2048,7 @@ run_test() {
 	case $ret in
 		0)
 			all_skipped=false
-			[ $exitcode=$ksft_skip ] && exitcode=0
+			[ $exitcode -eq $ksft_skip ] && exitcode=0
 		;;
 		$ksft_skip)
 			[ $all_skipped = true ] && exitcode=$ksft_skip
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 5f2b3f6c0d7499..26827ea4e3e5f2 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -297,7 +297,7 @@ kci_test_addrlft()
 	done
 
 	sleep 5
-	run_cmd_grep "10.23.11." ip addr show dev "$devdummy"
+	run_cmd_grep_fail "10.23.11." ip addr show dev "$devdummy"
 	if [ $? -eq 0 ]; then
 		check_err 1
 		end_test "FAIL: preferred_lft addresses remaining"
@@ -859,7 +859,7 @@ kci_test_gretap()
 
 
 	run_cmd ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24
-	run_cmd ip -netns "$testns" link set dev $DEV_NS ups
+	run_cmd ip -netns "$testns" link set dev $DEV_NS up
 	run_cmd ip -netns "$testns" link del "$DEV_NS"
 
 	# test external mode
diff --git a/tools/testing/selftests/net/vlan_hw_filter.sh b/tools/testing/selftests/net/vlan_hw_filter.sh
new file mode 100755
index 00000000000000..7bc804ffaf7c58
--- /dev/null
+++ b/tools/testing/selftests/net/vlan_hw_filter.sh
@@ -0,0 +1,29 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+readonly NETNS="ns-$(mktemp -u XXXXXX)"
+
+ret=0
+
+cleanup() {
+	ip netns del $NETNS
+}
+
+trap cleanup EXIT
+
+fail() {
+    echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2
+    ret=1
+}
+
+ip netns add ${NETNS}
+ip netns exec ${NETNS} ip link add bond0 type bond mode 0
+ip netns exec ${NETNS} ip link add bond_slave_1 type veth peer veth2
+ip netns exec ${NETNS} ip link set bond_slave_1 master bond0
+ip netns exec ${NETNS} ethtool -K bond0 rx-vlan-filter off
+ip netns exec ${NETNS} ip link add link bond_slave_1 name bond_slave_1.0 type vlan id 0
+ip netns exec ${NETNS} ip link add link bond0 name bond0.0 type vlan id 0
+ip netns exec ${NETNS} ip link set bond_slave_1 nomaster
+ip netns exec ${NETNS} ip link del veth2 || fail "Please check vlan HW filter function"
+
+exit $ret
diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index 92336721321af7..ae2b33c21c452a 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -85,6 +85,48 @@ void vsock_wait_remote_close(int fd)
 	close(epollfd);
 }
 
+/* Bind to <bind_port>, connect to <cid, port> and return the file descriptor. */
+int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type)
+{
+	struct sockaddr_vm sa_client = {
+		.svm_family = AF_VSOCK,
+		.svm_cid = VMADDR_CID_ANY,
+		.svm_port = bind_port,
+	};
+	struct sockaddr_vm sa_server = {
+		.svm_family = AF_VSOCK,
+		.svm_cid = cid,
+		.svm_port = port,
+	};
+
+	int client_fd, ret;
+
+	client_fd = socket(AF_VSOCK, type, 0);
+	if (client_fd < 0) {
+		perror("socket");
+		exit(EXIT_FAILURE);
+	}
+
+	if (bind(client_fd, (struct sockaddr *)&sa_client, sizeof(sa_client))) {
+		perror("bind");
+		exit(EXIT_FAILURE);
+	}
+
+	timeout_begin(TIMEOUT);
+	do {
+		ret = connect(client_fd, (struct sockaddr *)&sa_server, sizeof(sa_server));
+		timeout_check("connect");
+	} while (ret < 0 && errno == EINTR);
+	timeout_end();
+
+	if (ret < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	return client_fd;
+}
+
 /* Connect to <cid, port> and return the file descriptor. */
 static int vsock_connect(unsigned int cid, unsigned int port, int type)
 {
@@ -104,6 +146,10 @@ static int vsock_connect(unsigned int cid, unsigned int port, int type)
 	control_expectln("LISTENING");
 
 	fd = socket(AF_VSOCK, type, 0);
+	if (fd < 0) {
+		perror("socket");
+		exit(EXIT_FAILURE);
+	}
 
 	timeout_begin(TIMEOUT);
 	do {
@@ -132,11 +178,8 @@ int vsock_seqpacket_connect(unsigned int cid, unsigned int port)
 	return vsock_connect(cid, port, SOCK_SEQPACKET);
 }
 
-/* Listen on <cid, port> and return the first incoming connection.  The remote
- * address is stored to clientaddrp.  clientaddrp may be NULL.
- */
-static int vsock_accept(unsigned int cid, unsigned int port,
-			struct sockaddr_vm *clientaddrp, int type)
+/* Listen on <cid, port> and return the file descriptor. */
+static int vsock_listen(unsigned int cid, unsigned int port, int type)
 {
 	union {
 		struct sockaddr sa;
@@ -148,16 +191,13 @@ static int vsock_accept(unsigned int cid, unsigned int port,
 			.svm_cid = cid,
 		},
 	};
-	union {
-		struct sockaddr sa;
-		struct sockaddr_vm svm;
-	} clientaddr;
-	socklen_t clientaddr_len = sizeof(clientaddr.svm);
 	int fd;
-	int client_fd;
-	int old_errno;
 
 	fd = socket(AF_VSOCK, type, 0);
+	if (fd < 0) {
+		perror("socket");
+		exit(EXIT_FAILURE);
+	}
 
 	if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
 		perror("bind");
@@ -169,6 +209,24 @@ static int vsock_accept(unsigned int cid, unsigned int port,
 		exit(EXIT_FAILURE);
 	}
 
+	return fd;
+}
+
+/* Listen on <cid, port> and return the first incoming connection.  The remote
+ * address is stored to clientaddrp.  clientaddrp may be NULL.
+ */
+static int vsock_accept(unsigned int cid, unsigned int port,
+			struct sockaddr_vm *clientaddrp, int type)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_vm svm;
+	} clientaddr;
+	socklen_t clientaddr_len = sizeof(clientaddr.svm);
+	int fd, client_fd, old_errno;
+
+	fd = vsock_listen(cid, port, type);
+
 	control_writeln("LISTENING");
 
 	timeout_begin(TIMEOUT);
@@ -207,6 +265,11 @@ int vsock_stream_accept(unsigned int cid, unsigned int port,
 	return vsock_accept(cid, port, clientaddrp, SOCK_STREAM);
 }
 
+int vsock_stream_listen(unsigned int cid, unsigned int port)
+{
+	return vsock_listen(cid, port, SOCK_STREAM);
+}
+
 int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
 			   struct sockaddr_vm *clientaddrp)
 {
diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h
index a77175d25864c7..03c88d0cb8610b 100644
--- a/tools/testing/vsock/util.h
+++ b/tools/testing/vsock/util.h
@@ -36,9 +36,12 @@ struct test_case {
 void init_signals(void);
 unsigned int parse_cid(const char *str);
 int vsock_stream_connect(unsigned int cid, unsigned int port);
+int vsock_bind_connect(unsigned int cid, unsigned int port,
+		       unsigned int bind_port, int type);
 int vsock_seqpacket_connect(unsigned int cid, unsigned int port);
 int vsock_stream_accept(unsigned int cid, unsigned int port,
 			struct sockaddr_vm *clientaddrp);
+int vsock_stream_listen(unsigned int cid, unsigned int port);
 int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
 			   struct sockaddr_vm *clientaddrp);
 void vsock_wait_remote_close(int fd);
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index c1f7bc9abd2231..01fa816868bc4c 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -353,11 +353,12 @@ static void test_stream_msg_peek_server(const struct test_opts *opts)
 }
 
 #define SOCK_BUF_SIZE (2 * 1024 * 1024)
-#define MAX_MSG_SIZE (32 * 1024)
+#define MAX_MSG_PAGES 4
 
 static void test_seqpacket_msg_bounds_client(const struct test_opts *opts)
 {
 	unsigned long curr_hash;
+	size_t max_msg_size;
 	int page_size;
 	int msg_count;
 	int fd;
@@ -373,7 +374,8 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts)
 
 	curr_hash = 0;
 	page_size = getpagesize();
-	msg_count = SOCK_BUF_SIZE / MAX_MSG_SIZE;
+	max_msg_size = MAX_MSG_PAGES * page_size;
+	msg_count = SOCK_BUF_SIZE / max_msg_size;
 
 	for (int i = 0; i < msg_count; i++) {
 		size_t buf_size;
@@ -383,7 +385,7 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts)
 		/* Use "small" buffers and "big" buffers. */
 		if (i & 1)
 			buf_size = page_size +
-					(rand() % (MAX_MSG_SIZE - page_size));
+					(rand() % (max_msg_size - page_size));
 		else
 			buf_size = 1 + (rand() % page_size);
 
@@ -429,7 +431,6 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts)
 	unsigned long remote_hash;
 	unsigned long curr_hash;
 	int fd;
-	char buf[MAX_MSG_SIZE];
 	struct msghdr msg = {0};
 	struct iovec iov = {0};
 
@@ -457,8 +458,13 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts)
 	control_writeln("SRVREADY");
 	/* Wait, until peer sends whole data. */
 	control_expectln("SENDDONE");
-	iov.iov_base = buf;
-	iov.iov_len = sizeof(buf);
+	iov.iov_len = MAX_MSG_PAGES * getpagesize();
+	iov.iov_base = malloc(iov.iov_len);
+	if (!iov.iov_base) {
+		perror("malloc");
+		exit(EXIT_FAILURE);
+	}
+
 	msg.msg_iov = &iov;
 	msg.msg_iovlen = 1;
 
@@ -483,6 +489,7 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts)
 		curr_hash += hash_djb2(msg.msg_iov[0].iov_base, recv_size);
 	}
 
+	free(iov.iov_base);
 	close(fd);
 	remote_hash = control_readulong();
 
@@ -1180,6 +1187,51 @@ static void test_stream_shutrd_server(const struct test_opts *opts)
 	close(fd);
 }
 
+static void test_double_bind_connect_server(const struct test_opts *opts)
+{
+	int listen_fd, client_fd, i;
+	struct sockaddr_vm sa_client;
+	socklen_t socklen_client = sizeof(sa_client);
+
+	listen_fd = vsock_stream_listen(VMADDR_CID_ANY, 1234);
+
+	for (i = 0; i < 2; i++) {
+		control_writeln("LISTENING");
+
+		timeout_begin(TIMEOUT);
+		do {
+			client_fd = accept(listen_fd, (struct sockaddr *)&sa_client,
+					   &socklen_client);
+			timeout_check("accept");
+		} while (client_fd < 0 && errno == EINTR);
+		timeout_end();
+
+		if (client_fd < 0) {
+			perror("accept");
+			exit(EXIT_FAILURE);
+		}
+
+		/* Waiting for remote peer to close connection */
+		vsock_wait_remote_close(client_fd);
+	}
+
+	close(listen_fd);
+}
+
+static void test_double_bind_connect_client(const struct test_opts *opts)
+{
+	int i, client_fd;
+
+	for (i = 0; i < 2; i++) {
+		/* Wait until server is ready to accept a new connection */
+		control_expectln("LISTENING");
+
+		client_fd = vsock_bind_connect(opts->peer_cid, 1234, 4321, SOCK_STREAM);
+
+		close(client_fd);
+	}
+}
+
 static struct test_case test_cases[] = {
 	{
 		.name = "SOCK_STREAM connection reset",
@@ -1285,6 +1337,11 @@ static struct test_case test_cases[] = {
 		.run_client = test_stream_msgzcopy_empty_errq_client,
 		.run_server = test_stream_msgzcopy_empty_errq_server,
 	},
+	{
+		.name = "SOCK_STREAM double bind connect",
+		.run_client = test_double_bind_connect_client,
+		.run_server = test_double_bind_connect_server,
+	},
 	{},
 };
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 486800a7024b37..7db96875ac4627 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -115,8 +115,6 @@ EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
 
 static const struct file_operations stat_fops_per_vm;
 
-static struct file_operations kvm_chardev_ops;
-
 static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 			   unsigned long arg);
 #ifdef CONFIG_KVM_COMPAT
@@ -1157,9 +1155,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
 
-	/* KVM is pinned via open("/dev/kvm"), the fd passed to this ioctl(). */
-	__module_get(kvm_chardev_ops.owner);
-
 	KVM_MMU_LOCK_INIT(kvm);
 	mmgrab(current->mm);
 	kvm->mm = current->mm;
@@ -1279,7 +1274,6 @@ out_err_no_irq_srcu:
 out_err_no_srcu:
 	kvm_arch_free_vm(kvm);
 	mmdrop(current->mm);
-	module_put(kvm_chardev_ops.owner);
 	return ERR_PTR(r);
 }
 
@@ -1348,7 +1342,6 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	preempt_notifier_dec();
 	hardware_disable_all();
 	mmdrop(mm);
-	module_put(kvm_chardev_ops.owner);
 }
 
 void kvm_get_kvm(struct kvm *kvm)
@@ -3887,7 +3880,7 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static const struct file_operations kvm_vcpu_fops = {
+static struct file_operations kvm_vcpu_fops = {
 	.release        = kvm_vcpu_release,
 	.unlocked_ioctl = kvm_vcpu_ioctl,
 	.mmap           = kvm_vcpu_mmap,
@@ -4081,6 +4074,7 @@ static int kvm_vcpu_stats_release(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations kvm_vcpu_stats_fops = {
+	.owner = THIS_MODULE,
 	.read = kvm_vcpu_stats_read,
 	.release = kvm_vcpu_stats_release,
 	.llseek = noop_llseek,
@@ -4431,7 +4425,7 @@ static int kvm_device_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static const struct file_operations kvm_device_fops = {
+static struct file_operations kvm_device_fops = {
 	.unlocked_ioctl = kvm_device_ioctl,
 	.release = kvm_device_release,
 	KVM_COMPAT(kvm_device_ioctl),
@@ -4759,6 +4753,7 @@ static int kvm_vm_stats_release(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations kvm_vm_stats_fops = {
+	.owner = THIS_MODULE,
 	.read = kvm_vm_stats_read,
 	.release = kvm_vm_stats_release,
 	.llseek = noop_llseek,
@@ -5060,7 +5055,7 @@ static long kvm_vm_compat_ioctl(struct file *filp,
 }
 #endif
 
-static const struct file_operations kvm_vm_fops = {
+static struct file_operations kvm_vm_fops = {
 	.release        = kvm_vm_release,
 	.unlocked_ioctl = kvm_vm_ioctl,
 	.llseek		= noop_llseek,
@@ -5545,7 +5540,6 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 	return r < 0 ? r : 0;
 }
 
-/* Caller must hold slots_lock. */
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			    int len, struct kvm_io_device *dev)
 {
@@ -5553,6 +5547,8 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	struct kvm_io_bus *new_bus, *bus;
 	struct kvm_io_range range;
 
+	lockdep_assert_held(&kvm->slots_lock);
+
 	bus = kvm_get_bus(kvm, bus_idx);
 	if (!bus)
 		return -ENOMEM;
@@ -6095,6 +6091,9 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 		goto err_async_pf;
 
 	kvm_chardev_ops.owner = module;
+	kvm_vm_fops.owner = module;
+	kvm_vcpu_fops.owner = module;
+	kvm_device_fops.owner = module;
 
 	kvm_preempt_ops.sched_in = kvm_sched_in;
 	kvm_preempt_ops.sched_out = kvm_sched_out;